Browsing by Author "Pradeepika Verma"

Now showing 1 - 20 of 42

A Comprehensive Analysis of Indian Legal Documents Summarization Techniques
(Springer, 2023) Saloni Sharma; Surabhi Srivastava; Pradeepika Verma; Anshul Verma; Sachchida Nand Chaurasia
In the Legal AI field, the summarization of legal documents is very challenging. Since the Indian case documents are much noisier and poorly organized, the summarization of legal documents can be useful for legal professionals, who often have to read and analyze large amounts of legal text. During the review process of the legal documents, a team of reviewers may be needed to understand and for taking further actions. A branch of text summarization called ‘legal text summarization’ which is concerned with summarizing legal texts, such as court opinions, contracts, and legal briefs may reduce the need of these reviewers. Legal text summarization aims to highlight the key points of a legal document and convey them in a concise form so that decisions can be made in quick manner. In this paper, we experimented on seven machine learning-based summarization models to analyse their performance on judgment report datasets that has been collected from Indian national legal portal. The models that are taken here for the analysis are BART, LexRank, TextRank, Luhn, LSA, Legal Pegasus, and Longformer. We experimented with these models to find which model may perform well on the legal data. As a result, we observed that Legal Pegasus outperforms over all other models in the case legal summarization. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.
A COVID-19 Vaccine Notifier Android App “CoWin Mitra”
(CRC Press, 2023) Vikas Kumar Patel; Anshul Verma; Pradeepika Verma
The government of India has launched a web portal to register and schedule appointments for COVID-19 vaccination. This paper illustrates an android app model through which people can get notified about available slots according to their filters (age-group, dose type, vaccine name, centers). The proposed app checks for available slots for every given time in the background. Users can schedule their appointment and also enable/disable notifications at any time in the app. The project is developed in android studio. The data source is API Setu, and for client side, Java, XML, and SQLite are used. Software Development Life Cycle model and testing methods are used during the development process. ER diagram, message sequence chart, and flow chart have been shown for database, some important functions, and development process, respectively. The project developed is highly efficient, lightweight, and user-friendly. © 2023 selection and editorial matter, Anshul Verma, Pradeepika Verma, Kiran Kumar Pattanaik and Lalit Garg; individual chapters, the contributors.
A fusion of variants of sentence scoring methods and collaborative word rankings for document summarization
(John Wiley and Sons Inc, 2022) Pradeepika Verma; Anshul Verma; Sukomal Pal
Document summarization is an important task in natural language processing that helps deal with the problem of information overload occurring due to the existence of redundant content. Summary generation with highly relevant contents and maximum coverage is particularly challenging which can only be achieved when redundancy is minimized. This article introduces a novel approach for automatic text summarization based on sentence scoring and collaborative ranking to produce summaries with minimal redundancy and improved overall performance of summarization. The proposed model is a fusion of weighted and unweighted features-based sentence scoring methods. To learn optimal weights of text features, it has been modelled as an optimization problem. Moreover, the proposed model exploits the strength of collaborative ranking to generate the summary of a given document. Three similarity factors (proximity, significance and singularity)-based models have been employed to find the similarity between weighted and unweighted sentence scores. The results of the comparison experiment demonstrate that the proposed (PS + Jac) method generates a closer summary to the reference summary with minimal redundant contents. On average, the proposed (PS + Jac) method generates the summaries with 61% accurate contents with greater improved rates up to 40%. The statistical testing also confirms that the performance improvement is significant at a 5% level of significance. © 2022 John Wiley & Sons Ltd.
