Pub Date : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118570
Guoqing Deng, Yangguang Zhao, Long Zhang, Zhigang Li, Yong Liu, Yi Zhang, Bin Li
In order to guide the production of cigarette products and improve the quality of cigarette products, this paper proposes a classification method for cigarette combustion cones based on deep convolutional neural network model. The method is optimized based on the Inception Resnet V2 model and is innovatively used in the detection of cigarette burning cones. The classification accuracy of combustion cone fallout is characterized by the overall classification accuracy (OA) and the Kappa coefficient (Kappa). The experimental results show that the overall classification accuracy is 97.22%, and the Kappa coefficient is 0.9583. The deep convolutional neural network has better classification effect. Based on the classification method of deep convolutional neural network, the cigarette burning cone can be accurately identified.
{"title":"Image Classification and Detection of Cigarette Combustion Cone Based on Inception Resnet V2","authors":"Guoqing Deng, Yangguang Zhao, Long Zhang, Zhigang Li, Yong Liu, Yi Zhang, Bin Li","doi":"10.1109/ICCCS49078.2020.9118570","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118570","url":null,"abstract":"In order to guide the production of cigarette products and improve the quality of cigarette products, this paper proposes a classification method for cigarette combustion cones based on deep convolutional neural network model. The method is optimized based on the Inception Resnet V2 model and is innovatively used in the detection of cigarette burning cones. The classification accuracy of combustion cone fallout is characterized by the overall classification accuracy (OA) and the Kappa coefficient (Kappa). The experimental results show that the overall classification accuracy is 97.22%, and the Kappa coefficient is 0.9583. The deep convolutional neural network has better classification effect. Based on the classification method of deep convolutional neural network, the cigarette burning cone can be accurately identified.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121238260","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118589
Rui Li, Yongfu Zhang, Lihui Peng, X. Liao
Image reconstruction algorithm is essential for electrical capacitance tomography (ECT), which is still in the stage of popular research. With the development of image reconstruction algorithm, high-quality image is the key challenge for ECT all long. The paper proposes a kind of novel-image-reconstruction-algorithm for ECT using parametric level-set method to obtain high-image quality. Based on the relationship between dielectric constant distribution and capacitance value in the sensitivity area, parametric level set algorithm is capable of realizing absolute values ECT reconstruction. The paper presented simulation results of reconstructing the permittivity profiles of different water leakage using parametric level set method (PLS). Comparing with the state of the art image reconstruction algorithm, such as LBP regularization, landweber iterative algorithm and total variational regularization, the proposed method has better image quality, especially with high contrast multiphase data. PLS adopts Gaussian radial basis function (GRBF), which considerably reduces the number of unknowns. The parametric level set method can avoid the problem of regularization coefficients involved in the calculation process and reduce the Ill-posed Problem of image reconstruction. The proposed PLS method has demonstrated the superior image quality and better noise ratio (SNR).
{"title":"An Image Reconstruction For Electrical Capacitance Tomography Using Parametric Level Set","authors":"Rui Li, Yongfu Zhang, Lihui Peng, X. Liao","doi":"10.1109/ICCCS49078.2020.9118589","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118589","url":null,"abstract":"Image reconstruction algorithm is essential for electrical capacitance tomography (ECT), which is still in the stage of popular research. With the development of image reconstruction algorithm, high-quality image is the key challenge for ECT all long. The paper proposes a kind of novel-image-reconstruction-algorithm for ECT using parametric level-set method to obtain high-image quality. Based on the relationship between dielectric constant distribution and capacitance value in the sensitivity area, parametric level set algorithm is capable of realizing absolute values ECT reconstruction. The paper presented simulation results of reconstructing the permittivity profiles of different water leakage using parametric level set method (PLS). Comparing with the state of the art image reconstruction algorithm, such as LBP regularization, landweber iterative algorithm and total variational regularization, the proposed method has better image quality, especially with high contrast multiphase data. PLS adopts Gaussian radial basis function (GRBF), which considerably reduces the number of unknowns. The parametric level set method can avoid the problem of regularization coefficients involved in the calculation process and reduce the Ill-posed Problem of image reconstruction. The proposed PLS method has demonstrated the superior image quality and better noise ratio (SNR).","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121375987","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118549
Xinglin Gong, Erwu Liu, Rui Wang
Blockchain technology can be used to track billions of interconnected devices, enabling secure data exchange and data processing. The decentralized and autonomous ability of the blockchain makes it an ideal solution for Internet of Things(IoT) applications. In this paper, we explore a basic IoT-Blockchain fusion model with four layers which contains different types of IoT devices. Distributed file system is considered in the model to store huge amount of IoT data. Then, a case study for blockchain-based IoT application, a Machine-to-Machine(M2M) autonomous trading system, is proposed on the Ethereum blockchain. We build smart contracts for device registration, data storage, service provision and fair payment, and the proof-of-concept is implemented using two Raspberry Pis to interact with smart contracts. The proposed system verifies that blockchain could improve IoT applications in transparency, traceability and security.
