Mobile user devices, such as smartphones or laptops, run increasingly complex applications that require more computing power and more computing resources. However, the battery capacity and energy consumption of mobile devices limit these developments. Mobile-Edge Computing (MEC) is a technology that utilizes wireless network to provide IT and cloud computing services for nearby users. IT can build a network environment with low latency and high bandwidth and accelerate the response speed of network services. Transferring computing tasks of mobile devices to MEC server through task migration technology can effectively relieve computing pressure of devices. Efficient task migration method can minimize the energy consumption of mobile devices on the basis of ensuring the data delay requirement. According to the characteristics of coarse-grained task migration in current mobile edge computing, this paper proposes a finegrained task migration scheme based on Ant Colony Algorithm(ACO), aiming to minimize the energy consumption of mobile devices on the basis of strict delay constraints in mobile applications. Finally, experimental results show that the method used in this paper can effectively reduce the energy consumption of mobile devices by 26%, compared to the static strategy.
{"title":"A Single Task Migration Strategy Based on Ant Colony Algorithm in Mobile-Edge Computing","authors":"Juan Fang, Weihao Xu","doi":"10.1145/3404555.3404586","DOIUrl":"https://doi.org/10.1145/3404555.3404586","url":null,"abstract":"Mobile user devices, such as smartphones or laptops, run increasingly complex applications that require more computing power and more computing resources. However, the battery capacity and energy consumption of mobile devices limit these developments. Mobile-Edge Computing (MEC) is a technology that utilizes wireless network to provide IT and cloud computing services for nearby users. IT can build a network environment with low latency and high bandwidth and accelerate the response speed of network services. Transferring computing tasks of mobile devices to MEC server through task migration technology can effectively relieve computing pressure of devices. Efficient task migration method can minimize the energy consumption of mobile devices on the basis of ensuring the data delay requirement. According to the characteristics of coarse-grained task migration in current mobile edge computing, this paper proposes a finegrained task migration scheme based on Ant Colony Algorithm(ACO), aiming to minimize the energy consumption of mobile devices on the basis of strict delay constraints in mobile applications. Finally, experimental results show that the method used in this paper can effectively reduce the energy consumption of mobile devices by 26%, compared to the static strategy.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133436137","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}
Intrusion detection of abnormal objects is critical to avoid traffic accidents and ensure the safety of train operations. Computer-vision based approaches using RGB images have been intensively investigated for intrusion detection at daytime. However, the abnormal object detection using infrared images at nighttime remains more challenging because training samples of infrared images are limited to address this issue, we propose a data augmentation strategy motivated by image style transfer using CycleGAN. First, the synthetic images are generated which conditioned on railway scene images at daytime and non-railway scene images at nighttime. Then, a SSD object detection model is trained using the generated synthetic samples. Finally, the trained SSD model is used to detect abnormal objects for infrared images at nighttime. Experimental results demonstrate that the proposed data augmentation strategy and the object detection method for nighttime scene is effective.
{"title":"Intrusion Detection of Abnormal Objects for Railway Scenes Using Infrared Images","authors":"Yi Liu, Han Dong, Yundong Li","doi":"10.1145/3404555.3404579","DOIUrl":"https://doi.org/10.1145/3404555.3404579","url":null,"abstract":"Intrusion detection of abnormal objects is critical to avoid traffic accidents and ensure the safety of train operations. Computer-vision based approaches using RGB images have been intensively investigated for intrusion detection at daytime. However, the abnormal object detection using infrared images at nighttime remains more challenging because training samples of infrared images are limited to address this issue, we propose a data augmentation strategy motivated by image style transfer using CycleGAN. First, the synthetic images are generated which conditioned on railway scene images at daytime and non-railway scene images at nighttime. Then, a SSD object detection model is trained using the generated synthetic samples. Finally, the trained SSD model is used to detect abnormal objects for infrared images at nighttime. Experimental results demonstrate that the proposed data augmentation strategy and the object detection method for nighttime scene is effective.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114727607","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}
Reliability and energy consumption are the two important metrics in wireless body area network (WBAN) for medical application, and they are also the difficulties and key points in network research. In this article, we propose a new adaptive Markov-based transmission power control algorithm (MBPC) for a better compromise between energy consumption and reliability. The algorithm applies the Markov model to the link quality prediction using the grading strategy. Based on the prediction results, a new power adjustment strategy is proposed to extend the lifetime of the network while ensuring reliable transmission. In addition, we also incorporate open-loop thinking into the design of the algorithm to ensure the accuracy of the algorithm. The algorithm is simulated on the Castalia software platform. The simulation results show that the proposed algorithm has achieved good results in reliable transmission and energy consumption.
