Browse Items (11809 total)
Sort by:
-
An Efficient Compressive Data Collection Scheme for Wireless Sensor Networks
The Compressive Data Collection (CDC) scheme is an efficient data-acquiring method that uses compressive sensing to decrease the bulk of data transmitted. Most existing schemes are modeled as Non-Uniform Sparse Random Projection (NSRP), and an NSRP-based estimator is used. These models cannot deal with anomaly readings that deviate from their standards and norms. Therefore, we provide a new CDC strategy in this study that uses an opportunistic estimator and routing. Initially, neighbor nodes are identified using the covariance function following the Gaussian process regression, and the data transfer to the neighbor node is done using the compressive sensing technique. Compressed data are then projected by using conventional random projection. Finally, the sample required to retrieve data is estimated using margin-free and maximum likelihood estimators. Results show that the sample needed to retrieve the data is less in the proposed scheme. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Effectiveness of Telemedicine in Disaster Relief Response Management
Due to climate change many parts of the worlds are prone to natural disasters. Thus, disaster management is the need of the hour. Effectiveness of Telemedicine in Disaster Relief response management shows the demand for telemedicine in the current time to tackle disasters. This paper investigates the history and evolution of telemedicine, their types, demand, challenges and its prospects. The proposed model, CrisisResponsive E-Health Recovery, places an approach on a concise way to manage disaster in the least time without giving up accuracy. The suggested model has the best response time as compared to the other existing model. Wide implementation of this model will result in better recovery rates in disasters. 2024 IEEE. -
Economic Growth, Automation and Environmental Degradation: An Empirical Evidence from Asian Countries
In the era of Industry 4.0 the increase in population as a result of environmental erosion is the prime concern in the global scenario, Asia as the biggest continent is very much applied to it. In this context assessment of the interrelation relationship between automation, financial development, environmental degradation, and per capita growth of 12 Asian Countries from 1995 to 2022 using the panel ARDL model, in addition to assessing the cause-effect relationship panel causality test also incorporated. As a part of ARDL PMG estimation results demonstrated that capital formation, import automation machinery, urban population growth, and ecological footprint positively impact per capita in the long term. But in this phenomenon, aggregate industrial value added negatively impacts per capita, because of automation labor displacement. Results from the causality test suggest that economic upswing, and urban population growth two-way causal relationship. However, capital formation, value-added, and ecological footprint positively impacted per capita growth. Regarding policy formulation need to formulate the necessary skill development program so that individuals can cope with the new decade of automation, in addition, ecological footprint as an indicator of environmental degradation positively impacts per capita growth, so the government needs to make a strategy at the societal level toward sustainable ecofriendly behavior. 2024 IEEE. -
Machine Learning Algorithms for Stroke Risk Prediction Leveraging on Explainable Artificial Intelligence Techniques (XAI)
Stroke poses a significant global health challenge, contributing to widespread mortality and disability. Identifying predictors of stroke risk is crucial for enabling timely interventions, thereby reducing the increasing impact of strokes. This research addresses this imperative by employing Explainable Artificial Intelligence (XAI) techniques to pinpoint stroke risk predictors. To bridge existing gaps, six machine learning models were assessed using key performance metrics. Utilising the Synthetic Minority Over-sampling Technique (SMOTE) to minimize the impact of the imbalanced nature of the dataset used in this research, the Random Forest algorithm emerged as the most effective among the algorithms with an accuracy of 94.5%, AUC-ROC of 0.95, recall of 0.96, precision of 0.93, and an F1 score of 0.95. This study explored the interpretation of these algorithms and results using Local Interpretable Model-agnostic Explanations (LIME) and Explain Like I'm Five (ELI5). With the interpretations, healthcare providers can gain insight into patients' stroke risk predictions. Key stroke risk factors highlighted by the study include Age, Marital Status, Glucose Level, Body Mass Index, Work Type, Heart Disease, and Gender. This research significantly contributes to healthcare and healthcare informatics by providing insights that can enhance strategies for stroke prevention and management, ultimately leading to improved patient care. The identified predictors offer valuable information for healthcare professionals to develop targeted interventions, fostering a proactive approach to mitigating the impact of strokes on individuals and the healthcare system. 2024 IEEE. -
Combatting Phishing Threats: An NLP-Based Programming Approach for Detection of Malicious Emails and Texts
