Informatics Publishing Limited

P. Gnanasivam ¹, S. Muttan ²

Affiliations
1 Agni College of Technology, Thalambur, Chennai, Tamilnadu 603103, IN
2 Centre for Medical Electronics, Department of ECE, College of Engineering, Anna University, Chennai, Tamilnadu 600025, IN

Abstract

Gender classification using fingerprint will be helpful in shortlisting the victims. In this paper, singular value decomposition (SVD) has been used for automatic fingerprint gender classification. The classification was achieved by extracting the spatial features of non-zero singular values obtained from the SVD of fingerprint images. The most robust K nearest neighbor (KNN) classifier has been used for gender classification. The evaluation of the system is carried out using internal database of 2200 fingerprints in which 1320 were male fingerprints and 880 were female fingerprints. The proposed method had produced an accurate identification of female gender to the maximum of 92.05% for the left hand little finger) and by average 83.30% for any other finger. Similarly, male gender is identified accurately to the maximum of 93.94% (for the right hand index finger) and an average 91.74% for other fingers. In addition, it was found that the success rate was higher for the male thumb fingers of male and reduces towards the small fingers. Similarly, the success rate in female small fingers is higher than the other fingers and reduces gradually towards the thumb finger. Detailed comparisons with earlier published results have been provided and our method offers better classification accuracy.

Keywords

Gender Classification, Singular Value Decomposition, Spatial Features, KNN Classifier.

Full Text

     

Punal M. Arabi ¹, S. Muttan ², T. V. Padmavathy ¹

Affiliations
1 Department of Electronics and Communication Engineering, R.M.K. College of Engineering and Technology, IN
2 Department of Electronics and Communication Engineering, College of Engineering, Anna University, Guindy, IN

Abstract

Cancer is the uncontrolled growth of abnormal cells;if not detected and treated at the early stage cancer would become fatal. Early detection of the disease increases the survival rate. Though there are several diagnostic methods, each method is having its own merits and demerits. In this paper, a method of obtaining an active thermo gram by irradiating the patient’s breast twice, thrice using a microwave source of 2450 MHz and allowing them to cool naturally after every radiation is proposed. Results of the experiments conducted using phantom models show the temperature difference between the cancerous and normal breast tissues is increased by the first irradiation considerably;the second irradiation further elevated the temperature difference between the normal and breast tissues. The third irradiation did not have any impact. Results obtained show that both the double irradiation technique and triple irradiation technique produce a temperature difference of 6.75°C between the normal and cancerous breast tissues for a cancer tumor which produces a temperature difference of 1°C between normal and cancerous tissues by passive radiation. Hence there is a marked intensity variation between the normal and cancerous tissues of the breast in thermogram are produced by double irradiation and triple irradiation which makes the early diagnosis of breast carcinoma possible. Since even the third irradiation did not have any impact on the temperature difference between the normal and cancerous breast tissues multiple irradiations is not superior to double irradiation for early diagnosis of breast carcinoma. A thermogram of normal breast is taken as a base line image to simulate the images that would be produced by the proposed method; MATLAB7.1 is used for simulating 38°C, 41°C, 43.75°C thermal images. Thermal images for 37°C, 38°C, 39°C, and 43.75°C were taken using Thermal images (FLIR system-Model FLIR i5-Sweden).

Keywords

Breast Carcinoma, Double Irradiation, Multiple Irradiation, Early Diagnosis, Image Enhancement, MATLAB7.1, Microwave, Thermal Imaging.

Full Text

     

Punal M. Arabi ¹, S. Muttan ², T. V. Padmavathy ¹, D. Madhumalar ³

Affiliations
1 Department of Electronics and Communication Engineering, R.M.K. College of Engineering and Technology, IN
2 Department of Electronics and Communication Engineering, College of Engineering, Guindy, Anna University, IN
3 Department of Information and Technology, R.M.K. College of Engineering and Technology, IN

Abstract

Breast cancer becomes fatal if not detected at the early stage. Physical and psychological trauma could be avoided to a greater extent by early detection and treatment; Survival rate is also increased by this. There are many techniques presently used to detect breast cancer with their own merits and demerits. In this paper a method is described for early breast cancer detection. Phantom models irradiated by suitable FIR, Microwave (2450 MHZ) sources are used to find out the heating, cooling characteristics of normal and cancerous breast tissues. From the results obtained, images are simulated and proved that earlier diagnosis is possible by the proposed method. Thermo grams taken using a thermal imager (FLIR i5) at the resulting temperatures also proved the early diagnosis of breast carcinom is possible by the proposed method.

Keywords

Breast Carcinoma, Early Diction Hybrid Irradiation, Microwave and Fir, Matlab 7.1, Flir Thermal Imaging Camera.

Full Text

     

B. Suresh Chander Kapali ¹, S. Muttan ², K. Balasubramanian ³

Affiliations
1 Department of Biomedical Engineering, Vel Tech Multi Tech Dr.Rangarajan Dr. Sankunthala Engineering College, Chennai, Tamil Nadu, IN
2 Department of Electronics and Communication Engineering, College Of Engineering, Guindy, Chennai, Tamil Nadu, IN
3 Department of Physiology, Stanley Medical College, Chennai, Tamil Nadu, IN

Abstract

Myocardial Reinfarction means a subsequent heart attack after a Myocardial infarction. Myocardial infarction commonly known as heart attack, occurs when the blood supply to a part of the heart is interrupted causing some myocardial cells to die. This is most commonly due to occlusion (blockage) of a branch of coronary artery, which is due to deposition of lipids (like cholesterol) in the intimal layer of the coronary blood vessels The aim of this project is to record the ECG sequentially from Lead–II electrocardiogram (ECG). Then recorded ECG is analyzed using heart rate variability software. So the objective of my project is to find the flexibility of the heart and to confirm whether the patient may or may not suffer from subsequent attack (Reinfarction) in conditions like hypertensive Cardiomyopathy, alcoholic cardiomyopathy, diabetes induced Cardiomyopathy and Valvular Heart Diseases. The parameters monitored are analog signals in nature. They are amplified, filtered, and converted into a digital format for further processing by microcontroller or embedded unit. Then with the help of the software further analysis is done.

Keywords

Heart Rate Variability (HRV), Coronary Artery, Cardiomyopathy, Reinfarction, Autonomic Nervous System (ANS).

Full Text