Browse Items (11858 total)
Sort by:
-
Transforming online class recording into useful information repositories using NLP methods: An Empirical Study
Most educational institutions have adapted to the mode of online teaching which has resulted in an increase of online video recordings. Learner community can be benefited with the ability to retrieve required information from the online class recordings. In this paper, we propose a methodology for converting video transcript data into useful information repositories for the purpose of retrieving class transcripts relevant to user's information needs. We focus on the online video recording transcript data. We also discuss challenges in transcribing which are crucial to understand preliminary processing. Our dataset consists of transcripts from diverse subject domains deeper experimental insights. We use interactive transcripts obtained from ASR (automatic speech recognition) services and non-interactive human generated transcripts. State-of-the-art methods for keyword retrieval: Latent Dirichlet Topic Modelling (LDA), Term Frequency (TF.IDF) and Text Rank (graph based) are applied on the video transcript data. Further, cosine similarity metric is applied to obtain the similarity measure between the transcript documents and keywords. 2022 IEEE. -
Stacked LSTM a Deep Learning model to predict Stock market
The goal of Stock Market Prediction is to forecast the future value of a company's financial stocks. The use of machine learning and deep learning technologies in stock market prediction technologies is a recent trend. Machine learning makes predictions based on the values of current stock market indices by training on their previous values in sequential timely order using the artificial neural network, while deep learning makes predictions based on the values of current stock market indices by training on their previous values in sequential timely order using the artificial neural network. 2022 IEEE. -
Artificial Intelligence & Data Warehouse Regional Human Resource Management Decision Support System
High-quality data is utilized to make informed decisions that effectively help to successfully safeguard our environment. When there is an abundance of information that is both heterogeneous in nature (coming from a wide variety of fields or sources) and of unknown quality, various problems may occur. Furthermore, the problem's dynamic nature also imposes some other complications. In order to deal with such complications, the central role played by supercomputers in the modern environment is to promote protection initiatives like monitoring, data analysis, communication, and information storage and retrieval. In current days, the higher dependency on the data management process forced the developers to integrate and enhance all these initiatives with Artificial Intelligence knowledge-based techniques so that smart systems can be utilized by a vast number of people. In this context, this study has illustrated how Artificial Intelligence methods have changed the nature of Environmental Decision Support Systems (EDSS) over the course of the last two decades. The strengths that an EDSS should exhibit have been emphasized in this review. In the final section, we look at some of the more innovative solutions used for various environmental issues. 2022 IEEE. -
Artificial Intelligence Influence on Accounting Methods
Due to its benefits in terms of enhancing and redefining the actual manner of performing activities in this field, artificial intelligence is swiftly changing the reality of the accounting business. Accounting has seen a significant transformation over the years as computers, first and foremost, and more importantly, developers ready to spend less time on laborious work that minimises the amount of errors, have replaced the job done with paper and pencil. Although there has always been a fascination with artificial intelligence systems in this field, attention has recently shifted more toward it. Although technology has advanced, it seems that there aren't enough facts to back up businesses' readiness to include artificial intelligence systems into their accounting procedures. A crucial element of this reality is also the ability of professionals to quickly adjust to the new business climate, get the skills required to work with AI systems, and overcome their fear of losing their jobs. The requirements of the financial society, the quick development of data innovation, and artificial intelligence have brought about the modern era. Implementing artificial intelligence innovation is an unavoidable trend that will result in substantial changes and advancements in the accounting sector. In this essay, the usage of AI in the accounting industry is examined, its effects on the sector's expansion are examined, and significant solutions to current issues are suggested. 2022 IEEE. -
Multimodal Emotion Recognition Using Deep Learning Techniques
