Pub Date : 2023-10-05DOI: 10.53759/7669/jmc202303035
Preethi P, Lalitha K, Yogapriya J
The forum in the nation for reporting information security flaws had 14,871 reports by the end of 2021, a 46.6% increase from 2020. The total of 5,567 high risk vulnerabilities, an increase of nearly 1,400 over the previous year. Evidently, both the total number of vulnerabilities found annually, and the total number of high-risk vulnerabilities are rising. In order for data mining technology to play a wider part in the predictive investigation of network security models, it is advised that its capability have to be improved. This paper combines the concepts of data mining (DM) with machine learning (ML), which introduces similar technologies from DM technology and security establishing collection channel, thereby finally introduces the computer network security maintenance process based on data mining in order to improve the application effect of DM in the predictive analysis of network security models. In this paper, a self-organizing neural network technique that detects denial of service (DOS) in complicated networks quickly, effectively, and precisely is introduced. It also analyses a number of frequently employed computer data mining methods, including association, clustering, classification, neural networks, regression, and web data mining. Finally, it introduces a computer data mining method based on the self-organizing (SO) algorithm. In comparison to conventional techniques, the SO algorithm-based computer data mining technology is also used in defensive detection tests against Dos attacks. A detection average accuracy rate of more than 98.56% and a detection average efficiency gain of more than 20% are demonstrated by experimental data to demonstrate that tests based on the Data Mining connected SO algorithm have superior defensive detection effects than standard algorithms.
{"title":"Self-Organizing Computational System for Network Anomaly Exploration using Learning Algorithms","authors":"Preethi P, Lalitha K, Yogapriya J","doi":"10.53759/7669/jmc202303035","DOIUrl":"https://doi.org/10.53759/7669/jmc202303035","url":null,"abstract":"The forum in the nation for reporting information security flaws had 14,871 reports by the end of 2021, a 46.6% increase from 2020. The total of 5,567 high risk vulnerabilities, an increase of nearly 1,400 over the previous year. Evidently, both the total number of vulnerabilities found annually, and the total number of high-risk vulnerabilities are rising. In order for data mining technology to play a wider part in the predictive investigation of network security models, it is advised that its capability have to be improved. This paper combines the concepts of data mining (DM) with machine learning (ML), which introduces similar technologies from DM technology and security establishing collection channel, thereby finally introduces the computer network security maintenance process based on data mining in order to improve the application effect of DM in the predictive analysis of network security models. In this paper, a self-organizing neural network technique that detects denial of service (DOS) in complicated networks quickly, effectively, and precisely is introduced. It also analyses a number of frequently employed computer data mining methods, including association, clustering, classification, neural networks, regression, and web data mining. Finally, it introduces a computer data mining method based on the self-organizing (SO) algorithm. In comparison to conventional techniques, the SO algorithm-based computer data mining technology is also used in defensive detection tests against Dos attacks. A detection average accuracy rate of more than 98.56% and a detection average efficiency gain of more than 20% are demonstrated by experimental data to demonstrate that tests based on the Data Mining connected SO algorithm have superior defensive detection effects than standard algorithms.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"438 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-05DOI: 10.53759/7669/jmc202303038
Senthilkumar G, Rajendran P, Suresh Y, Herald Anantha Rufus N, Rama chaithanya Tanguturi, Rajdeep Singh Solanki
This research explores the integration of Artificial Intelligence (AI), specifically the Recurrent Neural Network (RNN) model, into the optimization of data center cooling systems through Computational Engineering. Utilizing Computational Fluid Dynamics (CFD) simulations as a foundational data source, the study aimed to enhance operational efficiency and sustainability in data centers through predictive modeling. The findings revealed that the RNN model, trained on CFD datasets, proficiently forecasted key data center conditions, including temperature variations and airflow dynamics. This AI-driven approach demonstrated marked advantages over traditional methods, significantly minimizing energy wastage commonly incurred through overcooling. Additionally, the proactive nature of the model allowed for the timely identification and mitigation of potential equipment challenges or heat hotspots, ensuring uninterrupted operations and equipment longevity. While the research showcased the transformative potential of merging AI with data center operations, it also indicated areas for further refinement, including the model's adaptability to diverse real-world scenarios and its management of long-term dependencies. In conclusion, the study illuminates a promising avenue for enhancing data center operations, highlighting the significant benefits of an AI-driven approach in achieving efficiency, cost reduction, and environmental sustainability.
