Pub Date : 2023-10-30DOI: 10.15837/ijccc.2023.6.5706
Hongzhang Han, Peizhong Shi
With the rapid development of wireless sensor networks (WSNs), designing energy-efficient routing protocols has become essential to prolong network lifetime. This paper proposes a minimum spanning tree-based energy-saving routing algorithm for WSNs. First, sensor nodes are clustered using the LEACH protocol and minimum spanning trees are constructed within clusters and between cluster heads. The spanning tree edge weights are optimized considering transmission energy, residual energy, and energy consumption rate. This avoids channel competition and improves transmission efficiency. An energy-saving routing model is then built whereby deep reinforcement learning (DRL) agents calculate paths optimizing the energy utilization rate. The DRL reward function integrates network performance metrics like energy consumption, delay, and packet loss. Experiments show the proposed approach leads to 10-15W lower average switch energy consumption compared to existing methods. The throughput is high since overloaded shortest paths are avoided. The average path length is close to shortest path algorithms while maintaining energy efficiency. In summary, the proposed minimum spanning tree-based routing algorithm successfully achieves energy-saving goals for WSNs while guaranteeing network performance. It provides an efficient and adaptive routing solution for resource-constrained WSNs.
{"title":"Energy Saving Routing Algorithm for Wireless Sensor Networks Based on Minimum Spanning Hyper Tree","authors":"Hongzhang Han, Peizhong Shi","doi":"10.15837/ijccc.2023.6.5706","DOIUrl":"https://doi.org/10.15837/ijccc.2023.6.5706","url":null,"abstract":"With the rapid development of wireless sensor networks (WSNs), designing energy-efficient routing protocols has become essential to prolong network lifetime. This paper proposes a minimum spanning tree-based energy-saving routing algorithm for WSNs. First, sensor nodes are clustered using the LEACH protocol and minimum spanning trees are constructed within clusters and between cluster heads. The spanning tree edge weights are optimized considering transmission energy, residual energy, and energy consumption rate. This avoids channel competition and improves transmission efficiency. An energy-saving routing model is then built whereby deep reinforcement learning (DRL) agents calculate paths optimizing the energy utilization rate. The DRL reward function integrates network performance metrics like energy consumption, delay, and packet loss. Experiments show the proposed approach leads to 10-15W lower average switch energy consumption compared to existing methods. The throughput is high since overloaded shortest paths are avoided. The average path length is close to shortest path algorithms while maintaining energy efficiency. In summary, the proposed minimum spanning tree-based routing algorithm successfully achieves energy-saving goals for WSNs while guaranteeing network performance. It provides an efficient and adaptive routing solution for resource-constrained WSNs.","PeriodicalId":54970,"journal":{"name":"International Journal of Computers Communications & Control","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136132510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.15837/ijccc.2023.6.5998
Yuchuan Jiang, Zhangjun Wang, ZhiXiong Jin
With the continuous integration of IoT technology and information technology, edge computing, as an emerging computing paradigm, makes full use of terminals to process and analyse real-time data. The explosion of Internet of Things (IoT) devices has created challenges for traditional cloud-based data processing models due to high latency and availability requirements. This paper proposes a new edge computation-based framework for iot data processing and scheduling using deep reinforcement learning. The system architecture incorporates distributed iot data access, realtime processing, and an intelligent scheduler based on Deep q networks (DQN). A large number of experiments show that compared with traditional scheduling methods, the average task completion time is reduced by 20% and resource utilization is increased by 15%. The unique integration of edge computing and deep reinforcement learning provides a flexible and efficient platform for lowlatency iot applications. Key results obtained from testing the proposed system, such as reduced task completion time and increased resource utilization.
