Pub Date : 2022-06-01DOI: 10.46300/9106.2022.16.124
Deepika Lokesh, N. V. U. Reddy
Target tracking is the greatest important applications in Wireless Sensor Networks (WSNs). The wireless sensor network applications have been increasing since the IoT has been established. Most of the applications have various kind of sensors to transmit the information from one source to another. The basic operation of a wireless sensor network is to sense the data, collect the data and transmit the data from time to time whenever the base station requires the data for evaluation. Improving the reliability, performance for the collection of the data is the main role of the wireless sensor device. Moreover, the objective of the wireless sensor network device is to minimize the latency and improve the energy efficiency in order to provide more reliability is a major performance metric for provisioning WSNs. In this paper, we have presented an Energy Efficient Low Latency Routing (EELLR) design for Target Tracking (TT) Applications of Wireless Sensor Network. This model provides reliability and has a better performance in terms of communication overhead, energy efficiency and packet processing latency reduction when compared with the existing routing-based models.
{"title":"Energy Efficient Low Latency Routing Design for Target Tracking Applications of Wireless Sensor Network","authors":"Deepika Lokesh, N. V. U. Reddy","doi":"10.46300/9106.2022.16.124","DOIUrl":"https://doi.org/10.46300/9106.2022.16.124","url":null,"abstract":"Target tracking is the greatest important applications in Wireless Sensor Networks (WSNs). The wireless sensor network applications have been increasing since the IoT has been established. Most of the applications have various kind of sensors to transmit the information from one source to another. The basic operation of a wireless sensor network is to sense the data, collect the data and transmit the data from time to time whenever the base station requires the data for evaluation. Improving the reliability, performance for the collection of the data is the main role of the wireless sensor device. Moreover, the objective of the wireless sensor network device is to minimize the latency and improve the energy efficiency in order to provide more reliability is a major performance metric for provisioning WSNs. In this paper, we have presented an Energy Efficient Low Latency Routing (EELLR) design for Target Tracking (TT) Applications of Wireless Sensor Network. This model provides reliability and has a better performance in terms of communication overhead, energy efficiency and packet processing latency reduction when compared with the existing routing-based models.","PeriodicalId":13929,"journal":{"name":"International Journal of Circuits, Systems and Signal Processing","volume":"64 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80902484","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 : 2022-06-01DOI: 10.18178/ijsps.10.2.7-13
P. Shrivastava, B. Abe
Abstract —With the growing complexity of communication systems, there is an increasing scope for antenna arrays with multi-beam capability for ultra-high broadband, inter-satellite links and inter-spacecraft communications. High data rate demands increased bandwidth requirements, the frequency of operation is increasing to the 60/70/80/90 GHz bands. These frequency bands are applicable to last-mile technologies for inter-satellite links and inter-spacecraft communications with data rates as high as 10 Gbit/s and even beyond. For these applications it is of paramount importance to develop planar technologies that can apply to millimeter-wave (MmW) frequencies with highly integrated system approach including smart antennas. This paper lays a robust foundation for MmW based smart antenna designs, its issues related to radio propagation and applications for inter-satellite links and inter-spacecraft communications. The intermediate and long-term objectives will create a unique and systematic understanding of the proposed innovative antenna array technology and its beamforming
