Automatic detection of erythemato-squamous diseases using adaptive neuro-fuzzy inference systems

Size: px
Start display at page:

Download "Automatic detection of erythemato-squamous diseases using adaptive neuro-fuzzy inference systems"

Transcription

1 Computers in Biology and Medicine 35 (25) Automatic detection of erythemato-squamous diseases using adaptive neuro-fuzzy inference systems Elif Derya Ubeyl, İnan Guler Department of Electronics and Computer Education, Faculty of Technical Education, Gazi University, 65 Teknikokullar, Ankara, Turkey Received 4 August 23; accepted 6 March 24 Abstract A newapproach based on adaptive neuro-fuzzy inference system (ANFIS) was presented for detection of erythemato-squamous diseases. The domain contained records of patients with known diagnosis. Given a training set of such records, the ANFIS classiers learned howto dierentiate a newcase in the domain. The six ANFIS classiers were used to detect the six erythemato-squamous diseases when 34 features dening six disease indications were used as inputs. To improve diagnostic accuracy, the seventh ANFIS classier (combining ANFIS) was trained using the outputs of the six ANFIS classiers as input data. The proposed ANFIS model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach. Some conclusions concerning the impacts of features on the detection of erythemato-squamous diseases were obtained through analysis of the ANFIS. The performances of the ANFIS model were evaluated in terms of training performances and classication accuracies and the results conrmed that the proposed ANFIS model has some potential in detecting the erythemato-squamous diseases. The ANFIS model achieved accuracy rates which were higher than that of the stand-alone neural network model.? 24 Elsevier Ltd. All rights reserved. Keywords: Adaptive neuro-fuzzy inference system (ANFIS); Fuzzy logic; Erythemato-squamous diseases detection. Introduction The dierential diagnosis of erythemato-squamous diseases is a dicult problem in dermatology. The diseases in this group are psoriasis, seboreic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis and pityriasis rubra pilaris. They all share the clinical features of erythema and scaling Corresponding author. Tel.: ; fax: address: iguler@gazi.edu.tr (İ. Guler) /$ - see front matter? 24 Elsevier Ltd. All rights reserved. doi:.6/j.compbiomed

2 422 E.D. Ubeyl, İ Guler / Computers in Biology and Medicine 35 (25) with very few dierences []. This is where fuzzy set theory plays an important role in dealing with uncertainty when making decisions in medical applications. Fuzzy sets have attracted the growing attention and interest in modern information technology, production technique, decision making, pattern recognition, diagnostics, data analysis, etc. [2 4]. Neuro-fuzzy systems are fuzzy systems which use articial neural networks (ANNs) theory in order to determine their properties (fuzzy sets and fuzzy rules) by processing data samples. Neuro-fuzzy systems harness the power of the two paradigms: fuzzy logic and ANNs, by utilizing the mathematical properties of ANNs in tuning rule-based fuzzy systems that approximate the way man processes information. A specic approach in neuro-fuzzy development is the adaptive neuro-fuzzy inference system (ANFIS), which has shown signicant results in modelling nonlinear functions. In ANFIS, the membership function parameters are extracted from a data set that describes the system behavior. The ANFIS learns features in the data set and adjusts the system parameters according to a given error criterion [5,6]. Successful implementations of ANFIS in biomedical engineering have been reported for classication [7,8] and data analysis [9]. In this study, a newapproach based on ANFIS was presented for the detection of erythematosquamous diseases. The six ANFIS classiers were used to detect the six erythemato-squamous diseases when 34 features dening six disease indications were used as inputs. Each of the ANFIS classier was trained so that they are likely to be more accurate for one type of erythemato-squamous disease than the other diseases. The predictions of the six ANFIS classiers were combined by the seventh ANFIS classier. The dermatology database investigated in this study consisted of 358 cases of erythemato-squamous diseases compiled by Guvenir et al. []. The proposed ANFIS model was then evaluated and performances of the ANFIS model were reported. We were able to achieve signicant improvement in accuracy by applying ANFIS model compared to the stand-alone neural networks. Finally, some conclusions were drawn concerning the impacts of features on the detection of erythemato-squamous diseases. 2. Dierential diagnosis of erythemato-squamous diseases The erythemato-squamous diseases are psoriasis, seboreic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis and pityriasis rubra pilaris. These diseases are frequently seen in the outpatient dermatology departments. Since they all share the clinical features of erythema and scaling with slight variations, the dierential diagnosis of erythemato-squamous diseases is dicult. At rst sight, all the diseases look very much alike with the erythema and scaling. When inspected more carefully, some patients have the typical clinical features of the disease at the predilection sites (localizations of the skin which a disease prefers) while another group has typical localizations. Patients were rst evaluated clinically with 2 features. The degree of erythema and scaling, whether the borders of lesions are denite or not, the presence of itching and koebner phenomenon, the formation of papules, whether the oral mucosa, elbows, knees and the scalp are involved or not, whether there is a family history or not, are all important in dierential diagnosis. The erythema and scaling of chronic dermatitis is less than that of psoriasis, the koebner phenomenon is present only in psoriasis, lichen planus and pityriasis rosea. Itching and polygonal papules are for lichen planus, whereas follicular papules are for pityriasis rubra pilaris. Oral mucosa is a predilection site for lichen

3 E.D. Ubeyl, İ Guler / Computers in Biology and Medicine 35 (25) planus whilst knee, elbow and scalp involvements are for psoriasis. Family history is usually present for psoriasis and pityriasis rubra pilaris usually starts during childhood. Some patients can be diagnosed with these clinical features only, however, a biopsy is usually necessary for a correct and denite diagnosis. Skin samples were taken for the evaluation of 22 histopathological features. Another diculty for dierential diagnosis is that a disease may showthe histopathological features of another disease at the beginning stage and may have the characteristic features at the following stages. Some samples show the typical histopathological features of the disease while some do not. Melanin incontinence is a diagnostic feature for lichen planus, brosis of the papillary dermis is for chronic dermatitis, exocytosis may be seen in lichen planus, pityriasis rosea and seboreic dermatitis. Acanthosis and parakeratosis can be seen in all of the diseases at dierent levels. Clubbing of the rete ridges, thinning of the suprapapillary epidermis are diagnostic for psoriasis. The disappearance of the granular layer, vacuolization and damage of basal layer, saw-tooth appearance of retes and a band-like inltrate are diagnostic for lichen planus. Follicular horn plug and perifollicular parakeratosis are hints for pityriasis rubra pilaris []. 3. Adaptive neuro-fuzzy inference system (ANFIS) 3.. Architecture of ANFIS The ANFIS is a fuzzy Sugeno model put in the framework of adaptive systems to facilitate learning and adaptation [5,6]. Such framework makes the ANFIS modeling more systematic and less reliant on expert knowledge. To present the ANFIS architecture, two fuzzy if then rules based on a rst order Sugeno model are considered Rule : If (x is A ) and (y is B ) then (f = p x + q y + r ). Rule 2: If (x is A 2 ) and (y is B 2 ) then (f 2 = p 2 x + q 2 y + r 2 ), where x and y are the inputs, A i and B i are the fuzzy sets, f i are the outputs within the fuzzy region specied by the fuzzy rule, p i ; q i and r i are the design parameters that are determined during the training process. The ANFIS architecture to implement these two rules is shown in Fig., in which a circle indicates a xed node, whereas a square indicates an adaptive node. In the rst layer, all the nodes are adaptive nodes. The outputs of layer are the fuzzy membership grade of the inputs, which are given by O i = Ai (x); i=; 2; O i = Bi 2 (y); i=3; 4; () (2) where Ai (x); Bi 2 (y) can adopt any fuzzy membership function. For example, if the bell shaped membership function is employed, Ai (x) is given by Ai (x)= +{((x c i )=a i ) 2 } bi ; where a i ; b i and c i are the parameters of the membership function, governing the bell-shaped functions, accordingly. (3)

