To address the problems of existing passenger flow prediction methods such as low accuracy, inadequate learning of spatial features of station topology, and inability to apply to large networks, a SAE-GCN-BiLSTM-based passenger flow forecasting method for urban rail transit is proposed. First, the external features are extracted layer by layer using stacked autoencoder (SAE). Then, graph convolutional network (GCN) is used to capture the spatial features of station topology, and bi-directional long and short-term memory network (BiLSTM) is used to extract the bi-directional temporal features, realizing the extraction of the spatio-temporal features. Finally, external features and spatio-temporal features are fused for accurate prediction of urban rail transit passenger flow. The experimental results show that the proposed method is higher than several other advanced models in the evaluation indexes under different granularities, indicating that the model effectively develops the accuracy and robustness of urban rail transit passenger flow prediction.
{"title":"A Passenger Flow Prediction Method Using SAE-GCN-BiLSTM for Urban Rail Transit","authors":"Fan Liu","doi":"10.4018/ijsir.335100","DOIUrl":"https://doi.org/10.4018/ijsir.335100","url":null,"abstract":"To address the problems of existing passenger flow prediction methods such as low accuracy, inadequate learning of spatial features of station topology, and inability to apply to large networks, a SAE-GCN-BiLSTM-based passenger flow forecasting method for urban rail transit is proposed. First, the external features are extracted layer by layer using stacked autoencoder (SAE). Then, graph convolutional network (GCN) is used to capture the spatial features of station topology, and bi-directional long and short-term memory network (BiLSTM) is used to extract the bi-directional temporal features, realizing the extraction of the spatio-temporal features. Finally, external features and spatio-temporal features are fused for accurate prediction of urban rail transit passenger flow. The experimental results show that the proposed method is higher than several other advanced models in the evaluation indexes under different granularities, indicating that the model effectively develops the accuracy and robustness of urban rail transit passenger flow prediction.","PeriodicalId":44265,"journal":{"name":"International Journal of Swarm Intelligence Research","volume":"79 ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139175873","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}
Jing Liu, Shoubao Su, Haifeng Guo, Yuhua Lu, Yuexia Chen
Magnetic flux leakage (MFL) detection of rail surface defects is an important research field for railway traffic safety. Due to factors such as magnetization and material, it can generate background noise and reduce detection accuracy. To improve the detection signal strength and enhance the detection rate of more minor defects, a signal filtering method based on minimum entropy deconvolution is proposed to denoise. By using the objective function method, the optimal inverse filter parameters are calculated, which are applied to the filtering detection of MFL signals of the rail surface. The detection results show that the peak-to-peak ratio of the defect signal and noise signal detected by this algorithm is 2.01, which is about 1.5 times that of the wavelet transform method and median filtering method. The defect signal is significantly enhanced, and the detection rate of minor defects on the rail surface can be effectively improved.
{"title":"A Signal Filtering Method for Magnetic Flux Leakage Detection of Rail Surface Defects Based on Minimum Entropy Deconvolution","authors":"Jing Liu, Shoubao Su, Haifeng Guo, Yuhua Lu, Yuexia Chen","doi":"10.4018/ijsir.332791","DOIUrl":"https://doi.org/10.4018/ijsir.332791","url":null,"abstract":"Magnetic flux leakage (MFL) detection of rail surface defects is an important research field for railway traffic safety. Due to factors such as magnetization and material, it can generate background noise and reduce detection accuracy. To improve the detection signal strength and enhance the detection rate of more minor defects, a signal filtering method based on minimum entropy deconvolution is proposed to denoise. By using the objective function method, the optimal inverse filter parameters are calculated, which are applied to the filtering detection of MFL signals of the rail surface. The detection results show that the peak-to-peak ratio of the defect signal and noise signal detected by this algorithm is 2.01, which is about 1.5 times that of the wavelet transform method and median filtering method. The defect signal is significantly enhanced, and the detection rate of minor defects on the rail surface can be effectively improved.","PeriodicalId":44265,"journal":{"name":"International Journal of Swarm Intelligence Research","volume":"18 1-2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135168064","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 diagnosis of pulmonary tuberculosis is a complicated process with a long wait. According to the WS 288-2017 standard, PTB can be divided into five types of imaging. To date, no relevant studies on PTB CT images based on the Yolov5 algorithm have been retrieved. To develop an improved strategy YOLOv5, for the classification of PTB lesions based on whole, CT slices were combined with three other modules. CT slices of PTB collected from hospitals were set as training, verification, and external test sets. It is compared with YOLOv5, SSD and RetinaNet neural network methods. The values of precision, recall, MAP, and F1-score of the improved strategy YOLOv5 for the external test were 0.707, 0.716, 0.715, and 0.71. In this study, based on the same dataset, the improved strategy YOLOv5 model has better results than other networks. Our method provides an effective method for the timely detection of PTB.