{"title":"Millimeter-Wave Antenna Circuitry for Inter-Satellite Communications at 60 GHz","authors":"P. Shrivastava, B. Abe","doi":"10.18178/ijsps.10.2.7-13","DOIUrl":"https://doi.org/10.18178/ijsps.10.2.7-13","url":null,"abstract":" Abstract —With the growing complexity of communication systems, there is an increasing scope for antenna arrays with multi-beam capability for ultra-high broadband, inter-satellite links and inter-spacecraft communications. High data rate demands increased bandwidth requirements, the frequency of operation is increasing to the 60/70/80/90 GHz bands. These frequency bands are applicable to last-mile technologies for inter-satellite links and inter-spacecraft communications with data rates as high as 10 Gbit/s and even beyond. For these applications it is of paramount importance to develop planar technologies that can apply to millimeter-wave (MmW) frequencies with highly integrated system approach including smart antennas. This paper lays a robust foundation for MmW based smart antenna designs, its issues related to radio propagation and applications for inter-satellite links and inter-spacecraft communications. The intermediate and long-term objectives will create a unique and systematic understanding of the proposed innovative antenna array technology and its beamforming","PeriodicalId":13929,"journal":{"name":"International Journal of Circuits, Systems and Signal Processing","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75448863","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 : 2022-06-01DOI: 10.46300/9106.2022.16.125
Takuto ,, Nakamura, T. Hirata, Eko Setiawan, I. Hodaka
This paper proposes a practical method for estimating mutual inductance in wireless power transmission system based on the principle of electromagnetic induction. Conventional estimation methods utilize a voltage, current, and phase of current in transmitter side, while our method requires only an amplitude of the voltage and current in transmitter side. Our method is designed so that the mutual inductance can be estimated under challenging situation which there is a measurement noise. Numerical simulations show that if the system has a small mutual inductance, a relative error and standard derivation of estimated mutual inductance tend to become larger. However, it will be shown that these factors can be improved to make a voltage of voltage source in the system high.
{"title":"A Practical Method for Estimating Mutual Inductance in Wireless Power Transmission System","authors":"Takuto ,, Nakamura, T. Hirata, Eko Setiawan, I. Hodaka","doi":"10.46300/9106.2022.16.125","DOIUrl":"https://doi.org/10.46300/9106.2022.16.125","url":null,"abstract":"This paper proposes a practical method for estimating mutual inductance in wireless power transmission system based on the principle of electromagnetic induction. Conventional estimation methods utilize a voltage, current, and phase of current in transmitter side, while our method requires only an amplitude of the voltage and current in transmitter side. Our method is designed so that the mutual inductance can be estimated under challenging situation which there is a measurement noise. Numerical simulations show that if the system has a small mutual inductance, a relative error and standard derivation of estimated mutual inductance tend to become larger. However, it will be shown that these factors can be improved to make a voltage of voltage source in the system high.","PeriodicalId":13929,"journal":{"name":"International Journal of Circuits, Systems and Signal Processing","volume":"52 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79819377","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 : 2022-05-30DOI: 10.46300/9106.2022.16.120
Mangesh Islampurkar, Kishanprasad G. Gunale, Sunil Somani, Nikhil Bagade
In an electronics circuit, the presence of a Fault leads to undesired or unexpected results. The output of many nodes on the circuit is changed due to the presence of the Fault at one node. So, it is necessary to detect the nature of the Fault present in a particular faulty node. To detect the fault present in the digital circuit, it is necessary to understand logical behavior using mathematical modeling. After the successful modeling, parameters are extracted, and the database is generated. The mathematical model uses Hebbian Artificial Neural Network algorithms [1] [2]. The database generated is used by the fault detection system to find the masked and multiple faults. A fault detection system monitors the faults present in the test circuit and finds the origin and nature of the Fault [3] [4]. The database generated for single stuck-at faults is used to find the multiple faults present in the faulty circuit. In this paper, Modified Vedic Multiplication [5] [4] method is used to optimize the utilization of the proposed system. In this proposed design multiplier of {N x N} bit input and {N} bit output is used, due to which device utilization is decreased, which is the expected outcome from the design. This system is designed using ISE Design Suite and implemented on Spartan-6 FPGA [6] [7].
