The adoption of 5G for Railways(5G-R)is expanding,particularly in high-speed trains,due to the benefits offered by 5G technology.High-speed trains must provide seamless connectivity and Quality of Service(QoS)to ensur...The adoption of 5G for Railways(5G-R)is expanding,particularly in high-speed trains,due to the benefits offered by 5G technology.High-speed trains must provide seamless connectivity and Quality of Service(QoS)to ensure passengers have a satisfactory experience throughout their journey.Installing base stations along urban environments can improve coverage but can dramatically reduce the experience of users due to interference.In particular,when a user with a mobile phone is a passenger in a high speed train traversing between urban centres,the coverage and the 5G resources in general need to be adequate not to diminish her experience of the service.The utilization of macro,pico,and femto cells may optimize the utilization of 5G resources.In this paper,a Genetic Algorithm(GA)-based approach to address the challenges of 5G network planning for 5G-R services is presented.The network is divided into three cell types,macro,pico,and femto cells—and the optimization process is designed to achieve a balance between key objectives:providing comprehensive coverage,minimizing interference,and maximizing energy efficiency.The study focuses on environments with high user density,such as high-speed trains,where reliable and high-quality connectivity is critical.Through simulations,the effectiveness of the GA-driven framework in optimizing coverage and performance in such scenarios is demonstrated.The algorithm is compared with the Particle Swarm Optimisation(PSO)and the Simulated Annealing(SA)methods and interesting insights emerged.The GA offers a strong balance between coverage and efficiency,achieving significantly higher coverage than PSO while maintaining competitive energy efficiency and interference levels.Its steady fitness improvement and adaptability make it well-suited for scenarios where wide coverage is a priority alongside acceptable performance trade-offs.展开更多
近年来,由于基于图像识别的粉尘检测方法不存在安装和检测范围局限性等问题,因此得到了充分重视和发展,但现有方法实时性和准确性仍需提升。为此,提出了一种基于改进YOLOv5算法的粉尘图像检测方法。首先,对现有YOLOv5算法主干网络以及N...近年来,由于基于图像识别的粉尘检测方法不存在安装和检测范围局限性等问题,因此得到了充分重视和发展,但现有方法实时性和准确性仍需提升。为此,提出了一种基于改进YOLOv5算法的粉尘图像检测方法。首先,对现有YOLOv5算法主干网络以及Neck网络进行改进,将轻量化网络GhostNet替换原有主干网络,以降低网络参数,再输出3个特征层;然后,针对主干网络输出的3个特征层,施加注意力机制CA,增加网络精度;最后,设计消融实验和对比实验验证改进算法的有效性。结果表明:改进算法的平均检测精度mAP(mean Average Precision)能达到92.11%,检测速度达37帧/s。展开更多
火灾是一种极具破坏性的灾害,对火焰和烟雾的检测有助于及时发现火灾,以便采取有效措施将损失最小化.现有的算法对火焰烟雾的检测精度较低,不能做到精确识别小目标火焰和烟雾.为了进一步提高检测准确率,提出了基于YOLOv5s算法进行改进...火灾是一种极具破坏性的灾害,对火焰和烟雾的检测有助于及时发现火灾,以便采取有效措施将损失最小化.现有的算法对火焰烟雾的检测精度较低,不能做到精确识别小目标火焰和烟雾.为了进一步提高检测准确率,提出了基于YOLOv5s算法进行改进的火焰烟雾检测算法FS-YOLO.首先,在主干网络的C3模块中融合CA注意力机制来增强模型对图像特征的感知能力;其次,为了实现高效多尺度特征融合,将双向加权特征金字塔网络(BiFPN)用于颈部的多尺度信息融合;此外,在主干网络中加入由混合卷积层和普通卷积层组成的CSPCM模块,以便通过少量计算代价来提取火焰烟雾显著特征;最后,为提高边界框回归准确率,采用了基于最小点的MPDIoU损失函数和ReLU激活函数加速网络的训练和推理.在Fire and Smoke数据集上的实验结果表明:FS-YOLO达到了mAP@0.5上0.606和mAP@0.5-0.95上0.275的检测精度,相较于YOLOv5s分别提升5.21%和8.27%,FS-YOLO在实际运行中的速度为303 FPS,实现了高精度快速的实时火焰烟雾检测.展开更多
The demands on conventional communication networks are increasing rapidly because of the exponential expansion of connected multimedia content.In light of the data-centric aspect of contemporary communication,the info...The demands on conventional communication networks are increasing rapidly because of the exponential expansion of connected multimedia content.In light of the data-centric aspect of contemporary communication,the information-centric network(ICN)paradigm offers hope for a solution by emphasizing content retrieval by name instead of location.If 5G networks are to meet the expected data demand surge from expanded connectivity and Internet of Things(IoT)devices,then effective caching solutions will be required tomaximize network throughput andminimize the use of resources.Hence,an ICN-based Cooperative Caching(ICN-CoC)technique has been used to select a cache by considering cache position,content attractiveness,and rate prediction.The findings show that utilizing our suggested approach improves caching regarding the Cache Hit Ratio(CHR)of 84.3%,Average Hop Minimization Ratio(AHMR)of 89.5%,and Mean Access Latency(MAL)of 0.4 s.Within a framework,it suggests improved caching strategies to handle the difficulty of effectively controlling data consumption in 5G networks.These improvements aim to make the network run more smoothly by enhancing content delivery,decreasing latency,and relieving congestion.By improving 5G communication systems’capacity tomanage the demands faced by modern data-centric applications,the research ultimately aids in advancement.展开更多
