Pub Date : 2024-04-05DOI: 10.53759/7669/jmc202404029
Anbumani K, Cuddapah Anitha, Achuta Rao S V, Praveen Kumar K, Meganathan Ramasamy, M. R.
Even though Convolutional Neural Networks (CNNs) have greatly improved face-related algorithms, it is still difficult to keep both accuracy and efficiency in real-world applications. The most cutting-edge approaches use deeper networks to improve performance, but the increased computing complexity and number of parameters make them impractical for usage in mobile applications. To tackle these issues, this article presents a model for object detection that combines Deeplabv3+ with Swin transformer, which incorporates GLTB and Swin-Conv-Dspp (SCD). To start with, in order to lessen the impact of the hole phenomena and the loss of fine-grained data, we employ the SCD component, which is capable of efficiently extracting feature information from objects at various sizes. Secondly, in order to properly address the issue of challenging object recognition due to occlusion, the study builds a GLTB with a spatial pyramid pooling shuffle module. This module allows for the extraction of important detail information from the few noticeable pixels of the blocked objects. Crocodile search algorithm (CSA) enhances classification accuracy by properly selecting the model's fine-tuning. On a benchmark dataset known as WFLW, the study experimentally validates the suggested model. Compared to other light models, the experimental findings show that it delivers higher performance with significantly fewer parameters and reduced computing complexity.
{"title":"Video Face Tracking for IoT Big Data using Improved Swin Transformer based CSA Model","authors":"Anbumani K, Cuddapah Anitha, Achuta Rao S V, Praveen Kumar K, Meganathan Ramasamy, M. R.","doi":"10.53759/7669/jmc202404029","DOIUrl":"https://doi.org/10.53759/7669/jmc202404029","url":null,"abstract":"Even though Convolutional Neural Networks (CNNs) have greatly improved face-related algorithms, it is still difficult to keep both accuracy and efficiency in real-world applications. The most cutting-edge approaches use deeper networks to improve performance, but the increased computing complexity and number of parameters make them impractical for usage in mobile applications. To tackle these issues, this article presents a model for object detection that combines Deeplabv3+ with Swin transformer, which incorporates GLTB and Swin-Conv-Dspp (SCD). To start with, in order to lessen the impact of the hole phenomena and the loss of fine-grained data, we employ the SCD component, which is capable of efficiently extracting feature information from objects at various sizes. Secondly, in order to properly address the issue of challenging object recognition due to occlusion, the study builds a GLTB with a spatial pyramid pooling shuffle module. This module allows for the extraction of important detail information from the few noticeable pixels of the blocked objects. Crocodile search algorithm (CSA) enhances classification accuracy by properly selecting the model's fine-tuning. On a benchmark dataset known as WFLW, the study experimentally validates the suggested model. Compared to other light models, the experimental findings show that it delivers higher performance with significantly fewer parameters and reduced computing complexity.","PeriodicalId":516221,"journal":{"name":"Journal of Machine and Computing","volume":"69 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140736275","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 : 2024-04-05DOI: 10.53759/7669/jmc202404031
Husam Alowaidi, Prashant G C, Gopalakrishnan T, Sundar Raja M, Padmaja S M, Anjali Devi S
The paper developed an approach for fault diagnosis in Hydro-Electrical Power Systems (HEPS). Using a Renewable Energy System (RES), HEPS has performed a significant part in contributing to addressing the evolving energy demands of the present. Several electro-mechanical elements that collectively comprise the Hydro-Electric (HE) system are susceptible to corrosion from routine usage and unplanned occurrences. Administration and servicing systems that are successful in implementing and achieving these goals are those that regularly track and predict failures. Detect models applied in the past included those that were primarily reactive or reliant on human involvement to identify and analyse abnormalities. The significant multiple variables intricacies that impact successful fault detection are disregarded by these frameworks. The research presented here proposes a Convolutional Deep Belief Network (CDBN) driven Deep Learning (DL) model for successful fault and failure detection in such power systems that address these problems. Applying sample data collected from two Chinese power plants, the proposed framework has been assessed compared to other practical DL algorithms. Different metrics have been employed to determine the effectiveness of the simulations, namely Accuracy, Precision, Recall, and F1-score. These outcomes indicated that the CDBN is capable of predicting unexpected failures. Graphic representations demonstrating control used to measure turbine blade load, vibration level, and generator heat for assessing the replicas.