{"title":"Computational Engineering based approach on Artificial Intelligence and Machine learning-Driven Robust Data Centre for Safe Management","authors":"Senthilkumar G, Rajendran P, Suresh Y, Herald Anantha Rufus N, Rama chaithanya Tanguturi, Rajdeep Singh Solanki","doi":"10.53759/7669/jmc202303038","DOIUrl":"https://doi.org/10.53759/7669/jmc202303038","url":null,"abstract":"This research explores the integration of Artificial Intelligence (AI), specifically the Recurrent Neural Network (RNN) model, into the optimization of data center cooling systems through Computational Engineering. Utilizing Computational Fluid Dynamics (CFD) simulations as a foundational data source, the study aimed to enhance operational efficiency and sustainability in data centers through predictive modeling. The findings revealed that the RNN model, trained on CFD datasets, proficiently forecasted key data center conditions, including temperature variations and airflow dynamics. This AI-driven approach demonstrated marked advantages over traditional methods, significantly minimizing energy wastage commonly incurred through overcooling. Additionally, the proactive nature of the model allowed for the timely identification and mitigation of potential equipment challenges or heat hotspots, ensuring uninterrupted operations and equipment longevity. While the research showcased the transformative potential of merging AI with data center operations, it also indicated areas for further refinement, including the model's adaptability to diverse real-world scenarios and its management of long-term dependencies. In conclusion, the study illuminates a promising avenue for enhancing data center operations, highlighting the significant benefits of an AI-driven approach in achieving efficiency, cost reduction, and environmental sustainability.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-05DOI: 10.53759/7669/jmc202303041
Dinesh Kumar K, Duraimutharasan N, Shanthi HJ, Vennila G, Prabu Shankar B, Senthil P
Blockchain technology garners significant attention and recognition due to several key advantages it offers. Trust, reliability, speed, and transparency are among the prominent benefits that contribute to its growing prominence. The decentralized nature of blockchain allows for a high level of trust as transactions are recorded and verified by multiple participants across the network. This, in turn, enhances reliability as there is no single point of failure. Speed is also a notable advantage, particularly when compared to traditional systems that involve intermediaries and complex processes for verification. Blockchain enables faster and more efficient transaction processing, reducing delays and costs. This research paper aims to provide a comprehensive comparative analysis of two prominent distributed ledger technologies, namely blockchain and hashgraph. Both blockchain and hashgraph offer decentralized and secure systems for recording and validating transactions or information. It explores the underlying mechanisms, consensus algorithms, advantages, and limitations of these technologies. It also examines their potential applications and discusses the implications of their respective design choices. By understanding the nuances of blockchain and hashgraph, seeks to contribute to the ongoing discourse on distributed ledger technologies and aids in decision-making for their appropriate adoption in various domains and applications.