{"title":"CT Image Detection of Pulmonary Tuberculosis Based on the Improved Strategy YOLOv5","authors":"Jing Liu, Haojie Xie, Mingli Lu, Ye Li, Bing Wang, Zhaogang Sun, Wei He, Limin Wen, Dailun Hou","doi":"10.4018/ijsir.329217","DOIUrl":"https://doi.org/10.4018/ijsir.329217","url":null,"abstract":"The diagnosis of pulmonary tuberculosis is a complicated process with a long wait. According to the WS 288-2017 standard, PTB can be divided into five types of imaging. To date, no relevant studies on PTB CT images based on the Yolov5 algorithm have been retrieved. To develop an improved strategy YOLOv5, for the classification of PTB lesions based on whole, CT slices were combined with three other modules. CT slices of PTB collected from hospitals were set as training, verification, and external test sets. It is compared with YOLOv5, SSD and RetinaNet neural network methods. The values of precision, recall, MAP, and F1-score of the improved strategy YOLOv5 for the external test were 0.707, 0.716, 0.715, and 0.71. In this study, based on the same dataset, the improved strategy YOLOv5 model has better results than other networks. Our method provides an effective method for the timely detection of PTB.","PeriodicalId":44265,"journal":{"name":"International Journal of Swarm Intelligence Research","volume":" ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47185909","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}
Particle swarm optimization (PSO) is one of the popular nature-inspired metaheuristic algorithms. It has been used in different applications. The convergence analysis is among the key theoretical studies in PSO. This paper discusses major contributions in the convergence analysis of PSO. A systematic classification will be used for the review purpose. Possible future works are also highlighted as to investigate the performance of PSO variants to deal with COPs through theoretical perspective and general discussions on experimental results on merits of the proposed approach.
{"title":"A Review on Convergence Analysis of Particle Swarm Optimization","authors":"Dereje Tarekegn, S. Tilahun, Tekle Gemechu","doi":"10.4018/ijsir.328092","DOIUrl":"https://doi.org/10.4018/ijsir.328092","url":null,"abstract":"Particle swarm optimization (PSO) is one of the popular nature-inspired metaheuristic algorithms. It has been used in different applications. The convergence analysis is among the key theoretical studies in PSO. This paper discusses major contributions in the convergence analysis of PSO. A systematic classification will be used for the review purpose. Possible future works are also highlighted as to investigate the performance of PSO variants to deal with COPs through theoretical perspective and general discussions on experimental results on merits of the proposed approach.","PeriodicalId":44265,"journal":{"name":"International Journal of Swarm Intelligence Research","volume":" ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44638364","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}
Robust optimization over time can effectively solve the problem of frequent solution switching in dynamic environments. In order to improve the search performance of dynamic robust optimization algorithm, a dynamic robust particle swarm optimization algorithm based on hybrid strategy (HS-DRPSO) is proposed in this paper. Based on the particle swarm optimization, the HS-DRPSO combines differential evolution algorithm and brainstorms an optimization algorithm to improve the search ability. Moreover, a dynamic selection strategy is employed to realize the selection of different search methods in the proposed algorithm. Compared with the other two dynamic robust optimization algorithms on five dynamic standard test functions, the results show that the overall performance of the proposed algorithm is better than other comparison algorithms.