A multivariate transformer-based monitor-analyze-plan-execute (MAPE) autoscaling framework for dynamic resource allocation in cloud environment
(Springer, 2025) Bablu Kumar; Anshul Verma; Pradeepika Verma
The rapid advancement of cloud technology has heightened the demand for real-time data processing systems that provide accuracy, flexibility, and scalability. Autoscaling manages cloud resources automatically in real-time, employing either reactive or proactive approaches. Reactive autoscaling adjusts resources based on predefined thresholds but can be inefficient during fluctuating workloads. In contrast, proactive autoscaling predicts future workloads, enabling preemptive resource adjustments to optimize performance. This study proposes an autoscaling approach based on the monitor-analyze-plan-execute (MAPE) framework, which emphasizes proactive strategies by integrating feature selection techniques with a multivariate transformer (MV-Transformer) approach. This MV-Transformer approach excels at capturing long-term dependencies and complex interactions among multiple variables while using less memory. The framework enhances resource provisioning, as evidenced by the lowest under-provisioning value of 0.2892240 and duration of time under-provisioning value of 10.6676060, indicating superior performance. Additionally, the MAPE autoscaling framework achieves an elastic speedup of 2.9818, compared to 1.3200 for Bi-LSTM, 1.0230 for LSTM, and 1.0000 for reactive without autoscaling. The proactive MV-Transformer approach demonstrates significant improvements in resource management by evaluating this elastic speedup and resource provisioning metrics against both reactive without autoscaling and other proactive autoscaling approaches. For real-world implementation, docker desktop and Kubernetes were used to dynamically scale VMs based on workload, orchestrated by the MAPE autoscaling framework. This approach also helps in handling high dynamic workloads and overall efficiency in cloud computing, particularly in scaling and de-scaling. Our implementation codes are available at the following GitHub link: https://github.com/BABLU-KUMAR/MV-Transformer-based-MAPE-Autoscaling-Framework/tree/main. © The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature 2025.
Addressing Graphviz File Generation Issue in CPN Tools: A Java-Based Solution
(Springer Science and Business Media Deutschland GmbH, 2025) Vikas Kumar Patel; Anshul Verma; Pradeepika Verma
This paper presents a novel approach to resolving a specific bug encountered in Colored Petri Nets (CPN) Tools during the generation of Graphviz files. CPN Tools, a powerful instrument for constructing and analyzing colored petri nets, has been identified to have limitations in graph visualization, particularly when dealing with token value strings or record/product with strings.The CPN Tools generate the Graphviz (dot) file, however it does not take into account color sets of strings, records, and products. If the color set is one of these, after generating the Graphviz file from CPN, Graphviz displays a syntax error. This issue results in a syntax mismatch with Graphviz, hindering the seamless visualization of graphs. To address this problem, the authors have developed a Java-based Graphical User Interface (GUI) program that takes the CPN Tools generated dot file as input, refactors it, and corrects the syntax, thereby enabling error-free graph visualization. The user merely needs to provide the CPN Tools created DOT file to the proposed system. It will make internal corrections and generate the graph. In addition, the user can download the revised version of the DOT file from the system. This solution not only resolves the identified bug but also enhances the overall user experience by simplifying the process of graph generation. The paper provides a detailed description of the bug, the development process of the Java GUI program, enhancing the page hierarchy graph of hierarchical colored petri nets, and its successful application in resolving the bug and generating correct graph. It also discusses the potential impact of this solution on the broader usability and efficiency of CPN Tools. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
An approach for extractive text summarization using fuzzy evolutionary and clustering algorithms
(Elsevier Ltd, 2022) Pradeepika Verma; Anshul Verma; Sukomal Pal
Automatic text summarization schemes are indeed helpful for glancing briefly at the text document. With this motivation, we introduce here a two-stage hybrid model for text summarization task by utilizing the strength of various approaches. In the first step, we cluster the sentences of a document according to their similarity using a partitional clustering algorithm. We then use a linear combination of the normalized Google distance and word mover's distance to differentiate two sentences. The notion of gap statistics is exploited to approximate the number of partitions for the given document needed in the partitional clustering algorithm. We extract the significant sentences from each cluster (partition), which are recognized by their adjusted text feature scores, in the second step. The teaching–learning based optimization approach is used to find the optimal weights for the text features whereas a fuzzy inference system with a full-fledged knowledge base generated by humans is employed to determine the final score of the sentences. Moreover, we have also proposed an exact method to give a solution for the summarization problem by modeling it as an Integer Linear Programming (ILP) problem. We evaluate the proposed methods on three different datasets: DUC 2001, DUC 2002, and CNN. The observed results on these standard datasets manifest the efficacy of the proposed methods. We further show that partitioning a document in an optimal number of clusters plays a major role in content coverage in summaries. The performance of the proposed hybrid method shows that the combination of fuzzy, evolutionary, and clustering algorithms produces good summaries of the documents. © 2022 Elsevier B.V.