{"title":"Comparative Analysis of Transaction Speed and Throughput in Blockchain and Hashgraph: A Performance Study for Distributed Ledger Technologies","authors":"Dinesh Kumar K, Duraimutharasan N, Shanthi HJ, Vennila G, Prabu Shankar B, Senthil P","doi":"10.53759/7669/jmc202303041","DOIUrl":"https://doi.org/10.53759/7669/jmc202303041","url":null,"abstract":"Blockchain technology garners significant attention and recognition due to several key advantages it offers. Trust, reliability, speed, and transparency are among the prominent benefits that contribute to its growing prominence. The decentralized nature of blockchain allows for a high level of trust as transactions are recorded and verified by multiple participants across the network. This, in turn, enhances reliability as there is no single point of failure. Speed is also a notable advantage, particularly when compared to traditional systems that involve intermediaries and complex processes for verification. Blockchain enables faster and more efficient transaction processing, reducing delays and costs. This research paper aims to provide a comprehensive comparative analysis of two prominent distributed ledger technologies, namely blockchain and hashgraph. Both blockchain and hashgraph offer decentralized and secure systems for recording and validating transactions or information. It explores the underlying mechanisms, consensus algorithms, advantages, and limitations of these technologies. It also examines their potential applications and discusses the implications of their respective design choices. By understanding the nuances of blockchain and hashgraph, seeks to contribute to the ongoing discourse on distributed ledger technologies and aids in decision-making for their appropriate adoption in various domains and applications.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-05DOI: 10.53759/7669/jmc202303037
Pabitha C, Kalpana V, Evangelin Sonia SV, Pushpalatha A, Mahendran G, Sivarajan S
Healthcare practices have a tremendous amount of potential to change as a result of the convergence of IoT technologies with cutting-edge machine learning. This study offers an IoT-connected sensor-based Intelligent Health Monitoring System for real-time patient health assessment. Our system offers continuous health monitoring and early anomaly identification by integrating temperature, blood pressure, and ECG sensors. The Support Vector Machine (SVM) model proves to be a reliable predictor after thorough analysis, obtaining astounding accuracy rates of 94% for specificity, 95% for the F1 score, 92% for recall, and 94% for total accuracy. These outcomes demonstrate how well our system performs when it comes to providing precise and timely health predictions. Healthcare facilities can easily integrate our Intelligent Health Monitoring System as part of the practical application of our research. Real-time sensor data can be used by doctors to proactively spot health issues and provide prompt interventions, improving the quality of patient care. This study's integration of advanced machine learning and IoT underlines the strategy's disruptive potential for transforming healthcare procedures. This study provides the foundation for a more effective, responsive, and patient-centered healthcare ecosystem by employing the potential of connected devices and predictive analytics.
{"title":"Development and Implementation of an Intelligent Health Monitoring System using IoT and Advanced Machine Learning Techniques","authors":"Pabitha C, Kalpana V, Evangelin Sonia SV, Pushpalatha A, Mahendran G, Sivarajan S","doi":"10.53759/7669/jmc202303037","DOIUrl":"https://doi.org/10.53759/7669/jmc202303037","url":null,"abstract":"Healthcare practices have a tremendous amount of potential to change as a result of the convergence of IoT technologies with cutting-edge machine learning. This study offers an IoT-connected sensor-based Intelligent Health Monitoring System for real-time patient health assessment. Our system offers continuous health monitoring and early anomaly identification by integrating temperature, blood pressure, and ECG sensors. The Support Vector Machine (SVM) model proves to be a reliable predictor after thorough analysis, obtaining astounding accuracy rates of 94% for specificity, 95% for the F1 score, 92% for recall, and 94% for total accuracy. These outcomes demonstrate how well our system performs when it comes to providing precise and timely health predictions. Healthcare facilities can easily integrate our Intelligent Health Monitoring System as part of the practical application of our research. Real-time sensor data can be used by doctors to proactively spot health issues and provide prompt interventions, improving the quality of patient care. This study's integration of advanced machine learning and IoT underlines the strategy's disruptive potential for transforming healthcare procedures. This study provides the foundation for a more effective, responsive, and patient-centered healthcare ecosystem by employing the potential of connected devices and predictive analytics.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-05DOI: 10.53759/7669/jmc202303047
Dong Jo Kim
Autonomous vehicles use remote-sensing technologies such as radar, GPS, cameras, and lidar to effectively observe their immediate environment and construct a comprehensive three-dimensional representation. The conventional constituents of this particular environment include structures, additional vehicles, people, as well as signage and traffic indicators. At now, a self-driving car is equipped with a wide array of sensors that are not found in a traditional automobile. Commonly used sensors include lasers and visual sensors, which serve the purpose of acquiring comprehensive understanding of the immediate environment. The cost of these sensors is high and they exhibit selectivity in their use requirements. The installation of these sensors in a mobile vehicle also significantly diminishes their operational longevity. Furthermore, the issue of trustworthiness is a matter of significant concern. The present article is structured into distinct parts, each of which delves into a significant aspect and obstacle pertaining to the trend and development of autonomous vehicles. The parts describing the obstacles in the development of autonomous vehicles define the conflict arising from the use of cameras and LiDAR technology, the influence of social norms, the impact of human psychology, and the legal complexities involved.
