Procedia Computer Science最新文献

{"title":"Cloud Based LoRaWAN Enabled Water Tank Automation Framework","authors":"Abubeker K M ,&nbsp;Aravind Nuthalapati","doi":"10.1016/j.procs.2025.01.037","DOIUrl":"10.1016/j.procs.2025.01.037","url":null,"abstract":"<div><div>Internet of Things (IoT), sensor technologies, and low-power long-range wide area network (LoRaWAN) protocols are crucial to reducing water wastage during storage and distribution. This letter proposes a LoRa-based automatic water pump for overhead tanks in domestic and public water services. This research uses an ESP32 LoRa IoT platform for gateway and wide area network communication and the JSN-SR04T sensor for water level monitoring. This IoT framework is integrated with mobile applications and a web server for the real-time monitoring and control of water pumps. In fully automated mode, the LoRa gateway coordinated the control of the water pump depending on the pre-configured water level during installation. In semi-automated mode, users can control the water pump with the mobile application or web server. The developed framework is tested in different environments and verified the efficacy and performance of LoRa in terms of energy consumption, RSSI, SNR and distance of communication from the host node to the LoRa gateway. The research also highlighted the reduction in water consumption, and this framework potentially addresses the sustainable development goals 6 (SDG-6).</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 768-775"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Educational Video Discovery Using Advanced Latent Semantic Analysis","authors":"B. Sindhu Dr. ,&nbsp;A. Bhaskar ,&nbsp;G. Yugesh ,&nbsp;S. Reshma ,&nbsp;B. Rohit","doi":"10.1016/j.procs.2025.01.039","DOIUrl":"10.1016/j.procs.2025.01.039","url":null,"abstract":"<div><div>The rapid growth of online educational videos has created abundant learning resources, but also has challenges in discovering high-quality, relevant content. This project mainly focuses on video-based content analysis and providing high-quality learning sources for scholars, easing the best possible way to discover accurate resources. Existing Systems often rely on round-robin, random selection which fails to grasp semantics and linguistic complexity. The proposed system focuses on content-based analytics using NLP, where the extraction of transcripts from videos, perform relevance assessment which maps content to concept and extract insights using Latent Semantic Analysis which effectively captures underlying structures in the transcript. Complexity Assessment measures readability metrics using the Flesch-Kincaid Grade Level and SMOG Index. Created a web-based interface for easy access to educational videos, with built-in analytics to assess relevance. The insights are shared with scholars to refine content and better meet user requirements.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 784-795"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Harnessing the Potato leaf disease detection process through proposed Conv2D and resnet50 deep learning models","authors":"Suman Chowdhury ,&nbsp;Dilip Kumar Das","doi":"10.1016/j.procs.2025.01.013","DOIUrl":"10.1016/j.procs.2025.01.013","url":null,"abstract":"<div><div>This paper endeavours to implement the image processing technique for finding out the potato leaf disease. Total two categories of leaf disease—early blight and late blight—have been taken into consideration for the data processing along with the healthy leaf. The total number of cases is 3251 for the transfer learning process in the leaf disease detection process. Before incorporating the data in the deep learning model, image size has been converted to (224, 224) along with the normalization of pixel values. Total two deep learning models- CNN and Resnet50—have been implemented to perform the potato leaf disease detection process with 20 epochs each. From the analysis of the results, it is found that reset50 has successfully tracked the validation accuracy with 97% overall, while the CNN has given 76% of validation accuracy. Finally, the classification report and the confusion matrix for each of the models have been produced to see the overall performance for the potato leaf disease detection process. And, the training loss and the validation loss have been documented in terms of graphical order of representation for deeper understanding of the model performance.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 539-547"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generative AI in Agri: Sustainability in Smart Precision Farming Yield Prediction Mapping System Based on GIS Using Deep Learning and GPS","authors":"Senthil G. A ,&nbsp;S.U. Suganthi ,&nbsp;L. Prinslin ,&nbsp;R. Selvi ,&nbsp;R. Prabha","doi":"10.1016/j.procs.2024.12.038","DOIUrl":"10.1016/j.procs.2024.12.038","url":null,"abstract":"<div><div>Agriculture faces many challenges of precision farming, such as the need for sustainable practices, improving yields, ensuring high yields. In resolution to these challenges, the present research provides an AI-based system that enables the use of deep learning, Global Positioning System (GPS), and Geographic Information System (GIS) technologies to create a highly intelligent smart agricultural precision farming system. Its goal is to monitoring crop health and reduce disease risk, which will lead to improved resource utilization and environmentally