Humans have the ability to perceive and depict a wide range of emotions. There are various models that can recognize seven primary emotions from facial expressions (joyful, gloomy, annoyed, dreadful, wonder, antipathy, and impartial). This can be accomplished by observing various activities such as facial muscle movements, speech, hand gestures, and so forth. Automatic emotion recognition is a significant issue that has been a hotly debated research topic in recent years. At the moment, several research people have taken a component in inheriting or extra multimodal for higher understanding. This paper indicates a method for emotion recognition that makes use of 3 modalities: facial images, audio indicators, and text detection from FER and CK+, RAVDESS, and Twitter tweets datasets, respectively. The CNN model achieved 66.67 percent on the FER-2013 dataset of labeled headshots while on the CK+ dataset, 98.4 percent accuracy was obtained. Finally, diverse fusion strategies had been approached, and each of those fusion techniques gave distinctive results. This project is a step towards the sense of interaction between human emotional aspects and the growing technology that is the future of development in today's world. 2022 IEEE. -
Comparison of Affine and DCGAN-based Data Augmentation Techniques for Chest X-Ray Classification
Data augmentation, also called implicit regularization, is one of the popular strategies to improve the generalization capability of deep neural networks. It is crucial in situations where there is a scarcity of high-quality ground-truth data. Also getting new samples is expensive and time consuming. This is a typical issue in the medical domain. Therefore, this study compares the performance of Affine and Generative Adversarial Networks (GAN)- based data augmentation techniques on the chest image X-Ray dataset. The Pneumonia dataset contains 5863 chest X-Ray images. The traditional Affine data augmentation technique is applied as a pre-processing technique to various deep learning-based CNN models like VGG16, Inception V3, InceptionResNetV2, DenseNet-169 and DenseNet-202 to compare their performance. On the other hand, DCGAN architecture is applied to the dataset for augmentation. Evaluation measures like accuracy, recall and AUC depict that DCGAN outperforms other traditional models. The most important advantage of DCGAN is that it is able to identify fake images with 100% accuracy. This is especially relevant for the medical domain as it deals with the life of individuals. Thus, it can be concluded that DCGAN has better performance as compared to affine transformations applied to traditional CNN models. 2023 The Authors. Published by Elsevier B.V. -
CDADITagger: An Approach Towards Content Based Annotations Driven Image Tagging Integrating Hybrid Semantics
Considering the rapid growth of multimedia data, especially images, image tagging is considered the most efficient way to organize or retrieve images. The significance of image tagging is growing extensively but the frameworks employed for tagging these images aren't sophisticated. These images aren't properly tagged because of a lack of resources for tagging or manual tagging is a challenging task considering such voluminous data. Already existing frameworks take both the image data and tag-related textual data but ultimately resulted in mediocre or unpalatable performance as they are dataset centered. To overcome these limitations in existing frameworks we proposed an image tagging mechanism, CDADITagger capable of automatically tagging images efficiently and much more reliable compared to existing frameworks. This framework can tackle real-world applications like tagging a new unknown image as the framework isn't powered by dataset alone but is designed to inculcate images from search engines like Google, Bing, etc. to have comprehensive knowledge of real-time data. These images are classified using CNN and tag-related textual data is classified using decision trees for enhanced performance. While tagging images from the classified tags, are sorted based on the semantic computation values, only the top 50% of the instances classified are selected. The tags which are more correlated to the image are ranked and finalized. The proposed semantically inclined framework CDADITagger outshined the well-established frameworks with an accuracy of 96.60% and a precision of 95.84% making it a more reliable approach. 2022 IEEE. -
An Effecient Approach to Detect Fraud Instagram Accounts Using Supervised ML Algorithms
Nowadays social media plays a vital role in different fields including business, economic communication and personal. Many person get profit from the different origins of availability of data from these social media, but cyber-crimes are increasing day by day. A person can generate many fake accounts and hence pretenders can easily be made. Instagram, as one of the popular types of online social media site, carries big information and messages through the posts. Most of the person use Instagram as a digital life marketing place because it is a one of the big social media site. The goal of the research paper is to recognize and stop fake IDs and pages. Because through the professional pages of Instagram, many fake cases and things are occurring present days. So the main thing is to recognize fake pages and fake accounts also. In this paper, we work on various IDs of Instagram. We want to observe an ID is real or not using Machine Learning techniques namely Logistic Regression, Naive Bayes, Support vector machine, Decision tree, Random Forest. 2022 IEEE. -