An in-depth and insightful exploration of failure detection in distributed systems
(Elsevier B.V., 2024) Bhavana Chaurasia; Anshul Verma; Pradeepika Verma
In today's world, everyone wants a good profit with a tiny investment and distributed computing is a boon for this purpose. Cloud computing, fog computing, and the Internet of Things (IoT) are well-known examples of distributed computing which provide good computing services and performance. However, providing reliable services in a real environment, which is failure-prone, remains a challenge. To address this issue, failure detectors are used in distributed systems, which are abstract modules responsible for detecting and monitoring the activity of nodes in order to determine whether they are faulty or not. In this paper, an approach is presented for the systematic literature review of failure detectors in distributed systems. Further, many existing review and survey papers on failure detectors are critically analyzed along with their key contributions and limitations. The classification of distributed systems is presented on the basis of the nodes’ properties and the components of system models are described in detail. Various issues and challenges related to agreement and failure problems are also explored. The strengths and limitations of various existing failure detectors are discussed along with their comparative evaluation. Finally, fault-tolerance and recovery techniques are discussed and analyzed. © 2024 Elsevier B.V.
An optimal three-tier prioritization-based multiflow scheduling in cloud-assisted smart healthcare
(Academic Press, 2025) Sarthak; Anshul Verma; Pradeepika Verma
Internet of Things is significantly advancing the development of modern interconnected networks. Coordinated with cloud computing, this technology becomes even more powerful, cost-effective, and reliable. These advancements are rapidly being integrated into modern healthcare through innovations such as smart ambulances, remote monitoring systems, and smart hospitals, enhancing tracking, analysis, and alerting capabilities. However, these innovations also bring challenges, particularly in task allocation and resource management for safety-critical systems that must meet stringent quality of service while efficiently utilizing resources. This paper introduces a new heuristic Three-Tier Prioritization based Multiflow Scheduling (TTPMS) approach for smart healthcare in cloud, utilizing the adaptive multi-criteria decision-making. The proposed TTPMS algorithm prioritizes tasks across three levels, considering factors such as urgency, deadlines, budget, and impact value within the workflow, and then dynamically selects the most suitable virtual machine for allocation. Performance comparisons were made against traditional approaches like the Prioritized Sorted Task-Based Algorithm (PSTBA) and the Max–Min algorithm. Experiments conducted using the Eclipse IDE with Java, demonstrated that the proposed approach significantly outperforms traditional algorithms across multiple metrics, including success rates for deadlines and budgets, as well as the resource utilization. It achieved a 98% deadline adherence rate, outperforming Max–Min (93%) and PSTBA (60%). Additionally, TTPMS surpassed budget adherence metrics, achieving a 76% success rate compared to PSTBA (72%) and Max–Min (70%). For combined adherence to both deadlines and budgets, TTPMS achieved a 74% success rate, outperforming PSTBA (33%) and Max–Min (63%). These results highlight the effectiveness of TTPMS in scheduling the healthcare applications. © 2025 Elsevier Ltd
Analysis and Implementation of Microservices Using Docker
(Springer Science and Business Media Deutschland GmbH, 2023) Keshav Sharma; Anshul Verma; Pradeepika Verma
Implementation of micro-services is among the most challenging and important tasks in the field of Computer Science. For implementing the microservice architecture, Docker has been used in the current scenario. Creating a machine learning model that works on one computer is not really difficult. But creating a model that can scale and run on all types of servers around the world, it’s more challenging. This work proposed a way to deploy a certain type of trained model in microservice architecture using Docker to use anywhere. For practical implementation, two models for machine learning has been used. One that addresses the handwritten digit recognition problem which has been an open problem in pattern classification since a long time, and another model resolves the issue of house pricing based on several attributes. The purpose of implementation of machine learning model in microservice architecture using Docker is to enable a method from which anyone can use a machine learning model without worrying for their machine configuration and dependencies of the machine learning model. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Average Time Based PRoPHET Routing Protocol for Opportunistic Networks