4 424 E.D. Ubeyl, İ Guler / Computers in Biology and Medicine 35 (25) Layer Layer 2 Layer 3 Layer 4 Layer 5 x y x A M w N w w f A 2 S f B y M N w 2 f 2 B 2 w 2 w 2 x y Fig.. ANFIS architecture. In the second layer, the nodes are xed nodes. They are labeled with M, indicating that they perform as a simple multiplier. The outputs of this layer can be represented as Oi 2 = w i = Ai (x) Bi (y); i=; 2; (4) which are the so-called ring strengths of the rules. In the third layer, the nodes are also xed nodes. They are labeled with N, indicating that they play a normalization role to the ring strengths from the previous layer. The outputs of this layer can be represented as Oi 3 =w i = w i ; i=; 2; (5) w + w 2 which are the so-called normalized ring strengths. In the fourth layer, the nodes are adaptive nodes. The output of each node in this layer is simply the product of the normalized ring strength and a rst-order polynomial (for a rst-order Sugeno model). Thus, the outputs of this layer are given by Oi 4 =w i f i =w i (p i x + q i y + r i ); i=; 2: (6) In the fth layer, there is only one single xed node labeled with S. This node performs the summation of all incoming signals. Hence, the overall output of the model is given by 2 Oi 5 = w i f i = ( 2 i= w if i ) : (7) w + w 2 i= It can be observed that there are two adaptive layers in this ANFIS architecture, namely the rst layer and the fourth layer. In the rst layer, there are three modiable parameters {a i ;b i ;c i }, which are related to the input membership functions. These parameters are the so-called premise parameters. In the fourth layer, there are also three modiable parameters {p i ;q i ;r i }, pertaining to the rst order polynomial. These parameters are so-called consequent parameters [5,6] Learning algorithm of ANFIS The task of the learning algorithm for this architecture is to tune all the modiable parameters, namely {a i ;b i ;c i } and {p i ;q i ;r i }, to make the ANFIS output match the training data. When the

5 E.D. Ubeyl, İ Guler / Computers in Biology and Medicine 35 (25) premise parameters a i ; b i and c i of the membership function are xed, the output of the ANFIS model can be written as f = w f + w 2 f 2 : w + w 2 w + w 2 Substituting Eq. (5) into Eq. (8) yields f =w f +w 2 f 2 : (8) (9) By substituting the fuzzy if then rules into Eq. (9), it becomes f =w (p x + q y + r )+ w 2 (p 2 x + q 2 y + r 2 ): () After rearrangement, the output can be expressed as f =(w x)p +(w y)q +(w )r +(w 2 x)p 2 +(w 2 y)q 2 +(w 2 )r 2 ; () which is a linear combination of the modiable consequent parameters p ; q ; r ; p 2 ; q 2 and r 2. The least squares method can be used to identify the optimal values of these parameters easily. When the premise parameters are not xed, the search space becomes larger and the convergence of the training becomes slower. A hybrid algorithm combining the least squares method and the gradient descent method is adopted to solve this problem. The hybrid algorithm is composed of a forward pass and a backward pass. The least squares method (forward pass) is used to optimize the consequent parameters with the premise parameters xed. Once the optimal consequent parameters are found, the backward pass starts immediately. The gradient descent method (backward pass) is used to adjust optimally the premise parameters corresponding to the fuzzy sets in the input domain. The output of the ANFIS is calculated by employing the consequent parameters found in the forward pass. The output error is used to adapt the premise parameters by means of a standard backpropagation algorithm. It has been proven that this hybrid algorithm is highly ecient in training the ANFIS [5,6]. In this study, a newapproach based on ANFIS was presented for the detection of erythematosquamous diseases. The six ANFIS classiers were used to detect the six erythemato-squamous diseases when 34 features dening six disease indications were used as inputs. To improve diagnostic accuracy, the seventh ANFIS classier (combining ANFIS) was trained using the outputs of the six ANFIS classiers as input data. The dermatology database investigated in this study consisted of 358 cases of erythemato-squamous diseases compiled by Guvenir et al. []. 4. Results and discussion The collection of well-distributed, sucient, and accurately measured input data is the basic requirement to obtain an accurate model. In the data set, the family history feature has a value of if any of the erythemato-squamous diseases have been observed in the family, otherwise it has a value of zero. The age feature simply represents the age of the patient. Every other feature (clinical and histopathological) was given a degree in the range 3. Here, indicates that the feature was not present, 3 indicates the largest amount possible, whilst, 2 indicate the relative intermediate

6 426 E.D. Ubeyl, İ Guler / Computers in Biology and Medicine 35 (25) Table The data set used in the present study Erythemato-squamous Features diseases Clinical Histopathological (number of patients) Psoriasis () Feature : erythema Feature 2: melanin incontinence Seboreic dermatitis (6) Feature 2: scaling Feature 3: eosinophils in the inltrate Lichen planus (7) Feature 3: denite borders Feature 4: PNL inltrate Pityriasis rosea (48) Feature 4: itching Feature 5: brosis of the papillary dermis Chronic dermatitis (48) Feature 5: koebner phenomenon Feature 6: exocytosis Pityriasis rubra pilaris (2) Feature 6: polygonal papules Feature 7: acanthosis Feature 7: follicular papules Feature 8: hyperkeratosis Feature 8: oral mucosal involvement Feature 9: parakeratosis Feature 9: knee and elbowfeature 2: clubbing of the rete ridges involvement Feature : scalp involvement Feature 2: elongation of the rete ridges Feature : family history Feature 22: thinning of the suprapapillary epidermis Feature 34: age Feature 23: pongiform pustule Feature 24: munro microabcess Feature 25: focal hypergranulosis Feature 26: disappearance of the granular layer Feature 27: vacuolization and damage of basal layer Feature 28: spongiosis Feature 29: saw-tooth appearance of retes Feature 3: follicular horn plug Feature 3: perifollicular parakeratosis Feature 32: inammatory mononuclear inltrate Feature 33: band-like inltrate values. The data set consisting of 34 features that used in the present study and the six classes of erythemato-squamous diseases are summarized in Table. The proposed technique involved training the six ANFIS classiers to detect the six classes of erythemato-squamous diseases when the features given in Table were used as inputs. We trained the six ANFIS classiers since there were six possible outcomes of the diagnosis of erythemato-squamous diseases (psoriasis, seboreic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis and pityriasis rubra pilaris). Each of the ANFIS classier was trained so that they are likely to be more accurate for one type of erythemato-squamous disease than the other diseases. For detection of the six classes of erythemato-squamous diseases, the data set consisting of 34 features of 358 patients were presented to each of the ANFIS classier. Samples with target outputs psoriasis, seboreic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis, and pityriasis rubra pilaris were given the binary target values of (,,,,,), (,,,,,), (,,,,,), (,,,,,), (,,,,,), and (,,,,,), respectively.

7 E.D. Ubeyl, İ Guler / Computers in Biology and Medicine 35 (25) input (3) input2 (3) anfis (sugeno) f(u) input3 (3) 562 rules output (562) input34 (3) Fig. 2. Fuzzy rule architecture of the six ANFIS classiers. System ANFIS: 34 inputs, output, 562 rules. We trained the seventh ANFIS classier to combine the predictions of the six ANFIS classiers. The outputs of the six ANFIS classiers were used as the inputs of the seventh ANFIS classier. Fig. 2 shows the fuzzy rule architecture of the six ANFIS classiers using a generalized bell shaped membership function dened in Eq. (3). There are a total of 562 fuzzy rules in the architecture. Fig. 3 shows the fuzzy rule architecture of the combining ANFIS classier (the seventh ANFIS classier) using a generalized bell shaped membership function. There are a total of 54 fuzzy rules in the architecture. Each ANFIS shown in Figs. 2 and 3 was implemented by using MATLAB software package (MATLAB version 6. with fuzzy logic toolbox). The data set (358 patients) was divided into two separate data sets the training data set and the testing data set. The training data set was used to train ANFIS model, whereas the testing data set was used to verify the accuracy and the eectiveness of the trained ANFIS model for the detection of the six classes of erythemato-squamous diseases. Each ANFIS shown in Figs. 2 and 3 used 79 training data in 5 training periods and the step size for parameter adaptation had an initial value of.. The steps of parameter adaptation of each ANFIS are shown in Fig. 4. At the end of 5 training periods, the network error convergence curve of each ANFIS was derived as shown in Fig. 5. From the curve, the nal convergence value is 5:36 6. In a real-world domain, just like the one used in the present study, all of the features used in the descriptions of instances may have dierent levels of relevancy. Therefore, in the present study changes of the nal (after training) generalized bell shaped membership functions with respect to the initial (before training) generalized bell shaped membership functions of the input parameters were examined. Membership function of each input parameter was divided into three regions, namely, small, medium, and large. Fig. 6 shows the initial and nal generalized bell shaped membership