Web Platforms for Fintech Products
Internet marketing and digital marketing are not synonymous in the minds of the majority of the population, yet this may not be true. Given the rise in popularity of digital marketing as a marketing tactic, it is critical to comprehend the distinctions between the two methods. Even while it should be evident that they might be connected, there is very little difference between them. Internet marketing is merely a subclass of digital marketing, as well as the extent of digital marketing encompasses much more than internet marketing. This paper discussed digital marketing technologies, as well as the advantages and disadvantages of employing digital marketing and digital finance tools in general. In order to remain competitive, businesses must overcome obstacles and seize possibilities presented by digital marketing technologies. Lastly, it's critical to prioritise digital marketing and make use of digital finance techniques in order to maintain a good performance without wasting time or money. 2022 IEEE. -
Sentiment Analysis on Amazon Product Review
Users throughout the world may now access massive amounts of data thanks to the internet and social media platforms. [5] In every facet of human existence, electronic commerce (e-commerce) plays a crucial role. E-commerce is a marketing approach that enables businesses and consumers to buy and sell things via the internet. When buyers look for product information and compare alternatives online, they generally have access to dozens or hundreds of product reviews from alternative shoppers. Machine learning is the most appropriate approach to training a neural network in today's age of practical artificial intelligence. So implementing a model to polarize those reviews and learn from them would make passing hundreds of comments a lot easier. [24] The interpretation will be a very basic product with positive, neutral, and negative polarization. The product is checked. This study suggests a sentiment evaluation model for shopper reviews based on the object and emotive word mining for emotional level analysis using machine learning approaches. 2022 IEEE. -
Building an International Entrepreneurship Index using the PSR framework
This paper builds an International Index for Entrepreneurship (IIE) for the year 2018, by using a conceptual framework named PSR (Pressures-State-Response) to encapsulate the contextual aspect of entrepreneurship globally. In the past, the indices have used a methodological framework of composite indices. This paper uses the PSR framework to show how these indicators fall into the categories of pressure, state, and response, and concentrates on how these subsystems are interrelated. The study considers 41 countries for the construction of the index. We also check the correlation between the IIE and other growth indicators such as the corruption perception index, the economic freedom summary index, GDP per capita, and trade openness using suitable statistical tools.The correlation analysis demonstrates that the IIE and the Economic Freedom Summary Index have a positive association. 2022 IEEE. -
Prediction of Stock Prices using Prophet Model with Hyperparameters tuning
As part of the data analytical process, predicting and time - series are crucial. In academics and financial research, anticipating share prices is a prominent and significant subject. A share market would be an uncontrolled environment for anticipating shares since there are no fundamental guidelines for evaluating or anticipating share prices there. As a result, forecasting share prices is a difficult time-series issue. fundamental, technical, time series predictions and analytical strategies are just a few of the various techniques and approaches that machine learning uses to execute stock value predictions. This article implements the stock price prediction, Researchers compared the model of the prophet with the tuned model of the prophet. By utilizing the tuning of hyperparameters using parameter grid search to improve the performance of the model accuracy for the best prediction. The findings of the study demonstrated that tuned model of the prophet with hyperparameters tuning which results in model accuracy and based on the experimental findings mean squared error (MSE) and mean absolute percentage error (MAPE) has significant improvement. 2022 IEEE. -
Challenges of Digital Transformation in Education in India
Online learning has been present since the 1960s and has risen in popularity over time. World-class universities have been using online teaching-learning methodologies to fulfill the needs of students who reside far away from academic institutions for more than a decade. Many people predicted that online education would be the way of the future, but with the arrival of COVID-19, online education was imposed upon stakeholders far sooner and more suddenly than expected. When the COVID-19 pandemic broke out, educational institutions began to explore digital ways to keep students studying even when they couldn't be together in person as governments enacted legislation prohibiting large groups of people from gathering for any reason, including education. The future of such a transition looks promising. However, transitioning from one mode of education to another is not easy. Historically, when educators adopt new tools, learning still continues in the conventional manner. Based on the responses of 176 students, this paper studies the challenges of Digital transformation in the Education sector. The research is extremely beneficial in evaluating the scope of societal opposition to change. 2022 IEEE. -