(Springer Science and Business Media Deutschland GmbH, 2023) Mehul Kumar Gond; Mohini Singh; Anshul Verma; Pradeepika Verma
An Opportunistic Network is an intermittently connected Mobile Ad-hoc Networks that exploits the communication opportunity between the nodes for data transmission whenever they are within the communication range of each other even for a short time. In contrast to the Mobile Ad-hoc Networks, Opportunistic Networks follow store-carry-forward approach for the data transmission. Routing in this type of network depends on many factors, like the direction of the node's movement, the supported interface bandwidth (Bluetooth, high-speed Internet, etc.), the node's speed, and the node's buffer size. In this research work, a context-aware routing protocol is proposed that uses the frequency of contacts among nodes as context information. The frequency of meetings between any two nodes is found to be a good heuristic to identify the message's best forwarder. The proposed routing protocol is simulated on opportunistic network environment (ONE) simulator and the results are compared with the most prominent routing protocols of context-oblivious and context-aware classes, and it was found that the proposed routing protocol performs better than other protocols in terms of delivery probability and buffer average time. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Critical Analysis of Train Operation Simulators
(Springer, 2024) Vikas Kumar Patel; Anshul Verma; Pradeepika Verma
Railway transportation is a cost-effective and reliable mode of transportation. The construction of an entire railway network is a challenging task that requires careful planning and execution. Infrastructure and schedule are just two of the many elements that must be accurate and cheap for greater performance. Train simulators are computer-based simulations of rail transport operations that can help in the planning, creation, and administration of effective train operations. These simulators can model various aspects of rail transport, such as train movements, signaling systems, and track layouts, allowing railway operators to test and optimize their operations before implementing them in the real world. In this study, 20 simulators with various parameters like simulator types, category, working, etc. were examined together with a total of top 10 companies that offer railway-related services for the year 2022. The results of this study shall offer insightful knowledge about the simulation, creation, and administration of effective train operations. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.
Developing LoRa-IoT infrastructure based advanced-airborne security systems for public healthcare centers using machine learning
(Elsevier Ltd, 2025) Kanak Kumar; Anshul Verma; Pradeepika Verma
Airborne security poses a growing threat in indoor and outdoor environments such as healthcare centres. The rapid growth of the Internet of Things (IoT) has integrated safety systems into our daily lives. This paper presents a solar-powered, energy-efficient and sustainable Long Range (LoRa) technology enabled IoT infrastructure based Advanced-Airborne Security systems for Public Healthcare Centers (LIA2S4PHC) by using Machine Learning (ML) for the detection and analysis of the signature of harmful pollutant/odors/volatile organic compounds (VOCs)/gases. For LIA2S4PHC framework development, we have applied two LoRa SX1278 (transmitter and receiver end), two ESP 32 microcontrollers, six tin-oxide-based cross-selective gas sensors, one particulate matter sensor, one temperature and humidity sensor, and one GPS module. LoRa is used to transmit airborne signatures from the experimental zone to the central monitoring station (CMS) for further processing. On performing the LIA2S4PHC range test, it was found that up to 745 m information was obtained correctly in open space. The messages started getting missed after that, and at about 765 m there was no reception. The captured airborne signatures were pre-processed using the standardized principal component analysis (SPCA) for 3D scattering. Naïve Bayes (NB), support vector machine (SVM), multi-layer perceptron (MLP), Categorical Boosting (CatBoost), and tabular network (TabNet) models were applied to classify the types of harmful gases/odors/airborne signatures with classification average accuracies such as 82%, 84%, 91%, 91%, and 92%, respectively. TabNet classification model outperforms other classification models with 92% accuracy. We found 4.7×10−6 and 1.34×10−3 minimum and maximum MSE respectively. LIA2S4PHC is a full y scalable and energy-efficient system applicable for public healthcare centres and a wide variety of applications. Our dataset and code are available at GitHub link: https://github.com/kanakkumarcs24/Advanced-Airborne-Security-Systems-for-Public-Healthcare-Centers. © 2025 Elsevier Ltd