{"title":"Iot Data Processing and Scheduling Based on Deep Reinforcement Learning","authors":"Yuchuan Jiang, Zhangjun Wang, ZhiXiong Jin","doi":"10.15837/ijccc.2023.6.5998","DOIUrl":"https://doi.org/10.15837/ijccc.2023.6.5998","url":null,"abstract":"With the continuous integration of IoT technology and information technology, edge computing, as an emerging computing paradigm, makes full use of terminals to process and analyse real-time data. The explosion of Internet of Things (IoT) devices has created challenges for traditional cloud-based data processing models due to high latency and availability requirements. This paper proposes a new edge computation-based framework for iot data processing and scheduling using deep reinforcement learning. The system architecture incorporates distributed iot data access, realtime processing, and an intelligent scheduler based on Deep q networks (DQN). A large number of experiments show that compared with traditional scheduling methods, the average task completion time is reduced by 20% and resource utilization is increased by 15%. The unique integration of edge computing and deep reinforcement learning provides a flexible and efficient platform for lowlatency iot applications. Key results obtained from testing the proposed system, such as reduced task completion time and increased resource utilization.","PeriodicalId":54970,"journal":{"name":"International Journal of Computers Communications & Control","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136132506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.15837/ijccc.2023.6.5728
Rodica Sobolu, Liana Stanca, Simona Aurelia Bodog
In our research, we propose a model that leverages transfer learning and active learning techniques to accumulate knowledge and effectively solve complex problems in the field of artificial intelligence. This model operates within a parallel learning paradigm, aiming to mimic the continuous learning and improvement observed in human beings. To facilitate knowledge accumulation, we introduce a convolutional deep classification auto encoder that extracts spatially localized features from images. This enhances the model’s ability to extract relevant information. Additionally, we propose a learning classification system based on a code fragment, enabling effective representation and transfer of knowledge across different domains. Our research culminates in a theoretical and practical prototype for active learning-based knowledge extraction in various living organisms, including humans, plants, and animals. This knowledge extraction is achieved through image-based learning transfer, focusing on advancing activity recognition in image processing. Experimental results confirm that our method outperforms both baseline approaches and state-of-the-art convolutional neural network methods, underscoring its effectiveness and potential.
{"title":"Automated Recognition Systems: Theoretical and Practical Implementation of Active Learning for Extracting Knowledge in Image-based Transfer Learning of Living Organisms","authors":"Rodica Sobolu, Liana Stanca, Simona Aurelia Bodog","doi":"10.15837/ijccc.2023.6.5728","DOIUrl":"https://doi.org/10.15837/ijccc.2023.6.5728","url":null,"abstract":"In our research, we propose a model that leverages transfer learning and active learning techniques to accumulate knowledge and effectively solve complex problems in the field of artificial intelligence. This model operates within a parallel learning paradigm, aiming to mimic the continuous learning and improvement observed in human beings. To facilitate knowledge accumulation, we introduce a convolutional deep classification auto encoder that extracts spatially localized features from images. This enhances the model’s ability to extract relevant information. Additionally, we propose a learning classification system based on a code fragment, enabling effective representation and transfer of knowledge across different domains. Our research culminates in a theoretical and practical prototype for active learning-based knowledge extraction in various living organisms, including humans, plants, and animals. This knowledge extraction is achieved through image-based learning transfer, focusing on advancing activity recognition in image processing. Experimental results confirm that our method outperforms both baseline approaches and state-of-the-art convolutional neural network methods, underscoring its effectiveness and potential.","PeriodicalId":54970,"journal":{"name":"International Journal of Computers Communications & Control","volume":"34 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136132512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.15837/ijccc.2023.6.5879
Wang Wang, Hua He, Changsong Ma
This paper proposes an improved Deeplabv3+ model for semantic segmentation of urban scenes targeting autonomous driving applications. A high-quality semantic segmentation dataset is constructed from 2,967 manually labeled aerial images captured at 200m height with a 5-eye camera. The images contain 5 classes - buildings, vegetation, ground, lake and playgrounds. The improved Deeplabv3+ network enriches high-level semantics by replacing max pooling with depthwise separable convolutions. Dilated convolutions extract multi-scale features to avoid overfitting. Experiments demonstrate that the model achieves an overall mean IoU of 0.87 on the test set, with IoU scores of 0.90, 0.92 and 0.94 on buildings, vegetation and water respectively. The model shows promising results for extracting semantic information from complex urban environments to support navigation for autonomous vehicles.
