Browse Items (2150 total)
Sort by:
-
Utilisation of Virtual Assistant and Its Impact on Retail Industry
Virtual assistant is nothing but an independent contractor, who offers administrative services to the clients of a particular organisation while operating outside of the office of the client. Generally, a virtual assistant operates from a home-based office. This virtual assistant application has the ability to access the required planning documents, such as shared calendars. The contemporary retail organisations like e-commerce companies in this competitive global business environment are using virtual assistant to enhance omnichannel experience, 24/7 customer service, order tracking, and product recommendations. Overall, virtual assistant helps the organisations in enhancing social media management activities. This concept of the use of virtual assistant has been significantly emerged after the increase in demands for e-commerce business activities in this decade. Research objectives related to the title of this research are developed and listed. Relevant theories on virtual assistant are applied in the literature review section of this study. The researcher has decided to adopt qualitative research methodology to achieve the objectives of the research. Moreover, the researcher has considered secondary data analysis approach to conduct this research. In terms of findings, it has been identified that virtual assistant has a positive impact on the business operation activities of retail organisations. Authentic secondary sources are considered to collect and analyse the data. Some challenges associated with the utilisation of virtual assistant also have been identified in the findings section. Some valuable recommendations are suggested for the future researchers to overcome those identified associated challenges. 2022 IEEE. -
Academic Certificate Validation Using Blockchain Technology
Academic certificates are essential for an individual's career and hence they are more prone to being tampered. This paper proposes an idea of sharing certificates and verifying their authenticity using blockchain technology. Blockchain paves the way for secure storage and sharing of information. Its main focus is to maintain trust among users. This proposal focuses on designing and implementing a system that will prove to be a solution for addressing the issue of fake certificates using Hyperledger Fabric. The technology here is tamper-proof and maintains transparency. This system will have a database of academic certificates awarded by the University, which is recorded as a transaction using the Hyperledger Fabric, which further can be referred by other organizations present in the network to verify the authenticity of the certificates using the information provided by the students to the database. This system provides end to end encryption. 2022 IEEE. -
Synthesis of Online Criminal User Behaviours Disseminating Bengali Fake News Using Sentiment Analysis
Even though research on artificial intelligence (AI) is still in its early phases, the field is growing in popularity. We created a hybrid machine learning model to better understand the pattern of results connected to illegal user behaviour. Then, after identifying the components of illegal user activity, we created a theory for forecasting criminal user behaviour that explains the patterns and results. Our study focuses on offenders spreading misleading information online and makes use of a Bengali dataset. Sentiment analysis is a modern technology that can help us understand how individuals feel in different scenarios during their everyday lives. To comprehend the pattern behind this agenda, machine learning and deep learning techniques will be applied throughout the categorization process. To determine the possible attitudes driving criminal conduct that spreads misleading information, sentiment levels on social media may be monitored or studied. This study examines the use of several artificial intelligence approaches to assess sentiment in social media data in order to identify criminal user activity occurring throughout the world. The hybrid model CNN with Adam optimizer exhibits higher precision levels while doing sentiment analysis. In addition to identifying solutions to the issues that people currently face in the modern world, we also propose a new categorization system for illicit user activity. In our analysis of the research's shortcomings, we make recommendations for a broader research agenda on illicit user conduct and how one can forecast the criminal user behaviour on psychological aspects. Our model was thus able to draw 87.33% accuracy in determining criminal behaviour patterns. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Deploying NLP techniques in Twitch application to comprehend online user behaviour
