Pub Date : 2022-08-01DOI: 10.1109/ihmsc55436.2022.00052
Ningning Dai, Xiaoli Zhong
This work investigated the effect of reflections on speech intelligibility (SI) using binaural auralization technology. Firstly, speech reception threshold, which is the subjective indicator of SI, was measured by one-up-one-down adaptive paradigm; then, two objective indicators of SI (inter-aural cross-correlation coefficient and better-ear speech transmission index) were calculated. Consistent results from both subjective and objective indicators show that (1) both early and late reflections are harmful to SI; (2) for short reverberation time, the negative effect of the late reflection on SI is insignificant, while this negative effect gradually becomes obvious with the increase of reverberation time; (3) as to the early reflection, its negative effect on SI is always significant, and increases with the increase of reverberation time.
{"title":"Effect of Reflections on Speech Intelligibility with Different Reverberation Times","authors":"Ningning Dai, Xiaoli Zhong","doi":"10.1109/ihmsc55436.2022.00052","DOIUrl":"https://doi.org/10.1109/ihmsc55436.2022.00052","url":null,"abstract":"This work investigated the effect of reflections on speech intelligibility (SI) using binaural auralization technology. Firstly, speech reception threshold, which is the subjective indicator of SI, was measured by one-up-one-down adaptive paradigm; then, two objective indicators of SI (inter-aural cross-correlation coefficient and better-ear speech transmission index) were calculated. Consistent results from both subjective and objective indicators show that (1) both early and late reflections are harmful to SI; (2) for short reverberation time, the negative effect of the late reflection on SI is insignificant, while this negative effect gradually becomes obvious with the increase of reverberation time; (3) as to the early reflection, its negative effect on SI is always significant, and increases with the increase of reverberation time.","PeriodicalId":447862,"journal":{"name":"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124673723","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 : 2022-08-01DOI: 10.1109/IHMSC55436.2022.00024
Menghan Xu, Jingying Ji, Cheng Fang
Expressions are an important way to communicate human emotional information. In order to address the inadequate capablity of a single convolutional neural network to characterize expressions, a multi-feature expression recognition method based on attention mechanism (AM-FER) is proposed. The method first uses the residual network as the base network to extract features, next uses the attention module to locate useful information and suppress the influence of useless features; then divides the output same-level size features into a stage, constructs a 4-layer feature pyramid network and performs expression prediction separately, and at last fuses the predicted values at the decision layer to obtain the final recognition result. The proposed AM-FER method achieves 73.64% recognition accuracy in the Fer2013 dataset, which is a 3.79% improvement over the original ResNet network, verifying the effectiveness of the algorithm; experiments are conducted for each expression category separately, and there is a significant improvement, with the most significant improvement of 17.4% for the recognition of fear expressions.
{"title":"Multi-Feature Facial Expression Recognition Based on Attention Mechanism","authors":"Menghan Xu, Jingying Ji, Cheng Fang","doi":"10.1109/IHMSC55436.2022.00024","DOIUrl":"https://doi.org/10.1109/IHMSC55436.2022.00024","url":null,"abstract":"Expressions are an important way to communicate human emotional information. In order to address the inadequate capablity of a single convolutional neural network to characterize expressions, a multi-feature expression recognition method based on attention mechanism (AM-FER) is proposed. The method first uses the residual network as the base network to extract features, next uses the attention module to locate useful information and suppress the influence of useless features; then divides the output same-level size features into a stage, constructs a 4-layer feature pyramid network and performs expression prediction separately, and at last fuses the predicted values at the decision layer to obtain the final recognition result. The proposed AM-FER method achieves 73.64% recognition accuracy in the Fer2013 dataset, which is a 3.79% improvement over the original ResNet network, verifying the effectiveness of the algorithm; experiments are conducted for each expression category separately, and there is a significant improvement, with the most significant improvement of 17.4% for the recognition of fear expressions.","PeriodicalId":447862,"journal":{"name":"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126406784","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 : 2022-08-01DOI: 10.1109/IHMSC55436.2022.00041
Yan Li, Ling Sun, Yongchuan Tang, W. You
In graph-based semi-supervised learning, using few samples as supervised information is usually not enough for classification tasks, while more labeled samples are often challenging and time-consuming to obtain. In this study, we use the clustering results as prior knowledge to guide the classification process in graph-based learning. At first, we combine density peaks clustering and label propagation algorithm to obtain the cluster information. Subsequently, the cluster information is transformed into a style factor represented by a symmetric nonnegative matrix. At last, the labels of labeled objects are propagated to others using the style factor as the supervised information. We validate our method in real datasets, and the results show that our method has statistically improved the accuracy of classification.