{"title":"A Discussion of Key Aspects and Trends in Self Driving Vehicle Technology","authors":"Dong Jo Kim","doi":"10.53759/7669/jmc202303047","DOIUrl":"https://doi.org/10.53759/7669/jmc202303047","url":null,"abstract":"Autonomous vehicles use remote-sensing technologies such as radar, GPS, cameras, and lidar to effectively observe their immediate environment and construct a comprehensive three-dimensional representation. The conventional constituents of this particular environment include structures, additional vehicles, people, as well as signage and traffic indicators. At now, a self-driving car is equipped with a wide array of sensors that are not found in a traditional automobile. Commonly used sensors include lasers and visual sensors, which serve the purpose of acquiring comprehensive understanding of the immediate environment. The cost of these sensors is high and they exhibit selectivity in their use requirements. The installation of these sensors in a mobile vehicle also significantly diminishes their operational longevity. Furthermore, the issue of trustworthiness is a matter of significant concern. The present article is structured into distinct parts, each of which delves into a significant aspect and obstacle pertaining to the trend and development of autonomous vehicles. The parts describing the obstacles in the development of autonomous vehicles define the conflict arising from the use of cameras and LiDAR technology, the influence of social norms, the impact of human psychology, and the legal complexities involved.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-05DOI: 10.53759/7669/jmc202303032
Kaladharan N, Arunkumar R
Automatic voice authentication based on deep learning is a promising technology that has received much attention from academia and industry. It has proven to be effective in a variety of applications, including biometric access control systems. Using biometric data in such systems is difficult, particularly in a centralized setting. It introduces numerous risks, such as information disclosure, unreliability, security, privacy, etc. Voice authentication systems are becoming increasingly important in solving these issues. This is especially true if the device relies on voice commands from the user. This work investigates the development of a text-independent voice authentication system. The spatial features of the voiceprint (corresponding to the speech spectrum) are present in the speech signal as a result of the spectrogram, and the weighted wavelet packet cepstral coefficients (W-WPCC) are effective for spatial feature extraction (corresponding to the speech spectrum). W- WPCC characteristics are calculated by combining sub-band energies with sub-band spectral centroids using a weighting scheme to generate noise-resistant acoustic characteristics. In addition, this work proposes an enhanced inception v3 model for voice authentication. The proposed InceptionV3 system extracts feature from input data from the convolutional and pooling layers. By employing fewer parameters, this architecture reduces the complexity of the convolution process while increasing learning speed. Following model training, the enhanced Inception v3 model classifies audio samples as authenticated or not based on extracted features. Experiments were carried out on the speech of five English speakers whose voices were collected from YouTube. The results reveal that the suggested improved method, based on enhanced Inception v3 and trained on speech spectrogram pictures, outperforms the existing methods. The approach generates tests with an average categorization accuracy of 99%. Compared to the performance of these network models on the given dataset, the proposed enhanced Inception v3 network model achieves the best results regarding model training time, recognition accuracy, and stability.