Sentiment analysis of emotion entails identifying and analyzing subjective information from language, such as views and attitudes, and helps to improve data visualization by employing a variety of strategies, tactics, and tools. New media channels have significantly changed how people interact, exchange ideas, and share information. Numerous businesses have begun to mine this data, concentrating on social media since it is a popular platform for customers to voice their ideas about various brands or goods and because it gives users an audience, enhancing the visibility and potential effect of this input. So far, as the internet expands and modern technology advances, new avenues have emerged with a higher ability to offer businesses pertinent feedback on their goods. The goal of this study is to investigate the many forms of online behaviour by analyzing chat interactions from the well-known streaming service Twitch. Emotes were occasionally employed in place of letters, to get attention, or to communicate emotions. We propose a system that may take in chat logs from a certain stream, use a sentiment analysis algorithm to classify each message, and then display the data in a way that might permit users to analyze the results according to its polarity (positive message, negative message, or neutral message). This application must be sufficiently versatile to be used with any platform broadcast type and to handle the datasets at very huge level. 2023 IEEE. -
Deploying Fact-Checking Tools to Alleviate Misinformation Promulgation in Twitter Using Machine Learning Techniques
In the present era, the rising portion of our lives is spending interactions online with social media platforms. Thanks to the latest technology adoption as well as smartphones proliferation. Gaining news from the platforms of social media is quicker, easier as well as cheaper in comparison with other traditional media platforms such as T.V and newspapers. Hence, social media is being exploited in order to spread misinformation. The study tends to construct fake corpus that comprises tweets for a product advertisement. The FakeAds corpus objective is to explore the misinformation impact on the advertising and marketing materials for a particular product as well as what kinds of products are targeted mostly on Twitter to draw the consumers attention. Products include cosmetics, fashions, health, electronics, etc. The corpus is varied and novel to the topic (i.e., Twitter role in spreading misinformation in relation to production promotion and advertising) as well as in terms of fine-grained annotations. The guidelines of the annotations were framed through the guidance of domain experts as well as the annotation is done with two domain experts, which results in higher quality annotation, through the agreement rate F-scores as higher as 0.976 using text classification. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Continuance Intention of ChatGPT Use by Students
ChatGPT, an AI language model, has gained significant attention for its potential to enhance educational experiences and foster interactive learning environments. The potential of student interaction via ChatGPT has engendered significant debate around educational technology. It is apparent that the current literature has yet to fully explore the role of ChatGPT in management education. Amidst the increasing integration of ChatGPT into educational contexts, the concept of continuance intention takes center stage. This research paper delves into the nuanced landscape of students continuance intention regarding the use of ChatGPT in educational settings. We ground our study in Technology Continuance Theory and Theory of Planned Behavior to examine students continuance intention to use ChatGPT. By investigating the determinants that shape this intention, we aim to provide insights that inform educators and educational technology designers in optimizing the integration of AI-driven tools like ChatGPT. This study contributes to the growing body of research at the intersection of AI and education, offering valuable implications for both theory and practice. 2024, IFIP International Federation for Information Processing. -
Hotel Recommendation System Based on Customer's Reviews Content Based Filtering Approach
Recommendation systems are fantastic tools for remembering people's ideas in order to gain knowledge more efficiently and selectively. Recently, booking and searching for hotels online has become more common. As it takes more time, online hotel research is growing more quickly. In addition, the amount of knowledge accessible online is continuously expanding. User preferences have a big impact on hotel recommendations. The most effective recommendations may be made by recommendation systems by utilising historical user preference data. To solve this problem, recommender systems have suggested content-based filtering methods. Product recommendations, recommendations for websites, news articles, restaurants, and TV series are all examples of applications for content-based recommender systems. The dataset for this project includes client evaluations of the offered Kaggle profile. Word embedding, word2vec, and TF-IDF natural language processing methods were used for feature extraction. The algorithm shows the user the top 10 suggested hotels based on the user's past knowledge of the hotel's location. 2022 IEEE. -
Diagnosis of compromised accounts for online social performance profile network