{"title":"Blockchain-Based IoT Application Using Smart Contracts: Case Study of M2M Autonomous Trading","authors":"Xinglin Gong, Erwu Liu, Rui Wang","doi":"10.1109/ICCCS49078.2020.9118549","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118549","url":null,"abstract":"Blockchain technology can be used to track billions of interconnected devices, enabling secure data exchange and data processing. The decentralized and autonomous ability of the blockchain makes it an ideal solution for Internet of Things(IoT) applications. In this paper, we explore a basic IoT-Blockchain fusion model with four layers which contains different types of IoT devices. Distributed file system is considered in the model to store huge amount of IoT data. Then, a case study for blockchain-based IoT application, a Machine-to-Machine(M2M) autonomous trading system, is proposed on the Ethereum blockchain. We build smart contracts for device registration, data storage, service provision and fair payment, and the proof-of-concept is implemented using two Raspberry Pis to interact with smart contracts. The proposed system verifies that blockchain could improve IoT applications in transparency, traceability and security.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122466808","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118453
Haiying Yuan, Tong Zheng, Kai Zhang, Yichen Wang
Time-Triggered Ethernet (TTEthernet) efficiently integrates distributed applications with different security levels and real-time requirements in the mixed-criticality system. The key of TTEthernet is the time-triggered mechanism that is achieved by following statically time slot schedule. In the paper, the network model and constraint model are mathematically detailed and exemplified. Constraint programming technology based on ILOG CPLEX is applied innovatively in solve the TTEthernet schedule synthesis problem. Finally, three topologies and two message density scenarios are set up to evaluate the performance of the algorithm in variables, constraint, memory occupancy, and synthesis time dimensions. Numerous experiment results show that the schedule synthesis method is well qualified for the schedules synthesis tasks of TTEthernet.
{"title":"An Efficient Schedule Synthesis Method based on Constraint Programming Technology for Time-Triggered Ethernet","authors":"Haiying Yuan, Tong Zheng, Kai Zhang, Yichen Wang","doi":"10.1109/ICCCS49078.2020.9118453","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118453","url":null,"abstract":"Time-Triggered Ethernet (TTEthernet) efficiently integrates distributed applications with different security levels and real-time requirements in the mixed-criticality system. The key of TTEthernet is the time-triggered mechanism that is achieved by following statically time slot schedule. In the paper, the network model and constraint model are mathematically detailed and exemplified. Constraint programming technology based on ILOG CPLEX is applied innovatively in solve the TTEthernet schedule synthesis problem. Finally, three topologies and two message density scenarios are set up to evaluate the performance of the algorithm in variables, constraint, memory occupancy, and synthesis time dimensions. Numerous experiment results show that the schedule synthesis method is well qualified for the schedules synthesis tasks of TTEthernet.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127700805","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}
Arousal labeling is one of the important methods in the diagnosis and treatment of sleep-related diseases, and are usually analyzed manually by doctors based on polysomnography (PSG) signals. In order to solve the problem of time-consuming and labor-intensive manual arousal analysis in sleep physiological signals, we propose an automatic arousal detection method using multi-model deep neural networks. Combining methods such as one-to-many formulation, LSTM, and network structure improvements, the performance of deep neural network models on clinical data set has been significantly improved, and multiple indicators have been improved (precision 86.7%, recall 86.0% and F1 86.3%). At the same time, the model parameters have been greatly streamlined, making them more efficient, laying a foundation for the application of automatic arousal detection methods on wearable sleep monitoring device signal analysis.