在电子电路中，故障的存在会导致不希望的或意想不到的结果。电路中许多节点的输出由于一个节点的故障而改变。因此，有必要检测特定故障节点中存在的故障的性质。为了检测数字电路中存在的故障，有必要使用数学建模来理解逻辑行为。建模成功后，提取参数，生成数据库。数学模型采用Hebbian人工神经网络算法[1][2]。生成的数据库用于故障检测系统查找被屏蔽故障和多故障。故障检测系统对测试电路中存在的故障进行监测，找出故障的来源和性质[3][4]。单个卡死故障生成的数据库用于查找故障电路中存在的多个故障。本文采用修正吠陀乘法[5][4]方法对所提出的系统进行优化利用。在这个建议的设计中，使用了{N x N}位输入和{N}位输出的乘法器，由于这降低了设备利用率，这是设计的预期结果。本系统采用ISE Design Suite设计，在Spartan-6 FPGA上实现[6][7]。
{"title":"Multiple Stuck At Fault Diagnosis System For Digital Circuit On FPGA Using Vedic Multiplier and ANN","authors":"Mangesh Islampurkar, Kishanprasad G. Gunale, Sunil Somani, Nikhil Bagade","doi":"10.46300/9106.2022.16.120","DOIUrl":"https://doi.org/10.46300/9106.2022.16.120","url":null,"abstract":"In an electronics circuit, the presence of a Fault leads to undesired or unexpected results. The output of many nodes on the circuit is changed due to the presence of the Fault at one node. So, it is necessary to detect the nature of the Fault present in a particular faulty node. To detect the fault present in the digital circuit, it is necessary to understand logical behavior using mathematical modeling. After the successful modeling, parameters are extracted, and the database is generated. The mathematical model uses Hebbian Artificial Neural Network algorithms [1] [2]. The database generated is used by the fault detection system to find the masked and multiple faults. A fault detection system monitors the faults present in the test circuit and finds the origin and nature of the Fault [3] [4]. The database generated for single stuck-at faults is used to find the multiple faults present in the faulty circuit. In this paper, Modified Vedic Multiplication [5] [4] method is used to optimize the utilization of the proposed system. In this proposed design multiplier of {N x N} bit input and {N} bit output is used, due to which device utilization is decreased, which is the expected outcome from the design. This system is designed using ISE Design Suite and implemented on Spartan-6 FPGA [6] [7].","PeriodicalId":13929,"journal":{"name":"International Journal of Circuits, Systems and Signal Processing","volume":"263 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84028742","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 : 2022-05-30DOI: 10.46300/9106.2022.16.121
M. Iskandarani
A new approach to wireless sensor network (WSN) communication through multi-hop routing is investigated in this work. The proposed approach utilizes search radius expansion in order to find highest energy nodes within a WSN network and preserves the energy of the lowest energy nodes. This approach which is built on trust in terms of providing good quality communication channels between a source node and a destination node considers energy as one parameter of trust that will enable strong, reliable communication channels and shorter routes to be used in a WSN. This approach enables efficient energy consumption during data communication, but with higher level energy consumption due to expanded search radius, which can be minimized using search time limit. The work also relates through mathematical equations, number of discovered routes, maximum hops, and search time to the considered search radius. The overall objective of this work is to enable faster and efficient channel communication between WSN nodes, through gradual cost effective search in neighborhoods. This is achieved by uncovering shorter and less number of routes within an acceptable time limits. The proposed and simulated approach presented in this work differ in terms of the gradual expansion of search and the equal increments in search radius compared to other used techniques. The presented work also adds a unique feature of allowing re-charging of low energy nodes using the already established routes connecting high energy nodes through the registration of weak nodes locations. A final general expression relates search radius to other WSN variables is also presented.