{"title":"An Efficient Voice Authentication System using Enhanced Inceptionv3 Algorithm","authors":"Kaladharan N, Arunkumar R","doi":"10.53759/7669/jmc202303032","DOIUrl":"https://doi.org/10.53759/7669/jmc202303032","url":null,"abstract":"Automatic voice authentication based on deep learning is a promising technology that has received much attention from academia and industry. It has proven to be effective in a variety of applications, including biometric access control systems. Using biometric data in such systems is difficult, particularly in a centralized setting. It introduces numerous risks, such as information disclosure, unreliability, security, privacy, etc. Voice authentication systems are becoming increasingly important in solving these issues. This is especially true if the device relies on voice commands from the user. This work investigates the development of a text-independent voice authentication system. The spatial features of the voiceprint (corresponding to the speech spectrum) are present in the speech signal as a result of the spectrogram, and the weighted wavelet packet cepstral coefficients (W-WPCC) are effective for spatial feature extraction (corresponding to the speech spectrum). W- WPCC characteristics are calculated by combining sub-band energies with sub-band spectral centroids using a weighting scheme to generate noise-resistant acoustic characteristics. In addition, this work proposes an enhanced inception v3 model for voice authentication. The proposed InceptionV3 system extracts feature from input data from the convolutional and pooling layers. By employing fewer parameters, this architecture reduces the complexity of the convolution process while increasing learning speed. Following model training, the enhanced Inception v3 model classifies audio samples as authenticated or not based on extracted features. Experiments were carried out on the speech of five English speakers whose voices were collected from YouTube. The results reveal that the suggested improved method, based on enhanced Inception v3 and trained on speech spectrogram pictures, outperforms the existing methods. The approach generates tests with an average categorization accuracy of 99%. Compared to the performance of these network models on the given dataset, the proposed enhanced Inception v3 network model achieves the best results regarding model training time, recognition accuracy, and stability.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A botnet is a malware application controlled from a distance by a programmer with the assistance of a botmaster. Botnets can launch enormous cyber-attacks like Denial-of-Service (DOS), phishing, spam, data stealing, and identity theft. The botnet can also affect the security and privacy of the systems. The conventional approach to detecting botnets is made by signature-based analysis, which cannot discover botnets that are not visible. The behavior-based analysis appears to be an appropriate solution to the current botnet characteristics that are constantly developing. This paper aims to develop an efficient botnet detection algorithm using machine learning with traffic reduction to increase accuracy. Based on behavioural analysis, a traffic reduction strategy is applied to reduce network traffic to improve overall system performance. Several network devices are typically used to retrieve network traffic information. With a detection accuracy of 98.4%, the known and unknown botnet activities are measured using the supplied datasets. The machine learning-based traffic reduction system has achieved a high rate of traffic reduction, about 82%, and false-positive rates range between 0% to 2%. Both findings demonstrate that the suggested technique is efficient and accurate.
{"title":"Hybrid Machine Learning Technique to Detect Active Botnet Attacks for Network Security and Privacy","authors":"Venkatesan C, Thamaraimanalan T, Balamurugan D, Gowrishankar J, Manjunath R, Sivaramakrishnan A","doi":"10.53759/7669/jmc202303044","DOIUrl":"https://doi.org/10.53759/7669/jmc202303044","url":null,"abstract":"A botnet is a malware application controlled from a distance by a programmer with the assistance of a botmaster. Botnets can launch enormous cyber-attacks like Denial-of-Service (DOS), phishing, spam, data stealing, and identity theft. The botnet can also affect the security and privacy of the systems. The conventional approach to detecting botnets is made by signature-based analysis, which cannot discover botnets that are not visible. The behavior-based analysis appears to be an appropriate solution to the current botnet characteristics that are constantly developing. This paper aims to develop an efficient botnet detection algorithm using machine learning with traffic reduction to increase accuracy. Based on behavioural analysis, a traffic reduction strategy is applied to reduce network traffic to improve overall system performance. Several network devices are typically used to retrieve network traffic information. With a detection accuracy of 98.4%, the known and unknown botnet activities are measured using the supplied datasets. The machine learning-based traffic reduction system has achieved a high rate of traffic reduction, about 82%, and false-positive rates range between 0% to 2%. Both findings demonstrate that the suggested technique is efficient and accurate.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-05DOI: 10.53759/7669/jmc202303050
Murali Dhar M S, Kishore Kumar A, Rajkumar B, Poonguzhali P K, Hemakesavulu O, Mahaveerakannan R
Due to human activities like global warming, pollution, ozone depletion, deforestation, etc., the frequency and severity of natural disasters have increased in recent years. Unlike many other types of natural disasters, floods may be anticipated and warned about in advance. This work presents a flood monitoring and alarm system enabled by a smart device. A microcontroller (Arduino) is included, and its support for detection and indication makes it useful for keeping tabs on and managing the gadget. The device uses its own sensors to take readings of its immediate surroundings, then uploads that data to the cloud and notifies a central administrator of the impending flood. When admin discovers a crisis situation based on the data it has collected, it quickly sends out alerts to those in the local vicinity of any places that are likely to be flooded. Using an Android app, it alerts the user's screen. The project's end goal is to develop an application that swiftly disseminates flood warning information to rural agricultural communities. Scaled principal component analysis (SPCA) is used to filter out extraneous data, and an ensemble machine learning technique is used to make flood predictions. The tests are performed on a dataset that is being collected in real-time and analysed in terms of a number of different parameters. In this research, we propose a strategy for long-term agricultural output through the mitigation of flood risk.
