Pub Date : 2024-06-15DOI: 10.17559/tv-20220829132003
Mohamed Sithik, Muthu Kumar
: Congestion control is among the most challenging tasks in enhancing QoS in the Internet of Things (IoT). Currently, wireless networks are able to have a large number of connections but with a limited amount of network resources. Consequently, congestion occurs, which adversely affects throughput, transmission delay, packet losses, power consumption management, and the lifespan of a network. This is certainly relevant in networks where transmissions are controlled by the Routing Protocol for Low-Power and Lossy Networks (RPL), which is commonly employed in the Internet of Things network. To solve this problem, a novel Geodetic fuzzy subgraph-based ranking (GFSR-RPL) for congestion control is proposed. Initially, the proposed GFSR-RPL selects the cluster head using K-means clustering. Then the rank calculation can be done via the final route setting for data transmission. A route setup scheme consists of three elements: 1) a Round Trip Time (RTT) estimator that assesses congestion conditions in a variety of ways; 2) a trend and relative strength indicator analysis; and 3) a geodetic fuzzy subgraph rank calculation method that calculates initial RTO (initial retransmission timeouts) accurately. The proposed GFSR-RPL method reduces the energy consumption of up to 43.58%, 25.8%, 14.82% and 6.85% than existing methods such as RPR, CBR-RPL, ACW and ECLRPL.
{"title":"Novel Geodetic Fuzzy Subgraph-Based Ranking for Congestion Control in RPL-IoT Network","authors":"Mohamed Sithik, Muthu Kumar","doi":"10.17559/tv-20220829132003","DOIUrl":"https://doi.org/10.17559/tv-20220829132003","url":null,"abstract":": Congestion control is among the most challenging tasks in enhancing QoS in the Internet of Things (IoT). Currently, wireless networks are able to have a large number of connections but with a limited amount of network resources. Consequently, congestion occurs, which adversely affects throughput, transmission delay, packet losses, power consumption management, and the lifespan of a network. This is certainly relevant in networks where transmissions are controlled by the Routing Protocol for Low-Power and Lossy Networks (RPL), which is commonly employed in the Internet of Things network. To solve this problem, a novel Geodetic fuzzy subgraph-based ranking (GFSR-RPL) for congestion control is proposed. Initially, the proposed GFSR-RPL selects the cluster head using K-means clustering. Then the rank calculation can be done via the final route setting for data transmission. A route setup scheme consists of three elements: 1) a Round Trip Time (RTT) estimator that assesses congestion conditions in a variety of ways; 2) a trend and relative strength indicator analysis; and 3) a geodetic fuzzy subgraph rank calculation method that calculates initial RTO (initial retransmission timeouts) accurately. The proposed GFSR-RPL method reduces the energy consumption of up to 43.58%, 25.8%, 14.82% and 6.85% than existing methods such as RPR, CBR-RPL, ACW and ECLRPL.","PeriodicalId":510054,"journal":{"name":"Tehnicki vjesnik - Technical Gazette","volume":"11 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141336122","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 : 2024-06-15DOI: 10.17559/tv-20231116001115
Ningzhou Shen, Xinyao Guo, Jiawei Cui, Zhengqi Wu
: Public emergencies are occurring with increasing frequency worldwide, leading to what is often referred to as a high-risk society. Amid various public emergencies, urban communities take on a more prominent role. However, studies on assessing the emergency preparedness and response capacity of urban communities are currently limited. To evaluate the essential factors, both inherent and external, that affect the emergency management capacities of urban communities, an index system for assessing community emergency preparedness and response capacity was developed by using the theory of the emergency management cycle. Acknowledging the complexity and ambiguity of emergency preparedness and response capacity within urban communities, a multilayer fuzzy comprehensive evaluation model was established using the entropy weight method. This model was then applied to assess the emergency preparedness and response capacity of communities against the backdrop of the COVID-19 public emergency. Results show that the assessment outcomes generated by the multilayer fuzzy comprehensive evaluation model, employing the entropy weight method, align with the real-world situation, signifying the soundness and effectiveness of the selected methods and index system. The conclusion offers a novel basis and methodology for evaluating the emergency preparedness and response capacity of urban communities, holding considerable practical value.