{"title":"Using cluster information to improve label propagation","authors":"Yan Li, Ling Sun, Yongchuan Tang, W. You","doi":"10.1109/IHMSC55436.2022.00041","DOIUrl":"https://doi.org/10.1109/IHMSC55436.2022.00041","url":null,"abstract":"In graph-based semi-supervised learning, using few samples as supervised information is usually not enough for classification tasks, while more labeled samples are often challenging and time-consuming to obtain. In this study, we use the clustering results as prior knowledge to guide the classification process in graph-based learning. At first, we combine density peaks clustering and label propagation algorithm to obtain the cluster information. Subsequently, the cluster information is transformed into a style factor represented by a symmetric nonnegative matrix. At last, the labels of labeled objects are propagated to others using the style factor as the supervised information. We validate our method in real datasets, and the results show that our method has statistically improved the accuracy of classification.","PeriodicalId":447862,"journal":{"name":"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130188862","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 : 2022-08-01DOI: 10.1109/IHMSC55436.2022.00042
Yan Li, Ling Sun, Yongchuan Tang, W. You
Density peaks clustering (DPC) is a succinct and efficient algorithm to discover the structure of datasets, and it has been used in a number of domains. However, applying DPC to real-world tasks faces two main challenges: how to estimate the appropriate local density in datasets with different density distributions, and how to robustly forms clusters. Substantial researches make efforts to improve DPC from the aspects of these two challenges so as to result in promising clustering results. In this study, at first, we comprehensively review the different types of local density estimation methods and cluster assignment strategies in DPC-related works, then briefly introduce the application of DPC. At last, we discuss potential future research directions of the DPC algorithm.
{"title":"A review of related density peaks clustering approaches","authors":"Yan Li, Ling Sun, Yongchuan Tang, W. You","doi":"10.1109/IHMSC55436.2022.00042","DOIUrl":"https://doi.org/10.1109/IHMSC55436.2022.00042","url":null,"abstract":"Density peaks clustering (DPC) is a succinct and efficient algorithm to discover the structure of datasets, and it has been used in a number of domains. However, applying DPC to real-world tasks faces two main challenges: how to estimate the appropriate local density in datasets with different density distributions, and how to robustly forms clusters. Substantial researches make efforts to improve DPC from the aspects of these two challenges so as to result in promising clustering results. In this study, at first, we comprehensively review the different types of local density estimation methods and cluster assignment strategies in DPC-related works, then briefly introduce the application of DPC. At last, we discuss potential future research directions of the DPC algorithm.","PeriodicalId":447862,"journal":{"name":"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133460352","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 : 2022-08-01DOI: 10.1109/ihmsc55436.2022.00026
Lijuan Han, Sisi Zang, Yiwei Zhao
To overcome the shortcomings of PageRank algorithm that neglects the time factor in author evaluation, a new method for evaluating author's academic influence is proposed. Firstly, the PageRank algorithm is applied to calculate the author's PR value in academic social network to distinguish the author's contribution. Secondly, timePageRank algorithm (abbreviated as T-PR) is given by incorporating the citation time heterogeneity of the author's paper into PageRank algorithm. Finally, the author's literature data in the field of information science is taken as an example to make an empirical analysis. By comparing with PageRank algorithm, it is found that T-PR algorithm can not only identify the core authors in this field, but also distinguish the ranking of authors'influence better, and the evaluation results are more objective and reliable.