Attackers are employing more advanced strategies to trick people into divulging private information or carrying out harmful deeds, and phishing is still a serious cybersecurity risk. We provide a new method in this study that combines algorithms based on AI-based expert systems and deep learning (ML) with the use of NLP-based programming (NLP) approaches to identify fraudulent emails and messages. Using a variety of datasets that include samples of both authentic and phishing messages, our approach preprocesses textual data, extracts relevant characteristics, and trains AI-based expert systems and deep learning models. Metrics including accuracy, precision, recall, and F1-score are used to assess the effectiveness of different AI-based expert systems and deep learning methods, such as logistic regression, random forests, decision trees, and neural networks, among others. To collect semantic information and increase detection accuracy, we also investigate the integration of sophisticated NLP-based techniques, such as word embeddings. The efficacy of our suggested strategy in reducing this common cybersecurity issue is highlighted by our results, which show promising performance in correctly recognizing phishing attempts. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
An Analysis of Financial and Technological Factors Influencing AgriTech Acceptance in Bengaluru Division, Karnataka
In 2023, India surpassed China to become the world's most populated nation. This demographic surge has precipitated an escalating exigency for sustenance as populace burgeons unabatedly. To satiate this burgeoning demand there arises an imperative to augment yield of agriculture commensurately. It is pertinent to acknowledge that as per Global Hunger Index of 2019, India occupies disconcerting rank of 102 amongst consortium of 117 nations when gauged by severity of hunger quantified through Hunger Severity Scale with disquieting score of 30.3. Aspiration of attaining utopian objective of zero hunger by 2030 as promulgated by Sustainable Development Goals appears to be quixotic endeavor seemingly beyond realm of plausibility. In this milieu agricultural technology (AgriTech) enterprises within India present veritable opportunity to invigorate agricultural sector. Agrarian landscape of India has been undergoing profound metamorphosis owing to technological renaissance that has permeated nation facilitated by innovative solutions proffered by nascent corporate entities. State of Karnataka stands as an epicenter of sorts for AgriTech enterprises within India. In this study we meticulously scrutinize impact wielded by financial factors on adoption of AgriTech solutions by agrarian stakeholders and elucidate technological determinants that actuate embracement of AgriTech within this demographic. The study uses descriptive statistics and chi-square analyses to rigorously assess predefined objectives. Geographic ambit of this inquiry encompasses regions of Chikkaballapura and Doddaballapura Taluks situated within Bengaluru division of Karnataka in 2022. The empirical revelations distinctly illuminate that individuals vested with access to technological and financial resources exemplified by parameters such as annual household income, accessibility to commercial banking services, cooperative financial institutions, mobile telephony, internet connectivity and Global Positioning System (GPS) technology exhibit palpable predilection for integration of AgriTech solutions into their agrarian practices. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Sentiment Analysis for Online Shopping Reviews Using Machine Learning
Everyday shoppers need reliable and insightful reviews of e-commerce websites to enhance their shopping experience. This research study explores sentiment analysis on Amazon reviews. It utilizes them as a diverse repository of customer opinions by unlocking their embedded sentiments, thereby recognizing their pivotal role in guiding potential buyers. Sentiment misinterpretations may result from many machine learning models that have trouble comprehending the context of Amazon reviews, particularly regarding subtle wordings, sarcasm, or irony. Additionally, these models can have biases that skew sentiment analysis results, mainly when working with a diverse set of Amazon review datasets. To overcome these, three machine learning models, namely, Bidirectional Encoder Representations from Transformers (BERT), Bidirectional and Auto-Regressive Transformers (BART), and Generative Pre-trained Transformers (GPT) are used in this study. During the experimental research, it was observed that BERT gave the highest accuracy of 90% when compared with BART (70%) and GPT (84%) models. BERTs bidirectional contextual comprehension at identifying subtleties in language provides a thorough and realistic representation of the sentiments of Amazon users, which is why the model gave the highest accuracy. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Securing the Digital Realm: Unmasking Fraud in Online Transactions Using Supervised Machine Learning Techniques
A key component of contemporary banking systems and e-commerce platforms is identifying fraud in online transactions. Traditional rule-based techniques are insufficient for preventing sophisticated fraud schemes because of the increasing complexity and number of expanding online transactions. This research study examines the development of fraud detection methods, emphasizing data analytics and machine learning (ML) models. The study also focuses on the fact that developing efficient fraud detection systems requires continuous observation, data preprocessing, feature selection, and testing of models. Seven ML models, Logistic Regression (LR), Decision Trees (DT), k-Nearest Neighbors (kNN), Nae Bayes (NB), Support Vector Machine (SVM), Random Forests (RF), and Extreme Gradient Boosting (XGBoost) are considered for classifying the dataset into fraudulent or not. During the experimentation study, it was observed that XGBoost yielded the highest accuracy of 99% when compared to other models. Users can determine which features significantly influence the model's predictions by using XGBoost's feature significance insights. Additionally, XGBoost provides integrated support for managing missing values in data, negating the requirement for imputation and other preprocessing procedures. Due to these, it performed better. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Text Summarization Techniques for Kannada Language
