Browse Items (9798 total)
Sort by:
-
Exploratory analysis of legal case citation data using node embedding
Legal case citation network is primary tool to understand mutable landscape of the legal domain. These networks are also used to study legal knowledge transfer, similar precedents and inter-relationship among laws of a judiciary. These networks are often very huge and complex due to the multidimensional texture of this domain. In recent years, network embedding using deep learning emerges as a promising breakthrough for analyzing networks. This paper presents a novel approach of learning vector representation for a legal case based on its citation context in the network using node2vec algorithm. These vector embedding are further used in understanding similarities between cases. Paper highlights that the tSNE reduced representation of the obtained vectors facilitates visual exploration and provides insights into the complex citation network. Suitability of node embedding for application of machine learning algorithm is demonstrated by clustering the node vectors for finding similar cases. ICIC International 2019. -
Exploratory Architectures Analysis of Various Pre-trained Image Classification Models for Deep Learning
The image classification is one of the significant applications in the area of Deep Learning (DL) with respective to various sectors. Different types of neural network architectures are available to perform the image classification and each of which produces the different accuracy. The dataset and the features used are influence the outcome of the model. The research community is working towards the generalized model at least to the domain specific. On this gesture the contemporary survey of various Deep Learning models is identified using knowledge information management methods to move further to provide optimal architecture and also to generalized Deep Learning model to classify images narrow down to the sector specific. The study systematically presents the different types of architecture, its variants, layers and parameters used for each version of Deep Learning model. Domain specific applications and limitations of the type of architecture are detailed. It helps the researchers to select appropriate Deep Learning architecture for specific sector. 2024 by the authors. -
Exploring Advances in Machine Learning and Deep Learning for Anticipating Air Quality Index and Forecasting Ambient Air Pollutants: A Comprehensive Review with Trend Analysis
India and the rest of the world are growing more and more worried about polluted atmosphere on a daily basis. A comprehensive prevision and prognostication of air quality parameters is vital due to the major harm that air pollution causes to both the environment and public health, causing concern on a global scale. In-depth analyses of the methods for predicting ambient air pollutants, like carbon monoxide (CO), sulfur dioxide (SO2), nitrogen dioxide (NO2), particulate matter with diameters less than 10? (PM10) and less than 2.5? (PM2.5), and ozone (O3), are provided in this work in tandem with the modeling of the Air Quality Index (AQI).To further enhance the anticipated precision and applicability of these models, the assessment additionally employs trend analysis to determine precedents and new trends in air quality. This paper offers insights into recent advances in algorithms using deep learning and machine learning for anticipating AQI and forecasting pollutant concentrations by combining current research in this topic. In order to inform policy decisions and measures aimed at reducing air pollution and its adverse effects on public health, trend analysis integration affords a more thorough comprehension of the dynamics of air quality. 2024 IEEE. -
Exploring AI and ML Strategies for Crop Health Monitoring and Management
This chapter offers a thorough examination of machine learning (ML) and artificial intelligence (AI) approaches designed especially for agricultural crop health monitoring. The story starts with a basic introduction to AI and ML ideas and then covers supervised and unsupervised learning approaches, the fundamentals of reinforcement learning, and the significance of high-quality data preparation in agricultural settings. This chapter explores the use of deep learning architectures and neural networks, explaining how they can be used to simulate human brain activity and how they can be used in picture identification to identify crop diseases. A detailed analysis is conducted of the practical aspects of ML for agriculture, encompassing feature engineering and model assessment methodologies. Additionally, the chapter highlights the ethical issues involved in the proper application of AI/ML models in agricultural contexts. These kinds of applications. In conclusion, the chapter discusses obstacles, offers predictions for future developments, and discusses new lines of inquiry for AI and ML research related to crop health monitoring. Through this thorough research, the chapter seeks to offer insightful information on the transformative potential of AI/ML approaches in supporting efficient and sustainable agriculture practices for improved crop health management. (Publisher name) (publishing year) all right reserved. -
Exploring ARIMA Models with Interacted Lagged Variables for Forecasting