{"title":"Automatic Arousal Detection Using Multi-model Deep Neural Network","authors":"Ziqian Jia, Xingjun Wang, Xiaoqing Zhang, Mingkai Xu","doi":"10.1109/ICCCS49078.2020.9118530","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118530","url":null,"abstract":"Arousal labeling is one of the important methods in the diagnosis and treatment of sleep-related diseases, and are usually analyzed manually by doctors based on polysomnography (PSG) signals. In order to solve the problem of time-consuming and labor-intensive manual arousal analysis in sleep physiological signals, we propose an automatic arousal detection method using multi-model deep neural networks. Combining methods such as one-to-many formulation, LSTM, and network structure improvements, the performance of deep neural network models on clinical data set has been significantly improved, and multiple indicators have been improved (precision 86.7%, recall 86.0% and F1 86.3%). At the same time, the model parameters have been greatly streamlined, making them more efficient, laying a foundation for the application of automatic arousal detection methods on wearable sleep monitoring device signal analysis.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"1144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113995026","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118485
Jun-Feng Wang, Chuan-Wen Lin, Xue-You Hu, Liu Gang
We performed 3D simulations of the temperature field and velocity field in the Czochralski (Cz) process by using computational fluid dynamics (CFD) analysis software. With the obtained velocity field and temperature field in the Cz process, we showed the relative intensity of natural convection and forced convection under different rotation speeds of the growth process based on the Boussinesq approximation and by considering the conduction, convection, and radiation of heat. We simultaneously simulated the change of natural convection and forced convection due to the fall of the liquid surface level in the crucible used for Cz growth. The results will help guide Nd:YAG Cz growth with large diameters and high quality.
{"title":"Three-Dimensional Simulation of Nd:YAG Crystal Growth Based on Computational Fluid Dynamics Analysis Software","authors":"Jun-Feng Wang, Chuan-Wen Lin, Xue-You Hu, Liu Gang","doi":"10.1109/ICCCS49078.2020.9118485","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118485","url":null,"abstract":"We performed 3D simulations of the temperature field and velocity field in the Czochralski (Cz) process by using computational fluid dynamics (CFD) analysis software. With the obtained velocity field and temperature field in the Cz process, we showed the relative intensity of natural convection and forced convection under different rotation speeds of the growth process based on the Boussinesq approximation and by considering the conduction, convection, and radiation of heat. We simultaneously simulated the change of natural convection and forced convection due to the fall of the liquid surface level in the crucible used for Cz growth. The results will help guide Nd:YAG Cz growth with large diameters and high quality.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115228076","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118575
H. Khairnar, B. Sonkamble
Periodic data related to vehicular traffic information have been flare-up and entered the era of big data. Vehicular traffic network is monitored continuously by motion detectors and video cameras. Advanced information about a travelling path is being used as an extraneous intervention tool to positively influence recommendation system performance. This situation directs us to think vehicular traffic path recommendation problem based on time series analysis. In this paper, a graph processing based vehicular traffic path recommendation method is proposed, which considers the spatial and temporal attributes. We cast a problem as an optimal path selection problem for the fixed origin and destination based on various data points acquired at a different time interval. Rigorous experimental evaluation on publicly available dataset shows the efficacy of the proposed method.
