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

The objective of this paper is to construct a model to predict stock value movement using the opinion mining and clustering method to predict National Stock Exchange (NSE). We have used domain specific approach to predict the stocks from each domain we have taken some stock with maximum capitalization. Proposed Method is Not at all like past methodologies where the general states of mind or sentiments are considered, sentiments of the particular subjects of the organization or sector are fused into the stock prediction model. Topics and related opinion of shareholders are automatically extracted from the writings in a message board by utilizing our proposed strategy alongside isolating clusters of comparable sort of stocks from others using clustering algorithms. Proposed methodology will give us two output set i.e. one from sentiment analysis and another from clustering based prediction with respect to some specialized parameters of stock exchange. By examining both the results an efficient prediction is produced. In this paper stocks with maximum capitalization within all the important sectors are taken into consideration for empirical analysis. © 2016 IEEE.

World University root node

Engineering and Technology

Proceeding - IEEE International Conference on Computing, Communication and Automation, ICCCA 2016

Stock market prediction using hybrid approach

In our day-to-day life Emotions play an vital role. They help in identifying a human state of mind. Information about the human state of mind can significantly help in human-machine interaction and brain-computer interface. Some of the existing researchers have used speech, text, gesture or facial expressions for emotion recognition. However, these factors vary across culture and nation. Because of which, it is difficult to detect emotions more accurately. Hence, present work considers EEG signals for emotion recognition which not only ignores external factors but also helps to detect real emotions arising directly from our brain. A benchmark DEAP (Dataset for Emotion Analysis using Physiological signals) dataset is used for emotion investigation. A novel feature extraction technique called Frequency Cepstral Coefficient (FCC) is proposed to extract features from DEAP dataset. FCC technique is compared with Kernel Density Estimation (KDE) on DEAP dataset for feature extraction. These extracted features are then classified into two emotional states-happy and sad using K-Nearest Neighbor (K-NN) classifier. The selection of most appropriate and reliable method of feature extraction greatly helps for accurate classification. Number of experiments was conducted to evaluate the efficiency of feature extraction techniques. The experimental results show that KDE gives 80% accuracy and FCC outperforms it by achieving 90% accuracy on DEAP. © 2017 IEEE.

2017 Innovations in Power and Advanced Computing Technologies, i-PACT 2017

A novel approach for analyzing human emotions based on electroencephalography (EEG)

This paper emphasis on different hierarchical routing protocols in wireless sensor network. The Clustering approached is used in LEACH protocol for better communication with energy saving. The Sectoring Scheme is used in MARS approach for dividing the sensor network into different sectors. It improves reliability of an application or network. The working of both the approaches is explained in algorithmic form. The mathematical modeling of LEACH and MARS protocol is discussed.

Proceedings - International Conference on Global Trends in Signal Processing, Information Computing and Communication, ICGTSPICC 2016

Modeling of clustering and sectoring approach in WSN

Agriculture growth is the key component in socioeconomic growth of our country due to liberalization and globalization. Gradually with significant increase in technology, advanced telecommunication services assist plant disease treatment at remote locations. Earlier systems were designed for either monocot or dicot plant family disease detection. The paper proposes an integrated approach for monocot and dicot plant disease detection and treatment along with precautionary measurement through smartphone and image processing techniques. The paper mainly focuses on plant disease detection technique based on integrated approach of K-means segmentation algorithm and SVM Classifier. The proposed and developed approach gives 83 % accuracy for plant diseases recognition. © Springer Science+Business Media Singapore 2017.

Advances in Intelligent Systems and Computing

Agri-guide: An integrated approach for plant disease precaution, detection, and treatment

In the era of Big Data where voluminous data is handled on a very large scale, traditional decision trees might be very time consuming and sometimes might even fail to work owing to its dataset size. Handling Big Data can also be a costly affair because of its high demand for memory and other hardware requirements. To the end of this paper, we have chosen a decision tree algorithm named Very Fast Decision Tree (VFDT) after comparing it with other decision tree algorithms like ID3 and C4.5. We have also proposed an algorithm for implementing VFDT on a Distributed Environment called Hadoop. This implementation can form a base for a large number of applications for handling Big Data. We have replaced the serial execution of VFDT algorithm by a series of Map and Reduce functions. We have also conducted an extensive analysis on various datasets which have proved our proposed algorithm to be more efficient in terms of time compared to the other existing decision tree models.