{"title":"Connectivity Analysis of WSN Nodes using Neighborhood Search Technique (WSNNST)","authors":"M. Iskandarani","doi":"10.46300/9106.2022.16.121","DOIUrl":"https://doi.org/10.46300/9106.2022.16.121","url":null,"abstract":"A new approach to wireless sensor network (WSN) communication through multi-hop routing is investigated in this work. The proposed approach utilizes search radius expansion in order to find highest energy nodes within a WSN network and preserves the energy of the lowest energy nodes. This approach which is built on trust in terms of providing good quality communication channels between a source node and a destination node considers energy as one parameter of trust that will enable strong, reliable communication channels and shorter routes to be used in a WSN. This approach enables efficient energy consumption during data communication, but with higher level energy consumption due to expanded search radius, which can be minimized using search time limit. The work also relates through mathematical equations, number of discovered routes, maximum hops, and search time to the considered search radius. The overall objective of this work is to enable faster and efficient channel communication between WSN nodes, through gradual cost effective search in neighborhoods. This is achieved by uncovering shorter and less number of routes within an acceptable time limits. The proposed and simulated approach presented in this work differ in terms of the gradual expansion of search and the equal increments in search radius compared to other used techniques. The presented work also adds a unique feature of allowing re-charging of low energy nodes using the already established routes connecting high energy nodes through the registration of weak nodes locations. A final general expression relates search radius to other WSN variables is also presented.","PeriodicalId":13929,"journal":{"name":"International Journal of Circuits, Systems and Signal Processing","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85170198","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 : 2022-05-30DOI: 10.46300/9106.2022.16.122
Atsushi Wada, S. Yoshizawa
This paper presents a three dimensional localization method for underwater acoustic positioning systems. In typical ultra-short baseline (USBL) acoustic positioning systems, the three dimensional position is localized by using multiple time difference of arrivals (TDOAs). Since the TDOA accuracy is less than the other sensor data, we focus on a localization method with the minimum number of TDOA. We propose a method of transmitting depth data by pulse position modulation (PPM), where the target position is localized by a single TDOA, a distance, and a depth. The proposed method shows a higher positional accuracy than the conventional method with two TDOAs. The effectiveness of the proposed method has been demonstrated in the evaluation of simulation and experiment.
{"title":"Transmission of Depth Data by Pulse Position Modulation for Underwater Acoustic Positioning Systems","authors":"Atsushi Wada, S. Yoshizawa","doi":"10.46300/9106.2022.16.122","DOIUrl":"https://doi.org/10.46300/9106.2022.16.122","url":null,"abstract":"This paper presents a three dimensional localization method for underwater acoustic positioning systems. In typical ultra-short baseline (USBL) acoustic positioning systems, the three dimensional position is localized by using multiple time difference of arrivals (TDOAs). Since the TDOA accuracy is less than the other sensor data, we focus on a localization method with the minimum number of TDOA. We propose a method of transmitting depth data by pulse position modulation (PPM), where the target position is localized by a single TDOA, a distance, and a depth. The proposed method shows a higher positional accuracy than the conventional method with two TDOAs. The effectiveness of the proposed method has been demonstrated in the evaluation of simulation and experiment.","PeriodicalId":13929,"journal":{"name":"International Journal of Circuits, Systems and Signal Processing","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88378967","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 : 2022-04-14DOI: 10.46300/9106.2022.16.119
M. Meena, Shreya Pare, Priti Singh, A. Rana, M. Prasad
Face recognition has achieved more attention in computer vision with the focus on modelling the expression variations of human. However, in computer vision system, face recognition is a challenging task, due to variation in expressions, poses, and lighting conditions. This paper proposes a facial recognition technique based on 2D Hybrid Markov Model (2D HMM), Cat Swam Optimization (CSO), Local Directional Pattern (LDP), and Tetrolet Transform. Skin segmentation method is used for pre-processing followed by filtering to extract the region of interest. Resultant image is fed to proposed feature extraction method comprising of Tetrolet Transform and LDP. Extracted features are classified using proposed classifier “CSO trained 2D-HMM classification method”. To prove the superiority of method, four face datasets are used, and comparative results are presented. Quantitively results are measured by False Acceptance Rate (FAR), False Rejection Rate (FRR) and Accuracy and the values are 0.0025, 0.0035 and 99.65% respectively