Proliferation of internet technologies has changed the way content is created and exchanged through the Internet, prompting expansion of online networking applications and administrations. Online networking empower creation and exchanged the clients produced content and design of a scope of Internet-based applications. This development is fueled by more administrations as well as by the rate of their adoption by the users. While determined spammers misuse the built up trust connections between account proprietors and their companions to proficiently spread malignant spam, auspicious discovery of traded off records is quite challenge, because of the fixed trust association among the administration suppliers, account proprietors, and their companions. The proposed paper depicts a novel method to notice the cooperated user account in systems like Facebook and twitter. Our novel scheme consists of statistical method of modelling and detected to identity accounts that behaves a sudden change along with detected the compromised accounts. This paper gives validation of these behavioral elements by gathering and dissecting genuine client clickstreams to an OSN site. Taking into account our estimation study, further devise every client's social behavioral profile (SBP) by joining its separate behavioral element measurements. We assess the capacity of social behavioral profiles in recognizing distinctive OSN clients, and the simulation results demonstrate the social behavioral profiles precisely separate every OSN clients and distinguish traded off records. 2016 IEEE. -
Insights of Evolving Methods Towards Screening of AI-Enhanced Malware in IoT Environment
Internet-of-Things (IoT) has been encountering a series of potential form of threats since past half decades. Artificial Intelligence (AI), which is frequently seen to be adopted to solve various challenges in IoT operation, has now been adopted even by attackers for their malicious purposes. Of all forms of threats, AI-enhanced malwares are one of the most potential forms of threats which has its extensive effectiveness towards the complete operation of the entire IoT environment. Hence, this manuscript discusses existing detection and prevention approaches evolved in current literatures to understand various taxonomies of solution-based methodologies for circumventing such threats. The paper also contributes towards highlighting the potential open-ended issues that are yet to be addressed. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Secure framework of authentication mechanism over cloud environment
Cloud computing offers a cost effective virtual infrastructure management along with storage and application-oriented services to its customers. This innovation quickly turns into a generally very widely accepted worldview for conveying administrations through web. In this way, this administration expert provider must be offer the trust and information security, on the grounds that there is a most vital and profitable and most delicate information in extremely secure using cryptographic techniques to secure the data in cloud. So for ensure the privacy of essential information, it must be secured utilizing encryptions algorithms and afterward transferring to cloud. This paper presents a novel technique for electronic distributed computing administrations utilizing two-variable validation (2FA) access control framework. The prime target of the projected framework is to guarantee a optimal security for all the actors involved in the component design of proposed authentication system. Furthermore, property based control in the framework likewise authorize cloud servers to maximum the access to those clients with the same arrangement of properties while saving client privacy. At long last, we additionally do a reproduction to show the practicability of our proposed framework. The assessment work is done by utilizing expense of communication, data transfer capacity and proficiency of the framework as an execution metric. Springer International Publishing AG 2017. -
A Compatible Hexadecimal Encryption-Booster Algorithm for Augmenting Security in the Advanced Encryption Standard
Among the most prominent encryption algorithms, Advanced Encryption Standard ranks first. Even so, many familiar characters can be seen when an AES encrypted file is opened. As of today, there have been very few contributions to research on suppressing known characters in AES encrypted files. It is possible to identify encrypted files not only by their name and content, but also by their size. As a result, hackers can identify files at source and target locations by comparing their sizes. In this paper, a methodology is presented to address these two research gaps. As a result of the proposed algorithm, almost all characters are transformed into an unintelligible format not only for humans, but also for computer interpreters. As an additional benefit, the proposed method makes the encrypted file appear smaller and conceals its actual size. The proposed Encryption Booster algorithm is also easily integrated with Advanced Encryption Standard. 2023 IEEE. -
Asynchronous Method of Oracle: A Cost-Effective and Reliable Model for Cloud Migration Using Incremental Backups
