Pub Date : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645690
Chao Lei, Yehao Wu, Jianhui Zhao
In this paper, a new type of v-shaped corrugated plate solar air heater is proposed by improving the structure of the collector plate and adding a heat storage unit built-in phase change material (PCM). We carry out experimental research combined with engineering examples to analyze and study the thermal performance parameters such as inlet and outlet temperature difference, instantaneous thermal efficiency and energy utilization ratio of the device. The results show that when the mass flow rate is 0.0545 kg/s and 0.0623 kg/s respectively, the average indoor temperature of v-type corrugated plate solar air heater with and without P CM heat storage unit is increased by 6.76, 16.80, 10.20, and 18.5 °C, respectively At the same time, the temperature difference between the inlet and outlet of the v-type corrugated plate solar air heater with P CM heat storage unit is 2.2 and 2.4 °C less than that of the v-type SAH without P CM heat storage unit, and the mass flow rate is 0.0545 kg/s. The V-type corrugated plate solar air heater with a PCM heat storage unit has the highest instantaneous thermal efficiency of 54.00 %. The mass flow rate is 0.0623 kg/s, the v-type corrugated plate solar air heater with a PCM heat storage unit has a maximum energy efficiency of 69.40 % and has a good application prospect.
{"title":"A Study on Thermal Properties of New V Corrugated Panel Solar Air Heater Based on Engineering Examples","authors":"Chao Lei, Yehao Wu, Jianhui Zhao","doi":"10.1109/ECICE52819.2021.9645690","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645690","url":null,"abstract":"In this paper, a new type of v-shaped corrugated plate solar air heater is proposed by improving the structure of the collector plate and adding a heat storage unit built-in phase change material (PCM). We carry out experimental research combined with engineering examples to analyze and study the thermal performance parameters such as inlet and outlet temperature difference, instantaneous thermal efficiency and energy utilization ratio of the device. The results show that when the mass flow rate is 0.0545 kg/s and 0.0623 kg/s respectively, the average indoor temperature of v-type corrugated plate solar air heater with and without P CM heat storage unit is increased by 6.76, 16.80, 10.20, and 18.5 °C, respectively At the same time, the temperature difference between the inlet and outlet of the v-type corrugated plate solar air heater with P CM heat storage unit is 2.2 and 2.4 °C less than that of the v-type SAH without P CM heat storage unit, and the mass flow rate is 0.0545 kg/s. The V-type corrugated plate solar air heater with a PCM heat storage unit has the highest instantaneous thermal efficiency of 54.00 %. The mass flow rate is 0.0623 kg/s, the v-type corrugated plate solar air heater with a PCM heat storage unit has a maximum energy efficiency of 69.40 % and has a good application prospect.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130171995","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645683
Zhenxing Fu, Peijiang Chen
Pedestrian detection is a key part of image processing technology, which needs to accurately identify the pedestrian’s images. How to improve the robustness of the detection algorithm while maintaining high detection efficiency has always been a research topic. This paper first introduces the application of pedestrian detection, then discusses the current research, and introduces the principle of Histogram of Oriented Gradient feature extraction and Support Vector Machine classifier based on a sliding window. This study helps to enhance the contrast of the test image by histogram equalization and then uses multiple training methods to improve the performance of the model. Experiments are carried out by using a self-built training set and test set, and the test results show good results.