{"title":"An Improved Deeplabv3+ Model for Semantic Segmentation of Urban Environments Targeting Autonomous Driving","authors":"Wang Wang, Hua He, Changsong Ma","doi":"10.15837/ijccc.2023.6.5879","DOIUrl":"https://doi.org/10.15837/ijccc.2023.6.5879","url":null,"abstract":"This paper proposes an improved Deeplabv3+ model for semantic segmentation of urban scenes targeting autonomous driving applications. A high-quality semantic segmentation dataset is constructed from 2,967 manually labeled aerial images captured at 200m height with a 5-eye camera. The images contain 5 classes - buildings, vegetation, ground, lake and playgrounds. The improved Deeplabv3+ network enriches high-level semantics by replacing max pooling with depthwise separable convolutions. Dilated convolutions extract multi-scale features to avoid overfitting. Experiments demonstrate that the model achieves an overall mean IoU of 0.87 on the test set, with IoU scores of 0.90, 0.92 and 0.94 on buildings, vegetation and water respectively. The model shows promising results for extracting semantic information from complex urban environments to support navigation for autonomous vehicles.","PeriodicalId":54970,"journal":{"name":"International Journal of Computers Communications & Control","volume":"36 17","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136132515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.15837/ijccc.2023.6.5274
None S. Gowthami, None R. Harikumar
The capability of recognizing skin cancer in its earliest stages has the potential to be a component that saves lives. It is of the utmost importance to devise an autonomous technique that can be relied upon for accurate melanoma detection using image analysis. In this paper, Generative adversarial network (GAN) with suitable preprocessing is used to classify the labels for the detection of melanoma skin types. The simulation is run to evaluate the effectiveness of the model about several performance measures, such as accuracy, precision, recall, f-measure, percentage error, Dice coefficient, and Jaccard index. These are all performance measures that are taken into consideration. These metrics for measuring achievement are as follows: The results of the simulations make it exceedingly clear that the proposed TE-SAAGAN is more effective than the existing GAN protocols when it comes to recognizing the test images.
{"title":"Residual Generative Adversarial Adaptation Network For The Classification Of Melanoma","authors":"None S. Gowthami, None R. Harikumar","doi":"10.15837/ijccc.2023.6.5274","DOIUrl":"https://doi.org/10.15837/ijccc.2023.6.5274","url":null,"abstract":"The capability of recognizing skin cancer in its earliest stages has the potential to be a component that saves lives. It is of the utmost importance to devise an autonomous technique that can be relied upon for accurate melanoma detection using image analysis. In this paper, Generative adversarial network (GAN) with suitable preprocessing is used to classify the labels for the detection of melanoma skin types. The simulation is run to evaluate the effectiveness of the model about several performance measures, such as accuracy, precision, recall, f-measure, percentage error, Dice coefficient, and Jaccard index. These are all performance measures that are taken into consideration. These metrics for measuring achievement are as follows: The results of the simulations make it exceedingly clear that the proposed TE-SAAGAN is more effective than the existing GAN protocols when it comes to recognizing the test images.","PeriodicalId":54970,"journal":{"name":"International Journal of Computers Communications & Control","volume":"45 S2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136132508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.15837/ijccc.2023.6.6147
Attila Simo, Simona Dzitac, Amalia Duțu, Ionuț Pandelica
The integration of Internet of Things (IoT) technologies in agriculture has emerged as a transformative force, revolutionizing traditional farming practices and driving efficiency and sustainability. This paper presents the development and implementation of a cost-effective greenhouse monitoring system utilizing LoRaWAN technology for data communication. The system’s design, deployment, and performance are discussed in detail. Key components include an array of sensors for monitoring environmental parameters and LoRaWAN for long-range, low-power communication. The low-cost nature of the system challenges the notion that advanced agricultural technology is prohibitively expensive, making it accessible to farmers of varying scales. The system’s affordability and realtime data accessibility make it a valuable tool for precision agriculture, contributing to improved crop yields and resource management.
