This paper proposed a chemical substance detection method using the Long Short-Term Memory of Recurrent Neural Networks (LSTM-RNN). The chemical substance data was collected using a mass spectrometer which is a time-series data. The classification accuracy using the LSTM-RNN classifier is 96.84%, which is higher than 75.07% of the ordinary feed forward neural networks. The experimental results show that the LSTM-RNN can learn the properties of the chemical substance dataset and achieve a high detection accuracy.
{"title":"Chemical substance classification using long short-term memory recurrent neural network","authors":"Jinlei Zhang, Junxiu Liu, Yuling Luo, Qiang Fu, Jinjie Bi, Senhui Qiu, Yi Cao, Xuemei Ding","doi":"10.1109/ICCT.2017.8359978","DOIUrl":"https://doi.org/10.1109/ICCT.2017.8359978","url":null,"abstract":"This paper proposed a chemical substance detection method using the Long Short-Term Memory of Recurrent Neural Networks (LSTM-RNN). The chemical substance data was collected using a mass spectrometer which is a time-series data. The classification accuracy using the LSTM-RNN classifier is 96.84%, which is higher than 75.07% of the ordinary feed forward neural networks. The experimental results show that the LSTM-RNN can learn the properties of the chemical substance dataset and achieve a high detection accuracy.","PeriodicalId":199874,"journal":{"name":"2017 IEEE 17th International Conference on Communication Technology (ICCT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121338579","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 : 2017-10-01DOI: 10.1109/ICCT.2017.8359819
Chenyu Yang, N. Yang, Yongbin Yu, Yifan Li, F. Díez
A model to introduce memristive components into the high pass filter (HPF) is highlighted in this paper. Based on the Memristor and Memcapacitor, a novel HPF circuit which is rarely researched before, is provided. In light of the first-order RC-HPF and the Memristor-Capacitor-HPF, a new Memristor-Memcapacitor-HPF is designed. By studying its transfer function, amplitude-frequency response and phase-frequency response, a time-varying model is verified. Finally, simulation results demonstrate our theoretical analysis. Furthermore, memristive elements can be extended to the other filter circuits.
{"title":"A new memristor and memcapacitor-based high pass filter","authors":"Chenyu Yang, N. Yang, Yongbin Yu, Yifan Li, F. Díez","doi":"10.1109/ICCT.2017.8359819","DOIUrl":"https://doi.org/10.1109/ICCT.2017.8359819","url":null,"abstract":"A model to introduce memristive components into the high pass filter (HPF) is highlighted in this paper. Based on the Memristor and Memcapacitor, a novel HPF circuit which is rarely researched before, is provided. In light of the first-order RC-HPF and the Memristor-Capacitor-HPF, a new Memristor-Memcapacitor-HPF is designed. By studying its transfer function, amplitude-frequency response and phase-frequency response, a time-varying model is verified. Finally, simulation results demonstrate our theoretical analysis. Furthermore, memristive elements can be extended to the other filter circuits.","PeriodicalId":199874,"journal":{"name":"2017 IEEE 17th International Conference on Communication Technology (ICCT)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124287870","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 : 2017-10-01DOI: 10.1109/ICCT.2017.8359782
Dan Zhao, Tan Yang, Yuehui Jin, Yue Xu
With the shortcoming of long network delay and long response time, traditional mobile cloud computing can't meet the need of delay sensitive business, such as Virtual Reality and Augmented Reality. Mobile edge computing has emerged and provided a way to solve the problems. During the movement of the user, if an optimal data center is detected, the virtual machine migrates from the current data center to the optimal one. It is important to note that virtual machine migration increases costs while enhancing the user's experience. How to balance costs and benefits is what we need to focus on. The core issue of the migration strategy is whether, when, and where to migrate. In this paper, we propose an edge computing migration strategy based on multiple attribute decision making to deal with the issue. Furthermore, we demonstrate the effectiveness of the migration strategy by simulation.