8 428 E.D. Ubeyl, İ Guler / Computers in Biology and Medicine 35 (25) input (3) input2 (3) anfis (sugeno) f(u) input3 (3) 54 rules output (54) input6 (3) Fig. 3. Fuzzy rule architecture of the combining ANFIS (the seventh ANFIS classier). System ANFIS: 6 inputs, output, 54 rules Step size Epoch Fig. 4. Adaptation of parameter steps of each ANFIS. functions of the two input parameters (inputs 5 and 32) having the greatest impact and the two input parameters (inputs 7 and 3) having the least impact on the detection of erythemato-squamous diseases. Fig. 6(a) shows the initial generalized bell-shaped membership functions of the input 5 (koebner phenomenon), input 7 (acanthosis), input 3 (follicular horn plug) and input 32 (inammatory mononuclear inltrate). Fig. 6(b) shows the considerable change in the nal membership function of koebner phenomenon (input 5) after training. Fig. 6(c) shows the nal membership

9 E.D. Ubeyl, İ Guler / Computers in Biology and Medicine 35 (25) x -3.8 Mean square error Epoch Fig. 5. The curve of network error convergence of each ANFIS. function of the inammatory mononuclear inltrate (input 32) and it also shows a distinctive change in the nal membership function of input 32. Fig. 6(d) shows the little change in the nal membership function of acanthosis (input 7). Fig. 6(e) shows the nal membership function of follicular horn plug (input 3) and it also shows a slight change in the nal membership function of input 3. The examination of initial and nal membership functions indicates that there is a considerable change in the nal membership function of koebner phenomenon (input 5), followed by inammatory mononuclear inltrate (input 32) and that changes in nal membership function of acanthosis (input 7) is the smallest, followed by follicular horn plug (input 3). This analysis was done since the amount of changes in the nal membership functions of inputs indicates the impact of inputs on the detection of output. By the analysis of membership functions the impact of inputs on the detection of erythemato-squamous diseases was determined. Based on the analysis of membership functions, it can be mentioned that koebner phenomenon has the greatest impact on the detection of erythemato-squamous diseases, followed by inammatory mononuclear inltrate and that acanthosis has the least impact, followed by follicular horn plug. After training, 79 testing data were used to validate the accuracy of the ANFIS model for the detection of erythemato-squamous diseases. All of the test cases had one of the six erythemato-squamous diseases. In classication, the aim is to assign the input patterns to one of several classes, usually represented by outputs restricted to lie in the range from to, so that they represent the probability of class membership. While the classication is carried out, a specic pattern is assigned to a specic class according to the characteristic features selected for it. In this application, there were six classes: psoriasis, seboreic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis, and pityriasis rubra pilaris. Classication results of the ANFIS model were displayed by a confusion matrix. The confusion matrix is dened by labeling the desired classication on the rows and the actual network outputs on the columns. The confusion matrix showing the classication results of the ANFIS model is given below.

10 43 E.D. Ubeyl, İ Guler / Computers in Biology and Medicine 35 (25) inmf inmf2 inmf3 in5mf in5mf2 in5mf3.8.8 Degree of membership Degree of membership (a) input 5, input 7, input 3,input32 (b) input 5 in32mf in32mf2 in32mf3 in7mf in7mf2 in7mf3.8.8 Degree of membership Degree of membership (c) input 32 (d) input 7 3 in3mf in3mf2 in3mf3.8 Degree of membership (e) input 3 Fig. 6. (a) Initial generalized bell-shaped membership functions of inputs 5, 7, 3, 32; (b) nal generalized bell-shaped membership function of input 5; (c) nal generalized bell shaped membership function of input 32; (d) nal generalized bell-shaped membership function of input 7; (e) nal generalized bell shaped membership function of input 3.

11 Confusion matrix: E.D. Ubeyl, İ Guler / Computers in Biology and Medicine 35 (25) Desired result Output result Psoriasis Seboreic Lichen Pityriasis Chronic Pityriasis dermatitis planus rosea dermatitis rubra pilaris Psoriasis 54 Seboreic dermatitis 29 Lichen planus 34 Pityriasis rosea 22 Chronic dermatitis 23 Pityriasis rubra pilaris 9 According to the confusion matrix, subject suering from psoriasis was classied incorrectly by the ANFIS model as a subject suering from seboreic dermatitis, subject suering from psoriasis was classied as a subject suering from pityriasis rosea, subject suering from seboreic dermatitis was classied as a subject suering from psoriasis, subject suering from lichen planus was classied as a subject suering from pityriasis rosea, subject suering from pityriasis rosea was classied as a subject suering from seboreic dermatitis, subject suering from pityriasis rosea was classied as a subject suering from chronic dermatitis, subject suering from chronic dermatitis was classied as a subject suering from psoriasis and subject suering from pityriasis rubra pilaris was classied as a subject suering from pityriasis rosea. The test performance of the ANFIS model was determined by the computation of the statistical parameters such as sensitivity, specicity and total classication accuracy. Binomial condence intervals (CIs) were calculated for sensitivity and specicity values []. The sensitivity, specicity and total classication accuracy are dened as follows: Sensitivity: number of true positive decisions/number of actually positive cases. Specicity: number of true negative decisions/number of actually negative cases. Total classication accuracy: number of correct decisions/total number of cases. A true positive decision occurs when the positive detection of the network coincided with a positive detection of the physician. A true negative decision occurs when both the network and the physician suggested the absence of a positive detection. The subjects suering from psoriasis, seboreic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis, and pityriasis rubra pilaris were classied with the accuracy of 95.5% (total classication accuracy). The values of sensitivity and 95% CIs of sensitivity values for the six erythematosquamous diseases are given in Table 2. The values of specicity and 95% CIs of specicity values for the six erythemato-squamous diseases are given in Table 3. As it is seen from Table 2, the ANFIS model classied subjects suering from psoriasis, seboreic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis, and pityriasis rubra pilaris with the accuracy of 96.4%, 96.7%, 97.%, 9.7%, 95.8%, and 9.%, respectively. The correct classication rates of the stand-alone neural network (multilayer perceptron neural network) were 85.7% for subjects suering from psoriasis, 86.7% for subjects suering from seboreic dermatitis, 85.7% for subjects suering from lichen planus, 83.3% for subjects suering from pityriasis rosea, 87.5% for subjects suering from chronic

12 432 E.D. Ubeyl, İ Guler / Computers in Biology and Medicine 35 (25) Table 2 The values of sensitivity and 95% CIs of sensitivity values for the six erythemato-squamous diseases Erythemato-squamous diseases Sensitivity (%) 95% CIs (%) Psoriasis Seboreic dermatitis Lichen planus Pityriasis rosea Chronic dermatitis Pityriasis rubra pilaris Table 3 The values of specicity and 95% CIs of specicity values for the six erythemato-squamous diseases Erythemato-squamous diseases Specicity (%) 95% CIs (%) Psoriasis Seboreic dermatitis Lichen planus Pityriasis rosea Chronic dermatitis Pityriasis rubra pilaris dermatitis and 8.% for subjects suering from pityriasis rubra pilaris. The total classication accuracy of the stand-alone neural network was 85.5%. Thus, the accuracy rates of the ANFIS model presented for this application were found to be higher than that of the stand-alone neural network model. These results indicate that the proposed ANFIS model has some potential in detecting the erythemato-squamous diseases. 5. Conclusion This paper presented a newapplication of ANFIS model for the detection of erythemato-squamous diseases. We chose fuzzy logic in the present study due to the uncertainty in dierential diagnosis of erythemato-squamous diseases, which is a result of imprecise boundaries among the six erythemato-squamous diseases. Using fuzzy logic enabled us to use this uncertainty in the classi- ers designs and consequently to increase the credibility of the systems outputs. The six ANFIS classiers were used to detect the six erythemato-squamous diseases when 34 features dening six disease indications were used as inputs. The predictions of the six ANFIS classiers were combined by the seventh ANFIS classier. The proposed ANFIS model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach. Some conclusions concerning the impacts of features on the detection of erythemato-squamous diseases were obtained through analysis of the ANFIS. The total classication accuracy of the ANFIS model was 95.5%. We, therefore, have concluded that the proposed ANFIS model can be used in detecting erythemato-squamous diseases by taking into consideration the misclassication rates.

