MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

School of Computer Engineering & Technology

Engineering and Technology

World University root node

Asian Journal For Convergence In Technology (AJCT) ISSN-2350-1146

Mood Detection through Aesthetic Assessment of Videos using Deep Learning

Emotion analysis is very significant from the perspective of many applications like E-learning, cognitive assessment, driver alert system, pain monitoring system, healthcare services, interactive TV, animation etc. Outcome of the work is depicted in the form of emotion profile which is defined as graphical representation of the degree of presence or absence of all the universally accepted seven emotions on a single scale. This simple but unique representation helps in determining the presence of complex/naturalistic emotions. Complex emotions represents the emotional state of a person when he/she is able to feel and express more than one emotions simultaneously at the time of observation. Emotion analysis through facial expressions is experimented on JAFFE and MIST Database-a locally created context specific database of images. Images of the subjects under study are captured and experimented for all seven universally accepted emotions and depicted in the form of emotion profiles. Emotions are categorized as neutral, positive and negative for MIST database and in seven categories of emotions like happy, surprise, anger, sad, disgust, fear and neutral for JAFFE database. Average accuracy obtained as 91.31% for MIST database and 93.84% for JAFFE Database. FPR-false positive rate and FNR-false negative rate, values for JAFFE database are 6.38% and 6.62% respectively. FPR and FNR values for MIST database are 8.18% and 8.60% respectively. Emotion recognition time for JAFFE database 1.108 sec and for MIST database 1.392 Sec. These performance parameters especially the accuracy more than 90% which is at par with the research results published in renowned journals in this domain makes this work qualify to be used for various applications. Analysis of complex emotions is typically useful for the professionals working in the field of Human resource, clinical psychology, cognitive analysis etc. More accurate emotion recognition is still challenging and open research problem.

Journal of theoretical and Applied Information Technology

Hybrid Approach for Facial Cues Based Emotion Profile Generation

Feature extraction of images are crucial in image retrieval systems. Many approaches are stated and proved by researchers for image feature extraction and processing. Research is being done from low-level feature extraction toward high-level feature extraction. This paper discusses the feature extraction from the DFT transformed color images in multiple color planes. DFT image transform provides effective way to differentiate the image textures. For dimensionality reduction statistical parameters such as kurtosis, standard deviation, and variance are used for feature vector generation. Euclidian distance is used in the proposed approach. Four different types of feature vectors are created and tested for each image class. The images are retrieved based on the image pixel values of DFT phase information and DFT magnitude information of different color spaces like RGB, YIQ, HSV, and YCbCr similar to that of image class. Image retrieval performance of the proposed approach is compared for database of 1000 images of ten different categories. Precision of image retrieval is above 60% for all classes and more than 80% for some of the image classes. © Springer Nature Singapore Pte Ltd. 2019.

Advances in Intelligent Systems and Computing

Color image retrieval using statistically compacted features of DFT transformed color images

Breast cancer is a very aggressive type of cancer with a very low median survival. Today the deaths of women in the age group 15-55 are increasing because of malignant cells are increasing in breast. For the death of women it is the main cause. So, the possibility of improvement is only the early diagnosis of patients. Machine Learning (ML) techniques can assist the physicians by expanding tools for detection at initial stage and analysis of breast cancer thus increasing the probability of patient's survival [1]. At present, mammography is the best imaging strategy utilized by radiologist for screening breast tumours. In this paper, author proposes a system using different classification method like Support Vector Machine (SVM), Naive Bayes, Decision tree and MLP (Multi-Layer Perceptron) for early detection of cancer. Propose system extracts the texture based features and shape based features using LBP, GLCM, Otsu, Compactness, Fourier Transform. The main focus of the presented work is on application of MLP for breast cancer classification. In addition medical images data has been used to improve accuracy. Proposed system will do the comparative study between both datasets by extracting the feature with and without removing pectoral muscles. © 2019 IEEE.