Text Summarization is summarizing the original text document into a shorter description. This short version should retain the meaning and information content of the original text document. A concise summary can help humans quickly understand a large original document better in a short time. Summarization can be used in many text documents, such as reviews of books, movies, newspaper articles, content, and huge documents. Text summarization is broadly classified into extractive Text Summarization (ETS) and Abstractive Text Summarization (ATS). Even though more research works are carried out using extractive methods, meaningful summaries can be attained using abstractive summary techniques, which are more complex. In Indian languages, very few works are carried out in abstract summarization, and there is a high need for research in this area. The paper aims to generate extractive and abstractive summaries of the text by using deep learning and extractive summaries and comparisons between them in the Kannada language. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Predictive Analytics for Network Traffic Management
It examines how this can be applied to monitoring network traffic and carrying out predictive analysis to improve the functionality and effectiveness of network management. The study uses historical data of the network traffics and uses machine learning techniques such as the Long Short Term Memory based models and the Ensemble Methods to predict the traffic patterns in the future. It includes data gathering, data pre-processing, feature selection, model choice, model training, model validation, and the architectural setup of the machine learning solution in a real-time stream processing pipeline using Apache Kafka and Apache Flink. It is evident from the results that the proposed models yield a high level of accuracy in terms of prediction and that the Ensemble method alone gives a slightly higher accuracy than LSTM in the specific metrics. Real-time values closely followed actual traffic level, thus allowing real-time adjustments in network usage. In light of this, there is a clear understanding of the significance of having reliable data preprocessing, feature engineering, and model optimization process. The study also notes the need in prediction concerning data quality and scalability issues taking into account that current and future networks are characterized as dynamic and highly complex to offer more effective solutions for intelligent and proactive networking. 2024 IEEE. -
A Comprehensive Review of Small Building Detection in Collapsed Images: Advancements and Applications of Machine Learning Algorithms
Accurately identifying small buildings in images of collapses is essential for disaster assessment and urban planning. In the context of collapsed images, this study provides an extensive overview of the methods and approaches used for small building detection. The investigation covers developments in machine learning algorithms, their uses, and the consequences for urban development and disaster management. This work attempts to give a brief grasp of the difficulties, approaches, and potential paths in the field of small building detection from collapsed imaging through a thorough investigation of the body of existing literature. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Recent Advances in Pedestrian Identification Using LiDAR and Deep Learning Methods in Autonomous Vehicles
The myriad benefits of autonomous vehicles (AVs) encompassing passenger convenience, heightened safety, fuel consumption reduction, traffic decongestion, accident mitigation, cost-efficiency and heightened dependability have underpinned their burgeoning popularity. Prior to their full-scale integration into primary road networks substantial functional impediments in AVs necessitate resolution. An indispensable feature for AVs is pedestrian detection crucial for collision avoidance. Advent of automated driving is swiftly materializing owing to consistent deployment of deep learning (DL) methodologies for obstacle identification coupled with expeditious evolution of sensor and communication technologies exemplified by LiDAR systems. This study undertakes exploration of DL-based pedestrian detection algorithms with particular focus on YOLO and R CNN for purpose of processing intricate imagery akin to LiDAR sensor outputs. Recent epochs have witnessed DL approaches emerge as potentially potent avenue for augmenting real-time obstacle recognition and avoidance capabilities of autonomous vehicles. Within this scholarly exposition we undertake exhaustive examination of latest breakthroughs in pedestrian detection leveraging synergy of LiDAR and DL systems. This discourse comprehensively catalogues most pressing unresolved issues within realm of LiDAR-DL solutions furnishing compass for prospective researchers embarking on journey to forge forthcoming generation of economically viable autonomous vehicles. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Real-time Traffic Prediction in 5G Networks Using LSTM Networks
This research explores the application of Long Short-Term Memory (LSTM) networks for real-time traffic prediction within 5G networks, aiming to address the critical need for accurate prediction models in dynamic network environments. Leveraging the sequential learning capabilities of LSTM networks, the proposed methodology encompasses dataset preparation, model architecture design, training, and evaluation. Experimental results demonstrate the effectiveness of the LSTM-based prediction model in capturing temporal dependencies and providing reliable predictions across various prediction horizons. While promising, further research is warranted to enhance the model's performance and address remaining challenges. This study contributes to advancing the state-of-the-art in traffic prediction methodologies, facilitating more efficient network management and optimization in 5G environments. 2024 IEEE. -