{"title":"Assessment of Urban Community Emergency Preparedness and Response Capacity Using Entropy Weight Method and Multilayer Fuzzy Comprehensive Model","authors":"Ningzhou Shen, Xinyao Guo, Jiawei Cui, Zhengqi Wu","doi":"10.17559/tv-20231116001115","DOIUrl":"https://doi.org/10.17559/tv-20231116001115","url":null,"abstract":": Public emergencies are occurring with increasing frequency worldwide, leading to what is often referred to as a high-risk society. Amid various public emergencies, urban communities take on a more prominent role. However, studies on assessing the emergency preparedness and response capacity of urban communities are currently limited. To evaluate the essential factors, both inherent and external, that affect the emergency management capacities of urban communities, an index system for assessing community emergency preparedness and response capacity was developed by using the theory of the emergency management cycle. Acknowledging the complexity and ambiguity of emergency preparedness and response capacity within urban communities, a multilayer fuzzy comprehensive evaluation model was established using the entropy weight method. This model was then applied to assess the emergency preparedness and response capacity of communities against the backdrop of the COVID-19 public emergency. Results show that the assessment outcomes generated by the multilayer fuzzy comprehensive evaluation model, employing the entropy weight method, align with the real-world situation, signifying the soundness and effectiveness of the selected methods and index system. The conclusion offers a novel basis and methodology for evaluating the emergency preparedness and response capacity of urban communities, holding considerable practical value.","PeriodicalId":510054,"journal":{"name":"Tehnicki vjesnik - Technical Gazette","volume":"7 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141337069","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 : 2024-06-15DOI: 10.17559/tv-20230912000934
: Due to advancements in the technology, video transmission is a key feature in several applications. The transmission of the video from the source to the sink is quite different from the transmission of images-based data. The transmission of the video over the wireless sensor network is not an easy task with the available protocols. They have several disadvantages related to the energy efficiency and the reliability. Novel architecture namely high-quality video transmission architecture has been proposed in this paper. This is an energy efficient architecture. To conserve the energy during the transmission, this architecture does not support retransmission of the packets. But the dropping of the packets helps in improving the reliability and the life time of the network. This architecture majorly involves three layers namely the application layer, the network layer and the transport layer. The transmission of the data packets is based on the priority levels. Moving Picture Experts Group (MPEG - 2) technologies is used in the proposed work. Two different frames namely the key frame and the variant frame are used to prioritize the packets. The data packets with the highest priority from the variant frame is transmitted first and then followed by the data packets of the key frame. The data is segmented into smaller units and discrete cosine transform is applied over each unit. The inter link between the transport layer, application layer and the network layer is analysed by means of the state diagram. The results have been tabulated and depicted by means of graphical representations. Comparative analysis has been made between the proposed high quality video transmission architecture and the diversified architecture. The proposed method has been found to have produced comparatively better results and possesses a high quality video transmission with enhanced Peak Signal to Noise Ratio (PSNR) and reduces energy consumption.