{"title":"Implementation of the Internet of Things for early Floods in Agricultural Land using Dimensionality Reduction Technique and Ensemble ML","authors":"Murali Dhar M S, Kishore Kumar A, Rajkumar B, Poonguzhali P K, Hemakesavulu O, Mahaveerakannan R","doi":"10.53759/7669/jmc202303050","DOIUrl":"https://doi.org/10.53759/7669/jmc202303050","url":null,"abstract":"Due to human activities like global warming, pollution, ozone depletion, deforestation, etc., the frequency and severity of natural disasters have increased in recent years. Unlike many other types of natural disasters, floods may be anticipated and warned about in advance. This work presents a flood monitoring and alarm system enabled by a smart device. A microcontroller (Arduino) is included, and its support for detection and indication makes it useful for keeping tabs on and managing the gadget. The device uses its own sensors to take readings of its immediate surroundings, then uploads that data to the cloud and notifies a central administrator of the impending flood. When admin discovers a crisis situation based on the data it has collected, it quickly sends out alerts to those in the local vicinity of any places that are likely to be flooded. Using an Android app, it alerts the user's screen. The project's end goal is to develop an application that swiftly disseminates flood warning information to rural agricultural communities. Scaled principal component analysis (SPCA) is used to filter out extraneous data, and an ensemble machine learning technique is used to make flood predictions. The tests are performed on a dataset that is being collected in real-time and analysed in terms of a number of different parameters. In this research, we propose a strategy for long-term agricultural output through the mitigation of flood risk.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135546541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-05DOI: 10.53759/7669/jmc202303033
Shreenidhi H S, Narayana Swamy Ramaiah
Forecasting the electricity load is crucial for power system planning and energy management. Since the season of the year, weather, weekdays, and holidays are the key aspects that have an effect on the load consumption, it is difficult to anticipate the future demands. Therefore, we proposed a weather-based short-term load forecasting framework in this paper. First, the missing data is filled, and data normalisation is performed in the pre-processing step. Normalization accelerates convergence and improves network training efficiency by preventing gradient explosion during the training phase. Then the weather, PV, and load features are extracted and fed into the proposed Highway Self-Attention Dilated Casual Convolutional Neural Network (HSAD-CNN) forecasting model. The dilated casual convolutions increase the receptive field without significantly raising computing costs. The multi-head self-attention mechanism (MHSA) gives importance to the most significant time steps for a more accurate forecast. The highway skip network (HS-Net) uses shortcut paths and skip connections to improve the information flow. This speed up the network convergence and prevents feature reuse, vanishing gradients, and negative learning problems. The performance of the HSAD-CNN forecasting technique is evaluated and compared to existing techniques under different day types and seasonal changes. The outcomes indicate that the HSAD-CNN forecasting model has low Mean Absolute Error (MAE), Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), and a high R2.