{"title":"A Robust Illumination and Intensity invariant Face Recognition System","authors":"M. Meena, Shreya Pare, Priti Singh, A. Rana, M. Prasad","doi":"10.46300/9106.2022.16.119","DOIUrl":"https://doi.org/10.46300/9106.2022.16.119","url":null,"abstract":"Face recognition has achieved more attention in computer vision with the focus on modelling the expression variations of human. However, in computer vision system, face recognition is a challenging task, due to variation in expressions, poses, and lighting conditions. This paper proposes a facial recognition technique based on 2D Hybrid Markov Model (2D HMM), Cat Swam Optimization (CSO), Local Directional Pattern (LDP), and Tetrolet Transform. Skin segmentation method is used for pre-processing followed by filtering to extract the region of interest. Resultant image is fed to proposed feature extraction method comprising of Tetrolet Transform and LDP. Extracted features are classified using proposed classifier “CSO trained 2D-HMM classification method”. To prove the superiority of method, four face datasets are used, and comparative results are presented. Quantitively results are measured by False Acceptance Rate (FAR), False Rejection Rate (FRR) and Accuracy and the values are 0.0025, 0.0035 and 99.65% respectively","PeriodicalId":13929,"journal":{"name":"International Journal of Circuits, Systems and Signal Processing","volume":"28 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76470771","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 : 2022-04-06DOI: 10.46300/9106.2022.16.118
Zaynab Hjouji, M. M’hamdi
We present in this paper a new approach for predicting creditworthiness of borrowers that we call “Method of splitting the learning set into two region”. The aim of this approach consists on the construction of two regions from a learning set, the first called "Solvency Region" that contains the feature vectors of the elements that have paid their financial obligations on time and the second one called "Non-Solvency Region", which contains the feature vectors of the elements that have defaulted in paying their debts. Therefore, to predict creditworthiness borrowers, it is sufficient to identify which of the two regions includes his feature vectors; if it doesn’t correspond to any region, the credit decision-making requires further analysis. To develop and test our predictive proposed approach, a large set of real and recent credit data obtained from the UCI repository is used, we trained also on a real credit database from a Moroccan bank and the creditworthiness of borrowers are analyzed using two performance measurement indicators such as Classification accuracy and the AUC of the ROC curve as a robustness measurement criteria. The proposed model was compared to three traditional machine-learning algorithms: LR, RBF-NN and the MLP-NN. The experimental results show the improved performance of our proposed predictive method for predicting creditworthiness of borrowers.
{"title":"A New Predictive Machine-learning Approach for Detecting Creditworthiness of Borrowers","authors":"Zaynab Hjouji, M. M’hamdi","doi":"10.46300/9106.2022.16.118","DOIUrl":"https://doi.org/10.46300/9106.2022.16.118","url":null,"abstract":"We present in this paper a new approach for predicting creditworthiness of borrowers that we call “Method of splitting the learning set into two region”. The aim of this approach consists on the construction of two regions from a learning set, the first called \"Solvency Region\" that contains the feature vectors of the elements that have paid their financial obligations on time and the second one called \"Non-Solvency Region\", which contains the feature vectors of the elements that have defaulted in paying their debts. Therefore, to predict creditworthiness borrowers, it is sufficient to identify which of the two regions includes his feature vectors; if it doesn’t correspond to any region, the credit decision-making requires further analysis. To develop and test our predictive proposed approach, a large set of real and recent credit data obtained from the UCI repository is used, we trained also on a real credit database from a Moroccan bank and the creditworthiness of borrowers are analyzed using two performance measurement indicators such as Classification accuracy and the AUC of the ROC curve as a robustness measurement criteria. The proposed model was compared to three traditional machine-learning algorithms: LR, RBF-NN and the MLP-NN. The experimental results show the improved performance of our proposed predictive method for predicting creditworthiness of borrowers.","PeriodicalId":13929,"journal":{"name":"International Journal of Circuits, Systems and Signal Processing","volume":"71 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73661763","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 : 2022-03-30DOI: 10.46300/9106.2022.16.115
A. Stoynova, B. Bonev
This paper examines the impact of post-processing of lock-in thermographic measurement data on the ability to detect and characterize in terms of geometric dimensions and location of specific types of defects in MCM-L. A thermal 3D model of a test specimen with hidden artificial defects is used and simulated lock-in thermography measurement is performed. Qualitative and quantitative assessment was performed of the correct detection and geometric dimensions characterization of the defects. The Shape Difference (SD) criteria was defined and used for qualitative and quantitative assessment of the confidence detection and characterization of defects in MCM-L. A Window Sliding Offset (WSO) approach is performed as method for improvement of the defects characterization quality. This study revel that providing information on the depth and shape of defects through the combined use of infrared thermography measurement and 3D thermal modeling can be used to determine the desired confidence levels of defects detection.