{"title":"Aggregated Time Series based Vehicular Traffic Path Recommendation","authors":"H. Khairnar, B. Sonkamble","doi":"10.1109/ICCCS49078.2020.9118575","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118575","url":null,"abstract":"Periodic data related to vehicular traffic information have been flare-up and entered the era of big data. Vehicular traffic network is monitored continuously by motion detectors and video cameras. Advanced information about a travelling path is being used as an extraneous intervention tool to positively influence recommendation system performance. This situation directs us to think vehicular traffic path recommendation problem based on time series analysis. In this paper, a graph processing based vehicular traffic path recommendation method is proposed, which considers the spatial and temporal attributes. We cast a problem as an optimal path selection problem for the fixed origin and destination based on various data points acquired at a different time interval. Rigorous experimental evaluation on publicly available dataset shows the efficacy of the proposed method.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116749495","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}
In natural environments, bird sounds are often accompanied by background noise, so denoising becomes crucial to automated bird sound recognition. Recently, thanks to neural network embeddings, the deep clustering method has achieved better performances than traditional denoising methods, like filter-based methods, due to its ability to solve the problem when noise is in the same frequency range as bird sounds. In this paper, we propose a generalized denoising method based on deep clustering, which can process more complex recordings with less distortion. Also, we optimize the original affinity loss function to get a novel loss function to ensure the embedding vectors with the minimum distance belong to the same source, named Joint Center Loss (JCL), which can both increase the inter-class variance and decrease the intra-class variance of embeddings. Experiments are conducted on the gated convolutional neural network architecture and the bidirectional long short term memory architecture respectively with different loss functions. Given the signal-noise ratio being -3dB, the recognition accuracy increases relatively by 9.5% with the proposed denoising method in the best case, and the Relative Root Mean Square Error (RRMSE) increases relatively by 14.2% by using JCL, compared with the original affinity loss function AL.
在自然环境中，鸟叫声往往伴随着背景噪声，因此去噪对鸟叫声的自动识别至关重要。最近，由于神经网络嵌入，深度聚类方法能够解决噪声与鸟鸣在同一频率范围内的问题，因此比传统的去噪方法(如基于滤波器的方法)取得了更好的性能。本文提出了一种基于深度聚类的广义去噪方法，该方法能够以较小的失真处理更复杂的录音。同时，我们对原有的亲和损失函数进行优化，得到一种新的损失函数，以保证距离最小的嵌入向量属于同一源，称为联合中心损失(Joint Center loss, JCL)，它既可以增加嵌入的类间方差，又可以减小嵌入的类内方差。分别用不同的损失函数对门控卷积神经网络结构和双向长短期记忆结构进行了实验。在信噪比为-3dB的情况下，与原始亲和损失函数AL相比，采用JCL去噪方法识别精度相对提高9.5%，相对均方根误差(RRMSE)相对提高14.2%。
{"title":"A Generalized Denoising Method with an Optimized Loss Function for Automated Bird Sound Recognition","authors":"Huangqiang Fang, Yulin He, Wanyang Xu, Yanyan Xu, Dengfeng Ke, Kaile Su","doi":"10.1109/ICCCS49078.2020.9118426","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118426","url":null,"abstract":"In natural environments, bird sounds are often accompanied by background noise, so denoising becomes crucial to automated bird sound recognition. Recently, thanks to neural network embeddings, the deep clustering method has achieved better performances than traditional denoising methods, like filter-based methods, due to its ability to solve the problem when noise is in the same frequency range as bird sounds. In this paper, we propose a generalized denoising method based on deep clustering, which can process more complex recordings with less distortion. Also, we optimize the original affinity loss function to get a novel loss function to ensure the embedding vectors with the minimum distance belong to the same source, named Joint Center Loss (JCL), which can both increase the inter-class variance and decrease the intra-class variance of embeddings. Experiments are conducted on the gated convolutional neural network architecture and the bidirectional long short term memory architecture respectively with different loss functions. Given the signal-noise ratio being -3dB, the recognition accuracy increases relatively by 9.5% with the proposed denoising method in the best case, and the Relative Root Mean Square Error (RRMSE) increases relatively by 14.2% by using JCL, compared with the original affinity loss function AL.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115402380","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118600
Jawwad Latif, P. Mehryar, Lei Hou, Ali Zulfiqur
Wireless sensor technology has revolutionised healthcare practices to deal with the increasing number of chronically ill patients. Real-time and continuous monitoring of health parameters can help in early diagnosis and timely treatment. Sensor nodes having limited resources in health monitoring systems are equipped with number of sensors which generates huge amount of data. An increase in data results in an increase in power consumption and memory requirement. An efficient data compression algorithm can be applied to reduce the power consumption and memory requirement. Minimalist, Adaptive and Streaming (MAS) algorithm proposed in literature can reduce significant power consumption during data transmission. In current work, MAS algorithm is further optimised to propose O-MAS-R algorithm by introducing R-bit to take advantage of consecutive repetition of data samples. MAS and O-MAS-R algorithms are applied on Electrocardiography (ECG), Electromyography (EMG) and accelerometer (Acc) datasets to compare the performance in terms of compression ratio (CR). O-MAS-R has shown 7.21 % average increase in CR of ECG datasets, 8.25% increase in EMG datasets and 45.24% increase in Acc datasets as compare to MAS algorithm.
