Abstract-Electro-dermal response of any bio-medical system is the change in electrical properties of skin due to variation in physiological and psychological conditions. The change is caused by the degree to which a person's sweat glands are active. Psychological status of a person tends to make the glands active and this change the skin resistance. Drier the skin is, higher will be the skin resistance. This variation in skin resistance ranges from 5kΩ to 25kΩ. In the current work, a subject whose Galvanic skin response (GSR) is to be measured, has been shown/played a movie clipping, images or recorded audio signals. Depending upon the theme, emotion will be evoked in the subject. Due to the change in emotion, GSR varies. This variation in GSR is recorded for a fixed time interval. In the present work, a total of 75 subjects are selected. People from different age groups and social background, both male and female have been carefully considered. Data acquisition and analysis is carried out by using LabVIEW. The results obtained are convincing and follows the ground reality with a high level of accuracy. As the subject also gives the feedback about the emotions he/she experienced, the results obtained are validated.

Abstract-clinically, finger tip temperature (FTT) has been used as a sensitive index to monitor if a person is relaxed or not. When a person is relaxed, his/her vessels will be dilated and finger tip will be warmer. If one is anxious or tense, the vessels will be constricted and finger tip will be cool. FTT is a method of bio-feedback to tell the patient if he/she is in a relaxed condition. The subjects experiencing emotion in a higher magnitude differ from those who can regulate the emotions and such a factor is termed as emotional intelligence. In this paper, the subject whose FTT is to be measured is shown a video clipping or photographs or recorded audio signals are played. The subject, upon the influence of these, will respond and emotions are evoked. The change in FTT due to this evoked emotion is recorded for a finite interval of time and then analyzed. In this work, a total of 75 subjects are chosen. During selection of subjects, enough care is taken to include persons from different age groups, gender and social background. The data corresponding to FTT is acquired and processed using National Instrument's LabVIEW software and hardware tools. The results obtained are encouraging with high level of accuracy and repeatability. Since, the subjects also give feedback about the emotion experienced, the obtained results are validated.

The exponential rise in technology and allied applications has always revitalized academia industries to achieve more efficient and robust solution to meet contemporary demands. Surveillance systems have always been the dominant area which has grabbed the attention of the scientific community to enable real-time events or target's characterization to make timely decision process. Crowd behavior analysis and classification is one of the most sought, though complex system to meet at hand surveillance purposes. However, unlike pedestrian movement detection methods, crowd analysis and behavioral characterization require robust feature learning and classification. With this motive, in this paper, a highly robust model is developed by applying hybrid deep features containing statistical features of the gray-level co-occurrence matrix (GLCM) and transferable deep learning AlexNet high-dimensional features. In addition, to perform multi-class classification multifeed forward neural network model (MFNN) is used. Here, the inclusion of hybrid features of GLCM and AlexNet provides deep spatio-temporal feature information which helps in making optimal classification decision. On the other hand, the use of MFNN algorithm enables optimal multi-class classification. Thus, the combined model with hybrid deep features and MFNN achieves crowd behavior classification with 91.35% accuracy, 89.92% precision, 88.34% recall and F-measure of 89.12%. KeywordsCrowd behavior analysis and classification • Hybrid deep features • GLCM • AlexNet • Fully connected layer (FC) • Deep learning • Multi-feed forward neural network (MFNN) • F-measure This article is part of the topical collection "Data Science and Communication" guest-edited by Kamesh Namudri, Naveen Chilamkurti, Sushma S. J. and S. Padmashree.

This paper is dedicated to detecting and counting vehicles in day environment by using real time traffic flux through differential techniques. The basic idea used is variation in the traffic flux density due to presence of vehicle in the scene. In the present work a simple differential algorithm is designed and tested with vehicle detection and counting application. Traffic flux estimation will play vital role in implementing vehicle detection and counting scheme. Real time dynamic scene analysis has become very important aspect as the increase in video analysis. The technique developed is having simple statistical background. Dynamic selection of images from the sequence is implemented successfully in order to reduce the computation time. The designed technique are evaluated such a 20 different video sequences and weighed thoroughly with simple confidence measures. In the present work we have achieved real time analysis with normal video rate of 15 and 30 frames per second. And for vehicle count computation we are taking specific frame period (such as 2,5,10 etc), normal subtraction for vehicle count done on the basis of frame period. The result produced with this analysis is extremely good and beneficial in real time traffic control, detecting and counting vehicles in urban areas. MATLAB image processing tool box is explored to implement the technique. In the normal condition the average accuracy raised near to 95%.

No abstract