sustainability techniques. The proposed framework addresses the urgent need for consistency in agricultural practices, especially as global agriculture deals with pressures from climate change, resource shortages, and increasing demand for food. Traditional agricultural methods for predicting and optimizing crop yields due to increasing factors affecting crop performance Not enough generative AI, especially the use of deep learning models, supports agricultural research in many cases, allowing patterns to be identified and future results to be predicted accurately. The integration of GPS and GIS allows for more accurate mapping, real-time analysis, and effective decision-making. Weather forecasting variability, resource constraints, and demand for more food are isolated from environmental influences using deep learning models, especially Artificial Neural Networks (ANN). By using large data sets, including historical crop yield performance, soil properties, and weather conditions, the system provides highly accurate crop forecasts. Generative Adversarial Networks (GANs) and You Only Look Once (YOLO) hybrid model is playing a key role in generating crop yield and growth potential under different conditions, adjusting model accuracy over time, and this combination of ANN, GANs and YOLO optimization algorithms ensures that the system continuously enhances its predictive accuracy and overall effectiveness. The proposed generative AI framework aims to deliver these improvements in agricultural production.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 365-380"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predictive Maintenance and Smart Sensors Aiming Sustainability: A Perspective From a Bibliometric Analysis","authors":"Daniel Augusto de Moura Pereira ,&nbsp;Bruno Pereira Diniz ,&nbsp;Marcos dos Santos ,&nbsp;Carlos Francisco Simões Gomes ,&nbsp;Fernanda Raquel Roberto Pereira ,&nbsp;Arthur Pinheiro de Araújo Costa ,&nbsp;Giovanna Paola Batista de Britto Lyra Moura","doi":"10.1016/j.procs.2024.12.009","DOIUrl":"10.1016/j.procs.2024.12.009","url":null,"abstract":"<div><div>Predictive maintenance is an approach that relies on the actual condition of equipment to determine when maintenance should be performed, aiming to predict failures before they occur. This minimizes downtime and the costs associated with corrective maintenance through the use of smart sensors and the Internet of Things (IoT). When these technologies are integrated with the sustainability of industrial operations, they can enhance the efficiency of resource use. In this context, the objective of this work was to conduct a bibliometric analysis on the topics of sensors, predictive maintenance, sustainability, or sustainable practices. The results indicated that publications on the studied topics only began in 2019, predominantly authored by countries such as India and China. The American continent did not present publications on the topics in question. The main study themes are related to predictive maintenance and IoT within areas such as agriculture and renewable energy. The findings of this work suggest that there is an opportunity for new publications on the researched topics.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 81-89"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated Skin Cancer Classification and Detection Using Convolutional Neural Networks and Dermoscopy Images","authors":"Umme Sara ,&nbsp;Utpol Kanti Das ,&nbsp;Juel Sikder ,&nbsp;Sudipta Roy Chowdhury","doi":"10.1016/j.procs.2024.12.012","DOIUrl":"10.1016/j.procs.2024.12.012","url":null,"abstract":"<div><div>The uncontrolled growth of skin cells in the epidermis producing the creation of a mass termed a tumor is a dangerous condition known as skin cancer. Current developments in deep learning artificial intelligence have greatly improved image-based diagnosis. In this study, we included a Skin Lesion Cancer feature extractor Convolutional Neural Network (SLC-CNN) model, which is used for both classification with the SVM classifier and segmentation with XGBoost for skin cancer. In our proposed system, a test image of skin cancer is taken and pre-processed for both classification and segmentation purposes. After applying pre-processing, the test image features are extracted using the SLC-CNN feature extractor, which features are used in SVM to classify the types of skin cancer (Benign and Malignant), and based on the classification result, a trained XGBoost model is called to segment the cancer region. We have tested our system using the dermoscopy image collection from the International Skin Imaging Collaboration (ISIC) and built it in Google Colab to best use the GPU. Our suggested approach has gained a segmentation accuracy of 95.25% and a classification accuracy of 99.6%.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 108-117"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Logistic Regression for Enhancing Scalability of Blockchain System","authors":"Manjula K Pawar ,&nbsp;Prakashgoud Patil","doi":"10.1016/j.procs.2024.12.016","DOIUrl":"10.1016/j.procs.2024.12.016","url":null,"abstract":"<div><div>Blockchain is a cutting-edge technology widely recognized for its applications to industry, business, and sustainable development goals. Its key features include tamper-proofing, decentralization, immutability, transparency, and security. Despite its numerous advantages, Challenges such as privacy and scalability persist. Scalability, is measured with respect to throughput, capacity, and latency, which are remains a crucial aspect of its functionality. The latency includes the timestamp of block inclusion in the blockchain. The proposed methodology suggests using a logistic regression method to enhance the scalability of a blockchain system. The suggested methodology involves analyzing the performance of logistic regression, resulting in higher transactions per second and lower latency time which is measured in milliseconds.