{"title":"Research on Optimized Pedestrian Detection Based on Sliding Window","authors":"Zhenxing Fu, Peijiang Chen","doi":"10.1109/ECICE52819.2021.9645683","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645683","url":null,"abstract":"Pedestrian detection is a key part of image processing technology, which needs to accurately identify the pedestrian’s images. How to improve the robustness of the detection algorithm while maintaining high detection efficiency has always been a research topic. This paper first introduces the application of pedestrian detection, then discusses the current research, and introduces the principle of Histogram of Oriented Gradient feature extraction and Support Vector Machine classifier based on a sliding window. This study helps to enhance the contrast of the test image by histogram equalization and then uses multiple training methods to improve the performance of the model. Experiments are carried out by using a self-built training set and test set, and the test results show good results.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129252136","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645651
Chien-Chang Chen, W. Hung
The positioning precisions of X, Y, and Z machine directions are susceptible to temperature variations around machine tools to shift the cutter positioning when the CNC machine tool spindles during high-speed rotation. In this context, the study proposes a modeling method of thermal error compensation for the displacement of the cutter position. In the X-direction, the mechanical structure is closer to symmetrical form, which evenly distributes the thermal energy, so the thermal error is always small. Therefore, this study only deals with the thermal error in the Y and Z directions. The explanatory power improvement of the multiple regression model largely depends on the feature selection. The paper proposes the backward elimination (BE) algorithm base on mean squares of K-fold errors minimization as feature selection of multiple regression model to establish thermal error compensation modeling. Firstly, BE fits the complete model with all features, and then deletes the feature one by one using the selected test criterion until deleting any feature cannot improve the model explanatory power. The K-fold Cross Validation (KCV) evaluates model performance in limited training data and be used as a criterion for model selection. KCV cut the data into K subsets to keep k-1 subsets as model training, and the remaining subsets as model validation. The procedure is repeated k-times until the last subset is set as the validation set, then the average error across all k trials is computed. To evaluate each feature to be eliminated through KCV, the smallest mean squares error is selected from the N results to determine the variable for elimination each time, where N is the number of features. The multiple regression model was established by using the features selected for the Y and Z axes. Test results show that the method can reduce the peak-to-peak value of thermal error from about 55 μm to below 14 μm in the Y direction, and in Z direction is from about 74 μm to below 19 μm.
{"title":"Thermal Error Modeling of CNC Machine Tool Spindle Based on Multiple Regression and Features Selection","authors":"Chien-Chang Chen, W. Hung","doi":"10.1109/ECICE52819.2021.9645651","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645651","url":null,"abstract":"The positioning precisions of X, Y, and Z machine directions are susceptible to temperature variations around machine tools to shift the cutter positioning when the CNC machine tool spindles during high-speed rotation. In this context, the study proposes a modeling method of thermal error compensation for the displacement of the cutter position. In the X-direction, the mechanical structure is closer to symmetrical form, which evenly distributes the thermal energy, so the thermal error is always small. Therefore, this study only deals with the thermal error in the Y and Z directions. The explanatory power improvement of the multiple regression model largely depends on the feature selection. The paper proposes the backward elimination (BE) algorithm base on mean squares of K-fold errors minimization as feature selection of multiple regression model to establish thermal error compensation modeling. Firstly, BE fits the complete model with all features, and then deletes the feature one by one using the selected test criterion until deleting any feature cannot improve the model explanatory power. The K-fold Cross Validation (KCV) evaluates model performance in limited training data and be used as a criterion for model selection. KCV cut the data into K subsets to keep k-1 subsets as model training, and the remaining subsets as model validation. The procedure is repeated k-times until the last subset is set as the validation set, then the average error across all k trials is computed. To evaluate each feature to be eliminated through KCV, the smallest mean squares error is selected from the N results to determine the variable for elimination each time, where N is the number of features. The multiple regression model was established by using the features selected for the Y and Z axes. Test results show that the method can reduce the peak-to-peak value of thermal error from about 55 μm to below 14 μm in the Y direction, and in Z direction is from about 74 μm to below 19 μm.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130512783","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645739
Yeonghyeon Park, M. Kim
The electric motor failure triggers the system paralyzation for various fields such as industry or transportation. Thus, continuous management is necessary. Recently, the automated anomaly detection system is adopted for reducing human exhaustion. Moreover, for improving the cost-effectiveness and monitoring stability, edge device computing is considered on system construction. For enabling edge computing, we need to achieve high performance with a low-complex anomaly detection model, considering the constrained resource. In this paper, we empirically evaluate various anomaly detection architectures from two perspectives for designing a cost-effective model. One of the perspectives is the feature aggregation method and the other one is whether to adopt the bottleneck structure or not for constructing autoencoder. The effectiveness and efficiency are improved by adopting linear feature aggregation and non-bottleneck structured auto-encoder. By combining the above two methods, the computational cost is reduced by 2 in 10k, while losing only 1.972% of the averaged anomaly detection performance.