该论文开发了一种水力发电系统（HEPS）故障诊断方法。作为一种可再生能源系统（RES），水力发电系统在满足当前不断变化的能源需求方面发挥了重要作用。水电（HE）系统中的多个机电元件容易受到日常使用和意外事故的腐蚀。能够成功实施和实现这些目标的管理和服务系统是那些能够定期跟踪和预测故障的系统。过去采用的检测模型主要是被动型的，或依靠人工参与来识别和分析异常情况。这些框架忽略了影响成功故障检测的多变量复杂性。本文介绍的研究提出了一种卷积深度信念网络（CDBN）驱动的深度学习（DL）模型，用于在此类电力系统中成功进行故障和失效检测，以解决这些问题。利用从中国两家发电厂收集的样本数据，对所提出的框架进行了评估，并与其他实用的深度学习算法进行了比较。我们采用了不同的指标来确定模拟的有效性，即准确度、精确度、召回率和 F1 分数。这些结果表明，CDBN 能够预测意外故障。图形表示法展示了用于测量涡轮叶片负载、振动水平和发电机热量的控制，以评估复制品。
{"title":"Convolutional Deep Belief Network Based Expert System for Automated Fault Diagnosis in Hydro Electrical Power Systems","authors":"Husam Alowaidi, Prashant G C, Gopalakrishnan T, Sundar Raja M, Padmaja S M, Anjali Devi S","doi":"10.53759/7669/jmc202404031","DOIUrl":"https://doi.org/10.53759/7669/jmc202404031","url":null,"abstract":"The paper developed an approach for fault diagnosis in Hydro-Electrical Power Systems (HEPS). Using a Renewable Energy System (RES), HEPS has performed a significant part in contributing to addressing the evolving energy demands of the present. Several electro-mechanical elements that collectively comprise the Hydro-Electric (HE) system are susceptible to corrosion from routine usage and unplanned occurrences. Administration and servicing systems that are successful in implementing and achieving these goals are those that regularly track and predict failures. Detect models applied in the past included those that were primarily reactive or reliant on human involvement to identify and analyse abnormalities. The significant multiple variables intricacies that impact successful fault detection are disregarded by these frameworks. The research presented here proposes a Convolutional Deep Belief Network (CDBN) driven Deep Learning (DL) model for successful fault and failure detection in such power systems that address these problems. Applying sample data collected from two Chinese power plants, the proposed framework has been assessed compared to other practical DL algorithms. Different metrics have been employed to determine the effectiveness of the simulations, namely Accuracy, Precision, Recall, and F1-score. These outcomes indicated that the CDBN is capable of predicting unexpected failures. Graphic representations demonstrating control used to measure turbine blade load, vibration level, and generator heat for assessing the replicas.","PeriodicalId":516221,"journal":{"name":"Journal of Machine and Computing","volume":"45 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140736799","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 : 2024-04-05DOI: 10.53759/7669/jmc202404030
Komala Devi K, Josephine Prem Kumar
Agriculture is the most vital sector for the global food supply, and it also provides raw materials for other types of industries. A crop recommendation system is essential for farmers who want to get the most out of their crop-choosing decisions. Over the last several decades, the world's ability to produce food has grown substantially owing to the extensive usage of fertilizers. Therefore, there has to be a more eco-friendly and effective way to utilize fertilizers that include nitrogen (N), phosphorous (P), and potassium (K) to ensure food security. For the reason, this study proposes an ensemble machine learning–assisted crop and fertilizer recommendation system (EML–CFRS) to maximize agricultural output while ensuring the correct use of mineral resources. The research used a dataset obtained from the Kaggle repository like that people can assess several distinct ML algorithms. The databases include data on three climate variables—temperature, rainfall, and humidity—and information on NPK and soil pH. The yields agricultural crops were used to train these models, including Decision Tree, KNN, XGBoost, Support Vector Machine, and Random Forest. Depending on the current weather and soil conditions, the trained model may then recommend the optimal fertiliser for a certain crop. Predicting the ideal kind and quantity of fertilizer for different crops was accomplished with a 96.5% accuracy rate by our suggested strategy.