{"title":"A service migration strategy based on multiple attribute decision in mobile edge computing","authors":"Dan Zhao, Tan Yang, Yuehui Jin, Yue Xu","doi":"10.1109/ICCT.2017.8359782","DOIUrl":"https://doi.org/10.1109/ICCT.2017.8359782","url":null,"abstract":"With the shortcoming of long network delay and long response time, traditional mobile cloud computing can't meet the need of delay sensitive business, such as Virtual Reality and Augmented Reality. Mobile edge computing has emerged and provided a way to solve the problems. During the movement of the user, if an optimal data center is detected, the virtual machine migrates from the current data center to the optimal one. It is important to note that virtual machine migration increases costs while enhancing the user's experience. How to balance costs and benefits is what we need to focus on. The core issue of the migration strategy is whether, when, and where to migrate. In this paper, we propose an edge computing migration strategy based on multiple attribute decision making to deal with the issue. Furthermore, we demonstrate the effectiveness of the migration strategy by simulation.","PeriodicalId":199874,"journal":{"name":"2017 IEEE 17th International Conference on Communication Technology (ICCT)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117233349","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 : 2017-10-01DOI: 10.1109/ICCT.2017.8359620
Baoxian Yu, Shutao Zhang, X. Dai, Han Zhang
Spectrally efficient frequency division multiplexing (SEFDM) can offer a spectral gain in comparison with OFDM. This paper considers the framework for coded SEFDM systems with iterative decoding. We show that with block interleaving and channel coding, sequential errors in SEFDM are effectively reduced, and in turn, the decoded data can be used as feedback at the receiver to recover the orthogonality between sub-carriers. With the complementary advantages of channel coding and block interleaving, the feedback of the iterations converges within only 2–3 iterations. Simulation results show that the proposed SEFDM with iterative decoding can offer an indistinguishable performance as that of coded OFDM, while achieving a higher spectral efficiency of up to 20%.
{"title":"Iterative decoder for coded SEFDM systems","authors":"Baoxian Yu, Shutao Zhang, X. Dai, Han Zhang","doi":"10.1109/ICCT.2017.8359620","DOIUrl":"https://doi.org/10.1109/ICCT.2017.8359620","url":null,"abstract":"Spectrally efficient frequency division multiplexing (SEFDM) can offer a spectral gain in comparison with OFDM. This paper considers the framework for coded SEFDM systems with iterative decoding. We show that with block interleaving and channel coding, sequential errors in SEFDM are effectively reduced, and in turn, the decoded data can be used as feedback at the receiver to recover the orthogonality between sub-carriers. With the complementary advantages of channel coding and block interleaving, the feedback of the iterations converges within only 2–3 iterations. Simulation results show that the proposed SEFDM with iterative decoding can offer an indistinguishable performance as that of coded OFDM, while achieving a higher spectral efficiency of up to 20%.","PeriodicalId":199874,"journal":{"name":"2017 IEEE 17th International Conference on Communication Technology (ICCT)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125006572","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 : 2017-10-01DOI: 10.1109/ICCT.2017.8359943
Chen Changwei, Qin Kaiyu
A two-dimensional (2D) weighted nonlinear two-box (2D-WNTB) model is proposed for concurrent dual-band power amplifiers (PAs) with strong nonlinearity. The proposed model is composed of two cascaded blocks of mildly nonlinearity order of dynamic part and highly nonlinearity static part with weighted polynomial. In comparison with the previous models, the proposed model can reduce the computation complexity of the linearization with high modeling accuracy. Measurements were carried out for a deep biased class-AB PA. The results prove the effectiveness of the 2D-WNTB model.
{"title":"2D weighted twin nonlinear two-box model for concurrent dual-band power amplifiers","authors":"Chen Changwei, Qin Kaiyu","doi":"10.1109/ICCT.2017.8359943","DOIUrl":"https://doi.org/10.1109/ICCT.2017.8359943","url":null,"abstract":"A two-dimensional (2D) weighted nonlinear two-box (2D-WNTB) model is proposed for concurrent dual-band power amplifiers (PAs) with strong nonlinearity. The proposed model is composed of two cascaded blocks of mildly nonlinearity order of dynamic part and highly nonlinearity static part with weighted polynomial. In comparison with the previous models, the proposed model can reduce the computation complexity of the linearization with high modeling accuracy. Measurements were carried out for a deep biased class-AB PA. The results prove the effectiveness of the 2D-WNTB model.","PeriodicalId":199874,"journal":{"name":"2017 IEEE 17th International Conference on Communication Technology (ICCT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125133400","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 : 2017-10-01DOI: 10.1109/ICCT.2017.8359865
Xiangrui Fan, Wenlong Cai, Jinyong Lin
The development and utilization of near space is making communication one of the most important design problems for flying nodes in it. Communication architecture based on infrastructure restricts the capability of the flying network systems. Ad Hoc networking among flying nodes named Flying Ad Hoc Network (FANET) can solve the problems raised from a fully infrastructure based network. However, because of the high mobility of the nodes, network segmentation, intermittent links, resource constraints and changes in QoS requirements, routing has become one of the most challenging issues for FANET. In this paper, we collected the existing protocols for FANET, and then introduced the main challenges of FANET routing protocol design. Open research issues were also discussed.