13 Acknowledgements E.D. Ubeyl, İ Guler / Computers in Biology and Medicine 35 (25) This study has been supported by the State Planning Organization of Turkey (Project No: 23K 247, Project name: Biomedical signal acquisition, processing and imaging) References [] H.A. Guvenir, G. Demiroz, N. İlter, Learning dierential diagnosis of erythemato-squamous diseases using voting feature intervals, Artif. Intell. Med. 3 (998) [2] D. Dubois, H. Prade, An introduction to fuzzy systems, Clin. Chim. Acta 27 (998) [3] L.I. Kuncheva, F. Steimann, Fuzzy diagnosis, Artif. Intell. Med. 6 (999) [4] D. Nauck, R. Kruse, Obtaining interpretable fuzzy classication rules from medical data, Artif. Intell. Med. 6 (999) [5] J.-S.R. Jang, ANFIS: Adaptive-network-based fuzzy inference system, IEEE Trans. Syst. Man Cybern. 23 (3) (993) [6] J.-S.R. Jang, Self-learning fuzzy controllers based on temporal backpropagation, IEEE Trans. Neural Networks 3 (5) (992) [7] J. Usher, D. Campbell, J. Vohra, J. Cameron, A fuzzy logic-controlled classier for use in implantable cardioverter debrillators, Pace-Pacing Clin. Electrophysiol. 22 (999) [8] S.Y. Belal, A.F.G. Taktak, A.J. Nevill, S.A. Spencer, D. Roden, S. Bevan, Automatic detection of distorted plethysmogram pulses in neonates and paediatric patients using an adaptive-network-based fuzzy inference system, Artif. Intell. Med. 24 (22) [9] I. Virant-Klun, J. Virant, Fuzzy logic alternative for analysis in the biomedical sciences, Comput. Biomed. Res. 32 (999) [] P. Armitage, G. Berry, Statistical Methods in Medical Research, Blackwell Science, Oxford, 994. İnan Guler graduated from Erciyes University in 98. He took his M.S. Degree from Middle East Technical University in 985, and his Ph.D. Degree from İstanbul Technical University in 99, all in Electronic Engineering. He is a professor at Gazi University where he is Head of Department. His areas of interest include biomedical systems, biomedical signal processing, biomedical instrumentation, electronic circuit design, neural network, and articial intelligence. He has written more than articles on biomedical engineering. Elif Derya Ubeyl graduated from C ukurova University in 996. She took her M.S. Degree in 998, all in electronic engineering. She took her Ph.D. Degree from Gazi University, electronics and computer technology. She is a research assistant at the Department of Electronics and Computer Education at Gazi University. Her areas of interest are biomedical signal processing, neural network, and articial intelligence.

NEURO-FUZZY SYSTEM FOR PROSTATE CANCER DIAGNOSIS LUIGI BENECCHI

NEURO-FUZZY SYSTEM FOR PROSTATE CANCER DIAGNOSIS LUIGI BENECCHI ADULT UROLOGY NEURO-FUZZY SYSTEM FOR PROSTATE CANCER DIAGNOSIS LUIGI BENECCHI ABSTRACT Objectives. To develop a neuro-fuzzy system to predict the presence of prostate cancer. Neuro-fuzzy systems harness

More information

Estimating the Optimal Dosage of Sodium Valproate in Idiopathic Generalized Epilepsy with Adaptive Neuro-Fuzzy Inference System

Estimating the Optimal Dosage of Sodium Valproate in Idiopathic Generalized Epilepsy with Adaptive Neuro-Fuzzy Inference System Estimating the Optimal Dosage of Sodium Valproate in Idiopathic Generalized Epilepsy with Adaptive Neuro-Fuzzy Inference System Somayyeh Lotfi Noghabi1*, Ali Vahidian Kamyad1, Mohsen Foroughipour, Amir

More information

Spectral broadening of ophthalmic arterial Doppler signals using STFT and wavelet transform

Spectral broadening of ophthalmic arterial Doppler signals using STFT and wavelet transform Computers in Biology and Medicine 34 (2004) 345 354 www.elsevierhealth.com/locate/compbiomed Spectral broadening of ophthalmic arterial Doppler signals using STFT and wavelet transform Elif Derya Ubeyli,

More information

A prediction model for type 2 diabetes using adaptive neuro-fuzzy interface system.

A prediction model for type 2 diabetes using adaptive neuro-fuzzy interface system. Biomedical Research 208; Special Issue: S69-S74 ISSN 0970-938X www.biomedres.info A prediction model for type 2 diabetes using adaptive neuro-fuzzy interface system. S Alby *, BL Shivakumar 2 Research

More information

Keywords: Adaptive Neuro-Fuzzy Interface System (ANFIS), Electrocardiogram (ECG), Fuzzy logic, MIT-BHI database.

Keywords: Adaptive Neuro-Fuzzy Interface System (ANFIS), Electrocardiogram (ECG), Fuzzy logic, MIT-BHI database. Volume 3, Issue 11, November 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Detection

More information

A Histopathologic Study of Papulosquamous Lesions of Skin

A Histopathologic Study of Papulosquamous Lesions of Skin Original 404 Article Indian Journal of Pathology: Research and Practice Volume 6 Number 2, April - June 2017 (Part 2) DOI: http://dx.doi.org/10.21088/ijprp.2278.148x.6217.11 A Histopathologic Study of

More information

fuzzy models for cardiac arrhythmia classication Rosaria Silipo 1 International Computer Science Institute, Berkeley, USA

fuzzy models for cardiac arrhythmia classication Rosaria Silipo 1 International Computer Science Institute, Berkeley, USA Investigating electrocardiographic features in fuzzy models for cardiac arrhythmia classication Rosaria Silipo 1 International Computer Science Institute, Berkeley, USA Abstract. Simple and composed measures

More information

Histopathological spectrum of non-infectious erythematous, papulo-squamous lesions

Histopathological spectrum of non-infectious erythematous, papulo-squamous lesions Histopathological spectrum of non-infectious erythematous, papulo-squamous lesions B. Rajasekhar Reddy 1*, Nalini Krishna.M 2 1 Associate Professor, Department of Pathology, Mediciti Institute of Medical

More information

Comparison of Mamdani and Sugeno Fuzzy Interference Systems for the Breast Cancer Risk

Comparison of Mamdani and Sugeno Fuzzy Interference Systems for the Breast Cancer Risk Comparison of Mamdani and Sugeno Fuzzy Interference Systems for the Breast Cancer Risk Alshalaa A. Shleeg, Issmail M. Ellabib Abstract Breast cancer is a major health burden worldwide being a major cause

More information

A Descriptive Study on Patients of Papulosquamous Lesion at Tertiary Care Institute

A Descriptive Study on Patients of Papulosquamous Lesion at Tertiary Care Institute MVP Journal of Medical Sciences, Vol 1(1), 30 35, January 2014 A Descriptive Study on Patients of Papulosquamous Lesion at Tertiary Care Institute S. D. Chavhan 1*, S. V. Mahajan 2 and A. J. Vankudre 3

More information

Neural Network based Heart Arrhythmia Detection and Classification from ECG Signal

Neural Network based Heart Arrhythmia Detection and Classification from ECG Signal Neural Network based Heart Arrhythmia Detection and Classification from ECG Signal 1 M. S. Aware, 2 V. V. Shete *Dept. of Electronics and Telecommunication, *MIT College Of Engineering, Pune Email: 1 mrunal_swapnil@yahoo.com,

More information

Detection and Classification of Epileptic Seizures using Wavelet feature extraction and Adaptive Neuro-Fuzzy Inference System

Detection and Classification of Epileptic Seizures using Wavelet feature extraction and Adaptive Neuro-Fuzzy Inference System Detection and Classification of Epileptic Seizures using Wavelet feature extraction and Adaptive Neuro-Fuzzy Inference System Dr. D. Najumnissa, * Dr. T. R. Rangaswamy B S Abdur Rahman University, Chennai,

More information

A Learning Method of Directly Optimizing Classifier Performance at Local Operating Range

A Learning Method of Directly Optimizing Classifier Performance at Local Operating Range A Learning Method of Directly Optimizing Classifier Performance at Local Operating Range Lae-Jeong Park and Jung-Ho Moon Department of Electrical Engineering, Kangnung National University Kangnung, Gangwon-Do,

More information

ECG Signal Analysis for Abnormality Detection in the Heart beat

ECG Signal Analysis for Abnormality Detection in the Heart beat GRD Journals- Global Research and Development Journal for Engineering Volume 1 Issue 10 September 2016 ISSN: 2455-5703 ECG Signal Analysis for Abnormality Detection in the Heart beat Vedprakash Gujiri

More information

An ECG Beat Classification Using Adaptive Neuro- Fuzzy Inference System

An ECG Beat Classification Using Adaptive Neuro- Fuzzy Inference System An ECG Beat Classification Using Adaptive Neuro- Fuzzy Inference System Pramod R. Bokde Department of Electronics Engineering, Priyadarshini Bhagwati College of Engineering, Nagpur, India Abstract Electrocardiography