{"title":"Energy Efficient and Reliable High Quality Video Transmission Architecture for Wireless Sensor Networks","authors":"","doi":"10.17559/tv-20230912000934","DOIUrl":"https://doi.org/10.17559/tv-20230912000934","url":null,"abstract":": Due to advancements in the technology, video transmission is a key feature in several applications. The transmission of the video from the source to the sink is quite different from the transmission of images-based data. The transmission of the video over the wireless sensor network is not an easy task with the available protocols. They have several disadvantages related to the energy efficiency and the reliability. Novel architecture namely high-quality video transmission architecture has been proposed in this paper. This is an energy efficient architecture. To conserve the energy during the transmission, this architecture does not support retransmission of the packets. But the dropping of the packets helps in improving the reliability and the life time of the network. This architecture majorly involves three layers namely the application layer, the network layer and the transport layer. The transmission of the data packets is based on the priority levels. Moving Picture Experts Group (MPEG - 2) technologies is used in the proposed work. Two different frames namely the key frame and the variant frame are used to prioritize the packets. The data packets with the highest priority from the variant frame is transmitted first and then followed by the data packets of the key frame. The data is segmented into smaller units and discrete cosine transform is applied over each unit. The inter link between the transport layer, application layer and the network layer is analysed by means of the state diagram. The results have been tabulated and depicted by means of graphical representations. Comparative analysis has been made between the proposed high quality video transmission architecture and the diversified architecture. The proposed method has been found to have produced comparatively better results and possesses a high quality video transmission with enhanced Peak Signal to Noise Ratio (PSNR) and reduces energy consumption.","PeriodicalId":510054,"journal":{"name":"Tehnicki vjesnik - Technical Gazette","volume":"14 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141337150","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 : 2024-06-15DOI: 10.17559/tv-20230913000935
Vedha Vinodha
: This paper aims to present and deploy an improved task scheduling algorithm for the allocation of user tasks across multiple computing resources. The primary goal of this algorithm is to minimize both execution time and costs while simultaneously enhancing resource utilization within the context of medical applications. Virtual machine scheduling in a heterogeneous cloud environment needs significant attention with the increase in the usage of cloud resources by end users and enterprises. It is one of the significant parameters that affects cloud data centers. The resources requested by every user vary in their configuration. Finding a suitable virtual machine for each process is dynamically a time-consuming process. Virtual machines are classified based on resources such as memory and processing units. Upon the arrival of a request with specific requirements, it can be effortlessly mapped to a corresponding virtual machine. This process is followed by a bilateral method encompassing queuing and scheduling. Queues are formed for requests with different requirements, which are followed by a scheduling algorithm that allocates VMs based on the minimum remaining resources in the resource pool. A scheduling mechanism has been designed to solve the problem of starvation that occurs with the Min-Min fit scheduling policy. The average turnaround time and waiting times are observed to be significantly reduced, which has an impact on the performance of the data center for medical applications. Using the CloudSim Plus tool, the experimental outcomes demonstrated that the proposed approach exhibited remarkable superiority over competing methods in relation to metrics such as average waiting time, turnaround time, and response time. This advantage was observed when compared to multiple algorithms that were examined during the study.
:本文旨在介绍和部署一种改进的任务调度算法，用于在多个计算资源之间分配用户任务。该算法的主要目标是最大限度地减少执行时间和成本，同时提高医疗应用中的资源利用率。随着终端用户和企业对云资源使用的增加，异构云环境中的虚拟机调度需要引起高度重视。它是影响云数据中心的重要参数之一。每个用户所需的资源配置各不相同。为每个进程寻找合适的虚拟机是一个动态的耗时过程。虚拟机根据内存和处理单元等资源进行分类。在收到具有特定要求的请求时，可以毫不费力地将其映射到相应的虚拟机上。这一过程之后是一个包括队列和调度的双边方法。为不同要求的请求建立队列，然后采用调度算法，根据资源池中的最小剩余资源分配虚拟机。设计了一种调度机制，以解决 Min-Min fit 调度策略中出现的饥饿问题。据观察，平均周转时间和等待时间明显缩短，这对医疗应用数据中心的性能产生了影响。通过使用 CloudSim Plus 工具，实验结果表明，在平均等待时间、周转时间和响应时间等指标方面，所提出的方法比其他竞争方法具有明显优势。与研究过程中考察的多种算法相比，这种优势更加明显。