Cloud Computing has reached a new level in flexibility to provide infrastructure. The proper migration method should be chosen for better cost management and to avoid overpayments to unused resources. So, the migrations from On-Premises to cloud infrastructure is a challenge. The migration can be done in synchronous or asynchronous modes. The synchronous method is mostly used to minimize downtime while doing the cloud migrations. The asynchronous methods can do the migrations in offline mode and very consistently. This paper addresses various issues related to the synchronous mode of Oracle while doing highly transactional database migrations. The proposed methodology provides a solution with a combination of asynchronous and incremental backups for highly transactional databases. This proposed method will be a more cost-effective and reliable model without compromising consistency and integrity. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Effects of Peer Monitoring on Student Stress Level of College Students Based on Multi-Layer Perceptron Approach
The classroom is just one of many places where the proposed approach encounter stress. Previous studies have shown that college students experience high rates of stress. It is not known if the Student Stress Inventory-Stress Manifestations (SSI-SM) is useful in identifying stressors and evaluating stress manifestations among college students. To this end, it was created a college-specific version of the Student Stress Inventory-Stress Manifestations (SSI-SM) and administered it to students to determine its validity and reliability. These procedures comprise the proposed technique and include preprocessing, feature selection, and model training. It uses Normalization as a preprocessing approach. The term' normalization' refers to the procedure of rescaling or modifying data so that all categories have the same variance. The proposed approach employed linear discriminant analysis as a means of selecting features. The models are then trained using MLP after information gain has been used to choose relevant features. The proposed approach achieves better results than the two leading alternatives, CNN and RNN. 2024 IEEE. -
Impact of Learning Functions on Prediction of Stock Data in Neural Network
Digitization has made a vast impact on the modern society. Financial sector is one field where a huge revolution has been experienced because of digitization. Financial data especially time series data is being stored in the digital repositories where it can be used for prediction and analysis. One such data is a stock market data which is a time series data and is generated in a huge amount every second. The stock market data is of great importance as the proper analysis and prediction of data can transform the fate of the global market. Thus the companies and the individuals are looking forward for the development of the automated techniques that can predict stock market data accurately in a real time. In this regard, many researchers developed machine learning techniques such as use of neural network for prediction of stock data. The most common learning function used in neural network is sigmoid function. However, we found that there are many learning functions are available for building neural network. In this paper we are studying the impact of four different learning functions in estimating/predicting the stock value. From the experimental study we found that unipolar sigmoid learning function produced an accuracy of 95.65%, bipolar sigmoid produced an accuracy of 91.34%, tan hyperbolic equation produced an accuracy of 91.02%, and radial base equation produced an accuracy of 87.53%. Clearly, unipolar sigmoid function emerged as the best learning function to build stock data prediction model. The main reason behind its out-performance of unipolar sigmoid is its less complex structure and the 0 to 1 range. 2018 IEEE. -
Fraud Detection in Credit Card Transaction Using ANN and SVM
Digital Payment fraudulent cases have increased with the rapid growth of e-commerce. Masses use credit card payments for both online and day-to-day purchasing. Hence, payment fraud utilizes a billion-dollar business, and it is growing fast. The frauds use different patterns to make the transactions from the cardholders account, making it difficult for the organization or the users to detect fraudulent transactions. The studys principal purpose is to develop an efficient supervised learning technique to detect credit card fraudulent transactions to minimize the customers and organizations losses. The respective classification accuracy compares supervised learning techniques such as deep learning-based ANN and machine learning-based SVM models. This studys significant outcome is to find an efficient supervised learning technique with minimum computational time and maximum accuracy to identify the fraudulent act in credit card transactions to minimize the losses incurred by the consumers and banks. 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. -
Exploring Investment Behaviour of Working Women for Economic Empowerment
Growth in investments leads to the economic and household upliftment of each person. We can see the presence of women in every area of our economy. They play the role of a teacher, doctor, nurse, engineer, accountant, military officers, entrepreneur, and many more. Now women are more educated; they have their assets in gold and other precious ornaments. They are also aware of various investment schemes available. This study analyzes working women's investment behavior and examines how it is beneficial for our society's economic and household upliftment. The data collection was carried out through 400 respondents using a questionnaire. The study area covers only the Bengaluru Urban population. Five Taluks in the Bengaluru urban were selected for the study. Cluster sampling is followed for selecting samples, and data is collected from each clusters. Eighty samples from each cluster were selected, and data is collected using the survey method. The tools used for data analysis consist of Henry Garrett ranking method, Weighted Average Method, and Percentage Analysis. Risk preferences of the investors were analyzed using the factors derived from the article written by Vashisht and Gupta, 2005. The current study aims at salaried women employees who have a regular income, which they can contribute to savings and investment for the economic and household developments. 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