Predicting Employee Attrition Using Machine Learning Algorithms
Employees are considered the foundation of any organization. Due to their importance, the Human resources department implements various policies to sustain them. Yet the attrition rate in any organization is increasing yearly. The attrition rate signifies the number of employees who leaves a firm without being replaced. It is regarded as a well-known issue that requires the administration to make the best choices to retain highly competent staff. It is interesting to note that artificial intelligence is frequently used as a successful technique for foreseeing such an issue. This review paper aims to study the different machine learning approaches that predict employee attrition and factors influencing an employee to attrite from an organization. A Hybrid model comprising the various ensemble models is proposed to predict attrition at its earliest. The forecasted attrition model aids in not only taking preventive action but also in improving recruiting choices and rewarding top performers who contribute to the company's success. 2022 IEEE. -
Neural Network based Student Grade Prediction Model
Student final grade GPA is the collective efforts of their previous and ongoing efforts of each semester examination may predict accurately using the neural network which receives the input weight of each matrix element of variables to next neuron. The GPA prediction based on regular class performance and previous grades with background variables were found much significant. This research tries to explore the model comparison and evaluate student grade prediction using various neural network models. The single-layer half i.e., successful student model predicts 90 total accuracies than the single layer with five hidden layer neurons (88.5 percent). The multi-layer with two hidden layers (7,3) is 84 percent accuracy is less than one percent accuracy than multilayer with three hidden layers. Similarly, the multilayered with four hidden layered 25,12,7,3 model predicts the least accuracy (77 percent accuracy) for student grade. Similarly, the passed student prediction model has less accuracy than both students' 86 percent. 2022 IEEE. -
Technologies in Transportation Engineering
Deteriorating quality of the air, traffic congestions, and rising accident rates have all resulted from an ever-increasing number of vehicles in Indian cities. As a result of a variety of issues, current public transit systems often fall short or are considered unreliable. The present paper deals with multiple ITS architecture and to be specific four major parts of the ITS. These four major parts are Advanced Public Transportation System (APTS), Advanced Traveler Information System (ATIS), Advanced Traffic Management System (ATMS), and Emergency Management System (EMS). Thus, the framework and produced models of four key divisions of ITS have been evaluated in order to conduct a comparative study of the many models currently being developed in respective investigations. 2022 IEEE. -
Customer Segmentation and Future Purchase Prediction using RFM measures
Winning in the E-Commerce business race at a competitive age like this requires proper usage of Customer data. Using that database and grouping it in similar segments in terms of spending expenditure, observation time, sex, and location so that every customer falls in a segment of characteristics. This mechanism is called Customer Segmentation. In the modern era of highly compatible technological advancements, Machine Learning Algorithms are being vastly used to bring solutions to these difficult yet essential services. In the field of research methods like simple clustering based on purchase behaviour, buyer targeting or automated customer promotion mechanism by dividing into two major categories, have been worked on. However, ensemble algorithms have come handy where different clustering algorithms are combined to deliver best segmentation. Lately combination techniques like clustering and classification mechanism have also delivered good results where, not only segmentation is done but also classification of existing and new customers are possible into the clusters. Depending on that an effective customer relationship management can really benefit the company to a huge extent. Unlike other studies where clustering was performed directly on RFM table, a different approach was taken in this study where, one dimensional clustering was done individually on Recency, Frequency, Monetary columns, then an overall score was calculated and customers were classified into three segments. However, for a new customer depending on his purchase behaviour he/she also can be classified into any of the categories. 2022 IEEE. -