{"title":"An Enhanced Trust Scheduling Algorithm for Medical Applications in a Heterogeneous Cloud Computing Environment","authors":"Vedha Vinodha","doi":"10.17559/tv-20230913000935","DOIUrl":"https://doi.org/10.17559/tv-20230913000935","url":null,"abstract":": This paper aims to present and deploy an improved task scheduling algorithm for the allocation of user tasks across multiple computing resources. The primary goal of this algorithm is to minimize both execution time and costs while simultaneously enhancing resource utilization within the context of medical applications. Virtual machine scheduling in a heterogeneous cloud environment needs significant attention with the increase in the usage of cloud resources by end users and enterprises. It is one of the significant parameters that affects cloud data centers. The resources requested by every user vary in their configuration. Finding a suitable virtual machine for each process is dynamically a time-consuming process. Virtual machines are classified based on resources such as memory and processing units. Upon the arrival of a request with specific requirements, it can be effortlessly mapped to a corresponding virtual machine. This process is followed by a bilateral method encompassing queuing and scheduling. Queues are formed for requests with different requirements, which are followed by a scheduling algorithm that allocates VMs based on the minimum remaining resources in the resource pool. A scheduling mechanism has been designed to solve the problem of starvation that occurs with the Min-Min fit scheduling policy. The average turnaround time and waiting times are observed to be significantly reduced, which has an impact on the performance of the data center for medical applications. Using the CloudSim Plus tool, the experimental outcomes demonstrated that the proposed approach exhibited remarkable superiority over competing methods in relation to metrics such as average waiting time, turnaround time, and response time. This advantage was observed when compared to multiple algorithms that were examined during the study.","PeriodicalId":510054,"journal":{"name":"Tehnicki vjesnik - Technical Gazette","volume":"85 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141337969","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 : 2024-06-15DOI: 10.17559/tv-20230907000917
Rajkumar Krishnan, Arunkumar Muniyandi, Vinoth Kumar Kalimuthu, Mano Joel Prabhu Pelavendran
: Over the previous decade, there has been a significant focus on researching underwater acoustic sensor networks (UW-ASNs) for a diverse range of underwater applications, which in turn has facilitated human exploration of the expansive underwater environment. This research introduces an innovative architectural approach that signifies a noteworthy advancement. By combining both acoustic and optical components, it establishes an underwater wireless sensor network. Additionally, the research introduces an innovative multiple levels Q learning-grounded direction-finding procedure, denoted as the proposed system Multi-layer Guidance Approach (MLGA) which is meticulously tailored for such underwater networks. The network's architecture encompasses both physical grouping and logical division into two tiers: the upper tier is overseen by group leaders responsible for managing routing within the lower tier, where group members execute the actual data packet routing. This design capitalizes on the wider viewpoint of upper-tier group leaders and the concurrent learning processes occurring across all groups, resulting in a substantial enhancement in routing efficiency in comparison with traditional methodologies. The empirical results obtained from experimental tests underscore the robustness of the proposed system when confronted with changes in network topology. Moreover, it showcases the system's ability to achieve higher delivery rates and reduced delays in dynamic networks compared to the established approach of flat Q-learning routing. This innovative strategy holds the potential to significantly push the boundaries of underwater sensor networks, surpassing the constraints of conventional communication methods and providing a more effective and dependable means of transmitting data underwater. This advancement not only contributes to the technical aspects but also holds promise for fostering greater exploration and understanding of underwater environments.