{"title":"Smart Agriculture in the Digital Age: A Comprehensive IoT-Driven Greenhouse Monitoring System","authors":"Attila Simo, Simona Dzitac, Amalia Duțu, Ionuț Pandelica","doi":"10.15837/ijccc.2023.6.6147","DOIUrl":"https://doi.org/10.15837/ijccc.2023.6.6147","url":null,"abstract":"The integration of Internet of Things (IoT) technologies in agriculture has emerged as a transformative force, revolutionizing traditional farming practices and driving efficiency and sustainability. This paper presents the development and implementation of a cost-effective greenhouse monitoring system utilizing LoRaWAN technology for data communication. The system’s design, deployment, and performance are discussed in detail. Key components include an array of sensors for monitoring environmental parameters and LoRaWAN for long-range, low-power communication. The low-cost nature of the system challenges the notion that advanced agricultural technology is prohibitively expensive, making it accessible to farmers of varying scales. The system’s affordability and realtime data accessibility make it a valuable tool for precision agriculture, contributing to improved crop yields and resource management.","PeriodicalId":54970,"journal":{"name":"International Journal of Computers Communications & Control","volume":"45 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136132509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.15837/ijccc.2023.6.5735
Sergiu-Alexandru Ionescu, Vlad Diaconita
Financial institutions face many challenges in managing modern financial transactions and vast data volumes. To overcome these challenges, they are increasingly harnessing advanced data man- agement technologies such as artificial intelligence and cloud computing. This paper presents a com- prehensive review of how these tools transform financial decision-making in various domains and ap- plications. We analyzed both foundational and recent advancements using a rigorous methodology based on the PRISMA 2020 guideline. Our findings indicate that many major financial institutions are adopting AI-driven solutions to potentially enhance real-time risk assessment, transactional efficiency, and predictive analytics. While they bring benefits like faster decision-making and reduced operational costs, they also pose challenges like data security and integration complexities that require further research and development. Looking ahead, we envision a more integrated, responsive, and secure financial ecosystem that leverages the convergence of AI, cloud computing, and advanced data storage. This synthesis underscores the significance of contemporary data management solutions in shaping the future of data-driven financial services, offering a guideline for stakeholders in this evolving domain.
{"title":"Transforming Financial Decision-Making: The Interplay of AI, Cloud Computing and Advanced Data Management Technologies","authors":"Sergiu-Alexandru Ionescu, Vlad Diaconita","doi":"10.15837/ijccc.2023.6.5735","DOIUrl":"https://doi.org/10.15837/ijccc.2023.6.5735","url":null,"abstract":"Financial institutions face many challenges in managing modern financial transactions and vast data volumes. To overcome these challenges, they are increasingly harnessing advanced data man- agement technologies such as artificial intelligence and cloud computing. This paper presents a com- prehensive review of how these tools transform financial decision-making in various domains and ap- plications. We analyzed both foundational and recent advancements using a rigorous methodology based on the PRISMA 2020 guideline. Our findings indicate that many major financial institutions are adopting AI-driven solutions to potentially enhance real-time risk assessment, transactional efficiency, and predictive analytics. While they bring benefits like faster decision-making and reduced operational costs, they also pose challenges like data security and integration complexities that require further research and development. Looking ahead, we envision a more integrated, responsive, and secure financial ecosystem that leverages the convergence of AI, cloud computing, and advanced data storage. This synthesis underscores the significance of contemporary data management solutions in shaping the future of data-driven financial services, offering a guideline for stakeholders in this evolving domain.","PeriodicalId":54970,"journal":{"name":"International Journal of Computers Communications & Control","volume":"45 S1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136132511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.15837/ijccc.2023.6.5890