农业是全球粮食供应最重要的部门，同时也为其他类型的工业提供原材料。对于希望从作物选择决策中获得最大收益的农民来说，作物推荐系统是必不可少的。过去几十年来，由于化肥的广泛使用，世界粮食生产能力大幅提高。因此，必须有一种更环保、更有效的方法来利用包括氮（N）、磷（P）和钾（K）在内的肥料，以确保粮食安全。为此，本研究提出了一种集合机器学习辅助作物和肥料推荐系统（EML-CFRS），在确保正确使用矿产资源的同时，最大限度地提高农业产量。研究使用了从 Kaggle 数据库中获得的数据集，以便人们评估几种不同的 ML 算法。数据库包括三个气候变量的数据--温度、降雨量和湿度，以及氮磷钾和土壤酸碱度的信息。农作物产量被用于训练这些模型，包括决策树、KNN、XGBoost、支持向量机和随机森林。根据当前的天气和土壤条件，经过训练的模型可以为某种作物推荐最佳肥料。通过我们建议的策略，为不同作物预测理想肥料种类和数量的准确率达到了 96.5%。
{"title":"Sustainable Food Development Based on Ensemble Machine Learning Assisted Crop and Fertilizer Recommendation System","authors":"Komala Devi K, Josephine Prem Kumar","doi":"10.53759/7669/jmc202404030","DOIUrl":"https://doi.org/10.53759/7669/jmc202404030","url":null,"abstract":"Agriculture is the most vital sector for the global food supply, and it also provides raw materials for other types of industries. A crop recommendation system is essential for farmers who want to get the most out of their crop-choosing decisions. Over the last several decades, the world's ability to produce food has grown substantially owing to the extensive usage of fertilizers. Therefore, there has to be a more eco-friendly and effective way to utilize fertilizers that include nitrogen (N), phosphorous (P), and potassium (K) to ensure food security. For the reason, this study proposes an ensemble machine learning–assisted crop and fertilizer recommendation system (EML–CFRS) to maximize agricultural output while ensuring the correct use of mineral resources. The research used a dataset obtained from the Kaggle repository like that people can assess several distinct ML algorithms. The databases include data on three climate variables—temperature, rainfall, and humidity—and information on NPK and soil pH. The yields agricultural crops were used to train these models, including Decision Tree, KNN, XGBoost, Support Vector Machine, and Random Forest. Depending on the current weather and soil conditions, the trained model may then recommend the optimal fertiliser for a certain crop. Predicting the ideal kind and quantity of fertilizer for different crops was accomplished with a 96.5% accuracy rate by our suggested strategy.","PeriodicalId":516221,"journal":{"name":"Journal of Machine and Computing","volume":"22 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140739956","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 : 2024-04-05DOI: 10.53759/7669/jmc202404048
In-Young Hyun, Seung-Mi Yun, Eui-Rim Jeong
The unmanned swarm robot system, which enables multiple robots to collaborate and perform a variety of tasks, is extensively researched for its potential applications. Accurate determination of the location of swarm robots during operation is of paramount importance, and various positioning algorithms are employed to achieve this. Specifically, in situations where global positioning system (GPS) signals are unavailable, fixed anchor nodes with known location information can be utilized for localization. However, in scenarios where fixed anchor nodes are not present, and the robots operate in a swarm, applying this technology poses challenges, necessitating a localization technique that relies solely on distance information between the robots. This paper proposes a deep neural network (DNN) technique that utilizes only the distance information between moving nodes to predict the real-time relative coordinates of each node. It is assumed that the distances between nodes are updated sequentially and periodically according to a predetermined measurement cycle. A grid-based localization technique is used as the existing method for performance comparison. Computer simulation results demonstrate that the proposed DNN-based relative Localization technique exhibits superior localization performance compared to the existing Grid-based method. Furthermore, the proposed technique shows similar performance regardless of the distance measurement cycle, indicating that it is not significantly affected by the cycle. Therefore, applying the proposed relative Localization algorithm to swarm robots could enable real-time and accurate relative positioning, facilitating precise location tracking of the swarm.