Including interactions among the explanatory variables in regression models is a common phenomenon. However, including interactions existing among lagged variables in autoregressive models has not been explored so far. In this paper, Autoregressive Integrated Moving Average (ARIMA) model with interactions among the lagged variables is proposed for improving forecast accuracy. The methodology for identifying the interacted lagged variables and including them in the ARIMA model is suggested. Using five different data sets of different types, the paper explores the effect of interacted lagged variables in ARIMA model. The experimental results exhibit that when interactions do actually exist, ARIMA model with interactions improves the forecast accuracy as compared to ARIMA model without interactions. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Exploring artificial intelligence techniques for diabetic retinopathy detection: A case study
There is a notable increase in the prevalence of Diabetic Retinopathy (DR) globally. This increase is caused due to type2 diabetes, diabetes mellitus (DM). Among people, diabetes leads to vision loss or Diabetic Retinopathy. Early detection is very much necessary for timely intervention and appropriate treatment on vision loss among diabetic patients. This chapter explores how Artificial Intelligence (AI) methods are helpful in automated detection of diabetic retinopathy. In this chapter deep learning algorithm is proposed that is used to extract important features from retinal images and classify the images to identify the presence of DR. The model is evaluated using various metrics like specificity, sensitivity etc. The results of the case study provide an AI driven solution to existing methods used to identify DR and this can improve the early detection and appropriate treatment at the right time. 2024, IGI Global. All rights reserved. -
Exploring BERT and Bi-LSTM for Toxic Comment Classification: A Comparative Analysis
This study analyzes on the classification of toxic comments in online conversations using advanced natural language processing (NLP) techniques. Leveraging advanced natural language processing (NLP) techniques and classification models, including BERT and Bi-LSTM models to classify comments into 6 types of toxicity: toxic, obscene, threat, insult, severe toxic and identity hate. The study achieves competitive performance. Specifically, fine-tuning BERT using TensorFlow and Hugging Face Transformers resulted in an AUC ROC rate of 98.23%, while LSTM yielded a binary accuracy of 96.07%. The results demonstrate the effectiveness of using transformer-based models like BERT for toxicity classification in text data. The study discusses the methodology, model architectures, and evaluation metrics, highlighting the effectiveness of each approach in identifying and classifying toxic language. Additionally, the paper discusses the implementation of a userfriendly interface for real-time toxic comment detection, leveraging the trained models for efficient moderation of online content. 2024 IEEE. -
Exploring best practices in mobile app design patterns and tools: A user-centered approach
Design patterns are reusable solutions to common design problems that provide a consistent user experience across different apps. This article explores the best practices in mobile app design patterns and tools with a focus on the user-centered approach to design. Design patterns such as navigation bars, tab bars, list views, and card views are discussed, along with design tools such as Sketch, Figma, Adobe XD, and InVision. The problem is to ensure that mobile app design is centered around the needs and preferences of the user, rather than the designer or the technology, and that the right design patterns and tools are used to create interfaces that are familiar and easy to use. The chapter emphasizes the importance of conducting user research to understand the needs and preferences of the target audience and using design patterns and tools to create interfaces that are familiar and easy to use. Mobile apps have become an integral part of our lives, and designing a successful mobile app is a challenging task that requires a thorough understanding of user needs and preferences. 2023, IGI Global. All rights reserved. -
Exploring Bio Signals for Smart Systems: An Investigation into the Acquisition and Processing Techniques
Bio signals play a vital role in terms of communication in the absence of normal communication. Bio signals were automatically evolved from the body whenever any actions took place. There are lots of different types of bio signal based research going on currently from several researchers. Signal acquisition, processing the signals and segmenting the signal were totally different from one technique to another. Placing electrodes and its standard measurements were varied. The signals gathered from each subject may be varied due to their involvement. Each and every trial of signals can generate different patterns. Each and every pattern generated from the activities also has a different meaning. In this study we planned to analyze the basic measurement techniques handled to record the bio signals like Electrooculogram. 2023 IEEE. -
Exploring challenges in online higher education for AI integration using MICMAC analysis