Venkatesan Muthukumar, R. Sivakami, Vinoth Kumar Venkatesan, J. Balajee, T.R. Mahesh, E. Mohan, B. Swapna
The Internet of Things (IoT) and associated capabilities are becoming indispensable in the planning, operation, and administration of intricate systems of all sizes. High-end learning solutions that go beyond the boundaries of the problem are necessary for addressing the variety of communication concerns (compatibility, secure communication, etc.) in IoT settings. Building machine learning (ML) networks from disparate data sources is a cutting-edge practice known as Federated Learning (FL). In this article, we implement FL between edge-based servers and devices in a sparsely populated cloud to facilitate cohesive learning and the storage of critical information in smart IoT systems. FL enables collaborative training from a common model by aggregating smaller unit models via regulated edge network participants. Further, all the susceptible device’s information and sensitive message transactions are addressed via blockchain technology. Thus, a blockchain-based security mechanism is integrated to secure user privacy and facilitate widespread practical adoption. Finally, a comparison is made between the proposed model and the three best free, open-source Federated Learning models already in use (FedPD, FedProx, and FedAvg). In terms of statistical, and data heterogeneity (>70% SDI, >97% accuracy), the experimental findings suggest that the proposed model performs better than the existing techniques.
{"title":"Optimizing Heterogeneity in IoT Infra Using Federated Learning and Blockchain-based Security Strategies","authors":"Venkatesan Muthukumar, R. Sivakami, Vinoth Kumar Venkatesan, J. Balajee, T.R. Mahesh, E. Mohan, B. Swapna","doi":"10.15837/ijccc.2023.6.5890","DOIUrl":"https://doi.org/10.15837/ijccc.2023.6.5890","url":null,"abstract":"The Internet of Things (IoT) and associated capabilities are becoming indispensable in the planning, operation, and administration of intricate systems of all sizes. High-end learning solutions that go beyond the boundaries of the problem are necessary for addressing the variety of communication concerns (compatibility, secure communication, etc.) in IoT settings. Building machine learning (ML) networks from disparate data sources is a cutting-edge practice known as Federated Learning (FL). In this article, we implement FL between edge-based servers and devices in a sparsely populated cloud to facilitate cohesive learning and the storage of critical information in smart IoT systems. FL enables collaborative training from a common model by aggregating smaller unit models via regulated edge network participants. Further, all the susceptible device’s information and sensitive message transactions are addressed via blockchain technology. Thus, a blockchain-based security mechanism is integrated to secure user privacy and facilitate widespread practical adoption. Finally, a comparison is made between the proposed model and the three best free, open-source Federated Learning models already in use (FedPD, FedProx, and FedAvg). In terms of statistical, and data heterogeneity (>70% SDI, >97% accuracy), the experimental findings suggest that the proposed model performs better than the existing techniques.","PeriodicalId":54970,"journal":{"name":"International Journal of Computers Communications & Control","volume":"45 S3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136132505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.15837/ijccc.2023.6.5505
Zhiling Jiang, Yining Chen, Ke Wang, Bowei Yang, Guanghua Song
Multi-Agent Reinforcement Learning (MARL) is widely used to solve various problems in real life. In the multi-agent reinforcement learning tasks, there are multiple agents in the environment, the existing Proximal Policy Optimization (PPO) algorithm can be applied to multi-agent reinforcement learning. However, it cannot deal with the communication problem between agents. In order to resolve this issue, we propose a Graph-based PPO algorithm, this approach can solve the communication problem between agents and it can enhance the exploration efficiency of agents in the environment and speed up the learning process. We apply our algorithms to the task of multi-UAV navigation for communication coverage to verify the functionality and performance of our proposed algorithms.
