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

Engineering and Technology

With the recent advances in machines technology, there is revolution in healthcare industry also. Thus, it gave rise to the concept of Electronic Health Record (EHR) which stores patients demographics, lab tests results, medical history, habits etc. in electronic form. EHR is voluminous data which is difficult to store, maintain or alter. To provide extended life for people, health risk prediction model using this EHR is formulated in this work. Feature Selection is used to select only associated or relevant data from the dataset. Logistic Regression is used with improved loss functionality parameter which increases the accuracy, response time and performance of the system. Representation Learning enables formation of feature vector of the selected features thus calculating their scores. Further, risk prediction is performed by the neural network model. Deep Neural Network (DNN) is used with many hidden layers containing activation functions. Transfer learning is used to avoid re-Training of the whole system every time new data enters the model. Dataset used here is of hypertension. EHR dataset is also synthetically created for analysis. © 2018 IEEE.

World University root node

School of Computer Engineering & Technology

Proceedings of the 2nd International Conference on Computing Methodologies and Communication, ICCMC 2018

Improved Automatic Feature Selection Approach for Health Risk Prediction

We are living in the era where the video contents are largely available on the internet and hard disk drives. Since the duration of videos ranges from few minutes to many hours, the progression of a system for decisive content classification, browsing, indexing, retrieval and storage become essential. Also, with the advancement of the digital video technologies, huge chunks of video data are producing every day. For processing these data, video summarization plays an important role, which is a process of generating a synopsis of the video. In this paper, we present application scenarios of video summarization and some of the techniques which fit in a particular application. With fast evolution of video technology, nowadays many new multimedia applications are available. We categorize different applications of video summarization and methods for generating the summary of a video. In this paper, we introduce different types of videos and need of summarization for each type of video. © 2018 IEEE.

Proceedings of the 2nd International Conference on Electronics, Communication and Aerospace Technology, ICECA 2018

A Study on Application Scenario of Video Summarization

We proposed a system to provide a recommendation system which will generate the user interested colleges list. This will be done by asking few questions related to the college like-college infrastructure, campus life, placement, sports and cultural activities. Information seeker will give ratings to the questions according to his interest rate. The list of college will be stored in the dataset for calculating the accuracy and precision of the system. Also the students will be giving feedback to the system for their performance. © 2017 IEEE.

International Conference on Advances in Computing, Communication and Control 2017, ICAC3 2017

Analysing recommendation of colleges for students using data mining techniques

Eye diseases are burning diseases nowadays. Eye illness identification is one of the basic issues in computer vision. Three such diseases have been considered in this paper, cataract, conjunctivitis, and stye. A cataract occurs once protein builds up within the lens of an eye and makes it cloudy which prompts the decrease in vision. Conjunctivitis or pink eye is a condition where the conjunctiva of the eye inflamed by an infection or by an allergic reaction. And the third sort of illness i.e. stye is an infection that causes a young red., painful lump near the edges of the eyelid. Generally., an eye doctor uses a slit lamp camera to find these sicknesses. But because of lack of specialist eye doctor and slit lamp camera in rural areas are the main problem of the belated in detecting those diseases. In this paper first, the captured eye images collected from different patients and processed for improvement. Then HOG used for detection of the feature vector. Finally recognition of disease done with the assistance of minimum distance classifier. This planned method is economical., computationally quick and price very low. The proposed system result with average accuracy is 96.5 percent in classification. © 2017 IEEE.

School of Electronics & Communication Engineering

2017 International Conference on Computing, Communication, Control and Automation, ICCUBEA 2017

Histogram of Oriented Gradient based Automatic Detection of Eye Diseases

The pictures taken in awful climatic conditions will adversely influence the picture quality. Fog and haze degrades the picture standard, air-light lessens whiteness of the image and attenuation lessens its contrast. This paper provides colour attenuation prior for haze removal of the image. The main aim is to solve the problem of reduced visibility by excellent image processing strategy and the purpose is to improve the quality of images that lack the shading, complication and depth when perceived by the human eye. By creating a straight model for display the scene extent of the hazy image, we can easily determine the transmission and resume the scene radiance via the atmospheric scattering model. © 2018 IEEE.

2018 International Conference on Information, Communication, Engineering and Technology, ICICET 2018

Single Image Haze Removal using Image Processing Algorithms

Cancer has been plaguing the society for a long time and still there is no certain treatment; especially if detected in later stages. That is why early detection and treatment of cancer is of utmost importance. Acute lymphoblastic leukemia is a type of blood cancer which is known to progress very rapidly and prove fatal if there is a delay in detection. Detection of this type of cancer is carried out manually by observing the blood samples of patient under microscope and conducting various other tests. This process may produce undesirable drawbacks: slowness, nonstandardized accuracy since it depends on examiner's / pathologist's capabilities and fatigue due to work overload can cause human errors in detection. A few automated systems for detection of Acute Lymphoblastic Leukemia (ALL) have been proposed which involve extracting features from blood images using MATLAB and implementing different classifiers to produce results, which gave remarkable accuracies though not enough for practical usage. Our proposed system is further improving the classification accuracy. It uses openCV and skimage for image processing to extract relevant features from blood image and not just sheer number of features and further classification is carried out using various classifiers: CNN, FNN, SVM and KNN of which CNN gives the highest accuracy of 98.33%. CNN and FNN are written using TensorFlow framework. The accuracies obtained by other classifiers: FNN, SVM, and KNN are 95.40%, 91.40% and 93.30% respectively. © 2018 IEEE.