{"title":"A Multi-layer Guidance Approach for Submerged Sensor Networks Integrating Acoustic and Optical Technologies","authors":"Rajkumar Krishnan, Arunkumar Muniyandi, Vinoth Kumar Kalimuthu, Mano Joel Prabhu Pelavendran","doi":"10.17559/tv-20230907000917","DOIUrl":"https://doi.org/10.17559/tv-20230907000917","url":null,"abstract":": Over the previous decade, there has been a significant focus on researching underwater acoustic sensor networks (UW-ASNs) for a diverse range of underwater applications, which in turn has facilitated human exploration of the expansive underwater environment. This research introduces an innovative architectural approach that signifies a noteworthy advancement. By combining both acoustic and optical components, it establishes an underwater wireless sensor network. Additionally, the research introduces an innovative multiple levels Q learning-grounded direction-finding procedure, denoted as the proposed system Multi-layer Guidance Approach (MLGA) which is meticulously tailored for such underwater networks. The network's architecture encompasses both physical grouping and logical division into two tiers: the upper tier is overseen by group leaders responsible for managing routing within the lower tier, where group members execute the actual data packet routing. This design capitalizes on the wider viewpoint of upper-tier group leaders and the concurrent learning processes occurring across all groups, resulting in a substantial enhancement in routing efficiency in comparison with traditional methodologies. The empirical results obtained from experimental tests underscore the robustness of the proposed system when confronted with changes in network topology. Moreover, it showcases the system's ability to achieve higher delivery rates and reduced delays in dynamic networks compared to the established approach of flat Q-learning routing. This innovative strategy holds the potential to significantly push the boundaries of underwater sensor networks, surpassing the constraints of conventional communication methods and providing a more effective and dependable means of transmitting data underwater. This advancement not only contributes to the technical aspects but also holds promise for fostering greater exploration and understanding of underwater environments.","PeriodicalId":510054,"journal":{"name":"Tehnicki vjesnik - Technical Gazette","volume":"7 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141337527","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 : 2024-06-15DOI: 10.17559/tv-20231013001024
TU Qun, Xiaoru Zhao, Daqing Gong, Qianqian Zhang
: With the rapid rise of online classrooms, monitoring student engagement is critical but challenging for educators. This work explores how artificial intelligence (AI) and big data techniques can automatically evaluate student concentration levels in online courses. We developed an end-to-end ResTCN model combining ResNet and temporal convolutional networks (TCN) to extract spatial and temporal video features. Further, we introduced a CutMix data augmentation method and an efficient channel attention (ECA) module to enhance model training. Evaluated on a public dataset of student videos, our approach achieved 63.28% accuracy in classifying student engagement, outperforming state-of-the-art methods. The contributions are a novel spatiotemporal neural architecture, data augmentation strategy, and attention mechanism tailored for the student engagement recognition task. This demonstrates the potential of AI in creating smart education systems.
{"title":"Improved ECA-ResTCN for Online Classroom Student Attention Recognition","authors":"TU Qun, Xiaoru Zhao, Daqing Gong, Qianqian Zhang","doi":"10.17559/tv-20231013001024","DOIUrl":"https://doi.org/10.17559/tv-20231013001024","url":null,"abstract":": With the rapid rise of online classrooms, monitoring student engagement is critical but challenging for educators. This work explores how artificial intelligence (AI) and big data techniques can automatically evaluate student concentration levels in online courses. We developed an end-to-end ResTCN model combining ResNet and temporal convolutional networks (TCN) to extract spatial and temporal video features. Further, we introduced a CutMix data augmentation method and an efficient channel attention (ECA) module to enhance model training. Evaluated on a public dataset of student videos, our approach achieved 63.28% accuracy in classifying student engagement, outperforming state-of-the-art methods. The contributions are a novel spatiotemporal neural architecture, data augmentation strategy, and attention mechanism tailored for the student engagement recognition task. This demonstrates the potential of AI in creating smart education systems.","PeriodicalId":510054,"journal":{"name":"Tehnicki vjesnik - Technical Gazette","volume":"10 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141337187","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 : 2024-06-15DOI: 10.17559/tv-20230809000866
LI Wei, Xeu-qin Meng, Chang-song Ma
792-799
792-799
{"title":"Optimal Differential Control for Accurate Positioning of Medical Electronic Wristband","authors":"LI Wei, Xeu-qin Meng, Chang-song Ma","doi":"10.17559/tv-20230809000866","DOIUrl":"https://doi.org/10.17559/tv-20230809000866","url":null,"abstract":"792-799","PeriodicalId":510054,"journal":{"name":"Tehnicki vjesnik - Technical Gazette","volume":"2 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141336505","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 : 2024-06-15DOI: 10.17559/tv-20230926000963
Xu Zhang
: The essence of computer vision technology is to combine computers with image data to enhance their understanding and perception abilities. One of the major research hotspots in computer vision technology is the object recognition, and in the field of object recognition, a major challenge is the recognition of weak and small target images. In response to the current difficulty in detecting weak and small target images, a visual communication design with image processing models and data fusion was proposed. The Single Shot MultiBox Detector was improved to construct a weak and small target detection model, and the feature fusion method was combined to enhance its weak and small target detection ability. The ablation experiment showed that in contrast with the original model, the improved model improved the detection ability of weak and small targets by 26.54%, and the overall accuracy improved by 11.05%. Two other advanced algorithms were selected for comparison with the research algorithm, and the accuracy of the research algorithm was better, with a higher accuracy of 47.67% -79.56% than the comparison algorithm. The response time was shorter, reaching 0.62 seconds. Visual communication time and success rate performed better, with a communication time lead of 9 s to 19 s and a success rate lead of 16% to 27%. In summary, the algorithm proposed by the research institute has higher accuracy in detecting small and weak images, as well as higher visual communication efficiency and success rate, which has stronger practical significance in the field of computer vision.