More information

Multilayer Perceptron Neural Network Classification of Malignant Breast. Mass

Multilayer Perceptron Neural Network Classification of Malignant Breast. Mass Multilayer Perceptron Neural Network Classification of Malignant Breast Mass Joshua Henry 12/15/2017 henry7@wisc.edu Introduction Breast cancer is a very widespread problem; as such, it is likely that

More information

CHAPTER 4 ANFIS BASED TOTAL DEMAND DISTORTION FACTOR

CHAPTER 4 ANFIS BASED TOTAL DEMAND DISTORTION FACTOR 47 CHAPTER 4 ANFIS BASED TOTAL DEMAND DISTORTION FACTOR In distribution systems, the current harmonic distortion should be limited to an acceptable limit to avoid heating, losses and malfunctioning of

More information

Implementation of Inference Engine in Adaptive Neuro Fuzzy Inference System to Predict and Control the Sugar Level in Diabetic Patient

Implementation of Inference Engine in Adaptive Neuro Fuzzy Inference System to Predict and Control the Sugar Level in Diabetic Patient , ISSN (Print) : 319-8613 Implementation of Inference Engine in Adaptive Neuro Fuzzy Inference System to Predict and Control the Sugar Level in Diabetic Patient M. Mayilvaganan # 1 R. Deepa * # Associate

More information

Identification and Classification of Coronary Artery Disease Patients using Neuro-Fuzzy Inference Systems

Identification and Classification of Coronary Artery Disease Patients using Neuro-Fuzzy Inference Systems Journal of mathematics and computer Science 13 (2014) 136-141 Identification and Classification of Coronary Artery Disease Patients using Neuro-Fuzzy Inference Systems Saeed Ayat 1, Asieh Khosravanian

More information

PROGNOSTIC COMPARISON OF STATISTICAL, NEURAL AND FUZZY METHODS OF ANALYSIS OF BREAST CANCER IMAGE CYTOMETRIC DATA

PROGNOSTIC COMPARISON OF STATISTICAL, NEURAL AND FUZZY METHODS OF ANALYSIS OF BREAST CANCER IMAGE CYTOMETRIC DATA 1 of 4 PROGNOSTIC COMPARISON OF STATISTICAL, NEURAL AND FUZZY METHODS OF ANALYSIS OF BREAST CANCER IMAGE CYTOMETRIC DATA H. Seker 1, M. Odetayo 1, D. Petrovic 1, R.N.G. Naguib 1, C. Bartoli 2, L. Alasio

More information

Edge Detection Techniques Based On Soft Computing

Edge Detection Techniques Based On Soft Computing International Journal for Science and Emerging ISSN No. (Online):2250-3641 Technologies with Latest Trends 7(1): 21-25 (2013) ISSN No. (Print): 2277-8136 Edge Detection Techniques Based On Soft Computing

More information

Chapter 1. Introduction

Chapter 1. Introduction Chapter 1 Introduction Artificial neural networks are mathematical inventions inspired by observations made in the study of biological systems, though loosely based on the actual biology. An artificial

More information

Diagnosis Prediction of Lichen Planus, Leukoplakia and Oral Squamous Cell Carcinoma by using an Intelligent System Based on Artificial Neural Networks

Diagnosis Prediction of Lichen Planus, Leukoplakia and Oral Squamous Cell Carcinoma by using an Intelligent System Based on Artificial Neural Networks Diagnosis Prediction of Lichen Planus, Leukoplakia and Oral Squamous Cell Carcinoma by using an Intelligent System Based on Artificial Neural Networks Original Article Rouhollah Maghsoudi 1, Abolfazl Bagheri

More information

Robust system for patient specific classification of ECG signal using PCA and Neural Network

Robust system for patient specific classification of ECG signal using PCA and Neural Network International Research Journal of Engineering and Technology (IRJET) e-issn: 395-56 Volume: 4 Issue: 9 Sep -7 www.irjet.net p-issn: 395-7 Robust system for patient specific classification of using PCA

More information

Artificial Neural Networks to Determine Source of Acoustic Emission and Damage Detection

Artificial Neural Networks to Determine Source of Acoustic Emission and Damage Detection Artificial Neural Networks to Determine Source of Acoustic Emission and Damage Detection Mehrdad Shafiei Dizaji 1, Farzad Shafiei Dizaji 2 1 Former graduate, Department of Civil Engineering, Sharif University

More information

Title: Dermographic, clinical and histopathological pro le of cutaneous lichen planus

Title: Dermographic, clinical and histopathological pro le of cutaneous lichen planus Original Research Paper Dermatology Title: Dermographic, clinical and histopathological pro le of cutaneous lichen planus Dr. Rikeeta S. Deshmukh Dr. Raju G. Chaudhary ABSTRACT KEYWORDS Introduction: Unique,

More information

Question 1 Multiple Choice (8 marks)

Question 1 Multiple Choice (8 marks) Philadelphia University Student Name: Faculty of Engineering Student Number: Dept. of Computer Engineering First Exam, First Semester: 2015/2016 Course Title: Neural Networks and Fuzzy Logic Date: 19/11/2015

More information

Automated Prediction of Thyroid Disease using ANN

Automated Prediction of Thyroid Disease using ANN Automated Prediction of Thyroid Disease using ANN Vikram V Hegde 1, Deepamala N 2 P.G. Student, Department of Computer Science and Engineering, RV College of, Bangalore, Karnataka, India 1 Assistant Professor,

More information

Papulosquamous: clinicopathological

Papulosquamous: clinicopathological International Journal of Research in Medical Sciences Narayankar SL et al. Int J Res Med Sci. 2018 Jan;6(1):309-316 www.msjonline.org pissn 2320-6071 eissn 2320-6012 Original Research Article DOI: http://dx.doi.org/10.18203/2320-6012.ijrms20175740

More information

A Hierarchical Artificial Neural Network Model for Giemsa-Stained Human Chromosome Classification

A Hierarchical Artificial Neural Network Model for Giemsa-Stained Human Chromosome Classification A Hierarchical Artificial Neural Network Model for Giemsa-Stained Human Chromosome Classification JONGMAN CHO 1 1 Department of Biomedical Engineering, Inje University, Gimhae, 621-749, KOREA minerva@ieeeorg

More information

Evaluation of Computer-aided Drug Delivery System with a Human Operator

Evaluation of Computer-aided Drug Delivery System with a Human Operator IJCSI International Journal of Computer Science Issues, Vol. 7, Issue 5, September 1 ISSN (Online): 1694-814 45 Evaluation of Computer-aided Drug Delivery System with a Human Operator Koji Kashihara 1

More information

Supplementary Online Content

Supplementary Online Content Supplementary Online Content Ross NA, Chung H-J, Li Q, Andrews JP, Keller MS, Uitto J. Pityriasis rubra pilaris: a case series of patients. Published online March 9, 26. JAMA Dermatol. doi:./jamadermatol.26.9.

More information

Clinico - Histopathological features of Lichen Planus-an Appraisal

Clinico - Histopathological features of Lichen Planus-an Appraisal Original Article Clinico - Histopathological features of Lichen Planus-an Appraisal Raghavendra B N 1, Jaffer Basha S K 1 Associate Professor, Department of Dermatology, M V J Medical College and Research

More information

Pathology of the skin. Dr Fónyad László, 1sz. Patológiai és Kísérleti Rákkutató Intézet, SE

Pathology of the skin. Dr Fónyad László, 1sz. Patológiai és Kísérleti Rákkutató Intézet, SE Pathology of the skin Dr Fónyad László, 1sz. Patológiai és Kísérleti Rákkutató Intézet, SE The skin Biggest organ Kb. 1.8 nm Kb. 10 kg Most frequent site for tumor development (BCC) Pathology of the skin

More information

Classıfıcatıon of Dıabetes Dısease Usıng Backpropagatıon and Radıal Basıs Functıon Network

Classıfıcatıon of Dıabetes Dısease Usıng Backpropagatıon and Radıal Basıs Functıon Network UTM Computing Proceedings Innovations in Computing Technology and Applications Volume 2 Year: 2017 ISBN: 978-967-0194-95-0 1 Classıfıcatıon of Dıabetes Dısease Usıng Backpropagatıon and Radıal Basıs Functıon

More information

ADVANCES in NATURAL and APPLIED SCIENCES

ADVANCES in NATURAL and APPLIED SCIENCES ADVANCES in NATURAL and APPLIED SCIENCES ISSN: 1995-772 Published BY AENSI Publication EISSN: 1998-19 http://www.aensiweb.com/anas 216 September 1(13): pages 27-213 Open Access Journal Extraction of Fetal