{"title":"A survey of routing protocols for highly dynamic mobile ad hoc networks","authors":"Xiangrui Fan, Wenlong Cai, Jinyong Lin","doi":"10.1109/ICCT.2017.8359865","DOIUrl":"https://doi.org/10.1109/ICCT.2017.8359865","url":null,"abstract":"The development and utilization of near space is making communication one of the most important design problems for flying nodes in it. Communication architecture based on infrastructure restricts the capability of the flying network systems. Ad Hoc networking among flying nodes named Flying Ad Hoc Network (FANET) can solve the problems raised from a fully infrastructure based network. However, because of the high mobility of the nodes, network segmentation, intermittent links, resource constraints and changes in QoS requirements, routing has become one of the most challenging issues for FANET. In this paper, we collected the existing protocols for FANET, and then introduced the main challenges of FANET routing protocol design. Open research issues were also discussed.","PeriodicalId":199874,"journal":{"name":"2017 IEEE 17th International Conference on Communication Technology (ICCT)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126048436","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 : 2017-10-01DOI: 10.1109/ICCT.2017.8359773
Peng Geng, Yan Liu, Jie Yang
Research on connectivity and coverage under the premise of ensuring the network lifetime is one of the basic problems for wireless sensor networks. The CDS-based topology construction algorithms A3 and A3Cov are well-known strategies to save energy and extend the lifetime of wireless sensor networks. By setting the time and energy thresholds in the topology maintenance phase, this paper analyzes the performances of Time-based A3, Time-based A3Cov, Energy-based A3 and Energy-based A3Cov from the aspects of lifetime and sensing coverage. Simulation results show that Energy-based A3Cov performs best before 10000 time units. But it does not perform well in the later stages of the lifetime. So we apply the network coding technology in the Energy-based A3Cov algorithm, and then a new algorithm named Energy-based NCA3Cov is proposed. In which different buffers are set for one-hop nodes (from sink), two-hop nodes (from sink), and important nodes (the node degree is greater than average degree). Information is forwarded only when the buffer is full. Simulation results show that the NCA3Cov is able to find better topologies than the A3Cov algorithm, and extending the network lifetime.
{"title":"A CDS-based topology control algorithm for ensuring area coverage and lifetime in wireless sensor networks","authors":"Peng Geng, Yan Liu, Jie Yang","doi":"10.1109/ICCT.2017.8359773","DOIUrl":"https://doi.org/10.1109/ICCT.2017.8359773","url":null,"abstract":"Research on connectivity and coverage under the premise of ensuring the network lifetime is one of the basic problems for wireless sensor networks. The CDS-based topology construction algorithms A3 and A3Cov are well-known strategies to save energy and extend the lifetime of wireless sensor networks. By setting the time and energy thresholds in the topology maintenance phase, this paper analyzes the performances of Time-based A3, Time-based A3Cov, Energy-based A3 and Energy-based A3Cov from the aspects of lifetime and sensing coverage. Simulation results show that Energy-based A3Cov performs best before 10000 time units. But it does not perform well in the later stages of the lifetime. So we apply the network coding technology in the Energy-based A3Cov algorithm, and then a new algorithm named Energy-based NCA3Cov is proposed. In which different buffers are set for one-hop nodes (from sink), two-hop nodes (from sink), and important nodes (the node degree is greater than average degree). Information is forwarded only when the buffer is full. Simulation results show that the NCA3Cov is able to find better topologies than the A3Cov algorithm, and extending the network lifetime.","PeriodicalId":199874,"journal":{"name":"2017 IEEE 17th International Conference on Communication Technology (ICCT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123595543","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 : 2017-10-01DOI: 10.1109/ICCT.2017.8359764
Xu Zhaoye, Lu Ruimin
In cognitive radio network, the primary user (PU) network and the secondary user (SU) network interfered with each other because of sharing the spectral resource. Also interference among multi-downlinks in SU network decreased the sum rate in SU network and the eavesdropper in PU network decreased the secrecy rate in PU network. Focusing on above problem, this paper raised two channel selection and beamforming methods based on singular value decomposition (SVD) and uplink-downlink duality respectively, and then analyzed the performance of them in physical layer security.