{"title":"DNN-Based Relative Localization Technique for Real-Time Positioning of Moving Unmanned Swarm Robots","authors":"In-Young Hyun, Seung-Mi Yun, Eui-Rim Jeong","doi":"10.53759/7669/jmc202404048","DOIUrl":"https://doi.org/10.53759/7669/jmc202404048","url":null,"abstract":"The unmanned swarm robot system, which enables multiple robots to collaborate and perform a variety of tasks, is extensively researched for its potential applications. Accurate determination of the location of swarm robots during operation is of paramount importance, and various positioning algorithms are employed to achieve this. Specifically, in situations where global positioning system (GPS) signals are unavailable, fixed anchor nodes with known location information can be utilized for localization. However, in scenarios where fixed anchor nodes are not present, and the robots operate in a swarm, applying this technology poses challenges, necessitating a localization technique that relies solely on distance information between the robots. This paper proposes a deep neural network (DNN) technique that utilizes only the distance information between moving nodes to predict the real-time relative coordinates of each node. It is assumed that the distances between nodes are updated sequentially and periodically according to a predetermined measurement cycle. A grid-based localization technique is used as the existing method for performance comparison. Computer simulation results demonstrate that the proposed DNN-based relative Localization technique exhibits superior localization performance compared to the existing Grid-based method. Furthermore, the proposed technique shows similar performance regardless of the distance measurement cycle, indicating that it is not significantly affected by the cycle. Therefore, applying the proposed relative Localization algorithm to swarm robots could enable real-time and accurate relative positioning, facilitating precise location tracking of the swarm.","PeriodicalId":516221,"journal":{"name":"Journal of Machine and Computing","volume":"22 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140738231","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 : 2024-04-05DOI: 10.53759/7669/jmc202404049
Lekha T R, Saravanakumar K, Akshaya V S, Aravindhan K
This article focuses on the progress of underwater robots and the importance of software architectures in building robust and autonomous systems. The researchers underscore the challenges linked to implementation and stress the need for comprehensive validation of both reliability and efficacy. Their argument is on the extensive implementation of a globally applicable architectural framework that complies with established standards and guarantees interoperability within the field of robotics. The research also covers advancements in underwater soft robotics, which include the development of models, materials, sensors, control systems, power storage, and actuation techniques. This article explores the challenges and potential applications of underwater soft robotics, highlighting the need of collaboration across many fields and advancements in mechanical design and control methods. In the last section of the paper, the control approach and algorithms used to underwater exploration robots are reviewed. Particular attention is given to the application of Proportional Integral Derivative (PID) control and the incorporation of Backpropagation Neural Network (BPNN) for PID parameter determination.