{"title":"Design of Cost-Effective Auto-Encoder for Electric Motor Anomaly Detection in Resource Constrained Edge Device","authors":"Yeonghyeon Park, M. Kim","doi":"10.1109/ECICE52819.2021.9645739","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645739","url":null,"abstract":"The electric motor failure triggers the system paralyzation for various fields such as industry or transportation. Thus, continuous management is necessary. Recently, the automated anomaly detection system is adopted for reducing human exhaustion. Moreover, for improving the cost-effectiveness and monitoring stability, edge device computing is considered on system construction. For enabling edge computing, we need to achieve high performance with a low-complex anomaly detection model, considering the constrained resource. In this paper, we empirically evaluate various anomaly detection architectures from two perspectives for designing a cost-effective model. One of the perspectives is the feature aggregation method and the other one is whether to adopt the bottleneck structure or not for constructing autoencoder. The effectiveness and efficiency are improved by adopting linear feature aggregation and non-bottleneck structured auto-encoder. By combining the above two methods, the computational cost is reduced by 2 in 10k, while losing only 1.972% of the averaged anomaly detection performance.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"254 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121324980","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645709
C. Yeh
In the author’s another study, the effect of helix length on the performance of a swirl flow tube (SFT) was investigated. In this study, The heat transfer enhancement and the pressure drop were investigated using CFD to obtain an optimal compromise between the temperature uniformity and the pressure drop gain. It was found that a helix length of 40d is an optimal compromise between the temperature uniformity and the pressure drop gain. In this paper, another two important parameters regarding the operation of an SFT, the helix amplitude and the helix pitch are investigated to get a more thorough understanding of the SFT performance. The pressure decreases to a larger extent for a larger helix amplitude and the pressure drop is nearly proportional to the helix amplitude. In addition, the temperature increases with the helix amplitude, and the improvement in temperature uniformity index enhances with increasing helix amplitude. Concerning the influence of the helix pitch, the pressure decreases to a larger extent for a smaller helix pitch and the pressure drop is nearly inversely proportional to the helix pitch. The temperature decreases with the helix pitch and the improvement in temperature uniformity index are enhanced by decreasing the helix pitch.
{"title":"Effect of Helix Amplitude and Helix Pitch on the Performance of a Swirl Flow Tube","authors":"C. Yeh","doi":"10.1109/ECICE52819.2021.9645709","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645709","url":null,"abstract":"In the author’s another study, the effect of helix length on the performance of a swirl flow tube (SFT) was investigated. In this study, The heat transfer enhancement and the pressure drop were investigated using CFD to obtain an optimal compromise between the temperature uniformity and the pressure drop gain. It was found that a helix length of 40d is an optimal compromise between the temperature uniformity and the pressure drop gain. In this paper, another two important parameters regarding the operation of an SFT, the helix amplitude and the helix pitch are investigated to get a more thorough understanding of the SFT performance. The pressure decreases to a larger extent for a larger helix amplitude and the pressure drop is nearly proportional to the helix amplitude. In addition, the temperature increases with the helix amplitude, and the improvement in temperature uniformity index enhances with increasing helix amplitude. Concerning the influence of the helix pitch, the pressure decreases to a larger extent for a smaller helix pitch and the pressure drop is nearly inversely proportional to the helix pitch. The temperature decreases with the helix pitch and the improvement in temperature uniformity index are enhanced by decreasing the helix pitch.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121669702","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645627
Aiqing Guo, Qin Wang
SOFM neural network algorithm adopts an unsupervised clustering algorithm, which can map the cluster center generated after calculation to a surface or plane, which makes the topology of the network have high stability. The GA algorithm completes the operation process through three operators: selection, crossover, and mutation. It has good global optimization and robustness. In this paper, the SOFM algorithm is improved by a GA algorithm and a hybrid GA- SOFM neural network algorithm is established. The algorithm is applied to the quality evaluation system. According to the results of the MATLAB simulation experiment, the evaluation accuracy and absolute error are determined and compared with the previous optimal GA-RBF hybrid algorithm model. The results show that the average evaluation accuracy of the proposed algorithm model evaluation is 89.43%, and its absolute error is 0.017. It shows that the quality evaluation model based on a hybrid GA-SOFM neural network can effectively and accurately evaluate quality.