The consequence of Covid-19 has affected the traditional higher education system. Acknowledging the significant role of online education in national development for accessibility and quality education, countries around the world have understood its importance in current digital era. Indian policymakers have been giving due importance to enhancing the education quality, however the progress made by the country in higher education is not adequate. Amidst all the inadequacies of traditional education system, artificial intelligence (AI) technologies are bringing new ray of hope to democratize education system. This chapter is subjected to identify the challenges in online education and suggest specific ways to address each of them. The challenges are categorized into internal and external challenges/barriers. These challenges have been modeled with the expertise of educationalist's opinions and interpretive structural modeling to create a hierarchy of the barriers using MICMAC analysis and categorize these barriers into four clusters. 2024, IGI Global. All rights reserved. -
Exploring chatbot trust: Antecedents and behavioural outcomes
An awareness about the antecedents and behavioural outcomes of trust in chatbots can enable service providers to design suitable marketing strategies. An online questionnaire was administered to users of four major banking chatbots (SBI Intelligent Assistant, HDFC Bank's Electronic Virtual Assistant, ICICI bank's iPal, and Axis Aha) in India. A total of 507 samples were received of which 435 were complete and subject to analysis to test the hypotheses. Based on the results, it is found that the hypothesised antecedents, except interface, design, and technology fear factors, could explain 38.6% of the variance in the banking chatbot trust. Further, in terms of behavioural outcomes chatbot trust could explain, 9.9% of the variance in customer attitude, 11.4% of the variance in behavioural intention, and 13.6% of the variance in user satisfaction. The study provides valuable insights for managers on how they can leverage chatbot trust to increase customer interaction with their brand. By proposing and testing a novel conceptual model and examining the factors that impact chatbot trust and its key outcomes, this study significantly contributes to the AI marketing literature. 2023 The Authors -
Exploring Cross-cultural Comfort Food Narratives in Beryl Shereshewskys YouTube Videos
This article explores how certain food and the stories linked to the same are capable of evoking feelings of comfort and security. Food binds people together. The rituals and practices surrounding food inspire and sustain the association of various memories, experiences and emotions. The area of food studies is especially interested in how these linkages translate into the practice of nourishment. The narratives surrounding comfort food take on a cross-cultural flavour in the videos from Beryl Shereshewskys YouTube channel. This article analyses these narratives through the lens of Symbolic Interactionism to explicate how these food narratives bring people together from across the world by evoking the universal needs of food and comfort. Consequently, it is seen that even though it is true that the experience of consuming comfort food is extremely personal, it is also rendered as a universal phenomenon through the narratives that are created and shared. 2023 MICA-The School of Ideas. -
Exploring digital twins: Attributes, challenges and risks
The recent approach to digitalization and digital transformation is based on the focus of every industry to develop systems and practices for optimizing the operational phase of the product lifecycle and beyond. Digital twins have become the buzzword in the domain of digital transformation. These Digital twins, which are a virtual representation of real-world occurrences such as processes, services, or products offer a new perspective to digitalization. It has emerged from Industry 4.0 and involves a mapping of the real physical world and the virtual world through Digital Twinning. Artificial Intelligence, Cryptography, Blockchain, Big Data technologies, and IoT act as technology enablers for Digital Twins. The capability of Digital Twin is its ability to cater to diverse applications. Within a decade, it has penetrated deeply into every functional aspect of business right from Patient Health Information Systems to remote control and maintenance of satellites/ space stations and to agriculture. This chapter has a focus on the key attributes, challenges, and risk factors that pertain to digital twin technologies and provides adequate examples from diverse sectors. The key challenges of digital twin technologies include Modeling the unknown, Transparency, Interpretability, Interactions with physical assets, Large-scale computation, Physical realism, Future projections, Data management, Privacy, Security and Quality. The four facets of risks related to Digital Twins include restrictions in access to system resources, theft of intellectual property, lack of compliance, and integrity issues in data/information. Hence, additional efforts and a holistic approach towards privacy and security are required to manage these risks. The holistic approach should cover hardware, software, and firmware together with the information that passes between them. Further, it is required to ensure that system, assets and data are adequately protected. Digital Twin technologies provide enormous competitive advantage for an organization, and a more pragmatic approach for mitigation of risks associated with digital twins is required. This would involve co-creation of Digital Twins with clients along with combined extensive knowledge of physical assets, disruptive technologies and appropriate security measures. 2023 Nova Science Publishers, Inc. All rights reserved. -