{"title":"Advancements and Challenges in Underwater Soft Robotics: Materials, Control and Integration","authors":"Lekha T R, Saravanakumar K, Akshaya V S, Aravindhan K","doi":"10.53759/7669/jmc202404049","DOIUrl":"https://doi.org/10.53759/7669/jmc202404049","url":null,"abstract":"This article focuses on the progress of underwater robots and the importance of software architectures in building robust and autonomous systems. The researchers underscore the challenges linked to implementation and stress the need for comprehensive validation of both reliability and efficacy. Their argument is on the extensive implementation of a globally applicable architectural framework that complies with established standards and guarantees interoperability within the field of robotics. The research also covers advancements in underwater soft robotics, which include the development of models, materials, sensors, control systems, power storage, and actuation techniques. This article explores the challenges and potential applications of underwater soft robotics, highlighting the need of collaboration across many fields and advancements in mechanical design and control methods. In the last section of the paper, the control approach and algorithms used to underwater exploration robots are reviewed. Particular attention is given to the application of Proportional Integral Derivative (PID) control and the incorporation of Backpropagation Neural Network (BPNN) for PID parameter determination.","PeriodicalId":516221,"journal":{"name":"Journal of Machine and Computing","volume":"27 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140735891","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 : 2024-04-05DOI: 10.53759/7669/jmc202404028
V. P, Venkatesh K
In ad hoc wireless sensor networks, the mobile nodes are deployed to gather data from source and transferring them to base station for reactive decision making. This process of data forwarding attributed by the sensor nodes incurs huge loss of energy which has the possibility of minimizing the network lifetime. In this context, cluster-based topology is determined to be optimal for reducing energy loss of nodes in WSNs. The selection of CH using hybrid metaheuristic algorithms is identified to be significant to mitigate the quick exhaustion of energy in entire network. This paper explores the concept of hybrid Crow Search and Particle Swarm Optimization Algorithm-based CH Selection (HCSPSO-CHS) mechanism is proposed with the merits of Flower Pollination Algorithm (FPA) and integrated Crow Search Algorithm (CSA) for efficient CH selection. It further adopted an improved PSO for achieving sink node mobility to improve delivery of packets to sink nodes. This HCSPSO-CHS approach assessed the influential factors like residual energy, inter and intra-cluster distances, network proximity and network grade during efficient CH selection. It facilitated better search process and converged towards the best global solution, such that frequent CH selection is avoided to maximum level. The outcomes of the suggested simulation HCSPSO-CHS confirm better performance depending on the maximum number of active nodes by 23.18%, prevent death of sensor nodes by 23.41% with augmented network lifetime of 33.58% independent of the number of nodes and rounds of data transmission.
{"title":"Hybrid Crow Search and Particle Swarm Algorithmic optimization based CH Selection method to extend Wireless Sensor Network operation","authors":"V. P, Venkatesh K","doi":"10.53759/7669/jmc202404028","DOIUrl":"https://doi.org/10.53759/7669/jmc202404028","url":null,"abstract":"In ad hoc wireless sensor networks, the mobile nodes are deployed to gather data from source and transferring them to base station for reactive decision making. This process of data forwarding attributed by the sensor nodes incurs huge loss of energy which has the possibility of minimizing the network lifetime. In this context, cluster-based topology is determined to be optimal for reducing energy loss of nodes in WSNs. The selection of CH using hybrid metaheuristic algorithms is identified to be significant to mitigate the quick exhaustion of energy in entire network. This paper explores the concept of hybrid Crow Search and Particle Swarm Optimization Algorithm-based CH Selection (HCSPSO-CHS) mechanism is proposed with the merits of Flower Pollination Algorithm (FPA) and integrated Crow Search Algorithm (CSA) for efficient CH selection. It further adopted an improved PSO for achieving sink node mobility to improve delivery of packets to sink nodes. This HCSPSO-CHS approach assessed the influential factors like residual energy, inter and intra-cluster distances, network proximity and network grade during efficient CH selection. It facilitated better search process and converged towards the best global solution, such that frequent CH selection is avoided to maximum level. The outcomes of the suggested simulation HCSPSO-CHS confirm better performance depending on the maximum number of active nodes by 23.18%, prevent death of sensor nodes by 23.41% with augmented network lifetime of 33.58% independent of the number of nodes and rounds of data transmission.","PeriodicalId":516221,"journal":{"name":"Journal of Machine and Computing","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140737728","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 : 2024-04-05DOI: 10.53759/7669/jmc202404033
Deepak Tulsiram Patil, Amiya Bhaumik
The revolutionary impact of Internet of Things (IoT) improvements on the construction enterprise is carefully tested on this extensive research, with a focus on cost-cutting strategies. Examining a wide range of IoT programs from the predictive repair of equipment to the actual-time monitoring of building materials the study highlights how those packages can appreciably lessen operating charges. This inquiry identifies key areas wherein IoT technology are expected to sell cost-saving measures by utilizing a thorough evaluation of relevant literature along with a robust method that includes case research and empirical records evaluation. Using 12 records points and a aggregate of documentation evaluation and interviews, this examine assesses the impact of IoT technology on constructing charges. It offers insights into how IoT adoption in creation might be financially viable with the aid of highlighting the way it influences fee dynamics and undertaking control. The observe concludes with the aid of dropping mild at the broader implications of IoT adoption inside the construction enterprise and emphasizing how important it is to promoting a sustainable environment and strengthening the competitive fringe of companies on this zone. The present investigation not only emphasizes the economic blessings of implementing IoT, but additionally indicates its capability to convert conventional building methods by way of facilitating the improvement of greater reasonably priced, efficient, and environmentally friendly venture execution strategies.