2019 Global Conference for Advancement in Technology, GCAT 2019

Classification Methods to Improve Performance in Breast Cancer Screening

Vehicle safety is the most important strategy used to address the international and national road casualty reduction targets to achieve a safer road traffic system. Traffic accidents are mainly caused by human mistakes such as lack of concentration, misbehavior and distraction. The vision based lane detection system is a valuable way to protect single vehicle from accident. In this paper a lane detection method for detecting the lanes accurately is proposed. Also the canny algorithm is determined as the edge detection algorithm and Hough transform method is selected as the efficient way to detect lanes. To meet the real requirement, the region of interest (ROI) is defined to reduce noise properly for accurate results and to enhance the processing speed.

Fulltext

International Journal of Advanced Trends in Computer Science and Engineering

Straight and curve lane detection system for car safety using hough transform and sobel operator

Smart captcha to provide high security against bots

Due to complex monitoring systems in various business domains, secrecy and privacy has become critical issue for movable resources including human being. In a mobile object monitoring systems, balancing computing resources and quality of privacy is required. Objects can be mobile devices, users or any other moving entity. This work is presented in wireless sensor network environment. Earlier work does not consider presence of mobile objects in 3D space. We can observe that objects also carry Z axis in city area where high rise buildings are present. Earlier monitoring applications are mainly designed in two dimensional space to protect privacy. Our novelty is to suggest and design mechanism that reflect Z position (height) of mobile objects for protecting privacy. While calculating cloaking area and counting of objects, height is also considered as third dimension. This results in better location privacy as compared to the privacy delivered by the scheme that considers two dimensional space. We have presented performance, communications cost, privacy strength of modified 3D quality algorithm and 3D resource algorithm. Moreover, we present novel containment resolution algorithm that handles duplicate counting due to 3D presence of wireless system and mobile devices.

iJIM International Journal: Interactive Mobile Technologies

Privacy Aware Monitoring of Mobile Users in Sensor Networks Environment

Dementia is one of the most prevalent conditions faced by the elderly caused by specific brain cell damage. Various effects of dementia include a loss of memory, reduction in problem solving ability, analytical skills, and decision making capability. Few systems have been developed for the early detection of dementia. Existing systems depend largely on hardware e.g. sensors, gateways. Factors like maintainability and sustainability compromise the efficiency of such systems. This paper presents a novel approach towards the early detection of dementia and aims at eliminating some of the challenges posed by these systems. It also provides a comparati ve study of the cognitive abilities of healthy old-age people and those afflicted by dementia. © 2019 IEEE.

2019 IEEE 5th International Conference for Convergence in Technology, I2CT 2019

Semi-Invasive System for Detecting and Monitoring Dementia Patients

Recent advancements in technology have made available a variety of image capturing devices, ranging from handheld mobiles to space-grade rovers. This has generated a tremendous visual data, which has made a necessity to organize and understand this visual data. Thus, there is a need to caption thousands of such images. This has resulted in tremendous research in computer vision and deep learning. Inspired by such recent works, we present an image caption generating system that uses convolutional neural network (CNN) for extracting the feature embedding of an image and feed that as an input to long short-term memory cells that generates a caption. We are using two pre-trained CNN models on ImageNet, VGG16 and ResNet-101. Both the models were tested and compared on Flickr8K dataset. Experimental results on this dataset demonstrate that the proposed architecture is as efficient as the state-of-the-art multi-label classification models. Experimental results on public benchmark dataset demonstrate that the proposed architecture performs as efficiently as the state-of-the-art image captioning model. © Springer Nature Singapore Pte Ltd. 2020.

International Conference on Machine Intelligence and Signal Processing

Generation of Image Captions Using VGG and ResNet CNN Models Cascaded with RNN Approach

Various operations performed by waiters like starting from taking orders till delivery of food/menu to the customer, also billing by cashier made manually. Due to manual process and paperwork may cause time delay, ignorance of customer, errors in billing leads to dissatisfaction of customers. As in today's digital era, customers expect high quality, smart services from restaurant. So to improve quality of service and to achieve customer satisfaction, we proposed improvised E-Menu Recommendation System. This system can build e-reputation of restaurant and customer community in live. All orders and expenses are stored in database and give statistics for expenses and profit. The proposed recommender system uses wireless technology and menu recommender to build improvised E-Menu Recommendation System for customer-centric service. Professional feels and environment are provided to the customers/delegates with additional information about food/menu by using interactive graphics. Outcomes of experimental are obtained by comparing results of two data mining algorithms Apriori and FP-growth which have practical potential in providing customer-centric service.