{"title":"A method of evaluation index of author’s academic influence based on author Citation Network","authors":"Lijuan Han, Sisi Zang, Yiwei Zhao","doi":"10.1109/ihmsc55436.2022.00026","DOIUrl":"https://doi.org/10.1109/ihmsc55436.2022.00026","url":null,"abstract":"To overcome the shortcomings of PageRank algorithm that neglects the time factor in author evaluation, a new method for evaluating author's academic influence is proposed. Firstly, the PageRank algorithm is applied to calculate the author's PR value in academic social network to distinguish the author's contribution. Secondly, timePageRank algorithm (abbreviated as T-PR) is given by incorporating the citation time heterogeneity of the author's paper into PageRank algorithm. Finally, the author's literature data in the field of information science is taken as an example to make an empirical analysis. By comparing with PageRank algorithm, it is found that T-PR algorithm can not only identify the core authors in this field, but also distinguish the ranking of authors'influence better, and the evaluation results are more objective and reliable.","PeriodicalId":447862,"journal":{"name":"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124431525","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 : 2022-08-01DOI: 10.1109/IHMSC55436.2022.00037
Wendian Zhang, Jiacai Huang
The rapid development of the computer industry greatly promotes the development of the entire computer vision field. The study of camera calibration is a prerequisite for many computer vision technology applications. The calibration of binocular camera is deeply studied,Using the calibration board provided by Halcon and Halcon’s huge library of functions on the Halcon platform. Designing calibration algorithms and working to improve calibration accuracy and speed. And the image is simply corrected using the obtained calibration results.
{"title":"Research on Camera Calibration of Binocular Vision System Based on Halcon","authors":"Wendian Zhang, Jiacai Huang","doi":"10.1109/IHMSC55436.2022.00037","DOIUrl":"https://doi.org/10.1109/IHMSC55436.2022.00037","url":null,"abstract":"The rapid development of the computer industry greatly promotes the development of the entire computer vision field. The study of camera calibration is a prerequisite for many computer vision technology applications. The calibration of binocular camera is deeply studied,Using the calibration board provided by Halcon and Halcon’s huge library of functions on the Halcon platform. Designing calibration algorithms and working to improve calibration accuracy and speed. And the image is simply corrected using the obtained calibration results.","PeriodicalId":447862,"journal":{"name":"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114620379","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 : 2022-08-01DOI: 10.1109/ihmsc55436.2022.00014
J. Xue, Xucheng Hu, Haifeng Chen, Gang Zhou
In view of the insufficient feature extraction that affects the accuracy of photovoltaic forecasting, a photovoltaic power generation power forecasting model is presented, which integrates the Long Short-Time Memory (LSTM) algorithm and the Extreme Gradient Boosting (XGBoost) algorithm. In this paper, the advantages and disadvantages of LSTM algorithm and XGBoost algorithm are analyzed, and the advantages of the two forecasting models are integrated to obtain a more accurate forecasting model, XGBoost-LSTM; and compare the model with the popular Gated Recurrent Unit (GRU) and Deep Belief network, DBN). The experimental results show that the PV power forecasting model based on XGBoost-LSTM integration has higher forecasting accuracy, which has guiding value for photovoltaic grid-connected and off-grid.
{"title":"Research on LSTM-XGBoost Integrated Model of Photovoltaic Power Forecasting System","authors":"J. Xue, Xucheng Hu, Haifeng Chen, Gang Zhou","doi":"10.1109/ihmsc55436.2022.00014","DOIUrl":"https://doi.org/10.1109/ihmsc55436.2022.00014","url":null,"abstract":"In view of the insufficient feature extraction that affects the accuracy of photovoltaic forecasting, a photovoltaic power generation power forecasting model is presented, which integrates the Long Short-Time Memory (LSTM) algorithm and the Extreme Gradient Boosting (XGBoost) algorithm. In this paper, the advantages and disadvantages of LSTM algorithm and XGBoost algorithm are analyzed, and the advantages of the two forecasting models are integrated to obtain a more accurate forecasting model, XGBoost-LSTM; and compare the model with the popular Gated Recurrent Unit (GRU) and Deep Belief network, DBN). The experimental results show that the PV power forecasting model based on XGBoost-LSTM integration has higher forecasting accuracy, which has guiding value for photovoltaic grid-connected and off-grid.","PeriodicalId":447862,"journal":{"name":"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125989483","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}
The power system will be connected to a large scale of photovoltaics, charging equipments, and energy storage devices as a result of the continuous improvement of clean energy production and consumption electrification. Load characteristics and energy forms will change dramatically. The purpose of the paper is researching the path to promote the development of low-carbon transition. Firstly, the model characteristics of the loads on the electricity user-side are analyzed. Secondly, the user-side load cooperative control system is established. Thirdly, three business models of coordinated control are proposed. Finally, the calculation results of a case show that the peak power can be reduced by 21.02%.