{"title":"Highway Self-Attention Dilated Casual Convolutional Neural Network Based Short Term Load Forecasting in Micro Grid","authors":"Shreenidhi H S, Narayana Swamy Ramaiah","doi":"10.53759/7669/jmc202303033","DOIUrl":"https://doi.org/10.53759/7669/jmc202303033","url":null,"abstract":"Forecasting the electricity load is crucial for power system planning and energy management. Since the season of the year, weather, weekdays, and holidays are the key aspects that have an effect on the load consumption, it is difficult to anticipate the future demands. Therefore, we proposed a weather-based short-term load forecasting framework in this paper. First, the missing data is filled, and data normalisation is performed in the pre-processing step. Normalization accelerates convergence and improves network training efficiency by preventing gradient explosion during the training phase. Then the weather, PV, and load features are extracted and fed into the proposed Highway Self-Attention Dilated Casual Convolutional Neural Network (HSAD-CNN) forecasting model. The dilated casual convolutions increase the receptive field without significantly raising computing costs. The multi-head self-attention mechanism (MHSA) gives importance to the most significant time steps for a more accurate forecast. The highway skip network (HS-Net) uses shortcut paths and skip connections to improve the information flow. This speed up the network convergence and prevents feature reuse, vanishing gradients, and negative learning problems. The performance of the HSAD-CNN forecasting technique is evaluated and compared to existing techniques under different day types and seasonal changes. The outcomes indicate that the HSAD-CNN forecasting model has low Mean Absolute Error (MAE), Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), and a high R2.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-05DOI: 10.53759/7669/jmc202303031
Balakumar D, Rangaraj J
Many real-time applications make use of advanced wireless sensor networks (WSNs). Because of the limited memory, power limits, narrow communication bandwidth, and low processing units of wireless sensor nodes (SNs), WSNs suffer severe resource constraints. Data prediction algorithms in WSNs have become crucial for reducing redundant data transmission and extending the network's longevity. Redundancy can be decreased using proper machine learning (ML) techniques while the data aggregation process operates. Researchers persist in searching for effective modelling strategies and algorithms to help generate efficient and acceptable data aggregation methodologies from preexisting WSN models. This work proposes an energy-efficient Adaptive Seagull Optimization Algorithm (ASOA) protocol for selecting the best cluster head (CH). An extreme learning machine (ELM) is employed to select the data corresponding to each node as a way to generate a tree to cluster sensor data. The Dual Graph Convolutional Network (DGCN) is an analytical method that predicts future trends using time series data. Data clustering and aggregation are employed for each cluster head to efficiently perform sample data prediction across WSNs, primarily to minimize the processing overhead caused by the prediction algorithm. Simulation findings suggest that the presented method is practical and efficient regarding reliability, data reduction, and power usage. The results demonstrate that the suggested data collection approach surpasses the existing Least Mean Square (LMS), Periodic Data Prediction Algorithm (P-PDA), and Combined Data Prediction Model (CDPM) methods significantly. The proposed DGCN method has a transmission suppression rate of 92.68%, a difference of 22.33%, 16.69%, and 12.54% compared to the current methods (i.e., LMS, P-PDA, and CDPM).
{"title":"A Prediction Model Based Energy Efficient Data Collection for Wireless Sensor Networks","authors":"Balakumar D, Rangaraj J","doi":"10.53759/7669/jmc202303031","DOIUrl":"https://doi.org/10.53759/7669/jmc202303031","url":null,"abstract":"Many real-time applications make use of advanced wireless sensor networks (WSNs). Because of the limited memory, power limits, narrow communication bandwidth, and low processing units of wireless sensor nodes (SNs), WSNs suffer severe resource constraints. Data prediction algorithms in WSNs have become crucial for reducing redundant data transmission and extending the network's longevity. Redundancy can be decreased using proper machine learning (ML) techniques while the data aggregation process operates. Researchers persist in searching for effective modelling strategies and algorithms to help generate efficient and acceptable data aggregation methodologies from preexisting WSN models. This work proposes an energy-efficient Adaptive Seagull Optimization Algorithm (ASOA) protocol for selecting the best cluster head (CH). An extreme learning machine (ELM) is employed to select the data corresponding to each node as a way to generate a tree to cluster sensor data. The Dual Graph Convolutional Network (DGCN) is an analytical method that predicts future trends using time series data. Data clustering and aggregation are employed for each cluster head to efficiently perform sample data prediction across WSNs, primarily to minimize the processing overhead caused by the prediction algorithm. Simulation findings suggest that the presented method is practical and efficient regarding reliability, data reduction, and power usage. The results demonstrate that the suggested data collection approach surpasses the existing Least Mean Square (LMS), Periodic Data Prediction Algorithm (P-PDA), and Combined Data Prediction Model (CDPM) methods significantly. The proposed DGCN method has a transmission suppression rate of 92.68%, a difference of 22.33%, 16.69%, and 12.54% compared to the current methods (i.e., LMS, P-PDA, and CDPM).","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：