A Study on Challenges and Solutions in the Uptake of Agricultural Technology Startups Services in Karnataka
In congruence with overarching trend of digitalization sweeping across India, agricultural sector is currently experiencing remarkable advancements propelled by innovative technological solutions introduced by emerging startups in agritech domain. The state of Karnataka is swiftly solidifying its position as preeminent leader in agritech industry attracting heightened interest from venture capital investors in recent times and emerging as dominant recipient of these investments garnering substantial 52% share followed by Maharashtra at 18% and Tamil Nadu at 9.2%. The principal aim of this research endeavor is to scrutinize socioeconomic impediments hindering adoption of AgriTech within rural precincts of Karnataka specifically in districts of Rural Bangalore (Doddabalapura and Nelmangala) and Davanagere (Shiramagondonahalli). The study seeks to gauge perceptions of farmers regarding potential solutions aimed at fostering greater adoption of AgriTech in these aforementioned regions. The study employed descriptive analysis by utilizing data obtained from judiciously selected sample of 120 farmers dichotomized into those who had availed themselves of AgriTech services and those who had not as provided by AgriTech firms. Empirical findings illuminate formidable impact of socioeconomic factors encompassing economic standing, land ownership classification and educational attainment in shaping farmers receptivity toward AgriTech utilization. The study unearthed valuable insights pertaining to propositions put forth by farmers to enhance adoption of AgriTech practices among their peers. The study furnishes valuable elucidations concerning barriers impeding adoption of AgriTech and offers viable solutions to invigorate increased participation among farmers in realm of AgriTech proffering pertinent recommendations to stakeholders such as AgriTech startup executives, researchers and policymakers urging them to meticulously assess local socioeconomic dynamics and tailor AgriTech services in accordance with discerned needs and preferences of farming community. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Behavioral Time Management Analysis: Clustering Productivity Patterns using K-Means
This paper focuses on investigating the efficiency profile through the three-time management behaviors using the K-Means clustering method. In the case of the study, the data gathered from digital time management tools for 100 participants for one month was preprocessed to distil features surrounding productivity, including daily working hours, focus time, break duration and frequency, and task completion ratios. The four groups that were agreed upon through K-Means clustering differed in terms of time management behaviours and productivity. Insert table 6 IT cluster 1 worked long hours with high productivity owing to the fact that they are IT professionals but had a tendency of multitasking. Employment Cluster 2 (marketing and sales professionals) achieved both personal and work-related self-care but identified the need for more concentrated time per task. As for the differences in the breaks, it can be noted that cluster 3 (management and administration personnel) had significantly higher task completion times and focus times, but their break intervals needed to be optimized. Hypothesis 2 stated that there will be many hours of leisure for Cluster 4 (students and interns) imply that their work hours should be adjusted to several small tasks a day, and their rates of task completion should be increased. From the study, it is possible to stress that time management should be considered as an individual activity that requires specific approaches to the given subject area and to the learner in particular. Specifically, demographic profiling identified the roles that age and occupational status may play in averting or exacerbating productivity deficiencies: insights that could be actionable in specific scenarios. The implications of this research offer practical insights into individual and organizational time management, as the usability aspects of machine learning techniques were considered and their applicability established, which further extends the scope of time management by revealing patterns and improving time management plans and practices. 2024 IEEE. -
Cloud-Based Cataract Recognition System Using Hybrid Classifier Model
One of the key challenges of ophthalmologists is to diagnose the various ranges of ophthalmological illnesses such as diabetic retinopathy, cataract, and glaucoma. Here, cataract disease is identified as the one of the leading and most common ophthalmological problems that occurs due to aging. A computer-assisted cataract detection and diagnosis support system is required by the ophthalmologists to overcome the error that occurs during manual screening process. So, a cloud-based cataract recognition system is proposed using the convolutional neural network with support vector machine classifier model to improve the prediction accuracy, sensitivity, specificity, precision, recall, F1-score, and Mathews correlation coefficient. Moreover, the four-layer convolutional neural network is finetuned with a rich set of features and trained with various network models such as Inception V3, MobileNet, VGG-16, VGG-19, and ResNet-101. Therefore, the proposed hybrid combination of ResNet-101 with support vector machine classifier makes better cataract detection and outperforms the existing classifier models in terms of above-mentioned performance evaluation metrics. Moreover, the proposed hybrid approach provides the better telemedical solution to remote people by providing accurate disease prediction and severity grading such as normal, mild, premature, and severe cataract. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Multimodal Emotion Recognition in HumanComputer Interaction Using MFF-CNN