{"title":"Researches on Coordinated Control Strategy of Electricity User Side Based on Multi-type Loads","authors":"Yuhang Liu, Liang Zhang, Yunkai Zhang, Suoyu Li, S. Xu, Zhiqiang Zhong","doi":"10.1109/IHMSC55436.2022.00011","DOIUrl":"https://doi.org/10.1109/IHMSC55436.2022.00011","url":null,"abstract":"The power system will be connected to a large scale of photovoltaics, charging equipments, and energy storage devices as a result of the continuous improvement of clean energy production and consumption electrification. Load characteristics and energy forms will change dramatically. The purpose of the paper is researching the path to promote the development of low-carbon transition. Firstly, the model characteristics of the loads on the electricity user-side are analyzed. Secondly, the user-side load cooperative control system is established. Thirdly, three business models of coordinated control are proposed. Finally, the calculation results of a case show that the peak power can be reduced by 21.02%.","PeriodicalId":447862,"journal":{"name":"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126499217","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 : 2022-08-01DOI: 10.1109/IHMSC55436.2022.00031
Han Wang, A. Zhang
Aiming at the problem that the traditional visual simultaneous localization and mapping (SLAM) algorithm is easily affected by moving targets in dynamic environment, which leads to the degradation of system localization accuracy, a visual SLAM algorithm based on object detection and K-Means is proposed for application in dynamic environment. It incorporates the YOLOv5n object detection network with the addition of a leak detection judgment and repair algorithm and the K-means clustering algorithm, which effectively rejects dynamic objects in images and maximizes the retention of static information. Experiments on publicly available datasets show that the error of this paper's method is smaller than that of other SLAM algorithms applied in dynamic environments, and it can guarantee real-time operation.
{"title":"RGB-D SLAM Method Based on Object Detection and K-Means","authors":"Han Wang, A. Zhang","doi":"10.1109/IHMSC55436.2022.00031","DOIUrl":"https://doi.org/10.1109/IHMSC55436.2022.00031","url":null,"abstract":"Aiming at the problem that the traditional visual simultaneous localization and mapping (SLAM) algorithm is easily affected by moving targets in dynamic environment, which leads to the degradation of system localization accuracy, a visual SLAM algorithm based on object detection and K-Means is proposed for application in dynamic environment. It incorporates the YOLOv5n object detection network with the addition of a leak detection judgment and repair algorithm and the K-means clustering algorithm, which effectively rejects dynamic objects in images and maximizes the retention of static information. Experiments on publicly available datasets show that the error of this paper's method is smaller than that of other SLAM algorithms applied in dynamic environments, and it can guarantee real-time operation.","PeriodicalId":447862,"journal":{"name":"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114769966","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 : 2022-08-01DOI: 10.1109/IHMSC55436.2022.00027
Ennan Shi, Defu Bao, yuxiang Yu
To explore the public’s cognitive process of the cultural connotations of urban public art, this paper investigates and analyses the elements of the public’s perception of the cultural connotations of sculpture in Hangzhou scenic areas and the suitability of sculpture in scenic scenes, using principal component analysis. The results suggest a two-factor structure, including information about the public’s cultural association with public art and sensory experience. This study provides theoretical support and design decision recommendations for local cultural considerations of urban public art.
{"title":"Cognitive Exploration of Urban Public Art and Analysis of Design Demands","authors":"Ennan Shi, Defu Bao, yuxiang Yu","doi":"10.1109/IHMSC55436.2022.00027","DOIUrl":"https://doi.org/10.1109/IHMSC55436.2022.00027","url":null,"abstract":"To explore the public’s cognitive process of the cultural connotations of urban public art, this paper investigates and analyses the elements of the public’s perception of the cultural connotations of sculpture in Hangzhou scenic areas and the suitability of sculpture in scenic scenes, using principal component analysis. The results suggest a two-factor structure, including information about the public’s cultural association with public art and sensory experience. This study provides theoretical support and design decision recommendations for local cultural considerations of urban public art.","PeriodicalId":447862,"journal":{"name":"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117258436","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：