Exploring Drivers of Healthcare Utilization amongthe Working and Non-Working Elderly Population: Insights from LASI
Background: The elderly population of India has been growing exponentially over the past few decades, caused by a decline in fertility and an increase in life expectancy. The growth eventually has transcended the disease burden on the public healthcare system. This calls for a need to evaluate the healthcare utilization pattern of the elderly based on their socioeconomic and working condition. Methods: Study used access to public and private healthcare services to measure healthcare utilization. Descriptive analysis and multivariable logistic regression were used to understand utilization patterns by working status and some selected sociodemographic parameters. All the results were reported at a 95% confidence interval. Results: Using the data from the first wave of Longitudinal Ageing Study in India (LASI) with a sample of 22,680 older persons 60 years and above. The study identified that 50% of the working elderly access private services; however, 26% access public healthcare services. It was found that the working status of the elderly alone did not influence access to healthcare services, but education is also an essential indicator for utilizing healthcare services. Further, factors such as gender, marital status, religion, wealth, tobacco usage, self-rated health, ADL and IADL were significant predictors of healthcare services utilization for the elderly. Conclusion: This study suggests that there are not many differences found among working and non-working status with healthcare utilization, although some sociodemographic indicators are associated with the utilization of healthcare services, highlighting that increasing health needs among the elderly requires strengthening the quality and appropriate public investment in health. 2024 Taylor & Francis Group, LLC. -
Exploring effect of instagram influencer likeability and personality traits on self-concept and impact on consumer buying intention towards cosmetic products
With the advent of visual micro-blogging platforms like Instagram the communication environment for businesses has certainly undergone massive change. Over the years these platforms have evolved and brands have had to adapt themselves to gain visibility among the millennial audience by being available on the social media platforms. The disruptive force of these social media platforms has a great impact on the consumer decision making processes. As a result, consumers now rely more on recommendation from their peers. The sharing of views, experiences, opinions and expectations online by the users on various social media platforms have become a trusted source of information for the consumers. This had led to brands connecting to online celebrities known as Social media influencers (SMI) to distribute information and influence consumer's product perceptions i.e., the concept of influencer marketing. SMI's are referred to as online opinion leaders with large numbers of followers to drive messages through their promotional posts. A lot of research has been done to study the impact of celebrity endorsements but currently there is a gap in research pertaining to consumer's perspective towards the SMI's and SMI's effects on consumers. The online survey of self -concept and alters its buying intentions when an influencer posts promotional conducted in the studies how the likeability and personality traits of an influencer affects the consumer understanding posts on Instagram. Significant relationships were found for both, the likability traits and consumer self-concept and personality traits and consumer self-concept. Also using predictive analysis, the extent to which each of the consumer self-concept statements affected the buying intentions was determined. These results provide practical implications for brand managers who plan to invest in influencer marketing. 2021 Ecological Society of India. All rights reserved. -
exploring effective Online-Teaching Transition of College Teachers During COVID-19
The study attempts to identify what is effective online teaching from teacher and student perspectives. What are the challenges faced by teachers which hampered effective online teaching? The study employed mixed method research design including a survey questionnaire and semi-structured interview. The study collected data from 500 students out of which 200 are boys and 300 are girls on effective online teaching. The study conducted semi-structured interview with eight college teachers through snowball sampling. The survey revealed that almost 80% of the teachers are not effective. Girls are less satisfied with online teaching transition of teachers than boys are. Similarly, postgraduates (PG) are not as satisfied as undergraduate (UG) students are. Interview data revealed themes and subthemes on challenges of effective online teaching faced by college teachers. Overall, the perceived online-teaching effectiveness is low, and further research may find the causes for the same. 2022 IGI Global. All rights reserved. -
Exploring Ethical Considerations: Privacy and Accountability in Conversational Agents like ChatGPT