{"title":"Visual Communication Design of Weak and Small Target Images Based on Image Processing Model and Data Fusion","authors":"Xu Zhang","doi":"10.17559/tv-20230926000963","DOIUrl":"https://doi.org/10.17559/tv-20230926000963","url":null,"abstract":": The essence of computer vision technology is to combine computers with image data to enhance their understanding and perception abilities. One of the major research hotspots in computer vision technology is the object recognition, and in the field of object recognition, a major challenge is the recognition of weak and small target images. In response to the current difficulty in detecting weak and small target images, a visual communication design with image processing models and data fusion was proposed. The Single Shot MultiBox Detector was improved to construct a weak and small target detection model, and the feature fusion method was combined to enhance its weak and small target detection ability. The ablation experiment showed that in contrast with the original model, the improved model improved the detection ability of weak and small targets by 26.54%, and the overall accuracy improved by 11.05%. Two other advanced algorithms were selected for comparison with the research algorithm, and the accuracy of the research algorithm was better, with a higher accuracy of 47.67% -79.56% than the comparison algorithm. The response time was shorter, reaching 0.62 seconds. Visual communication time and success rate performed better, with a communication time lead of 9 s to 19 s and a success rate lead of 16% to 27%. In summary, the algorithm proposed by the research institute has higher accuracy in detecting small and weak images, as well as higher visual communication efficiency and success rate, which has stronger practical significance in the field of computer vision.","PeriodicalId":510054,"journal":{"name":"Tehnicki vjesnik - Technical Gazette","volume":"2 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141336987","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 : 2024-06-15DOI: 10.17559/tv-20230911000930
C. Bethala, M. Kamsali
: The hybrid Dielectric Resonator Antenna (DRA) with circular polarization is another key research area since it can provide better antenna characteristics required by modern-day communication standards than the DRA with linear polarization. In this article, a Hybrid rectangular DRA is proposed. The Proposed DRA is excited with a novel feeding structure which is the combination of apex etched rectangular monopole and microstrip feed. The feeding structure is printed on a material with a dielectric constant of 4.4. The DR of 9.8 dielectric constants is placed on top of the patch. The proposed structure resonates at four different bands 1.42-1.52 GHz, 3.76-4.36 GHz, 4.92-5.35 GHz, and 7.02-8.74 GHz. The Critical parameters are analyzed and optimal dimensions are identified using the CST software. The proposed antenna exhibits circular polarization, which is validated with the axial ratio and electrical field distribution. The simulated results of the surface current are presented to validate the performance The measurement result is compared with the simulated results and found to be in agreement. The gain is well maintained above 1.5 dBi in all the resonating bands. A stable radiation pattern across all the resonating bands is achieved.