Development of an Intelligent Electronic-Nose Framework for Perishable Food Quality Assessment
(Springer, 2025) Kanak Kumar; Anshul Verma; Pradeepika Verma
The proposed system utilizes an array of tin-oxide-based gas sensors and temperature & humidity sensors to detect odors emitted by food items, capturing unique odor signatures associated with different stages of freshness and spoilage. The central data processing station pre-processes the sensor responses using signal pre-processing techniques like noise filtration, dimensionality reduction, and feature extraction to improve the quality of the data. The system then applies an artificial neural network model to classify food items into four freshness categories: fresh, may still be useful, not suitable for use, and completely spoiled. The system demonstrates high accuracy in distinguishing freshness levels across various perishable food types, including meat, fish, eggs, and dairy products, with 95%, 97%, 97% and 97% accuracy, respectively. The integration of machine learning with E-Nose technology offers a rapid, non-invasive, and scalable solution for real-time food quality assessment. By automating the assessment process, the framework minimizes human error, reduces operational costs, and enhances food safety compliance. This study demonstrates how intelligent sensing systems have the potential to revolutionize quality control within the food supply chain. This could have big effects on public health, reducing waste, and the long-term health of the industry. Future work includes optimizing sensor arrays for broader food categories and enhancing model explainability for better decision-making. © The Author(s), under exclusive licence to Springer Na ture Singapore Pte Ltd. 2025.
Emerging Real-World Applications of Internet of Things
(CRC Press, 2022) Anshul Verma; Pradeepika Verma; Yousef Farhaoui; Zhihan Lv
The Internet of things (IoT) is a network of connected physical objects or things that are working along with sensors, wireless transceiver modules, processors, and software required for connecting, processing, and exchanging data among the other devices over the Internet. These objects or things are devices ranging from simple handheld devices to complex industrial heavy machines. A thing in IoT can be any living or non-living object that can be provided capabilities to sense, process, and exchange data over a network. The IoT provides people with the ability to handle their household works to industrial tasks smartly and efficiently without the intervention of another human. The IoT provides smart devices for home automation as well as business solutions for delivering insights into everything from real-time monitoring of working systems to supply chain and logistics operations. The IoT has become one of the most prominent technological inventions of the 21st century. Due to the versatility of IoT devices, there are numerous real-world applications of the IoT in various domains such as smart home, smart city, health care, agriculture, industry, and transportation. The IoT has emerged as a paradigm-shifting technology that is influencing various industries. Many companies, governments, and civic bodies are shifting to IoT applications to improve their works and to become more efficient. The world is slowly transforming toward a “smart world” with smart devices. As a consequence, it shows many new opportunities coming up in the near “smart” future for IoT professionals. Therefore, there is a need to keep track of advancements related to IoT applications and further investigate several research challenges related to the applicability of IoT in different domains to make it more adaptable for practical and industrial use. With this goal, this book provides the most recent and prominent applications of IoT in different domains as well as issues and challenges in developing IoT applications for various new domains. © 2023 Anshul Verma, Pradeepika Verma, Yousef Farhaoui and Zhihan Lv.