无线传感器技术已经彻底改变了医疗保健实践，以应对越来越多的慢性病患者。实时和持续监测健康参数有助于早期诊断和及时治疗。在健康监测系统中，资源有限的传感器节点配备了大量的传感器，产生了大量的数据。数据量的增加导致功耗和内存需求的增加。采用有效的数据压缩算法可以降低功耗和内存需求。文献中提出的MAS (Minimalist, Adaptive and Streaming)算法可以显著降低数据传输过程中的功耗。在目前的工作中，MAS算法进一步优化，通过引入r位，利用数据样本的连续重复，提出O-MAS-R算法。MAS和O-MAS-R算法应用于心电图(ECG)、肌电图(EMG)和加速度计(Acc)数据集，比较压缩比(CR)方面的性能。与MAS算法相比，O-MAS-R在心电数据集、肌电数据集和Acc数据集上的CR平均提高了7.21%、8.25%和45.24%。
{"title":"An Efficient Data Compression Algorithm For Real-Time Monitoring Applications In Healthcare","authors":"Jawwad Latif, P. Mehryar, Lei Hou, Ali Zulfiqur","doi":"10.1109/ICCCS49078.2020.9118600","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118600","url":null,"abstract":"Wireless sensor technology has revolutionised healthcare practices to deal with the increasing number of chronically ill patients. Real-time and continuous monitoring of health parameters can help in early diagnosis and timely treatment. Sensor nodes having limited resources in health monitoring systems are equipped with number of sensors which generates huge amount of data. An increase in data results in an increase in power consumption and memory requirement. An efficient data compression algorithm can be applied to reduce the power consumption and memory requirement. Minimalist, Adaptive and Streaming (MAS) algorithm proposed in literature can reduce significant power consumption during data transmission. In current work, MAS algorithm is further optimised to propose O-MAS-R algorithm by introducing R-bit to take advantage of consecutive repetition of data samples. MAS and O-MAS-R algorithms are applied on Electrocardiography (ECG), Electromyography (EMG) and accelerometer (Acc) datasets to compare the performance in terms of compression ratio (CR). O-MAS-R has shown 7.21 % average increase in CR of ECG datasets, 8.25% increase in EMG datasets and 45.24% increase in Acc datasets as compare to MAS algorithm.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124189254","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118433
Zhengbo Chen, Liu Xiu, Xing Yafei, Hu Miao, Xiaoming Ju
In order to improve the buffering performance of the data encrypted by CP-ABE (ciphertext policy attribute based encryption), this paper proposed a Markov prefetching model based on attribute classification. The prefetching model combines the access strategy of CP-ABE encrypted file, establishes the user relationship network according to the attribute value of the user, classifies the user by the modularity-based community partitioning algorithm, and establishes a Markov prefetching model based on attribute classification. In comparison with the traditional Markov prefetching model and the classification-based Markov prefetching model, the attribute-based Markov prefetching model is proposed in this paper has higher prefetch accuracy and coverage.
{"title":"Markov Encrypted Data Prefetching Model Based On Attribute Classification","authors":"Zhengbo Chen, Liu Xiu, Xing Yafei, Hu Miao, Xiaoming Ju","doi":"10.1109/ICCCS49078.2020.9118433","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118433","url":null,"abstract":"In order to improve the buffering performance of the data encrypted by CP-ABE (ciphertext policy attribute based encryption), this paper proposed a Markov prefetching model based on attribute classification. The prefetching model combines the access strategy of CP-ABE encrypted file, establishes the user relationship network according to the attribute value of the user, classifies the user by the modularity-based community partitioning algorithm, and establishes a Markov prefetching model based on attribute classification. In comparison with the traditional Markov prefetching model and the classification-based Markov prefetching model, the attribute-based Markov prefetching model is proposed in this paper has higher prefetch accuracy and coverage.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130118239","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：