Proceedings - 2nd International Conference on Computing, Communication, Control and Automation, ICCUBEA 2016

Very fast decision tree (VFDT) algorithm on hadoop

In this paper, we explain a cross platform mobile expert system for agriculture task scheduling, which will be developed to help Indian farmers. In spite of so many reforms and initiatives introduced by the government of India in the past decades, the quality of information provided to the marginalized farmer is uneven. Dangerous issues that infect Indian farming at hand are the data shortage and high risk because of the volatile nature of the factors involved, like, natural weather change. This paper introduces an advisory, information and financial system available on mobiles, which is designed for farmers to help them stay on track, avoid troubles, and receive all the latest and updated information, government schemes and strategies related to the field of agriculture. Information System has tools forecasting schedule that creates a systematic schedule for farmers for crop cultivation based on the weather predictions. This proposed idea is to ensure that the farmer plan their resources properly and also suggest a sequence of tactical decisions throughout a production cycle. The advisory system will enable its users to receive real-time and interactive advices and alerts on crop. Alerts would include phase of the plantation, weather conditions, diseases and nutrition. Farmers will also receive regular weather bulletins to support on-farm decision-making. Finance related tools, helps the farmer to keep track and control his financial income and expenses. It helps the farmer to get better control of his financial condition, productivity. In turn it will help him to increase profitability and fulfill their long-term goals. This paper is a start of a complete solution for addressing Indian farmer's needs, which would help them grow systematically. © 2016 IEEE.

A cross platform mobile expert system for agriculture task scheduling

Software testing is required to detect the faults and to ensure the quality of the software under development. Usually, test suites are used to evaluate the software system during the software development cycle. But often test suites contain more redundant test cases due to overlapped test objectives. So, the test-suite reduction is an important step to reduce the number of test cases so as to satisfy the entire objectives with less computational cost. Literature presents different methods to select the suitable test suites of optimal subsets for regression testing. Accordingly, this research aims to develop an effective test suite reduction approach for regression testing. The proposed algorithm (GTAP) is newly designed using TAP measure and greedy search algorithm. This algorithm uses TAP-measure which is specially developed for measuring the importance of test cases. The performance of the GTAP algorithm is evaluated using four different evaluation metrics with eleven subject programs available in SIR repository. From the experimentation, the average performance of the proposed GTAP algorithm in all the programs is 93.07% which is higher than the DIV-GA which obtained the value of 90.27%.

Fulltext

International Journal of Intelligent Engineering and Systems

A Cost-Aware Test Suite Minimization Approach Using TAP Measure and Greedy Search Algorithm

Driving an automobile taxes the driver in almost all of his sensory systems and uses his deduction power to the fullest. The mental state of the driver is vital to safe and correct driving. This paper focuses on identifying the emotional state of the driver based on his interactions with the automobile while driving and inferring when the driver is in an unpleasant state of mind. The driver's actions are monitored and driver profiles are generated which lead to identifying his usual behavior. If the behavior of the driver, based on his actions and interactions with the automobile, implies he is in a negative state of mind, we propose to deviate his mind from negative to positive emotions. For this we have instrumented a system which is both single mode and multimodal to alert the driver with includes feedback in the form of auditory, haptic and visual. © 2016 IEEE.

2016 2nd International Conference on Contemporary Computing and Informatics (IC3I)

Automobile driver profiling: Infering emotions through actions for safe driving

While browsing the web, the meaning and importance of time changes as perspectives change. From the communications perspective, speed to data transmission matters. The network perspective webpage load times matter. Search Engine Optimisation perspective focuses on dwell time, total time spent on each webpage from the corpus of webpage's visited. From an average user's perspective, the initial few seconds of a webpage being visited is critical to determine whether the user will stay on the webpage or leave the webpage. The probability of the user leaving the webpage is very high during these first few seconds. After the user stays on the webpage, determining whether it is relevant to the user, is he actually engaged on the content represented on the webpage during the period of the visit is important too. Higher engagement indicates the user has a higher chance of returning to the webpage. This paper tries to address another issue of time, and intends to determine, whether the time spent by a user on a webpage actually indicates its relevancy to the user. © 2016 IEEE.

Time alone is not the clear indicator of relevancy

Selfie is the act of taking self portrait through the front camera of the mobile. By visualizing the captured image one can identify the details regarding the image such as number of objects, location and much more. By the method of object recognition in the image we can identify whether the image taken is a selfie or not. For this we should first segregate both the foreground and background details from an image. From the details of foreground one can identify the object (i.e., the person taking the selfie) and from the background we can tell about the location. Using various object recognition methods such as exhaustive search, segmentation, selective search, Gaussian mixture model the information regarding objects, foreground and background can be detected. And further the value of foreground and background will be compared with a certain threshold value and according to the obtained result can recognized whether an image is a selfie or not. In this paper we are presenting an approach which can be used to detect an image is a selfie. © 2019, Springer Nature Singapore Pte Ltd.