{"title":"Markov-Based Transmission Power Control in Wireless Body Area Network","authors":"Wenjing Guo, Mengxing Xu, Ting Lu","doi":"10.1145/3404555.3404584","DOIUrl":"https://doi.org/10.1145/3404555.3404584","url":null,"abstract":"Reliability and energy consumption are the two important metrics in wireless body area network (WBAN) for medical application, and they are also the difficulties and key points in network research. In this article, we propose a new adaptive Markov-based transmission power control algorithm (MBPC) for a better compromise between energy consumption and reliability. The algorithm applies the Markov model to the link quality prediction using the grading strategy. Based on the prediction results, a new power adjustment strategy is proposed to extend the lifetime of the network while ensuring reliable transmission. In addition, we also incorporate open-loop thinking into the design of the algorithm to ensure the accuracy of the algorithm. The algorithm is simulated on the Castalia software platform. The simulation results show that the proposed algorithm has achieved good results in reliable transmission and energy consumption.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117166552","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}
Shuangyue Niu, Xiang Ji, Jingmei Li, Di Xue, Weifei Wu
With the rapid development of network technology, network intrusion has become increasingly frequent. In network intrusion detection technology, how to reduce feature dimensions and reduce redundant information is the key to improve the detection accuracy. To solve this problem, this paper proposes a new feature selection method SIFWA for intrusion detection based on improved fireworks algorithm. SIFWA optimized and improved the selection strategy of fireworks algorithm, which adopted the selection strategy based on fitness value to screen the next generation of fireworks, which could greatly improve the ability of fireworks algorithm to find the optimal solution and search efficiency to select more effective features for intrusion detection. Simulation experiments were conducted using UCI data. Simulation results show that SIFWA has higher detection accuracy than the benchmark algorithm.
{"title":"An Intrusion Detection Feature Selection Method Based on Improved Fireworks Algorithm","authors":"Shuangyue Niu, Xiang Ji, Jingmei Li, Di Xue, Weifei Wu","doi":"10.1145/3404555.3404556","DOIUrl":"https://doi.org/10.1145/3404555.3404556","url":null,"abstract":"With the rapid development of network technology, network intrusion has become increasingly frequent. In network intrusion detection technology, how to reduce feature dimensions and reduce redundant information is the key to improve the detection accuracy. To solve this problem, this paper proposes a new feature selection method SIFWA for intrusion detection based on improved fireworks algorithm. SIFWA optimized and improved the selection strategy of fireworks algorithm, which adopted the selection strategy based on fitness value to screen the next generation of fireworks, which could greatly improve the ability of fireworks algorithm to find the optimal solution and search efficiency to select more effective features for intrusion detection. Simulation experiments were conducted using UCI data. Simulation results show that SIFWA has higher detection accuracy than the benchmark algorithm.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122480337","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}
Unsupervised image-to-image translation, which aims in translating two irrelevant domains of images, has increased substantially in recent years with the success of Generative Adversarial Networks (GANs) based on the cycle-consistency assumption. Especially, the Cycle-Consistent Generative Adversarial Network (CycleGAN) has shown remarkable success for two domains translation. However, the details about texture and style are often accompanied with unpleasant artifacts. To further enhance the translational quality, we thoroughly study the key components of CycleGAN - network architecture and adversarial loss, and improve each of them to derive an Enhanced CycleGAN (ECycleGAN). In particular, we propose a perceptual loss function which motivated by perceptual similarity instead of similarity in pixel space. Moreover, we introduce the Residual Dense Normalization Block (RDNB) to replace the residual blocks as the basic network building unit. Finally, we borrow the idea from WGAN-GP as the adversarial loss functions. The ECycleGAN, thanks to these changes, demonstrates appealing visual quality with more realistic and natural textures than any state-of-the-art methods.
{"title":"ECycleGAN","authors":"Xianchao Zhang, Changjia Zhou","doi":"10.1145/3404555.3404597","DOIUrl":"https://doi.org/10.1145/3404555.3404597","url":null,"abstract":"Unsupervised image-to-image translation, which aims in translating two irrelevant domains of images, has increased substantially in recent years with the success of Generative Adversarial Networks (GANs) based on the cycle-consistency assumption. Especially, the Cycle-Consistent Generative Adversarial Network (CycleGAN) has shown remarkable success for two domains translation. However, the details about texture and style are often accompanied with unpleasant artifacts. To further enhance the translational quality, we thoroughly study the key components of CycleGAN - network architecture and adversarial loss, and improve each of them to derive an Enhanced CycleGAN (ECycleGAN). In particular, we propose a perceptual loss function which motivated by perceptual similarity instead of similarity in pixel space. Moreover, we introduce the Residual Dense Normalization Block (RDNB) to replace the residual blocks as the basic network building unit. Finally, we borrow the idea from WGAN-GP as the adversarial loss functions. The ECycleGAN, thanks to these changes, demonstrates appealing visual quality with more realistic and natural textures than any state-of-the-art methods.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123240899","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}
Deep neural networks have gained success recently in learning distributed representations for text classification. However, due to the sparsity of information in user-generated comments, existing approaches still suffer from the problem of exploiting the semantic information by halves to classify current sentence. In this paper, we propose a novel attention-based joint representation learning network (AJRLN). The proposed model provides two attention-based subnets to extract different attentive features of the sentence embedding. Then, these features are combined by the representation combination layer to get the joint representation of the whole sentence for classification. We conduct extensive experiments on SST, TREC and SUBJ datasets. The experimental results demonstrate that our model achieved comparable or better performance than other state-of-the-art methods.