{"title":"A Graph-Based PPO Approach in Multi-UAV Navigation for Communication Coverage","authors":"Zhiling Jiang, Yining Chen, Ke Wang, Bowei Yang, Guanghua Song","doi":"10.15837/ijccc.2023.6.5505","DOIUrl":"https://doi.org/10.15837/ijccc.2023.6.5505","url":null,"abstract":"Multi-Agent Reinforcement Learning (MARL) is widely used to solve various problems in real life. In the multi-agent reinforcement learning tasks, there are multiple agents in the environment, the existing Proximal Policy Optimization (PPO) algorithm can be applied to multi-agent reinforcement learning. However, it cannot deal with the communication problem between agents. In order to resolve this issue, we propose a Graph-based PPO algorithm, this approach can solve the communication problem between agents and it can enhance the exploration efficiency of agents in the environment and speed up the learning process. We apply our algorithms to the task of multi-UAV navigation for communication coverage to verify the functionality and performance of our proposed algorithms.","PeriodicalId":54970,"journal":{"name":"International Journal of Computers Communications & Control","volume":"45 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136132507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.15837/ijccc.2023.6.5086
None V. Mani, None S. Thilagamani
As an emerging trend in data science, applications based on big data analytics are reshaping health informatics and medical scenarios.Currently, peoples are more cognizant and seek solutions to their healthcareproblems online. In the chorus, selecting a healthcare professional or organization is a tedious and time-consuming process. Patients may vainly spend time and meet severaldoctors until one is found that suits theirexact needs. Frequently, they do not have sufficient information on whereupon to base a decision. This has led to a dire requirementfor an efficient anddependablepatient-specific online tool to find out an appropriatedoctor in a limited time.In this paper, we propose a hybrid Physician Recommender System(PRS) by integrating various recommender approaches such asdemographic, collaborative, and content-based filtering for findingsuitabledoctors in line with the preferred choices of patients and their ratings. The proposed system resolves the problem of customization by studyingthe patient’s criteriaforchoosing a physician. It employs an adaptive algorithm to find the overall rank of the particular doctor. Furthermore, this ranking method is applied to convert patients’ preferred choices into a numerical base rating, which will ultimately be employed inour physician recommender system. The proposed system has been appraisedcarefully, and the result reveals that recommendations are rational and can satisfythe patient’s need for consistentphysician selection successfully.
{"title":"Hybrid Filtering-based Physician Recommender Systems using Fuzzy Analytic Hierarchy Process and User Ratings","authors":"None V. Mani, None S. Thilagamani","doi":"10.15837/ijccc.2023.6.5086","DOIUrl":"https://doi.org/10.15837/ijccc.2023.6.5086","url":null,"abstract":"As an emerging trend in data science, applications based on big data analytics are reshaping health informatics and medical scenarios.Currently, peoples are more cognizant and seek solutions to their healthcareproblems online. In the chorus, selecting a healthcare professional or organization is a tedious and time-consuming process. Patients may vainly spend time and meet severaldoctors until one is found that suits theirexact needs. Frequently, they do not have sufficient information on whereupon to base a decision. This has led to a dire requirementfor an efficient anddependablepatient-specific online tool to find out an appropriatedoctor in a limited time.In this paper, we propose a hybrid Physician Recommender System(PRS) by integrating various recommender approaches such asdemographic, collaborative, and content-based filtering for findingsuitabledoctors in line with the preferred choices of patients and their ratings. The proposed system resolves the problem of customization by studyingthe patient’s criteriaforchoosing a physician. It employs an adaptive algorithm to find the overall rank of the particular doctor. Furthermore, this ranking method is applied to convert patients’ preferred choices into a numerical base rating, which will ultimately be employed inour physician recommender system. The proposed system has been appraisedcarefully, and the result reveals that recommendations are rational and can satisfythe patient’s need for consistentphysician selection successfully.","PeriodicalId":54970,"journal":{"name":"International Journal of Computers Communications & Control","volume":"34 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136132513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","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：