More information

Learning and Adaptive Behavior, Part II

Learning and Adaptive Behavior, Part II Learning and Adaptive Behavior, Part II April 12, 2007 The man who sets out to carry a cat by its tail learns something that will always be useful and which will never grow dim or doubtful. -- Mark Twain

More information

Auto-Encoder Pre-Training of Segmented-Memory Recurrent Neural Networks

Auto-Encoder Pre-Training of Segmented-Memory Recurrent Neural Networks Auto-Encoder Pre-Training of Segmented-Memory Recurrent Neural Networks Stefan Glüge, Ronald Böck and Andreas Wendemuth Faculty of Electrical Engineering and Information Technology Cognitive Systems Group,

More information

ECG Beat Recognition using Principal Components Analysis and Artificial Neural Network

ECG Beat Recognition using Principal Components Analysis and Artificial Neural Network International Journal of Electronics Engineering, 3 (1), 2011, pp. 55 58 ECG Beat Recognition using Principal Components Analysis and Artificial Neural Network Amitabh Sharma 1, and Tanushree Sharma 2

More information

Spikes that count: rethinking spikiness in neurally embedded systems

Spikes that count: rethinking spikiness in neurally embedded systems Neurocomputing 58 60 (2004) 303 311 www.elsevier.com/locate/neucom Spikes that count: rethinking spikiness in neurally embedded systems Keren Saggie a;, Alon Keinan a, Eytan Ruppin a;b a School of Computer

More information

CHAPTER 2 LITERATURE REVIEW

CHAPTER 2 LITERATURE REVIEW 9 CHAPTER 2 LITERATURE REVIEW In this chapter, a review of literature on Epileptic Seizure Detection, Wavelet Transform techniques, Principal Component Analysis, Artificial Neural Network, Radial Basis

More information

MORPHOLOGICAL CHARACTERIZATION OF ECG SIGNAL ABNORMALITIES: A NEW APPROACH

MORPHOLOGICAL CHARACTERIZATION OF ECG SIGNAL ABNORMALITIES: A NEW APPROACH MORPHOLOGICAL CHARACTERIZATION OF ECG SIGNAL ABNORMALITIES: A NEW APPROACH Mohamed O. Ahmed Omar 1,3, Nahed H. Solouma 2, Yasser M. Kadah 3 1 Misr University for Science and Technology, 6 th October City,

More information

A HMM-based Pre-training Approach for Sequential Data

A HMM-based Pre-training Approach for Sequential Data A HMM-based Pre-training Approach for Sequential Data Luca Pasa 1, Alberto Testolin 2, Alessandro Sperduti 1 1- Department of Mathematics 2- Department of Developmental Psychology and Socialisation University

More information

J2.6 Imputation of missing data with nonlinear relationships

J2.6 Imputation of missing data with nonlinear relationships Sixth Conference on Artificial Intelligence Applications to Environmental Science 88th AMS Annual Meeting, New Orleans, LA 20-24 January 2008 J2.6 Imputation of missing with nonlinear relationships Michael

More information

A model to explain the emergence of reward expectancy neurons using reinforcement learning and neural network $

A model to explain the emergence of reward expectancy neurons using reinforcement learning and neural network $ Neurocomputing 69 (26) 1327 1331 www.elsevier.com/locate/neucom A model to explain the emergence of reward expectancy neurons using reinforcement learning and neural network $ Shinya Ishii a,1, Munetaka

More information

Retrospective 10 years review of 100 patients with psoriasis in the Kingdom of Saudi Arabia (KSA)

Retrospective 10 years review of 100 patients with psoriasis in the Kingdom of Saudi Arabia (KSA) Retrospective 10 years review of 100 patients with psoriasis in the Kingdom of Saudi Arabia (KSA) Ahmed Abdullah Alhumidi King saud university, Riyadh, kingdom of Saudi Arabia Abstract Background: This

More information

The 29th Fuzzy System Symposium (Osaka, September 9-, 3) Color Feature Maps (BY, RG) Color Saliency Map Input Image (I) Linear Filtering and Gaussian

The 29th Fuzzy System Symposium (Osaka, September 9-, 3) Color Feature Maps (BY, RG) Color Saliency Map Input Image (I) Linear Filtering and Gaussian The 29th Fuzzy System Symposium (Osaka, September 9-, 3) A Fuzzy Inference Method Based on Saliency Map for Prediction Mao Wang, Yoichiro Maeda 2, Yasutake Takahashi Graduate School of Engineering, University

More information

Adaptive Type-2 Fuzzy Logic Control of Non-Linear Processes

Adaptive Type-2 Fuzzy Logic Control of Non-Linear Processes Adaptive Type-2 Fuzzy Logic Control of Non-Linear Processes Bartolomeo Cosenza, Mosè Galluzzo* Dipartimento di Ingegneria Chimica dei Processi e dei Materiali, Università degli Studi di Palermo Viale delle

More information

Minimum Feature Selection for Epileptic Seizure Classification using Wavelet-based Feature Extraction and a Fuzzy Neural Network

Minimum Feature Selection for Epileptic Seizure Classification using Wavelet-based Feature Extraction and a Fuzzy Neural Network Appl. Math. Inf. Sci. 8, No. 3, 129-1300 (201) 129 Applied Mathematics & Information Sciences An International Journal http://dx.doi.org/10.1278/amis/0803 Minimum Feature Selection for Epileptic Seizure

More information

Mucinoses Diverse group of disorders which have in common deposition of basophilic, finely granular and stringy material in the connective tissues of

Mucinoses Diverse group of disorders which have in common deposition of basophilic, finely granular and stringy material in the connective tissues of Cutaneous Mucinoses Nathan C. Walk, M.D. Mucinoses Diverse group of disorders which have in common deposition of basophilic, finely granular and stringy material in the connective tissues of the dermis.

More information

A Hybrid Approach for Mining Metabolomic Data

A Hybrid Approach for Mining Metabolomic Data A Hybrid Approach for Mining Metabolomic Data Dhouha Grissa 1,3, Blandine Comte 1, Estelle Pujos-Guillot 2, and Amedeo Napoli 3 1 INRA, UMR1019, UNH-MAPPING, F-63000 Clermont-Ferrand, France, 2 INRA, UMR1019,

More information

International Journal for Science and Emerging

International Journal for Science and Emerging International Journal for Science and Emerging ISSN No. (Online):2250-3641 Technologies with Latest Trends 8(1): 7-13 (2013) ISSN No. (Print): 2277-8136 Adaptive Neuro-Fuzzy Inference System (ANFIS) Based

More information

and errs as expected. The disadvantage of this approach is that it is time consuming, due to the fact that it is necessary to evaluate all algorithms,

and errs as expected. The disadvantage of this approach is that it is time consuming, due to the fact that it is necessary to evaluate all algorithms, Data transformation and model selection by experimentation and meta-learning Pavel B. Brazdil LIACC, FEP - University of Porto Rua Campo Alegre, 823 4150 Porto, Portugal Email: pbrazdil@ncc.up.pt Research

More information

Computational Intelligence Lecture 21: Integrating Fuzzy Systems and Neural Networks

Computational Intelligence Lecture 21: Integrating Fuzzy Systems and Neural Networks Computational Intelligence Lecture 21: Integrating Fuzzy Systems and Neural Networks Farzaneh Abdollahi Department of Electrical Engineering Amirkabir University of Technology Fall 2013 Farzaneh Abdollahi

More information

ECG Rhythm Analysis by Using Neuro-Genetic Algorithms

ECG Rhythm Analysis by Using Neuro-Genetic Algorithms MASAUM Journal of Basic and Applied Sciences, Vol. 1, No. 3, October 2009 522 ECG Rhythm Analysis by Using Neuro-Genetic Algorithms Safaa S. Omran, S.M.R. Taha, and Nassr Ali Awadh Abstract The heart is

More information

JMSCR Vol 05 Issue 10 Page October 2017

JMSCR Vol 05 Issue 10 Page October 2017 www.jmscr.igmpublication.org Impact Factor 5.84 Index Copernicus Value: 71.58 ISSN (e)-2347-176x ISSN (p) 2455-0450 DOI: https://dx.doi.org/10.18535/jmscr/v5i10.125 Histomorphological Study of Lichen Planus

More information

EC352 Econometric Methods: Week 07

EC352 Econometric Methods: Week 07 EC352 Econometric Methods: Week 07 Gordon Kemp Department of Economics, University of Essex 1 / 25 Outline Panel Data (continued) Random Eects Estimation and Clustering Dynamic Models Validity & Threats

More information

Inflammatory skin disease I Jade Wititsuwannakul, MD Chulalongkorn University, Thailand