{"title":"Multiband Circularly Polarized Apex Etched Hybrid Rectangular Dielectric Resonator for Wireless Applications","authors":"C. Bethala, M. Kamsali","doi":"10.17559/tv-20230911000930","DOIUrl":"https://doi.org/10.17559/tv-20230911000930","url":null,"abstract":": The hybrid Dielectric Resonator Antenna (DRA) with circular polarization is another key research area since it can provide better antenna characteristics required by modern-day communication standards than the DRA with linear polarization. In this article, a Hybrid rectangular DRA is proposed. The Proposed DRA is excited with a novel feeding structure which is the combination of apex etched rectangular monopole and microstrip feed. The feeding structure is printed on a material with a dielectric constant of 4.4. The DR of 9.8 dielectric constants is placed on top of the patch. The proposed structure resonates at four different bands 1.42-1.52 GHz, 3.76-4.36 GHz, 4.92-5.35 GHz, and 7.02-8.74 GHz. The Critical parameters are analyzed and optimal dimensions are identified using the CST software. The proposed antenna exhibits circular polarization, which is validated with the axial ratio and electrical field distribution. The simulated results of the surface current are presented to validate the performance The measurement result is compared with the simulated results and found to be in agreement. The gain is well maintained above 1.5 dBi in all the resonating bands. A stable radiation pattern across all the resonating bands is achieved.","PeriodicalId":510054,"journal":{"name":"Tehnicki vjesnik - Technical Gazette","volume":"81 14","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141338097","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 : 2024-06-15DOI: 10.17559/tv-20230604001172
LI Linzi
: Wetland restoration work is crucial for ecosystem development, and how to scientifically evaluate wetland restoration programmes is the key to improve the effectiveness of wetland restoration. In order to solve the problems of inadequate judgement and human influence in the evaluation of wetland restoration programmes, this paper proposes a wetland restoration programme evaluation model based on Fuzzy Neural Network method, which is based on fuzzy theory and combines the adaptive function and self-learning function of neural network to evaluate three wetland restoration programmes. The results show that programme B is better than programmes A and C and is suitable for long-term application in wetland restoration work in this area. It is concluded that the use of Fuzzy Neural Network model to evaluate the wetland restoration programmes is more accurate, more personalised, and has a better operation rate, which is an important means of evaluating the wetland restoration programmes and an important guideline to carry out the wetland work.
:湿地恢复工作对生态系统发展至关重要，如何科学评价湿地恢复方案是提高湿地恢复效果的关键。为解决湿地恢复方案评价中存在的判断不足和人为影响等问题，本文提出了基于模糊神经网络方法的湿地恢复方案评价模型，该模型以模糊理论为基础，结合神经网络的自适应功能和自学习功能，对三种湿地恢复方案进行评价。结果表明，方案 B 优于方案 A 和 C，适合在该地区湿地恢复工作中长期应用。由此得出结论，利用模糊神经网络模型评价湿地恢复方案，准确性更高，个性化更强，运行率更好，是评价湿地恢复方案的重要手段，也是开展湿地工作的重要指导思想。
{"title":"A Fuzzy Neural Network Approach for Evaluation of Wetland Restoration Programmes","authors":"LI Linzi","doi":"10.17559/tv-20230604001172","DOIUrl":"https://doi.org/10.17559/tv-20230604001172","url":null,"abstract":": Wetland restoration work is crucial for ecosystem development, and how to scientifically evaluate wetland restoration programmes is the key to improve the effectiveness of wetland restoration. In order to solve the problems of inadequate judgement and human influence in the evaluation of wetland restoration programmes, this paper proposes a wetland restoration programme evaluation model based on Fuzzy Neural Network method, which is based on fuzzy theory and combines the adaptive function and self-learning function of neural network to evaluate three wetland restoration programmes. The results show that programme B is better than programmes A and C and is suitable for long-term application in wetland restoration work in this area. It is concluded that the use of Fuzzy Neural Network model to evaluate the wetland restoration programmes is more accurate, more personalised, and has a better operation rate, which is an important means of evaluating the wetland restoration programmes and an important guideline to carry out the wetland work.","PeriodicalId":510054,"journal":{"name":"Tehnicki vjesnik - Technical Gazette","volume":"81 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141338106","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：