文摘The adoption of 5G for Railways(5G-R)is expanding,particularly in high-speed trains,due to the benefits offered by 5G technology.High-speed trains must provide seamless connectivity and Quality of Service(QoS)to ensure passengers have a satisfactory experience throughout their journey.Installing base stations along urban environments can improve coverage but can dramatically reduce the experience of users due to interference.In particular,when a user with a mobile phone is a passenger in a high speed train traversing between urban centres,the coverage and the 5G resources in general need to be adequate not to diminish her experience of the service.The utilization of macro,pico,and femto cells may optimize the utilization of 5G resources.In this paper,a Genetic Algorithm(GA)-based approach to address the challenges of 5G network planning for 5G-R services is presented.The network is divided into three cell types,macro,pico,and femto cells—and the optimization process is designed to achieve a balance between key objectives:providing comprehensive coverage,minimizing interference,and maximizing energy efficiency.The study focuses on environments with high user density,such as high-speed trains,where reliable and high-quality connectivity is critical.Through simulations,the effectiveness of the GA-driven framework in optimizing coverage and performance in such scenarios is demonstrated.The algorithm is compared with the Particle Swarm Optimisation(PSO)and the Simulated Annealing(SA)methods and interesting insights emerged.The GA offers a strong balance between coverage and efficiency,achieving significantly higher coverage than PSO while maintaining competitive energy efficiency and interference levels.Its steady fitness improvement and adaptability make it well-suited for scenarios where wide coverage is a priority alongside acceptable performance trade-offs.
文摘近年来,由于基于图像识别的粉尘检测方法不存在安装和检测范围局限性等问题,因此得到了充分重视和发展,但现有方法实时性和准确性仍需提升。为此,提出了一种基于改进YOLOv5算法的粉尘图像检测方法。首先,对现有YOLOv5算法主干网络以及Neck网络进行改进,将轻量化网络GhostNet替换原有主干网络,以降低网络参数,再输出3个特征层;然后,针对主干网络输出的3个特征层,施加注意力机制CA,增加网络精度;最后,设计消融实验和对比实验验证改进算法的有效性。结果表明:改进算法的平均检测精度mAP(mean Average Precision)能达到92.11%,检测速度达37帧/s。
文摘火灾是一种极具破坏性的灾害,对火焰和烟雾的检测有助于及时发现火灾,以便采取有效措施将损失最小化.现有的算法对火焰烟雾的检测精度较低,不能做到精确识别小目标火焰和烟雾.为了进一步提高检测准确率,提出了基于YOLOv5s算法进行改进的火焰烟雾检测算法FS-YOLO.首先,在主干网络的C3模块中融合CA注意力机制来增强模型对图像特征的感知能力;其次,为了实现高效多尺度特征融合,将双向加权特征金字塔网络(BiFPN)用于颈部的多尺度信息融合;此外,在主干网络中加入由混合卷积层和普通卷积层组成的CSPCM模块,以便通过少量计算代价来提取火焰烟雾显著特征;最后,为提高边界框回归准确率,采用了基于最小点的MPDIoU损失函数和ReLU激活函数加速网络的训练和推理.在Fire and Smoke数据集上的实验结果表明:FS-YOLO达到了mAP@0.5上0.606和mAP@0.5-0.95上0.275的检测精度,相较于YOLOv5s分别提升5.21%和8.27%,FS-YOLO在实际运行中的速度为303 FPS,实现了高精度快速的实时火焰烟雾检测.
基金New Brunswick Innovation Foundation(NBIF)for the financial support of the global project.
文摘The demands on conventional communication networks are increasing rapidly because of the exponential expansion of connected multimedia content.In light of the data-centric aspect of contemporary communication,the information-centric network(ICN)paradigm offers hope for a solution by emphasizing content retrieval by name instead of location.If 5G networks are to meet the expected data demand surge from expanded connectivity and Internet of Things(IoT)devices,then effective caching solutions will be required tomaximize network throughput andminimize the use of resources.Hence,an ICN-based Cooperative Caching(ICN-CoC)technique has been used to select a cache by considering cache position,content attractiveness,and rate prediction.The findings show that utilizing our suggested approach improves caching regarding the Cache Hit Ratio(CHR)of 84.3%,Average Hop Minimization Ratio(AHMR)of 89.5%,and Mean Access Latency(MAL)of 0.4 s.Within a framework,it suggests improved caching strategies to handle the difficulty of effectively controlling data consumption in 5G networks.These improvements aim to make the network run more smoothly by enhancing content delivery,decreasing latency,and relieving congestion.By improving 5G communication systems’capacity tomanage the demands faced by modern data-centric applications,the research ultimately aids in advancement.