{"title":"Application of Hybrid GA-SOFM Neural Network in Quality Evaluation of English Teaching","authors":"Aiqing Guo, Qin Wang","doi":"10.1109/ECICE52819.2021.9645627","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645627","url":null,"abstract":"SOFM neural network algorithm adopts an unsupervised clustering algorithm, which can map the cluster center generated after calculation to a surface or plane, which makes the topology of the network have high stability. The GA algorithm completes the operation process through three operators: selection, crossover, and mutation. It has good global optimization and robustness. In this paper, the SOFM algorithm is improved by a GA algorithm and a hybrid GA- SOFM neural network algorithm is established. The algorithm is applied to the quality evaluation system. According to the results of the MATLAB simulation experiment, the evaluation accuracy and absolute error are determined and compared with the previous optimal GA-RBF hybrid algorithm model. The results show that the average evaluation accuracy of the proposed algorithm model evaluation is 89.43%, and its absolute error is 0.017. It shows that the quality evaluation model based on a hybrid GA-SOFM neural network can effectively and accurately evaluate quality.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122499493","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645678
X. Cui, Guifen. Chen
This paper presents an improved ant colony optimization for vehicular ad-hoc network routing. The algorithm can quickly find the route with optimal network connectivity. Assuming that each vehicle has a digital map composed of intersections and streets, using the information contained in the data packet called ant, the vehicle can calculate the weight of each street, which is proportional to the network connection of the road section. The ant is launched by the vehicle in the intersection area. In order to find the best route between the source and destination, the source vehicle determines the best route on the street map with the minimum distance of the complete route. The performance is evaluated in the simulation environment. The simulation results show that compared with the VACO using ant algorithm, when the speed reaches 70 km/h, the transmission rate of data packets is increased by more than 10%. In addition, the routing control overhead and end-to-end delay of the proposed protocol are also reduced.
{"title":"Application of Improved Ant Colony Optimization in Vehicular Ad-hoc Network Routing","authors":"X. Cui, Guifen. Chen","doi":"10.1109/ECICE52819.2021.9645678","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645678","url":null,"abstract":"This paper presents an improved ant colony optimization for vehicular ad-hoc network routing. The algorithm can quickly find the route with optimal network connectivity. Assuming that each vehicle has a digital map composed of intersections and streets, using the information contained in the data packet called ant, the vehicle can calculate the weight of each street, which is proportional to the network connection of the road section. The ant is launched by the vehicle in the intersection area. In order to find the best route between the source and destination, the source vehicle determines the best route on the street map with the minimum distance of the complete route. The performance is evaluated in the simulation environment. The simulation results show that compared with the VACO using ant algorithm, when the speed reaches 70 km/h, the transmission rate of data packets is increased by more than 10%. In addition, the routing control overhead and end-to-end delay of the proposed protocol are also reduced.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115511957","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645644
Kirill Kononov, Roman Lavrenov, T. Tsoy, E. Martínez-García, E. Magid
Precise robot localization is important for all mobile robots, which has to deal with accumulating odometry errors, onboard sensory noise, harsh environmental conditions, unstable or missing GPS signal, and absence or uncertainties of a global map. Yet, localization is considered in Smart Environments applying dynamic connectivity with external local sensors within the Internet of Things (IoT) paradigm. This paper presents experimental results of robot indoor localization using a single external smart RGB-D camera. The virtual experiments were performed in the ROS Gazebo simulator with Turtlebot3 Waffle Pi mobile robot model. Three types of robot motion within a virtual office environment were considered: static state, linear motion, and three different cases of curvilinear locomotion. In all cases, external RGB-D camera usage allowed to obtain a reasonably accurate location of the robot.
{"title":"Virtual Experiments on Mobile Robot Localization with External Smart RGB-D Camera Using ROS","authors":"Kirill Kononov, Roman Lavrenov, T. Tsoy, E. Martínez-García, E. Magid","doi":"10.1109/ECICE52819.2021.9645644","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645644","url":null,"abstract":"Precise robot localization is important for all mobile robots, which has to deal with accumulating odometry errors, onboard sensory noise, harsh environmental conditions, unstable or missing GPS signal, and absence or uncertainties of a global map. Yet, localization is considered in Smart Environments applying dynamic connectivity with external local sensors within the Internet of Things (IoT) paradigm. This paper presents experimental results of robot indoor localization using a single external smart RGB-D camera. The virtual experiments were performed in the ROS Gazebo simulator with Turtlebot3 Waffle Pi mobile robot model. Three types of robot motion within a virtual office environment were considered: static state, linear motion, and three different cases of curvilinear locomotion. In all cases, external RGB-D camera usage allowed to obtain a reasonably accurate location of the robot.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132347431","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645664
Jing Li, Yao Wang
The deep learning network simulates the human neural system and its nonlinear hierarchical characteristics, extracts the nonlinear features of the information layer by layer and processes them comprehensively. This is suitable for various evaluation models. The excitation level time-frequency spectrum is used to establish the convolution neural network (CNN) evaluation model. In this paper, the excitation is smoothed in time-domain by using filter first, then the mapping relationship between the global subjective evaluation result and the time sequence smooth excitation is constructed by CNN. The overall comprehensive CNN evaluation model was established based on the time sequence smooth excitation. The time series smoothing excitation CNN model has better performance in the evaluation than the ordinary CNN model and improves the prediction accuracy (the mean error is reduced by 8.64 %), stability (the error variance is reduced by 31.97 %) and consistency (the Pearson correlation coefficient is increased by 2.48 %).