{"title":"IoT Innovations as a Strategy for Minimizing Construction Expenses","authors":"Deepak Tulsiram Patil, Amiya Bhaumik","doi":"10.53759/7669/jmc202404033","DOIUrl":"https://doi.org/10.53759/7669/jmc202404033","url":null,"abstract":"The revolutionary impact of Internet of Things (IoT) improvements on the construction enterprise is carefully tested on this extensive research, with a focus on cost-cutting strategies. Examining a wide range of IoT programs from the predictive repair of equipment to the actual-time monitoring of building materials the study highlights how those packages can appreciably lessen operating charges. This inquiry identifies key areas wherein IoT technology are expected to sell cost-saving measures by utilizing a thorough evaluation of relevant literature along with a robust method that includes case research and empirical records evaluation. Using 12 records points and a aggregate of documentation evaluation and interviews, this examine assesses the impact of IoT technology on constructing charges. It offers insights into how IoT adoption in creation might be financially viable with the aid of highlighting the way it influences fee dynamics and undertaking control. The observe concludes with the aid of dropping mild at the broader implications of IoT adoption inside the construction enterprise and emphasizing how important it is to promoting a sustainable environment and strengthening the competitive fringe of companies on this zone. The present investigation not only emphasizes the economic blessings of implementing IoT, but additionally indicates its capability to convert conventional building methods by way of facilitating the improvement of greater reasonably priced, efficient, and environmentally friendly venture execution strategies.","PeriodicalId":516221,"journal":{"name":"Journal of Machine and Computing","volume":"10 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140738198","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 : 2024-04-05DOI: 10.53759/7669/jmc202404027
Hussein Z, Balaji V, Ramesh R, Arokia Jesu Prabhu L, Venubabu Rachapudi, E. V
The deployment of Machine Learning (ML) for improving Water Treatment Plants (WTPs) predictive maintenance is investigated in the present article. Proactively detecting and fixing functional difficulties which might cause catastrophic effects has historically been an endeavour for reactive or schedule-based maintenance methods. Anomaly Detection (AD) in WTP predictive maintenance frameworks is the primary goal of this investigation, which recommends a novel approach based on autoencoder (AE)-based ML models. For the objective of examining high-dimensional time-series sensor data collected from a WTP over a long time, Sparse Autoencoders (SAEs) are implemented. The data collected involves an array of operational measurements that, evaluated together, describe the plant's overall performance. With the support of the AE, this work aims to develop a practical framework for WTP operation predictive maintenance. Anomalies are all system findings from testing that might result in flaws or malfunctions. The research article analyses January and July 2023 WTP data from Jiangsu Province China. The AE paradigm had been evaluated using F1-scores, recall, accuracy, and precision. SAE has substantially improved AD functionality.