2018 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018

Identification of Acute Lymphoblastic Leukemia in Microscopic Blood Image Using Image Processing and Machine Learning Algorithms

The rate of depression is growing at an alarming rate. A study found that people are more likely to open up to a talking computer than a human. The aim of this paper is to motivate a person going through low phase of his life and to avoid ill-effects of depression. We propose a chatbot that can enable positivity boosting conversation with the user. The chatbot will personalize its replies as per user to keep the conversation engaging. It is made emotionally supportive by training it over a motivating dialogue corpus. The corpus is extended with the users historical chat data from social media platforms. Tensorflow framework and high power GPU is required by server for training. The advantage of such a system is that instead of reaching a phase requiring a visit to a psychiatrist, an online free service will reach many people, will mediate ill-effects of depression and contribute to the betterment of society.

International Journal of Pure and Applied Mathematics

User Adaptive Chatbot for Mitigating Depression

The Internet is a powerful medium for accessing online documents but it is not a tool for locating or organizing information. Tools like search engines assist users in locating information. The web pages can present different and varied information depending on the characteristics of its content. The use of a website user classifier can help us in providing safety to the websites from malign users. The uncontrolled nature of web content presents additional challenges to classifying the website users, but the interconnected nature of hypertext also provides features that can assist the process. This paper analyses the feasibility of various classifiers for the purpose of classifying website visitors and studies their precision. In this sense, Data Mining techniques are of great importance and will be used to construct the classifiers. The main research area is for computer programs to automatically learn to recognize complex patterns and make intelligent decisions based on data. This paper also focuses on supervised learning aspect of machine learning. The problem we have set out to solve by this survey is to find the best classification algorithm to design a system to categorize website visitors into a set of pre-defined classes. With the continued growth of web application traffic, an increasing amount of sensitive data is exposed to potential theft, security vulnerabilities, and multi-layer attacks. An optimal classification algorithm will enable us to provide significant performance advantages over our competition. By implementing an always-on defence we can successfully identify and protect against automated layer DDoS attacks, web scraping, and brute force attacks.

A Study of Classification Algorithms for Categorizing Website Users using Machine Learning

Cloud computing is a technology that allows the end-users to access the network through a shared area of resources. As the demand for the cloud computing increases, vulnerabilities in the service provision also increase. EDoS is one of the attacks that take over the provider, financially affecting the various organizations which use the cloud data. This paper utilizes fuzzy entropy and lion neural learner (FLNL) for the classification of cloud users to mitigate EDoS attacks in the cloud. This technique includes a training phase, which creates a log file using various parameters and then transforms the features into database considering certain key features. There are two important stages in this classification approach: feature selection and classification. Here, the fuzzy entropy function is utilized for feature selection which effectively selects useful features without information loss. The classification is performed using lion neural learner (LNL) which incorporates Lion algorithm (LA) into the neural network and uses Levenberg–Marquardt (LM) algorithm. The experimental results finalize that the proposed FLNL is effective with 89% precision, 78% recall, and 83.13% of f-measure compared with the existing Naïve Bayes (NB), Neural Network+Back Propagation (NN+BP), and Neural Network+Levenberg–Marquardt (NN+LM).

International Journal of Modeling, Simulation, and Scientific Computing

Fuzzy entropy and lion neural learner for EDoS attack mitigation in cloud computing

Cloud Computing is a newly emerged technology. It is a solution for next generation of IT enterprise which enables ubiquitous, on demand and convenient access to pool of configurable resources. Along with reduced cost & complexity of applications or resources, cloud enables flexibility and scalability making it one of the exciting technologies. Virtualization is the major paradigm of cloud technology making it robust and flexible. It creates virtual versions of device or resource known as virtual machines which are shared amongst the available users. In virtual machines, hypervisor is a key element that is more prone to attacks. So, to protect these hypervisors and virtual machines a technique known as Intrusion Detection System (IDS) is used on large scale. IDS defend the attacks mostly occurring on virtual machines. Hence Virtual Machine Hypervisor based Intrusion Detection System (VMHIDS) is developed that can protect both hypervisors as well as virtual machines. This helps in early detection of attacks and can take preventive measures as soon as possible. In IDS, Hybrid IDS is chosen which can detect known and unknown class of attacks. It leads to better performance and efficiency of the system.