A Review On Geospatial Intelligence For Investigative Journalism
Throughout the ongoing Russian invasion of Ukraine, satellite images like the vast convoy of Russian military vehicles approaching the beleaguered Ukrainian city of Kyiv, Russian aircraft deployed at Zyabrovka, Belarus and many more such visuals have been in circulation and are being used as a tool to facilitate investigative journalistic studies. Such satellite-based images are one of the latest means of accessing vital data that can help in expanding the scope and impact of investigative journalism. Geospatial intelligence uses varied graphical content to convey information about the activities that occur on the surface of the earth. It includes colour and panchromatic (black and white) aerial photographs, multispectral or hyperspectral digital imagery, and products such as shaded relief maps or three-dimensional images produced from digital elevation models. The improving technology in geospatial spectra has broadened the scope of its usage to investigative journalism which lies at the core of this review paper. Some of the path-breaking journalistic stories that have come up in the past decade - imaging of the Uttarakhand landslide in 2021 using satellite images, coverage of the Fukushima nuclear plant since 2011, and 2021 tracking of Asia's border disputes emerging due to climate change and the satellite journalism built around the blockage of Suez canal in 2021 - showcase the potential that geospatial intelligence has in the domain of journalism. All four identified stories point out how we can practice satellite-based investigative studies, especially, for scrutinizing and comparing historical records regarding cross-border issues as well as the disappearance of pastures and forests in vast open lands. However, the arena of using geospatial intelligence, enabled by satellite images, remains underutilized and limited to specific journalistic organizations, based in a few countries. This exploratory review of the four mentioned journalistic accounts identifies the contexts where such efforts are feasible, methods that are required, sources that could be tapped, associated skill sets needed for its usage, the dynamics of such investigative approaches, and their scope and limitations. This review and the conclusions drawn from the above-mentioned cases provides a direction for journalists from small organizations and low income countries to explore the potential of satellite-based images in furthering their investigative reporting with a technological edge that persists to be sovereign in the geopolitical powerplay. Copyright 2022 by the International Astronautical Federation (IAF). All rights reserved. -
Relative Efficiencies of Farmer Producer Companies in India- Slack-Based Model Approach
The concept of the farmer producer company (FPC) model has received a large momentum especially during the 20202021 farmers' protest in India. This paper examines the relative efficiencies of 46 FPCs in Kerala using non-radial data envelopment analysis (DEA) for the financial year 2018-19. We use a non-oriented slack-based model (SBM) under assumptions of constant and variable returns to scale. The results reveal that 36.96 per cent of the sample FPCs are overall technical efficient and 50 per cent of the FPCs are pure technical efficient. It is found that technical inefficiency is reported for a few FPCs due to scale inefficiency. Among the input and output targets suggested for inefficient FPCs, reduction in the 'number of shareholders' and augmentation of 'profits' reported in most cases to improve their efficiency scores. Based on the findings, we suggest the concerned stakeholders to provide additional financial and non-financial supports to the needy rather than focusing on establishing new FPCs. 2022 IEEE. -
Performance Evaluation of Time-based Recommendation System in Collaborative Filtering Technique
The Collaborative Filtering (CF) technique is the most common neighbourhood-based recommendation strategy, that provides personalized recommendation to a user for the items using a similarity measure. Hence, the selection of the appropriate similarity measure becomes crucial in the CF based recommendation system. The traditional similarity measures merely focus only on the historical ratings provided by the users to compute the similarity, completely ignoring the fact that preferences change over a period of time. Considering this, the paper aims to develop an effective Recommendation System that uses temporal information to capture the changes in the preferences over a period of time. For this, the existing exponential and power time decay functions are integrated with Cosine, Pearson Correlation, and Gower's similarity measures to compute similarity. The similarity is computed at the similarity computation and prediction levels of recommendation processes. Experimental findings in terms of MAE and RMSE on the MovieLens-100k demonstrate that performance of Gower's coefficient is better when applied with the exponential function at the similarity computation level of the recommendation process. 2022 Elsevier B.V.. All rights reserved.