Impact of Prolonged Screen Time on the Mental Health of Students During COVID-19
The COVID-19 pandemic has struck every sector around the world, including the education sector. The pandemic has forced educational institutions around the world to close, putting academic calendars in jeopardy. To keep academic activities going, most educational institutes have switched to online learning platforms. However, the lack of e-learning readiness and the current crisis has taken a toll on students mental health significantly. In this study, we hope to understand better students impressions of online education and the impact of prolonged screen time on students mental health. From the responses of 438 students, our study aims to identify the causes of stress in students due to the online mode of education. From eye stress to limited social interaction, all factors leading to poor mental health are considered. Suggestions for addressing the challenges of online education and approaches to create a more successful online learning environment are also provided. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Tumor Infiltration of Microrobot using Magnetic torque and AI Technique
Because of their surroundings and lifestyle alternatives, human beings, these days be afflicted by a huge style of illnesses. thus, early contamination prediction will become crucial. on the other hand, primarily based just on signs, docs warfare to make correct forecasts. The most challenging issue is accurately forecasting illnesses, which is why machine learning is essential to accomplish this task. To identify concealed patterns within vast amounts of medical data, disease information is processed using data mining techniques. We evolved a extensive contamination prediction primarily based on the affected person's signs. We rent the device getting to know techniques Convolutional Neural network (CNN) and ANFIS to exactly count on sickness (adaptive community-based totally fuzzy inference machine). For an correct forecast, this trendy illness prediction considers the character's way of life picks and fitness history. ANFIS outperforms CNN's set of rules in phrases of popular infection prediction, with an accuracy price of 96.7%. additionally, CNN consumes extra memory and processing energy than ANFIS because it trains and assessments on facts from the UCI repository. The Anaconda notebook is a suitable tool for implementing Python programming as it contains a range of libraries and header files that enhance the accuracy and precision of the process. 2023 IEEE. -
Real-time Litter Recognition Using Improved YOLOv4 Tiny Algorithm
Littered roads have become a familiar sight in India. The main reason is the increasing population and inefficient waste disposal system. Since garbage collectors cannot pick litter in all the places, there is a need for an efficient way to detect it. Hence, a machine learning-based object detection model is used. In this, we have applied an improved YOLOv4-Tiny algorithm to detect the garbage, classify it and make the detection process easier on custom datasets. We have improved the algorithm in terms of the object prediction time, this is done by replacing a max pooling layer with one of two layers present in a fully connected layer. When an input is given, the algorithm detects the litter in the image with a bounding box around it along with the label and confidence score. The proposed model reduces the prediction time by 0.517 milliseconds less than the original algorithm employed which concludes that the object is predicted faster. 2022 IEEE. -
Explainable Artificial Intelligence: Frameworks for Ensuring the Trustworthiness
The growing computer power and ubiquity of big data are allowing Artificial Intelligence (AI) to gain widespread adoption and applicability in a wide range of sectors. The absence of an explanation for the conclusions made by today's AI algorithms is a significant disadvantage in crucial decision-making systems. For example, existing black-box AI systems are vulnerable to bias and adversarial assaults, which can taint the learning and inference processes. Explainable AI (XAI) is a recent trend in AI algorithms that gives explanations for their AI conclusions. Many contemporary AI systems have been shown to be vulnerable to undetectable assaults, biased against underrepresented groups, and deficient in user privacy protection. These flaws damage the user experience and undermine people's faith in all AI systems. This study proposes a systematic way to tie the social science notions of trust to the technology employed in AI-based services and products. 2024 IEEE.