Empirical Analysis of The Performance of Routing Protocols in Opportunistic Networks
(CRC Press, 2023) Mohini Singh; Anshul Verma; Pradeepika Verma
Opportunistic Networks are a kind of network where the source and destination may not have an end-to-end path or a path that exists for a very short and unpredictable span of time. Hence, there are differences in Opportunistic Networks in contrast to Mobile Ad hoc Networks (MANETs) in which a path is established between a source and destination before message transmission. The knowledge of network topology is irrelevant to nodes in Opportunistic Networks as opposed to MANETs, where it is a necessity. In Opportunistic Networks, routes are constructed dynamically instead of being static as the source selects a node from neighbouring ones for the next hop by having an assumption regarding the delivery of a message that it will reach close enough to the destination. This work presents simulation and performance evaluation of various routing protocols of Opportunistic Networks. The existing routing protocols of Opportunistic Networks are compared among each other with the help of various factors used for performance evaluation. Opportunistic Network Environment simulator version 1.4.1 is used for the implementation of routing protocols. The performance is analysed on five metrics: message delivery probability, overhead ratio, average buffer time, number of deliveries, and average latency. © 2023 selection and editorial matter, Anshul Verma, Pradeepika Verma, Kiran Kumar Pattanaik and Lalit Garg; individual chapters, the contributors.
Encounter Count and Interaction Time-Based Routing Protocol for Opportunistic Networks
(Springer, 2024) Mohini Singh; Anshul Verma; Pradeepika Verma
Opportunistic network is an extension of Mobile Ad-hoc network, and therefore, it shares most of the properties of the Mobile Ad-hoc network except routing protocols. Highly intermittent connections between nodes in opportunistic networks make the development of routing protocols more challenging. This paper proposes an Encounter Count and Interaction Time-based (ECIT) routing protocol for opportunistic networks that combines context information and effective buffer technique to reduce overhead as well as to improve delivery rates. The ECIT routing protocol uses context information of nodes and neighbourhoods to select the next forwarding node for a message in the network. A buffer management policy is also added to improve efficiency of selection of the next forwarding node. Further, the proposed routing protocol is compared with well-known routing protocols of opportunistic networks, i.e., Epidemic, Probabilistic Routing Protocol using History of Encounters and Transitivity (PRoPHET), and PRoPHETv2. Opportunistic Network Environment Simulator (ONE) is used for the implementation of the proposed routing protocol. Simulation results and analysis show that out of the three existing routing protocols, the PRoPHETv2 performs better than the other two. Whereas, the proposed routing protocol performs even better than PRoPHETv2 in terms of delivery probability by 32% and the overhead ratio by 22.1%, respectively. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.
Hybrid Heuristic for Solving the Euclidean Travelling Salesman Problem
(Springer, 2024) Dharm Raj Singh; Manoj Kumar Singh; Sachchida Nand Chaurasia; Pradeepika Verma
This study introduces a hybrid methodology that integrates the ant colony optimization (ACO) with genetic algorithm (GA) techniques. ACO is employed first to create an initial population and to derive a sub-optimal solution for the TSP using a newly designed inver-over (IO) operator. The Proposed IO operator is utilized to improve the solution derived from the ACO. This refined solution is then employed in the GA, where a genetic operator is applied alongside other randomly selected members from the initial population during the second phase. GA is used with the proposed crossover operator and the 2-opt heuristic in this phase to achieve optimal solution refinement towards a global optimum. Our evaluation of the algorithm’s efficacy uses benchmark datasets from TSPLIB. The proposed approach gives superior solution quality, both the average and the best solution metrics, demonstrating enhanced performance with a lower percentage of best error and percentage of average error. Experimental results indicate that the hybrid approach outperforms the efficiency of other state-of-the-art techniques. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.
IoT integrated quantile principal component analysis based framework for toxic pesticides recognition and classification
(Elsevier B.V., 2025) Kanak Kumar; Anshul Verma; Pradeepika Verma
Pesticides present significant concerns regarding environmental sustainability and global stability. This study investigates the types, benefits, and environmental challenges associated with pesticide use. To address these concerns, we developed an innovative Internet of Things (IoT) integrated quantile principal component analysis (QPCA) framework for the recognition of toxic pesticides in smart farming, termed IoT-TPR. The proposed IoT-TPR system is an intelligent electronic nose based on a tin-oxide sensor array, consisting of eight commercial metal–oxide–semiconductor gas sensors, which detect toxic pesticides and transmit the data to the Amazon Web Services cloud for further analysis. A two-stage QPCA preprocessing technique is employed to analyze sensor responses. Subsequently, four classifiers such as radial basis function (RBF), extreme learning machine (ELM), decision tree (DT), and k-nearest neighbor (KNN) are used for comparative performance evaluation. The results indicate that QPCA-KNN achieves the highest accuracy at 99.05%, outperforming other methods across all performance metrics and demonstrating superior classification capability. RBF (96.24%) and ELM (95.81%) also exhibit strong performance, though slightly lower than QPCA-KNN, while DT (92.35%) shows the lowest accuracy but still maintains reasonable performance. Overall, QPCA-KNN emerges as the most effective and robust classification model in this study. © 2025 Elsevier B.V.
