College of Engineering, Pune

About: College of Engineering, Pune is a based out in . It is known for research contribution in the topics: Computer science & Sliding mode control. The organization has 4264 authors who have published 3492 publications receiving 19371 citations. The organization is also known as: COEP.

Decision Making in Positive and Negative Prospects: Influence of Certainty and Affectivity

Abstract: This study examines (a) whether the individuals are risk averse in positive prospects and risk seeker in negative prospects and (b) whether certainty and affectivity determine the choices in prospects. Four hundred undergraduate and graduate students of the Indian Institute of Technology Kharagpur participated in this study. Standard questions were used to assess the responses to prospects, certainty in choice, and the positive and negative affectivity. Findings suggest that in positive prospects, individuals are risk averse with the availability of a certain option and risk seeker with availability of two uncertain options of nearly equal value. In contrast to the preference for gain in positive prospects, individuals prefer to avoid loss and are risk seeker in negative prospects. They express more confidence in choices preferred by the majority. The interactive effects of certainty and affectivity determine choices. Certainty interacting with low positive affectivity influenced the decision in two problems and high certainty interacting with high negative affectivity influenced the decision in six problems. Although certainty indicating information possession and processing is a consistent predictor of choices, neither affectivity nor the interaction of affectivity with certainty do so.

Transforming the Know Your Customer (KYC) Process using Blockchain

Abstract: A major yet trivial problem in the banking industry right now is how tedious and costly the traditional Know- Your-Customer(KYC) process is. The process is also tiresome for customers as they need to undergo the same process for each bank or financial institution with which they intend to work. Personal experiences of people dictate the cumbersome nature of the process, thereby demanding an efficacious alternative. Through this paper, we intend to do exactly that. We propose a new solution based on Distributed Ledger Technology or Blockchain technology, which will reduce the traditional KYC verification process cost for Institutions and cut short the general time line of the completion of the process while making it smoother for the customers. Major enhancement in our solution over the conventional methods is that the whole verification process is conducted only once for each customer, irrespective of number of institutions he or she wishes to be linked to. Also, since we are using the DLT, verification results can be securely shared with the customers thereby increasing transparency. Following this approach, we developed a Proof of Concept (POC) with the Ethereum API, websites as endpoints and an android app as front office; realising the feasibility and effectiveness of this approach. All in all, this approach improves customer experience, reduces cost overheads, and increases transparency in the process of onboarding a customer.

Experiments on detection of Denial of Service attacks using Naive Bayesian classifier

Abstract: Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks can result in huge loss of data and make resources unavailable for legitimate users With continuous growth of Internet users and traffic, the importance of Intrusion Detection System (IDS) for detection of DoS/DDoS network attacks has also grown Different techniques such as data mining and pattern recognition are being used to design IDS Naive Bayesian is a widely used classifier for design of IDS This paper evaluates variation in performance of Naive Bayesian classifier for intrusion detection when used in combination with different data pre-processing and feature selection methods Experimental results prove that accuracy of Naive Bayesian classifier is improved and performs better than other classifiers when used in combination with Feature Selection and data pre-processing methods

Experimental study on productivity of modified single-basin solar still with a flat plate absorber

Abstract: Solar still is an apparatus which uses solar energyto producedistilled water from saline water This can be used in remote areas effectively wherein electricity is not available The output from a conventional single basin solar still is found to be very low Hence research is required to increase the productivity of the conventional solar still This work is an attempt to increase the productivity of solar still A flat mica plate is embedded in the conventional solar still to augment evaporation of the water from the input saline water The flat plate absorber is placed in such a way that it is parallel to the glass cover of the solar still so as to maximize the absorption of solar radiations By this modification, the maximum temperature of the absorber plate achieved was 95°C in comparison to 67°C of the conventional solar still Experimental results of modified solar still were compared with conventional solar still It was found that distillate output increased by 25% with a flat plate absorber when compared to conventional still

Machine Learning Based Identification of Tomato Leaf Diseases at Various Stages of Development

Abstract: Mosaic, early blight, late blight, Septoria virus, leaf mold, Brown spot, and spider mite are the nine common types of tomato leaf diseases. The early and accurate analysis of tomato leaf disease can increase the productivity and quality of the tomato product. The existing research in image processing does not guarantee an accurate diagnosis of the disease. Also, existing methods are complex. In this paper, an accurate and robust method for tomato leaf disease identification as well as classification into various stages of development using machine learning is proposed. The work is carried out in two stages. Firstly the tomato leaf images will be classified into appropriate disease types. Then in the second phase, the tomato leaf disease is diagnosed at various stages of development. Identifying the stage of development of tomato leaf would help to decide the type and amount of treatment required for the plant. The diseased leaf images which are taken from the PlantVillage dataset have been classified into high, medium, low, and normal severity grading. The images are preprocessed using median filtering. For feature extraction, the system using shape, color, and texture features is evaluated. The performance evaluation is also done on various classification techniques including SVM, KNN, Naive Bayes, Decision Trees, and LDA. The research indicated that the proposed model provides a robust solution for tomato leaf disease severity grading.