The rise of technology in the digital era has amplified the importance of understanding human emotions in enhancing humancomputer interactions. Traditional interfaces, mainly focused on logical tasks, often miss the nuances of human emotion, creating a gap between human users and technology. Addressing this gap, the development of the HumanComputer Interface for emotional intelligence uses advanced algorithms and deep learning models to accurately recognize emotions from various cues like facial expressions, voice, and written text. This paper presented a significant approach for emotion detection in HCI and the challenges faced in capturing genuine emotional responses. Historically, the emphasis in HCI design was on operational tasks, neglecting emotional nuances. However, the tide is changing toward embedding emotional intelligence into these interfaces, leading to enhanced user experiences. This research introduces the MFF-CNN, a neural network model combining both textual and visual data for accurate emotion detection. Through sophisticated algorithms and the integration of advanced machine learning techniques, this paper presents a refined approach to emotion detection in HCI, supported by a comprehensive review of related works and a detailed methodology. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
A Narrative Synthesis on the Role of Affective Computing in Fostering Workplace Well-Being Using a Deep Learning Model
Emotional information is more valued in the modern workplaces with increased focus on the need for sensing, recognizing and responding to human emotions. Integrating human emotions as information for communication and decision-making is possible through the computer-based solution called as affective computing. Affective computing is a relatively less explored AI platform though the notion is more than two decades old. The cognitive algorithms employed in affective computing operates in three key areas, viz. context sensitivity, augmented reality, and proactiveness, with outcomes in the fields of emotion management, health, and productivity. Affective computing promises better management of organizational outcomes such as fostering workplace well-being, promoting happiness, productivity, engagement levels, and communication. Further, affective computing can play vital roles in an employees life cycle with applications in functional areas of HRM like employee selection, training and development, and performance management. Even as workplaces are increasingly adopting affective computing, an analysis of its positive effects can help practitioners take informed decisions about its implementation. This paper outlines the theoretical underpinnings of affective computing, discusses the relevance of ResNet50 in image analysis, and proposes a step-by-step methodology for implementing affective computing techniques in the workplace. The potential benefits and challenges of adopting affective computing in fostering workplace well-being are also discussed. Thus, this chapter investigates the role of affective computing in fostering well-being in the workplace usinga deep learning model. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
LULC Analysis of Green Cover Loss in Bangalore
Urbanization of the cities especially the Indian City of Bangalore has led to the creation of an important discourse concerning development and conservation. The study carries out a detailed LULC study with special reference to Green Cover Loss in city of Bangalore. Using satellite images from 2014 to 2023 period and machine learning tools, the study establishes declines in green spaces with economic, environmental and health consequences of the city's uncontrolled expansion. The innovations afforded to the study regard methodologically on the use of ResNet50 for accurate LULC classification with an accuracy of 92% Hence the study reveals the interaction between urbanization and conservation, the efficiency of which requires policy adjustments that depend on existing knowledge. The study not only accustomizes the progression in the geography of Bangalore but it also shapes the technology and methodology for the further geospatial research in the areas under rapidly urbanizing in the future. 2024 IEEE. -
Optimization Ensemble Learning Techniques for Reliable Crop Yield Prediction using ML
The agricultural sector's increasing reliance on technology has paved the way for advanced data-driven methodologies, with crop yield prediction emerging as a critical focus. This study dives into the complex landscape of crop yield prediction, employing a comprehensive approach that involves data preprocessing, model development, and performance evaluation. This research goes into enhancing crop yield prediction through a thorough data-driven approach. Beginning with comprehensive data preprocessing, including outlier analysis and feature scaling, the study ensures dataset integrity. Ensemble learning, employing Gradient Boosting Regressor, Random Forest Regressor and Decision Tree Regressor, captures intricate relationships within the dataset. Model performance, assessed through R-squared scores, demonstrates promising predictive capabilities. Subsequent outlier analysis and hyperparameter tuning yield substantial improvements, contributing valuable insights for agricultural decision-making. The research not only advances crop yield prediction but also offers practical guidance for integrating machine learning into agriculture, promising transformative outcomes for sustainable practices. The research also highlights how significant interpretability is to machine learning models so that stakeholders can comprehend and embrace them. This allows for a smooth integration of the models into current agricultural practices and encourages openness and reliability in decision-making. 2024 IEEE.