{"title":"Physical layer security transmission in cognitive radio network composed of multi-downlinks SU network","authors":"Xu Zhaoye, Lu Ruimin","doi":"10.1109/ICCT.2017.8359764","DOIUrl":"https://doi.org/10.1109/ICCT.2017.8359764","url":null,"abstract":"In cognitive radio network, the primary user (PU) network and the secondary user (SU) network interfered with each other because of sharing the spectral resource. Also interference among multi-downlinks in SU network decreased the sum rate in SU network and the eavesdropper in PU network decreased the secrecy rate in PU network. Focusing on above problem, this paper raised two channel selection and beamforming methods based on singular value decomposition (SVD) and uplink-downlink duality respectively, and then analyzed the performance of them in physical layer security.","PeriodicalId":199874,"journal":{"name":"2017 IEEE 17th International Conference on Communication Technology (ICCT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125432383","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 : 2017-10-01DOI: 10.1109/ICCT.2017.8359796
Bin Wang, Xin Song
With the development of technology and the increase of people's demand, there are more and more intelligent requirements for radar. Intelligent radar should be more flexible, and transmits different waveforms according to different working conditions. In this paper, after analysis of point target echo, we propose an improved ambiguity function for uniform coherent pulse train signal (UCPTS), which can obtain more flexible waveform. In simulations, time frequency characteristics and ambiguity characteristics of the proposed waveform design method are provided. Simulations results demonstrate that the novel waveform design method for uniform coherent pulse train signal has good range and velocity resolution. Finally, a summary of the paper is presented.
{"title":"A novel waveform design method based on improved ambiguity function","authors":"Bin Wang, Xin Song","doi":"10.1109/ICCT.2017.8359796","DOIUrl":"https://doi.org/10.1109/ICCT.2017.8359796","url":null,"abstract":"With the development of technology and the increase of people's demand, there are more and more intelligent requirements for radar. Intelligent radar should be more flexible, and transmits different waveforms according to different working conditions. In this paper, after analysis of point target echo, we propose an improved ambiguity function for uniform coherent pulse train signal (UCPTS), which can obtain more flexible waveform. In simulations, time frequency characteristics and ambiguity characteristics of the proposed waveform design method are provided. Simulations results demonstrate that the novel waveform design method for uniform coherent pulse train signal has good range and velocity resolution. Finally, a summary of the paper is presented.","PeriodicalId":199874,"journal":{"name":"2017 IEEE 17th International Conference on Communication Technology (ICCT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125522632","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 : 2017-10-01DOI: 10.1109/ICCT.2017.8359820
Z. Zhiyuan, Liang Shengli
When measuring a non-insertable device using a vector network analyzer, calibration based on eight-term error model such as TRL or SOLR is commonly used. The VNA is in the form of a single reference receiver, and the signals of the two reference receivers cannot be measured simultaneously during calibration. In this paper, we propose a method based on different error models transformation to calculate the switching error terms and realize the eight-term error model calibration of single reference receiver VNAs.
{"title":"Calibration of a single reference receiver VNAs for non-insertable devices test","authors":"Z. Zhiyuan, Liang Shengli","doi":"10.1109/ICCT.2017.8359820","DOIUrl":"https://doi.org/10.1109/ICCT.2017.8359820","url":null,"abstract":"When measuring a non-insertable device using a vector network analyzer, calibration based on eight-term error model such as TRL or SOLR is commonly used. The VNA is in the form of a single reference receiver, and the signals of the two reference receivers cannot be measured simultaneously during calibration. In this paper, we propose a method based on different error models transformation to calculate the switching error terms and realize the eight-term error model calibration of single reference receiver VNAs.","PeriodicalId":199874,"journal":{"name":"2017 IEEE 17th International Conference on Communication Technology (ICCT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115248085","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：