Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

Visual similarity recommendations have an immense role in E-commerce portals. Fetching the appropriate similar products and suggesting to the buyers based on the product image's visual features is complex. Here in our research, we presented an efficient E-commerce similar product network model (e-SimNet) for visually similar recommendations. To achieve our objective, we have performed image feature extraction and generating embeddings using deep learning techniques and built an Index tree using the approximate nearest neighbor oh yeah (ANNOY) algorithm. Further, we have fetches top-N the near similar items using distance measure. We have benchmarked our model in terms of accuracy, error rate, and results show that better than other state-of-the-art approaches with 96.22% of accuracy. © 2021 Institute of Advanced Engineering and Science. All rights reserved.

World University root node

Department of Software Systems

School of Computer Science and Engineering

Vellore Campus

Fulltext

Indonesian Journal of Electrical Engineering and Computer Science

e-SimNet: A visual similar product recommender system for E-commerce

The recommender system is the most profound research area for e-commerce product recommendations. Currently, many e-commerce platforms use a text-based product search, which has limitations to fetch the most similar products. An image-based similarity search for recommendations had considerable gains in popularity for many areas, especially for the e-commerce platforms giving a better visual search experience by the users. In our research work, we proposed a machine-learning-based approach for a similar image-based recommender system. We applied a dimensionality reduction technique using Principal Component Analysis (PCA) through Singular Value Decomposition (SVD) for transforming the extracted features into lower-dimensional space. Further, we applied the K-Means++ clustering approach for the possible cluster identification for a similar group of products. Later, we computed the Manhattan distance measure for the input image to the target clusters set for fetching the top-N similar products with low distance measure. We compared our approach with five different unsupervised clustering algorithms, namely Minibatch, K-Mediod, Agglomerative, Brich, and the Gaussian Mixture Model (GMM), and used the 40,000 fashion product image dataset from the Kaggle web platform for the product recommendation process. We computed various cluster performance metrics on K-means++ and achieved a Silhouette Coefficient (SC) of 0.1414, a Calinski-Harabasz (CH) index score of 669.4, and a Davies–Bouldin (DB) index score of 1.8538. Finally, our proposed PCA-SVD transformed K-mean++ approach showed superior performance compared to the other five clustering approaches for similar image product recommendations. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.

Symmetry

Probabilistic unsupervised machine learning approach for a similar image recommender system for E-commerce

Recommendation System (RS) gains considerable popularity from the past decade in E-Commerce and other allied fields. This paper investigates the various traditional Recommendation System like Content-based (CB), Collaboration Filtering-based (CF), Demographic-based, Knowledge-based and discussed current trends in recommendation system like location-aware, context-aware, and Deep Learning techniques. Various improvements and limitations in Recommendation systems have been listed out with evolution metrics for analyzing the accuracy of the algorithms. This paper well-elaborated for the past, present and future scope of the Recommendation System which would be useful for researchers to get familiarity with this domain.&nbsp;

International journal of electronic commerce studies

A SURVEY ON COMPREHENSIVE TRENDS IN RECOMMENDATION SYSTEMS &amp; APPLICATIONS

End users encounter difficulties while spending time and effort in learning and using some software products. Ultimately, the foremost goal of all the organizations and companies developing product lies in the improvement of userâs satisfaction and interest toward the product. One of the methods by which the improvement could be performed is by designing a simple and guiding user interface that is suitable for all the users of an application. Especially, in the domain of information systems, the impediment raises due to the lack of effective user interfaces. The context of use and the end userâs knowledge about user interface pose a strenuous demand in usability. Thus, there is a demand to design interface with utmost care considering the end userâs motor skills and their abilities. Though several laws and principles exist for the stated purpose, effective design involves creativity and some amount of craft which may involve series of procedures, techniques, and tools. However, the decision making in dynamic environments to choose the techniques and tools is seemingly intractable and is complex because of natural trade-offs. Apparently, choosing from existing alternatives will frequently involve making trade-offs that may fail to satisfy requirements. Hence, the selection of alternate solution in lieu of multiple criteria has been challenging. One of the methods that were successful for this objective is multi-criteria decision analysis (MCDA). This technique defines several approaches for decision making and tries to converge toward the optimal solution. The work attempts to design user interface for any information systems with minimal number of interactions for the different categories of users.