Inflammatory skin disease I Jade Wititsuwannakul, MD Chulalongkorn University, Thailand Inflammatory skin disease I Jade Wititsuwannakul, MD Chulalongkorn University, Thailand Superficial Perivascular Dermatitis Interface Dermatitis Vacuolar Dermatitis Lichenoid Dermatitis Barnhill Textbook

More information

Segmentation of Tumor Region from Brain Mri Images Using Fuzzy C-Means Clustering And Seeded Region Growing

Segmentation of Tumor Region from Brain Mri Images Using Fuzzy C-Means Clustering And Seeded Region Growing IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 18, Issue 5, Ver. I (Sept - Oct. 2016), PP 20-24 www.iosrjournals.org Segmentation of Tumor Region from Brain

More information

HYDI: A Hybrid System with Feedback. Yeona Jang. August, 1993

HYDI: A Hybrid System with Feedback. Yeona Jang. August, 1993 HYDI: A Hybrid System with Feedback for Diagnosing Multiple Disorders by Yeona Jang August, 1993 cmassachusetts Institute of Technology, 1993 HYDI: A Hybrid System with Feedback for Diagnosing Multiple

More information

Clinical Examples as Non-uniform Learning and Testing Sets

Clinical Examples as Non-uniform Learning and Testing Sets Clinical Examples as Non-uniform Learning and Testing Sets Piotr Augustyniak AGH University of Science and Technology, 3 Mickiewicza Ave. 3-9 Krakow, Poland august@agh.edu.pl Abstract. Clinical examples

More information

Actinic keratosis (AK): Dr Sarma s simple guide

Actinic keratosis (AK): Dr Sarma s simple guide Actinic keratosis (AK): Dr Sarma s simple guide Actinic keratosis is a very common lesion that you will see in your day-to-day practice. First, let me explain the name Actinic keratosis. It means keratosis

More information

Combining Approximate Front End Signal Processing with Selective. Reprocessing in Auditory Perception. Frank Klassner Victor Lesser Hamid Nawab y

Combining Approximate Front End Signal Processing with Selective. Reprocessing in Auditory Perception. Frank Klassner Victor Lesser Hamid Nawab y Combining Approximate Front End Signal Processing with Selective Reprocessing in Auditory Perception Frank Klassner Victor Lesser Hamid Nawab y Computer Science Department University of Massachusetts Amherst,

More information

IJISET - International Journal of Innovative Science, Engineering & Technology, Vol. 1 Issue 6, August

IJISET - International Journal of Innovative Science, Engineering & Technology, Vol. 1 Issue 6, August Prediction of blood sugar in people according to such inputs as age, simulation level, BMI, and diet by using of fuzzy control and Adaptive Nero-Fuzzy Inference System(ANFIS) Seyyed Amin Hosseini 1, Ali

More information

Available online at ScienceDirect. Procedia Computer Science 93 (2016 )

Available online at  ScienceDirect. Procedia Computer Science 93 (2016 ) Available online at www.sciencedirect.com ScienceDirect Procedia Computer Science 93 (2016 ) 431 438 6th International Conference On Advances In Computing & Communications, ICACC 2016, 6-8 September 2016,

More information

Time-to-Recur Measurements in Breast Cancer Microscopic Disease Instances

Time-to-Recur Measurements in Breast Cancer Microscopic Disease Instances Time-to-Recur Measurements in Breast Cancer Microscopic Disease Instances Ioannis Anagnostopoulos 1, Ilias Maglogiannis 1, Christos Anagnostopoulos 2, Konstantinos Makris 3, Eleftherios Kayafas 3 and Vassili

More information

Edge Detection Techniques Using Fuzzy Logic

Edge Detection Techniques Using Fuzzy Logic Edge Detection Techniques Using Fuzzy Logic Essa Anas Digital Signal & Image Processing University Of Central Lancashire UCLAN Lancashire, UK eanas@uclan.a.uk Abstract This article reviews and discusses

More information

Modifying the Classic Peak Picking Technique Using a Fuzzy Multi Agent to Have an Accurate P300-based BCI

Modifying the Classic Peak Picking Technique Using a Fuzzy Multi Agent to Have an Accurate P300-based BCI Modifying the Classic Peak Picking Technique Using a Fuzzy Multi Agent to Have an Accurate P3-based BCI Gholamreza Salimi Khorshidi School of cognitive sciences, Institute for studies in theoretical physics

More information

Artificial Intelligence For Homeopathic Remedy Selection

Artificial Intelligence For Homeopathic Remedy Selection Artificial Intelligence For Homeopathic Remedy Selection A. R. Pawar, amrut.pawar@yahoo.co.in, S. N. Kini, snkini@gmail.com, M. R. More mangeshmore88@gmail.com Department of Computer Science and Engineering,

More information

Original Research Article

Original Research Article CLINICOPATHOLOGICAL STUDY OF PAPULOSQUAMOUS SKIN LESIONS Chowdari Balaji 1, Metta Parvathi 2, Seeram Satish Kumar 3, Gunta Divya Lekha 4, Latchupatula Lavanya 5, Mantripragada Vidya Soundarya Lahari 6,

More information

Frequency Tracking: LMS and RLS Applied to Speech Formant Estimation

Frequency Tracking: LMS and RLS Applied to Speech Formant Estimation Aldebaro Klautau - http://speech.ucsd.edu/aldebaro - 2/3/. Page. Frequency Tracking: LMS and RLS Applied to Speech Formant Estimation ) Introduction Several speech processing algorithms assume the signal

More information

ARTIFICIAL NEURAL NETWORKS TO DETECT RISK OF TYPE 2 DIABETES

ARTIFICIAL NEURAL NETWORKS TO DETECT RISK OF TYPE 2 DIABETES ARTIFICIAL NEURAL NETWORKS TO DETECT RISK OF TYPE DIABETES B. Y. Baha Regional Coordinator, Information Technology & Systems, Northeast Region, Mainstreet Bank, Yola E-mail: bybaha@yahoo.com and G. M.

More information

Fuzzy Expert System Design for Medical Diagnosis

Fuzzy Expert System Design for Medical Diagnosis Second International Conference Modelling and Development of Intelligent Systems Sibiu - Romania, September 29 - October 02, 2011 Man Diana Ofelia Abstract In recent years, the methods of artificial intelligence

More information

Analysing the Performance of Classifiers for the Detection of Skin Cancer with Dermoscopic Images

Analysing the Performance of Classifiers for the Detection of Skin Cancer with Dermoscopic Images GRD Journals Global Research and Development Journal for Engineering International Conference on Innovations in Engineering and Technology (ICIET) - 2016 July 2016 e-issn: 2455-5703 Analysing the Performance

More information

A micropower support vector machine based seizure detection architecture for embedded medical devices

A micropower support vector machine based seizure detection architecture for embedded medical devices A micropower support vector machine based seizure detection architecture for embedded medical devices The MIT Faculty has made this article openly available. Please share how this access benefits you.

More information

Application of Tree Structures of Fuzzy Classifier to Diabetes Disease Diagnosis

Application of Tree Structures of Fuzzy Classifier to Diabetes Disease Diagnosis , pp.143-147 http://dx.doi.org/10.14257/astl.2017.143.30 Application of Tree Structures of Fuzzy Classifier to Diabetes Disease Diagnosis Chang-Wook Han Department of Electrical Engineering, Dong-Eui University,

More information

Available online at ScienceDirect. Procedia Computer Science 102 (2016 ) Kamil Dimililer a *, Ahmet lhan b

Available online at  ScienceDirect. Procedia Computer Science 102 (2016 ) Kamil Dimililer a *, Ahmet lhan b Available online at www.sciencedirect.com ScienceDirect Procedia Computer Science 0 (06 ) 39 44 th International Conference on Application of Fuzzy Systems and Soft Computing, ICAFS 06, 9-30 August 06,

More information

Copyright 2008 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, vol. 6915, Medical Imaging 2008:

Copyright 2008 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, vol. 6915, Medical Imaging 2008: Copyright 28 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, vol. 695, Medical Imaging 28: Computer Aided Diagnosis and is made available as an electronic

More information

Assessment of Reliability of Hamilton-Tompkins Algorithm to ECG Parameter Detection

Assessment of Reliability of Hamilton-Tompkins Algorithm to ECG Parameter Detection Proceedings of the 2012 International Conference on Industrial Engineering and Operations Management Istanbul, Turkey, July 3 6, 2012 Assessment of Reliability of Hamilton-Tompkins Algorithm to ECG Parameter

More information

International Journal of Computer Engineering and Applications, Volume XI, Issue VIII, August 17, ISSN