本文研究了如何利用机器学习（ML）技术改进水处理厂（WTPs）的预测性维护。主动检测和修复可能导致灾难性后果的功能故障，一直以来都是被动或基于计划的维护方法的努力方向。WTP 预测性维护框架中的异常检测（AD）是本研究的主要目标，它推荐了一种基于自动编码器（AE）的 ML 模型的新方法。为了检查从水处理厂长期收集的高维时间序列传感器数据，采用了稀疏自动编码器（SAE）。收集到的数据包括一系列运行测量值，这些测量值经过综合评估，可以描述工厂的整体性能。在 AE 的支持下，这项工作旨在为水处理厂运行预测性维护开发一个实用框架。异常是指测试中发现的可能导致缺陷或故障的所有系统结果。研究文章分析了中国江苏省 2023 年 1 月和 7 月的 WTP 数据。AE 范例使用 F1 分数、召回率、准确率和精确度进行了评估。SAE大幅提高了AD功能。
{"title":"Enhancing Predictive Maintenance in Water Treatment Plants through Sparse Autoencoder Based Anomaly Detection","authors":"Hussein Z, Balaji V, Ramesh R, Arokia Jesu Prabhu L, Venubabu Rachapudi, E. V","doi":"10.53759/7669/jmc202404027","DOIUrl":"https://doi.org/10.53759/7669/jmc202404027","url":null,"abstract":"The deployment of Machine Learning (ML) for improving Water Treatment Plants (WTPs) predictive maintenance is investigated in the present article. Proactively detecting and fixing functional difficulties which might cause catastrophic effects has historically been an endeavour for reactive or schedule-based maintenance methods. Anomaly Detection (AD) in WTP predictive maintenance frameworks is the primary goal of this investigation, which recommends a novel approach based on autoencoder (AE)-based ML models. For the objective of examining high-dimensional time-series sensor data collected from a WTP over a long time, Sparse Autoencoders (SAEs) are implemented. The data collected involves an array of operational measurements that, evaluated together, describe the plant's overall performance. With the support of the AE, this work aims to develop a practical framework for WTP operation predictive maintenance. Anomalies are all system findings from testing that might result in flaws or malfunctions. The research article analyses January and July 2023 WTP data from Jiangsu Province China. The AE paradigm had been evaluated using F1-scores, recall, accuracy, and precision. SAE has substantially improved AD functionality.","PeriodicalId":516221,"journal":{"name":"Journal of Machine and Computing","volume":"37 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140735864","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 : 2024-04-05DOI: 10.53759/7669/jmc202404043
Kanchana S, Jayakarthik R, Dineshbabu V, Saranya M, Srikanth Mylapalli, Rajesh Kumar T
To keep track of changes to the Earth's surface, extensive time series of data from remote sensing using image processing is required. This research is motivated by the effectiveness of computational modelling techniques; however, the problem of missing data is multifaceted. When data at numerous a-periodic timestamps are absent during multi-temporal analysis, the issue becomes increasingly problematic. To make remote sensing time series analysis easier, weight optimised machine learning is used in this study to rebuild lost data. Keeping the causality restriction in mind, this method makes use of data from previous and subsequent timestamps. The architecture is based on an ensemble of numerous forecasting modules, built on the observed data in the time-series order. Dummy data is used to connect the forecasting modules, which were previously linked by the earlier half of the sequence. After that, iterative improvements are made to the dummy data to make it better fit the next segment of the sequence. On the basis of Landsat-7 TM-5 satellite imagery, the work has been proven to be accurate in forecasting missing images in normalised difference vegetation index time series. In a performance evaluation, the proposed forecasting model was shown to be effective.