Knowledge Computing and Its Applications

User Interface Design Recommendations Through Multi-Criteria Decision Analysis

Social networking is a multidimensional content and knowledge-sharing online communication media. Presently, the social network influences users' activities, such as identity creation, sharing, conversation, relationship establishment, presence indication, group participation, and reputation. In a way, these activities do reflect an individual's behaviour. As social networks allow any online content to be shared, it is possible to utilise this channel to employ marketing in an effective way. As of now, the major challenge of social marketing is selecting and understanding the target audience to develop marketing and campaigning strategies. One way to understand users is to know the emotions they express when they communicate content through social networking. This paper attempts to study the nine basic human emotions and their significance in various social network activities to determine the right strategies of marketing in e-business. In order to personalise this process for the social network users, initially, a survey is conducted to analyse the influence of human emotions on performing activities on social networks. With the help of the extracted information, developing a suitable marketing strategy and tools to attract users to the product being advertised may be easier in e-business.

International Journal of Business Information Systems

Influence of human emotion expressed through social networks in viral marketing

Social networks play a significant role in information sharing and have become an essential part of user's daily activities. Social networks help share users' ideas, views, status and opinions in the form of text, music and videos. The inherent difficulties involved in sharing the information is the sustenance of the values attached to the dependability of the functional blocks of the user - identity, sharing, conversation, relationship, presence, group and reputation. Review of social networks in terms of user influence ranking would throw light on the role of these functional blocks. The user influence ranking generally reveals the impact that an individual has on the social network. In the present scenario, the user influence ranking factors are not systematically determined. Instead, each social network adopts its own method to determine users' influence. Hence, the review has been done to identify the adoption of these functional blocks in popular social networks to determine users' influence ranking method.

International Journal of Web Based Communities

A review on user influence ranking factors in social networks

The social networks help sharing user’s multidimensional content which includes text, image, audio and video at any time. Emoticons are helpful in precise content sharing as an alternative of text and need to be analyzed for sharing of the right content. The content being shared mostly reflects the behavioral characteristics of the users and imitates their emotions. Therefore, each emoticon needs to be mapped with standard emotions. The emoticons proposed by Unicode consortium are considered and mapped with nine basic emotions such as love, happiness, pity, furious, heroic, fearful, disgust, wonder and peace. A prediction model based on decision tree classifier is designed to classify user’s contentaccording to the emotions expressed through the emoticons, especially for tweets. The designed methodology is demonstrated using two thousand tweets. Tweets are adopted for its simplicity and limited processing with only hundred and forty characters. The outcome obtained by applying the designed methodology provided satisfactory results of 83% accuracy which is more than the average accuracy (75%) of standard machine learning classification process. Therefore, it is possible to guess the behavior of the users through sharing the different forms of emoticons at various instances. This classification of users’ content would reflect the dominant emotions possessed by them. This finding helps in understanding the basic nature of an individual in social networks. Having identified the basic nature of an individual through emoticons, it is very easy to personalize the user’s social network page to filter disinterested and disgusting content at any time.

Indian Journal of Science and Technology

Social Network User’s Content Personalization based on Emoticons

E-Governance systems are built for the government to interact with citizens and efficiently provide workflow between the organizations. These systems play major role in efficiently organizing the government knowledge and enabling citizen friendly services. Traditionally E-Governance systems are developed as a requirement basis trend, where the requirement of establishing a service is evaluated and a system for that particular requirement is deployed. A framework has been introduced to develop an E-Governance system in an evolutionary fashion where the core government model is deployed and further services are deployed over the core. The key element in achieving such evolutionary system is by adding semantics to the knowledge which is represented in the form of Linked Data.

VIT Unitversity

A Framework for E-Governance System using Linked Data and Belief-desire-intention Agent

This paper presents a highly robust watermarking scheme for color images in spatial domain using block probability with a password authentication technique. There are two main phases; one is Invisible watermarking phase and other is the Password insertion phase inside the image. In the watermarking phase a binary watermark is permuted using a random numbers and converted to gray code, in which each bit of the binary encoded watermark is embedded by modifying the intensities of the 8 *8 blocks and finally inserted into the blue component of the original image. In the Password insertion phase a 16-bit binary key (password) is embedded in the original image along with the watermark. Extraction of the watermark is done by comparing the intensities of watermarked image with the original image. The same watermark has been embedded in four different positions to provide high robustness and it also secure, only the person with the correct password can extract the watermark and also the use of random number (32 *32) as a secret key intensifies the security of the information.