{"title":"Application of Time-series Smoothed Excitation CNN Model","authors":"Jing Li, Yao Wang","doi":"10.1109/ECICE52819.2021.9645664","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645664","url":null,"abstract":"The deep learning network simulates the human neural system and its nonlinear hierarchical characteristics, extracts the nonlinear features of the information layer by layer and processes them comprehensively. This is suitable for various evaluation models. The excitation level time-frequency spectrum is used to establish the convolution neural network (CNN) evaluation model. In this paper, the excitation is smoothed in time-domain by using filter first, then the mapping relationship between the global subjective evaluation result and the time sequence smooth excitation is constructed by CNN. The overall comprehensive CNN evaluation model was established based on the time sequence smooth excitation. The time series smoothing excitation CNN model has better performance in the evaluation than the ordinary CNN model and improves the prediction accuracy (the mean error is reduced by 8.64 %), stability (the error variance is reduced by 31.97 %) and consistency (the Pearson correlation coefficient is increased by 2.48 %).","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114329116","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645741
Yih-Chuan Lin, Ci-Fong Lin, Kevin Chen
This paper presents an approach to improve the cybersecurity of Modbus protocol in industrial control systems by the security proxy strategy, which helps Modbus used in SCADA systems be more capable of dealing with malicious intrusion threats from external networks to the SCADA environment. On designing the security control scheme, there is one critical requirement taken into consideration for minimally changing the original configuration of SCADA systems. To validate the feasibility of the proposed security proxy approach, techniques for protecting the privacy and integrity of Modbus protocol messages are implemented in the proxy functions. Advanced encryption system (AES) is adopted by the proxy function to encrypt the messages before transmitting to prevent commands or data from being interpreted easily. In addition, the hash function is employed to generate an authentication token to make sure the received message is the same as the sender sent. The extra processing delay time required for each Modbus message after passing through the proxy functions is treated as the important factor for the success of the proposed approach in SCADA systems. Based on the experiments with replay and man-in-the-middle (MITM) attacks, satisfactory results are obtained, demonstrating the usefulness of applying the proposed security approach to network-based SCADA systems.
{"title":"Security Enhancement of Industrial Modbus Message Transmission with Proxy Approach","authors":"Yih-Chuan Lin, Ci-Fong Lin, Kevin Chen","doi":"10.1109/ECICE52819.2021.9645741","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645741","url":null,"abstract":"This paper presents an approach to improve the cybersecurity of Modbus protocol in industrial control systems by the security proxy strategy, which helps Modbus used in SCADA systems be more capable of dealing with malicious intrusion threats from external networks to the SCADA environment. On designing the security control scheme, there is one critical requirement taken into consideration for minimally changing the original configuration of SCADA systems. To validate the feasibility of the proposed security proxy approach, techniques for protecting the privacy and integrity of Modbus protocol messages are implemented in the proxy functions. Advanced encryption system (AES) is adopted by the proxy function to encrypt the messages before transmitting to prevent commands or data from being interpreted easily. In addition, the hash function is employed to generate an authentication token to make sure the received message is the same as the sender sent. The extra processing delay time required for each Modbus message after passing through the proxy functions is treated as the important factor for the success of the proposed approach in SCADA systems. Based on the experiments with replay and man-in-the-middle (MITM) attacks, satisfactory results are obtained, demonstrating the usefulness of applying the proposed security approach to network-based SCADA systems.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115450473","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：