{"title":"Attention-based Joint Representation Learning Network for Short text Classification","authors":"Xinyue Liu, Yexuan Tang","doi":"10.1145/3404555.3404578","DOIUrl":"https://doi.org/10.1145/3404555.3404578","url":null,"abstract":"Deep neural networks have gained success recently in learning distributed representations for text classification. However, due to the sparsity of information in user-generated comments, existing approaches still suffer from the problem of exploiting the semantic information by halves to classify current sentence. In this paper, we propose a novel attention-based joint representation learning network (AJRLN). The proposed model provides two attention-based subnets to extract different attentive features of the sentence embedding. Then, these features are combined by the representation combination layer to get the joint representation of the whole sentence for classification. We conduct extensive experiments on SST, TREC and SUBJ datasets. The experimental results demonstrate that our model achieved comparable or better performance than other state-of-the-art methods.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131159021","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}
Jinfeng Dou, Lei Chu, Jiabao Cao, Yang Qiu, Baolin Zhao
With the development of new information technologies, the accumulation of data volume has been exploding, and big data retrieval has played an increasingly important role in big data technology. The challenge of data retrieval are the improvement of retrieval accuracy and retrieval speed. Aiming at the demand of big data platform for efficient data retrieval, an efficient optimized strategy is proposed. We found when the primary key query is used, the query response can be quick. However, when using a non-primary key query, the cache table needs to be comprehensively scanned and the longer response delay may be induced. This paper proposes a secondary index based on Solr to increase the accuracy of information retrieval and the quality of user experience. Then a cache-heat evaluation algorithm categorizes data according to access frequency to reduce query latency. Moreover, an index optimization method based on memory cache updates the cache to save space and enhance utilization. The experiments and simulation demonstrate that the proposed strategy can effectively improves the big data retrieval.
{"title":"Efficient Optimized Strategy of Big Data Retrieval","authors":"Jinfeng Dou, Lei Chu, Jiabao Cao, Yang Qiu, Baolin Zhao","doi":"10.1145/3404555.3404630","DOIUrl":"https://doi.org/10.1145/3404555.3404630","url":null,"abstract":"With the development of new information technologies, the accumulation of data volume has been exploding, and big data retrieval has played an increasingly important role in big data technology. The challenge of data retrieval are the improvement of retrieval accuracy and retrieval speed. Aiming at the demand of big data platform for efficient data retrieval, an efficient optimized strategy is proposed. We found when the primary key query is used, the query response can be quick. However, when using a non-primary key query, the cache table needs to be comprehensively scanned and the longer response delay may be induced. This paper proposes a secondary index based on Solr to increase the accuracy of information retrieval and the quality of user experience. Then a cache-heat evaluation algorithm categorizes data according to access frequency to reduce query latency. Moreover, an index optimization method based on memory cache updates the cache to save space and enhance utilization. The experiments and simulation demonstrate that the proposed strategy can effectively improves the big data retrieval.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126857672","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}
Nuclei segmentation plays an important role in medical image analysis but it is also a challenging area due to the tiny size of nuclei especially for breast cancer nuclei. To address these challenges, in this paper we present an improved UNet++ architecture, a more powerful architecture for nuclei segmentation. The original UNet++, which is an encoder-decoder architecture with a series of nested and dense skip pathways, is used as the framework in our work. The main reason for the increase in ability is that the Inception-ResNet-V2 network is added as backbone, which is a very deep network with brilliant performance in object detection. We have evaluated our improved UNet++ in comparison with UNet and the original UNet++ architectures in breast cancer nuclei segmentation dataset. The experiments demonstrate that our improved UNet++ is superior to U-Net and the original U-Net++.
{"title":"An Improved Breast Cancer Nuclei Segmentation Method Based on UNet++","authors":"Hong Wang, Yinhan Li, Zhiyi Luo","doi":"10.1145/3404555.3404577","DOIUrl":"https://doi.org/10.1145/3404555.3404577","url":null,"abstract":"Nuclei segmentation plays an important role in medical image analysis but it is also a challenging area due to the tiny size of nuclei especially for breast cancer nuclei. To address these challenges, in this paper we present an improved UNet++ architecture, a more powerful architecture for nuclei segmentation. The original UNet++, which is an encoder-decoder architecture with a series of nested and dense skip pathways, is used as the framework in our work. The main reason for the increase in ability is that the Inception-ResNet-V2 network is added as backbone, which is a very deep network with brilliant performance in object detection. We have evaluated our improved UNet++ in comparison with UNet and the original UNet++ architectures in breast cancer nuclei segmentation dataset. The experiments demonstrate that our improved UNet++ is superior to U-Net and the original U-Net++.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129187617","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：