International Journal of Computer Engineering and Applications, Volume XI, Issue VIII, August 17,  ISSN International Journal of Computer Engineering and Applications, Volume XI, Issue VIII, August 17, www.ijcea.com ISSN 2321-3469 COMPARISON OF MAMDANI, SUGENO AND NEURO FUZZY MODELS FOR DIAGNOSIS OF DIABETIC

More information

Original Article. Palmoplantar Psoriasis versus Eczema: Major Histopathologic Clues for Diagnosis

Original Article. Palmoplantar Psoriasis versus Eczema: Major Histopathologic Clues for Diagnosis Iranian Journal of Pathology (2014) 9 (4), 251-256 251 Original Article Palmoplantar Psoriasis versus Eczema: Major Histopathologic Clues for Diagnosis Kambiz Kamyab Hesari, Zahra Safaei Naraghi, Azita

More information

A FUZZY LOGIC BASED CLASSIFICATION TECHNIQUE FOR CLINICAL DATASETS

A FUZZY LOGIC BASED CLASSIFICATION TECHNIQUE FOR CLINICAL DATASETS A FUZZY LOGIC BASED CLASSIFICATION TECHNIQUE FOR CLINICAL DATASETS H. Keerthi, BE-CSE Final year, IFET College of Engineering, Villupuram R. Vimala, Assistant Professor, IFET College of Engineering, Villupuram

More information

MRI Image Processing Operations for Brain Tumor Detection

MRI Image Processing Operations for Brain Tumor Detection MRI Image Processing Operations for Brain Tumor Detection Prof. M.M. Bulhe 1, Shubhashini Pathak 2, Karan Parekh 3, Abhishek Jha 4 1Assistant Professor, Dept. of Electronics and Telecommunications Engineering,

More information

A framework for the Recognition of Human Emotion using Soft Computing models

A framework for the Recognition of Human Emotion using Soft Computing models A framework for the Recognition of Human Emotion using Soft Computing models Md. Iqbal Quraishi Dept. of Information Technology Kalyani Govt Engg. College J Pal Choudhury Dept. of Information Technology

More information

Some skin conditions

Some skin conditions Some skin conditions Some skin conditions Acute Inflammatory Dermatoses Chronic Inflammatory Dermatoses Blistering (Bullous) Diseases Panniculitis Disorders of Epidermal Appendages -Urticaria -Acute eczematous

More information

The effects of the underlying disease and serum albumin on GFR prediction using the Adaptive Neuro Fuzzy Inference System (ANFIS)

The effects of the underlying disease and serum albumin on GFR prediction using the Adaptive Neuro Fuzzy Inference System (ANFIS) The effects of the underlying disease and serum albumin on GFR prediction using the Adaptive Neuro Fuzzy Inference System (ANFIS) Jamshid Nourozi 1*, Mitra Mahdavi Mazdeh 2, Seyed Ahmad Mirbagheri 3 ABSTRACT

More information

CARDIAC ARRYTHMIA CLASSIFICATION BY NEURONAL NETWORKS (MLP)

CARDIAC ARRYTHMIA CLASSIFICATION BY NEURONAL NETWORKS (MLP) CARDIAC ARRYTHMIA CLASSIFICATION BY NEURONAL NETWORKS (MLP) Bochra TRIQUI, Abdelkader BENYETTOU Center for Artificial Intelligent USTO-MB University Algeria triqui_bouchra@yahoo.fr a_benyettou@yahoo.fr

More information

Extraction of Blood Vessels and Recognition of Bifurcation Points in Retinal Fundus Image

Extraction of Blood Vessels and Recognition of Bifurcation Points in Retinal Fundus Image International Journal of Research Studies in Science, Engineering and Technology Volume 1, Issue 5, August 2014, PP 1-7 ISSN 2349-4751 (Print) & ISSN 2349-476X (Online) Extraction of Blood Vessels and

More information

RELEVANT MEDICAL TERMS AND CONDITIONS

RELEVANT MEDICAL TERMS AND CONDITIONS Acrokeratosis Paraneoplastica Paraneoplastic acrokeratosis, Bazex syndrome (also known as acrokeratosis paraneoplastica of Bazex and acrokeratosis neoplastica) is a cutaneous condition characterized by

More information

Epileptic Seizure Classification using Statistical Features of EEG Signal

Epileptic Seizure Classification using Statistical Features of EEG Signal International Conference on Electrical, Computer and Communication Engineering (ECCE), February 6-8,, Cox s Bazar, Bangladesh Epileptic Seizure Classification using Statistical Features of EEG Signal Md.

More information

Intelligent Edge Detector Based on Multiple Edge Maps. M. Qasim, W.L. Woon, Z. Aung. Technical Report DNA # May 2012

Intelligent Edge Detector Based on Multiple Edge Maps. M. Qasim, W.L. Woon, Z. Aung. Technical Report DNA # May 2012 Intelligent Edge Detector Based on Multiple Edge Maps M. Qasim, W.L. Woon, Z. Aung Technical Report DNA #2012-10 May 2012 Data & Network Analytics Research Group (DNA) Computing and Information Science

More information

A Fuzzy Expert System for Heart Disease Diagnosis

A Fuzzy Expert System for Heart Disease Diagnosis A Fuzzy Expert System for Heart Disease Diagnosis Ali.Adeli, Mehdi.Neshat Abstract The aim of this study is to design a Fuzzy Expert System for heart disease diagnosis. The designed system based on the

More information

Wavelet Neural Network for Classification of Bundle Branch Blocks

Wavelet Neural Network for Classification of Bundle Branch Blocks , July 6-8, 2011, London, U.K. Wavelet Neural Network for Classification of Bundle Branch Blocks Rahime Ceylan, Yüksel Özbay Abstract Bundle branch blocks are very important for the heart treatment immediately.

More information

Input-speci"c adaptation in complex cells through synaptic depression

Input-specic adaptation in complex cells through synaptic depression 0 0 0 0 Neurocomputing }0 (00) } Input-speci"c adaptation in complex cells through synaptic depression Frances S. Chance*, L.F. Abbott Volen Center for Complex Systems and Department of Biology, Brandeis

More information

Probabilistic Plan Recognition for Hostile Agents. Christopher W. Geib and Robert P. Goldman. Honeywell Technology Center

Probabilistic Plan Recognition for Hostile Agents. Christopher W. Geib and Robert P. Goldman. Honeywell Technology Center Probabilistic Plan Recognition for Hostile Agents Christopher W. Geib Robert P. Goldman Honeywell Technology Center Minneapolis, MN 55418 USA fgeib,goldmang@htc.honeywell.com Abstract This paper presents

More information

University of Cambridge Engineering Part IB Information Engineering Elective

University of Cambridge Engineering Part IB Information Engineering Elective University of Cambridge Engineering Part IB Information Engineering Elective Paper 8: Image Searching and Modelling Using Machine Learning Handout 1: Introduction to Artificial Neural Networks Roberto

More information

IPUS: An Architecture for the Integrated. Electrical, Computer, and. March 20, Abstract

IPUS: An Architecture for the Integrated. Electrical, Computer, and. March 20, Abstract IPUS: An Architecture for the Integrated Processing and Understanding of Signals Victor R. Lesser S. Hamid Nawab y Frank I. Klassner Computer Science Department University of Massachusetts Amherst, Massachusetts

More information

4. Pityriasis lichenoides

4. Pityriasis lichenoides Go Back to the Top To Order, Visit the Purchasing Page for Details usually more than 5 cm in diameter and accompanied by poikiloderma. Some but not all patients may develop mycosis fungoides (Fig. 22.35).

More information

Temporally asymmetric Hebbian learning and neuronal response variability

Temporally asymmetric Hebbian learning and neuronal response variability Neurocomputing 32}33 (2000) 523}528 Temporally asymmetric Hebbian learning and neuronal response variability Sen Song*, L.F. Abbott Volen Center for Complex Systems and Department of Biology, Brandeis

More information

CD30 + cells in benign inflammatory infiltrate of some dermatological diseases. Abstract. Latef M. El Balshy. Benha University-Benha, Egypt.

CD30 + cells in benign inflammatory infiltrate of some dermatological diseases. Abstract. Latef M. El Balshy. Benha University-Benha, Egypt. CD30 + cells in benign inflammatory infiltrate of some dermatological diseases 1 Asmaa M. El Refaeie, 1 Osama H. Abdel Salam, 1 Sherine H.Abd EL-Rahman and 2 Abdel Latef M. El Balshy. 1 Dermatology & Andrology

More information