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 146-153"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigation of Blockchain for Security and Transparency in Intelligent Transportation Systems","authors":"T. Vairam ,&nbsp;M. Srijeimathy","doi":"10.1016/j.procs.2025.01.046","DOIUrl":"10.1016/j.procs.2025.01.046","url":null,"abstract":"<div><div>Incorporating blockchain technology into vehicle classification systems shows potential progress in data security, transparency, and decentralization. This work examines how blockchain technology can improve vehicle classification procedures, emphasizing the advantages and hurdles of various consensus mechanisms. Conventional methods of categorizing vehicles typically depend on centralized databases susceptible to data tampering and breaches. Using blockchain ensures data integrity by utilizing decentralized and immutable ledgers. We assess different consensus algorithms such as Proof of Stake (PoS), Delegated Proof of Stake (DPoS), Practical Byzantine Fault Tolerance (PBFT), Federated Byzantine Agreement (FBA), and DAG (Directed Acyclic Graph) to determine their appropriateness for vehicle categorization. Our aim is to determine the most effective and secure method for incorporating blockchain technology into vehicle classification systems by analyzing these consensus mechanisms.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 851-861"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SARCASAM Analysis in Social Networks Using Deep Learning Algorithm","authors":"Priya M ,&nbsp;Vijaya kumar K ,&nbsp;Vennila P ,&nbsp;Prasanna M A","doi":"10.1016/j.procs.2025.01.010","DOIUrl":"10.1016/j.procs.2025.01.010","url":null,"abstract":"<div><div>Twitter is the one of the biggest social media sites, where users may share their thoughts, ideas, and opinions as well as discuss current events and live tweets. In the subject of opinion mining, creating reliable and effective algorithms for sarcasm detection on Twitter is an intriguing task. Sarcasm is the use of positive language to convey depressing emotions while speaking in opposition to one’s own intentions. Sarcasm is frequently employed on social networking and micro blogging platforms, where users can offend others and find it difficult to express their true feelings. The deep learning technique utilised in the current algorithms to identify these sarcastic tweets has the limitation of not being able to predict continuous variables. A novel deep learning algorithm is proposed to identify both positive and negative terms as well as sarcasm in comments. Deep neural networks are used to classify the comments into positive and negative word categories. Customers’ opinions are mined using sentiment analysis to find and extract information from the text. Sarcastically stated statements from social networking sites can be quickly categorised and recognised by using VADER (Valence Aware Dictionary and Sentiment Reasoner).</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 510-518"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Innovative Fire and Gas Recognition System Featuring Remote Monitoring and Automated Alerts","authors":"S Kanagamalliga ,&nbsp;S Rajalingam","doi":"10.1016/j.procs.2024.12.002","DOIUrl":"10.1016/j.procs.2024.12.002","url":null,"abstract":"<div><div>An advance safety system has been developed to effectively address the critical risks associated with fire and gas leakages in both industrial and residential environments. This advanced system integrates a range of sensors, including flame sensors, gas sensors, and temperature sensors, all connected to a microcontroller. The microcontroller is responsible for processing data from these sensors to continuously monitor and evaluate environmental conditions for any signs of fire or gas leaks. Upon recognizing an anomaly, the system activates an alert mechanism that includes displaying status updates on an LCD screen, sounding an audible alarm via a buzzer, and sending instant notifications through SMS via a GSM module to prompt immediate response. A key innovation of this system is its utilization of the Message Queuing Telemetry Transport (MQTT) protocol for cloud-based monitoring and data management. This protocol supports real-time data transmission and analysis through the Ubidots platform, facilitating efficient and reliable communication between the system and cloud services. The lightweight and efficient MQTT protocol ensures seamless remote monitoring and control, while the cloud integration allows for continuous data storage and detailed analysis. This combination of real-time monitoring, remote access, and advanced alerting mechanisms provides a comprehensive solution for hazard recognition and management, significantly enhancing safety by enabling prompt responses and safeguarding both lives and property.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 7-14"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}