为了跟踪地球表面的变化，需要利用图像处理遥感技术获得大量时间序列数据。这项研究的动力来自于计算建模技术的有效性；然而，数据缺失的问题是多方面的。在进行多时分析时，如果缺少大量 a 周期时间戳的数据，问题就会越来越严重。为了简化遥感时间序列分析，本研究采用了权重优化机器学习来重建丢失的数据。考虑到因果关系的限制，该方法利用了前后时间戳的数据。该架构基于众多预测模块的集合，按时间序列顺序建立在观察到的数据上。假数据用于连接预测模块，这些模块之前是由序列的前半部分连接起来的。之后，对虚拟数据进行迭代改进，使其更适合序列的下一部分。在 Landsat-7 TM-5 卫星图像的基础上，这项工作已被证明能准确预报归一化差异植被指数时间序列中的缺失图像。在性能评估中，建议的预测模型被证明是有效的。
{"title":"Weight Optimization for missing data prediction of Landslide Susceptibility Mapping in Remote sensing Analysis","authors":"Kanchana S, Jayakarthik R, Dineshbabu V, Saranya M, Srikanth Mylapalli, Rajesh Kumar T","doi":"10.53759/7669/jmc202404043","DOIUrl":"https://doi.org/10.53759/7669/jmc202404043","url":null,"abstract":"To keep track of changes to the Earth's surface, extensive time series of data from remote sensing using image processing is required. This research is motivated by the effectiveness of computational modelling techniques; however, the problem of missing data is multifaceted. When data at numerous a-periodic timestamps are absent during multi-temporal analysis, the issue becomes increasingly problematic. To make remote sensing time series analysis easier, weight optimised machine learning is used in this study to rebuild lost data. Keeping the causality restriction in mind, this method makes use of data from previous and subsequent timestamps. The architecture is based on an ensemble of numerous forecasting modules, built on the observed data in the time-series order. Dummy data is used to connect the forecasting modules, which were previously linked by the earlier half of the sequence. After that, iterative improvements are made to the dummy data to make it better fit the next segment of the sequence. On the basis of Landsat-7 TM-5 satellite imagery, the work has been proven to be accurate in forecasting missing images in normalised difference vegetation index time series. In a performance evaluation, the proposed forecasting model was shown to be effective.","PeriodicalId":516221,"journal":{"name":"Journal of Machine and Computing","volume":"4 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140738438","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 : 2024-04-05DOI: 10.53759/7669/jmc202404036
Nabeel S. Alsharafa, Suguna R, Raguru Jaya Krishna, Vijaya Krishna Sonthi, Padmaja S M, Mariaraja P
This study develops a new technique for optimising Energy Consumption (EC) and occupant satisfaction in business centres using Building Energy Management Systems (BEMS) that implement Deep Reinforcement Learning (DRL). Energy Management Models (EMM) are growing increasingly advanced and vital for intelligent power systems due to the growing demand for energy efficiency and the adoption of Renewable Energy Sources (RES), which are subject to variability. Flawed energy Consumption (EC) and problems are typical effects of traditional BEMS due to their unpredictability and failure to adapt to new environments. In this intended investigation, a DRL framework is demonstrated that may evolve its decision-making in real-time to control energy savings, electricity, and HVAC through input from the environment in which it operates. A pair of significant metrics, namely the cost of energy and room temperature stability, are employed to assess the effectiveness of the model compared to that provided by conventional rule-driven and predictive control systems. As investigated with different baseline models, the experimental findings proved that the DRL approach significantly reduced the cost of electricity while maintaining stable levels of comfort.
{"title":"Optimizing Building Energy Management with Deep Reinforcement Learning for Smart and Sustainable Infrastructure","authors":"Nabeel S. Alsharafa, Suguna R, Raguru Jaya Krishna, Vijaya Krishna Sonthi, Padmaja S M, Mariaraja P","doi":"10.53759/7669/jmc202404036","DOIUrl":"https://doi.org/10.53759/7669/jmc202404036","url":null,"abstract":"This study develops a new technique for optimising Energy Consumption (EC) and occupant satisfaction in business centres using Building Energy Management Systems (BEMS) that implement Deep Reinforcement Learning (DRL). Energy Management Models (EMM) are growing increasingly advanced and vital for intelligent power systems due to the growing demand for energy efficiency and the adoption of Renewable Energy Sources (RES), which are subject to variability. Flawed energy Consumption (EC) and problems are typical effects of traditional BEMS due to their unpredictability and failure to adapt to new environments. In this intended investigation, a DRL framework is demonstrated that may evolve its decision-making in real-time to control energy savings, electricity, and HVAC through input from the environment in which it operates. A pair of significant metrics, namely the cost of energy and room temperature stability, are employed to assess the effectiveness of the model compared to that provided by conventional rule-driven and predictive control systems. As investigated with different baseline models, the experimental findings proved that the DRL approach significantly reduced the cost of electricity while maintaining stable levels of comfort.","PeriodicalId":516221,"journal":{"name":"Journal of Machine and Computing","volume":"4 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140735755","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：