In recent years, advances in artificial intelligence (AI) and machine learning have transformed the landscape of scientific study. Out of all of these, chatbot technology has come a long way in the last few years, especially since ChatGPT became a well-known artificial intelligence language model. This comprehensive review investigates ChatGPT's background, applications, primary challenges, and possible future advancements. We first look at its history, progress, and fundamental technology before delving into its many applications in customer service, health care, and education. We also discuss potential countermeasures and highlight the major challenges that ChatGPT faces, including data biases, moral dilemmas, and security threats. Finally, we go over our plans for ChatGPT's future, outlining areas that need further research and development, improved human-AI communication, closing the digital gap, and ChatGPT integration with other technologies. This study offers useful information for scholars, developers, and stakeholders interested in the rapidly evolving subject of artificial intelligence-powered conversational bots. This study looks at the ways that ChatGPT has changed scientific research in several domains, such as data processing, developing hypotheses, collaboration, and public outreach. In addition, the paper examines potential limitations and ethical quandaries associated with the use of ChatGPT in research, highlighting the importance of striking a balance between human expertise and AI-assisted innovation. The paper addresses multiple ethical issues with the state of computers today and how ChatGPT can cause people to oppose this notion. This study also has a number of ChatGPT biases and restrictions. It is noteworthy that in a very short period, ChatGPT has garnered significant interest from academics, research, and enterprises, notwithstanding several challenges and ethical issues. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Exploring evolution, development, and contribution of International Journal of Industrial and Systems Engineering (20052022): a bibliometric study
International Journal of Industrial and Systems Engineering (IJISE) reached its 18th year of publishing in 2023. A comprehensive assessment of 1,096 publications using the bibliometric data analysis technique is performed to understand growth of the journal for the past 18 years. Different indicators like co-occurrence of all keywords, co-authorship, citation and co-citation analysis of authors, countries, and institutions is performed through VOS Viewer software. The findings of the study emphasise contribution of IJISE to knowledge domain. Copyright 2024 Inderscience Enterprises Ltd. -
Exploring Explainable Artificial Intelligence for Transparent Decision Making
Artificial intelligence (AI) has become a potent tool in many fields, allowing complicated tasks to be completed with astounding effectiveness. However, as AI systems get more complex, worries about their interpretability and transparency have become increasingly prominent. It is now more important than ever to use Explainable Artificial Intelligence (XAI) methodologies in decision-making processes, where the capacity to comprehend and trust AI-based judgments is crucial. This abstract explores the idea of XAI and how important it is for promoting transparent decision-making. Finally, the development of Explainable Artificial Intelligence (XAI) has shown to be crucial for promoting clear decision-making in AI systems. XAI approaches close the cognitive gap between complicated algorithms and human comprehension by empowering users to comprehend and analyze the inner workings of AI models. XAI equips stakeholders to evaluate and trust AI systems, assuring fairness, accountability, and ethical standards in fields like healthcare and finance where AI-based choices have substantial ramifications. The development of XAI is essential for attaining AI's full potential while retaining transparency and human-centric decision making, despite ongoing hurdles. 2023 EDP Sciences. All rights reserved. -
Exploring factors of consumer perception and attitude towards organic food consumption in India
Organic food market is witnessing an exponential growth in India. However, contradictory to expectations consumption of organic foods as compared to conventional food is still at nascent stage and many empirical studies have indicated this trend. Many of the food retailers have started organic food business across the nation but consumption level has remained significantly low. Impetus for this study came from this contrarian trend and it is crucial to garner insights from awareness and attitude of consumers towards organic food products in terms of why there is gap between awareness and attitude and actual consumption. While there are many empirical studies, not many studies have been conducted in India context. This study is based on descriptive research design constituting a sample of 250 respondents and the data was collected by administering a questionnaire on Likert scale. Study revealed that there was significant gap between perception and attitude of consumers. Factors namely health benefits and concern for environment have higher influence Price sensitivity. Thus, this study helps to bring about an understanding regarding the awareness and attitude of consumers towards organic food products in terms of opportunities ahead and overcoming unaddressed issues. 2021 Ecological Society of India. All rights reserved.