{"title":"Post-processing Improvement of Lock-in Thermography Study of MCM-L for Better Hidden Defect Localization","authors":"A. Stoynova, B. Bonev","doi":"10.46300/9106.2022.16.115","DOIUrl":"https://doi.org/10.46300/9106.2022.16.115","url":null,"abstract":"This paper examines the impact of post-processing of lock-in thermographic measurement data on the ability to detect and characterize in terms of geometric dimensions and location of specific types of defects in MCM-L. A thermal 3D model of a test specimen with hidden artificial defects is used and simulated lock-in thermography measurement is performed. Qualitative and quantitative assessment was performed of the correct detection and geometric dimensions characterization of the defects. The Shape Difference (SD) criteria was defined and used for qualitative and quantitative assessment of the confidence detection and characterization of defects in MCM-L. A Window Sliding Offset (WSO) approach is performed as method for improvement of the defects characterization quality. This study revel that providing information on the depth and shape of defects through the combined use of infrared thermography measurement and 3D thermal modeling can be used to determine the desired confidence levels of defects detection.","PeriodicalId":13929,"journal":{"name":"International Journal of Circuits, Systems and Signal Processing","volume":"79 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85752939","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 : 2022-03-30DOI: 10.46300/9106.2022.16.117
Xiao Yang
Speech recognition is an important research field in natural language processing. In Chinese and English, which have rich data resources, the performance of end-to-end speech recognition model is close to that of Hidden Markov Model—Deep Neural Network (HMM-DNN) model. However, for the low resource speech recognition task of Chinese English hybrid, the end-to-end speech recognition system does not achieve good performance. In the case of limited mixed data between Chinese and English, the modeling method of end-to-end speech recognition is studied. This paper focuses on two end-to-end speech recognition models: connection timing distribution and attention based codec network. In order to improve the performance of Chinese English hybrid speech recognition, this paper studies how to improve the performance of the coder based on connection timing distribution model and attention mechanism, and tries to combine the two models to improve the performance of Chinese English hybrid speech recognition. In low resource Chinese English mixed data, the advantages of different models are used to improve the performance of end-to-end models, so as to improve the recognition accuracy of speech recognition technology in legal Chinese English simultaneous interpretation.
{"title":"Application of Speech Recognition Technology in Chinese English Simultaneous Interpretation of Law","authors":"Xiao Yang","doi":"10.46300/9106.2022.16.117","DOIUrl":"https://doi.org/10.46300/9106.2022.16.117","url":null,"abstract":"Speech recognition is an important research field in natural language processing. In Chinese and English, which have rich data resources, the performance of end-to-end speech recognition model is close to that of Hidden Markov Model—Deep Neural Network (HMM-DNN) model. However, for the low resource speech recognition task of Chinese English hybrid, the end-to-end speech recognition system does not achieve good performance. In the case of limited mixed data between Chinese and English, the modeling method of end-to-end speech recognition is studied. This paper focuses on two end-to-end speech recognition models: connection timing distribution and attention based codec network. In order to improve the performance of Chinese English hybrid speech recognition, this paper studies how to improve the performance of the coder based on connection timing distribution model and attention mechanism, and tries to combine the two models to improve the performance of Chinese English hybrid speech recognition. In low resource Chinese English mixed data, the advantages of different models are used to improve the performance of end-to-end models, so as to improve the recognition accuracy of speech recognition technology in legal Chinese English simultaneous interpretation.","PeriodicalId":13929,"journal":{"name":"International Journal of Circuits, Systems and Signal Processing","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81859803","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：