IoT-HGDS: Internet of Things integrated machine learning based hazardous gases detection system for smart kitchen
(Elsevier B.V., 2024) Kanak Kumar; Anshul Verma; Pradeepika Verma
This paper proposes an Internet of Things (IoT) and Machine Learning (ML) integrated Hazardous Gas Detection System (IoT-HGDS) for smart kitchens. The design incorporates six tin-oxide-based metal–oxide–semiconductor (MOS) gas sensor arrays and one DHT22 (temperature & humidity sensor). This IoT-HGDS can detect different hazardous gases, Volatile Organic Compounds (VOCs), and odors responses released from the kitchen's materials and transmit them to a Remote Data Processing Centre (RDPC) through Amazon-Web Services (AWS) in real time. In this experiment, we collected 150×9=1350 samples from 9 kitchen materials like ghee, milk, liquid petroleum gas (LPG), bread, mustard oil, compressed natural gas (CNG), pigeon peas, refined oil, and kerosene. The Standardized Independent Component Analysis (SICA) pre-processing technique has been used to clean data, standardize the features, and remove outliers. ML approaches like Logistic Regression (LR), Adaptive Boosting (AdaBoost) and Regularized Discriminant Analysis (RDA) have been applied for accurate identification of gases/VOCs class and provide immediate alerts to improve kitchen safety. The SICA-RDA classifier outperformed (highest accuracy at 97.78 %) as compared to LR and AdaBoost in terms of performance and balanced precision, recall, and F1-Score. LR has the lowest performance in all metrics. LPG has the lowest Mean Squared Error (MSE) of 6.62×10−7, while CNG has the highest MSE of 3.60×10−4. This system can intelligently preserve gases, ensure safety precautions, and prevent accidents in the kitchens. © 2024 Elsevier B.V.
MCDPS: Enhancing Clinical Decision Support for Multiple Chronic Disease Prediction Systems Using Ensemble Machine Learning Approaches
(Springer Science and Business Media Deutschland GmbH, 2025) Kanak Kumar; Anshul Verma; Pradeepika Verma
People today suffer from various chronic diseases due to lifestyle choices and environmental conditions. Early prediction of these diseases is crucial to prevent them from worsening. However, it is often challenging for physicians to accurately diagnose these issues independently. A computational model based on big data analytics has numerous applications in the medical field. Advancements in machine learning (ML) and information technology have enabled more accurate recognition of diseases, health emergencies, and conditions. The advent of predictive algorithms has transformed disease diagnosis in the medical field. Previously, patient data records were meticulously examined to predict diseases and develop advanced models for trend analysis. However, with the rise of data analytics-driven intelligence, the evaluation of disease symptoms has become more accurate and efficient. These technologies enable the creation of predictive models capable of analyzing vast amounts of patient data to identify hidden patterns, aiding in early disease detection and diagnosis. This study explores the development of an ensemble ML-based multiple chronic disease prediction system (MCDPS) focused on three major diseases: chronic kidney disease (CKD), liver disease, and heart disease. The system utilizes ensemble ML models, including Decision Tree (DT), Gradient Boosting Classifier (GBC), Extreme Gradient Boosting (XGBoost), and Extra-Trees classifiers (ETC), to predict diseases. Its user-friendly and straightforward design makes it accessible to beginners. The system’s performance in predicting the three chronic diseases has been evaluated and compared with other traditional models. The results show that the DT algorithm achieved an accuracy of 99%, 85%, and 83% for predicting CKD, heart disease, and liver disease, respectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.