{"title":"Dynamic Robust Particle Swarm Optimization Algorithm Based on Hybrid Strategy","authors":"Jian Zeng, Xiaoyong Yu, Guoyan Yang, H. Gui","doi":"10.4018/ijsir.325006","DOIUrl":"https://doi.org/10.4018/ijsir.325006","url":null,"abstract":"Robust optimization over time can effectively solve the problem of frequent solution switching in dynamic environments. In order to improve the search performance of dynamic robust optimization algorithm, a dynamic robust particle swarm optimization algorithm based on hybrid strategy (HS-DRPSO) is proposed in this paper. Based on the particle swarm optimization, the HS-DRPSO combines differential evolution algorithm and brainstorms an optimization algorithm to improve the search ability. Moreover, a dynamic selection strategy is employed to realize the selection of different search methods in the proposed algorithm. Compared with the other two dynamic robust optimization algorithms on five dynamic standard test functions, the results show that the overall performance of the proposed algorithm is better than other comparison algorithms.","PeriodicalId":44265,"journal":{"name":"International Journal of Swarm Intelligence Research","volume":" ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48574735","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}
Spatial location features extracted by denoising convolutional neural network. At this time, an attention mechanism is introduced into denoising convolutional neural network. The dual attention model of local area is presented from two dimensions of channel and space—channel attention mechanism weights channel and spatial attention mechanism weights location. A variety of machine learning methods are used to classify and train different features. Multi-semantic features and heterogeneous features are fused by adaptive weighted fusion algorithm. Finally, the data sets Cifar-10, STL-10, Cifar-100 and GHIM-1OK are verified on the proposed method. Compared with a single semantic feature, the accuracy is improved by 10%-15%. Compared with several advanced algorithms, the performance has a significant advantage, which proves the complementarity of heterogeneous features and multi-network semantic features and the effectiveness of the adaptive weighted fusion algorithm.
{"title":"A Multi-Feature Fusion Model Based on Denoising Convolutional Neural Network and Attention Mechanism for Image Classification","authors":"Jingsi Zhang, Xiaosheng Yu, Xiaoliang Lei, Chengdong Wu","doi":"10.4018/ijsir.324074","DOIUrl":"https://doi.org/10.4018/ijsir.324074","url":null,"abstract":"Spatial location features extracted by denoising convolutional neural network. At this time, an attention mechanism is introduced into denoising convolutional neural network. The dual attention model of local area is presented from two dimensions of channel and space—channel attention mechanism weights channel and spatial attention mechanism weights location. A variety of machine learning methods are used to classify and train different features. Multi-semantic features and heterogeneous features are fused by adaptive weighted fusion algorithm. Finally, the data sets Cifar-10, STL-10, Cifar-100 and GHIM-1OK are verified on the proposed method. Compared with a single semantic feature, the accuracy is improved by 10%-15%. Compared with several advanced algorithms, the performance has a significant advantage, which proves the complementarity of heterogeneous features and multi-network semantic features and the effectiveness of the adaptive weighted fusion algorithm.","PeriodicalId":44265,"journal":{"name":"International Journal of Swarm Intelligence Research","volume":" ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42824415","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}
Floor planning is indeed an obvious design process in VLSI physical layout since it specifies the dimensions, structure, as well as positions of components upon the chip; in addition, information regarding the overarching silicon area, interlinks, and latency is also provided. VLSI floor planning is an NP-hard issue as the floor plan representations are a crucial component in this process. The intricacy, as well as solution space of the floor plan layout, is influenced by the floorplan visualizations. To tackle the VLSI floor plan challenge, numerous researchers have developed numerous meta-heuristic optimization techniques. The main objective of this work presents a novel multi-objective hybrid optimization method for solving the floor plan optimization issue. Standard DOX and ALO are conceptually combined in the proposed hybrid optimization referred to as Dingo Updated Ant Lion Optimization (DUALO) model. The multi-objectives like wire length, area, and penalty function are taken into consideration.
{"title":"Very Large-Scale Integration Floor Planning on FIR and Lattice Filters Design With Multi-Objective Hybrid Optimization","authors":"Pushpalatha Pondreti, Babulu Kaparapu","doi":"10.4018/ijsir.321237","DOIUrl":"https://doi.org/10.4018/ijsir.321237","url":null,"abstract":"Floor planning is indeed an obvious design process in VLSI physical layout since it specifies the dimensions, structure, as well as positions of components upon the chip; in addition, information regarding the overarching silicon area, interlinks, and latency is also provided. VLSI floor planning is an NP-hard issue as the floor plan representations are a crucial component in this process. The intricacy, as well as solution space of the floor plan layout, is influenced by the floorplan visualizations. To tackle the VLSI floor plan challenge, numerous researchers have developed numerous meta-heuristic optimization techniques. The main objective of this work presents a novel multi-objective hybrid optimization method for solving the floor plan optimization issue. Standard DOX and ALO are conceptually combined in the proposed hybrid optimization referred to as Dingo Updated Ant Lion Optimization (DUALO) model. The multi-objectives like wire length, area, and penalty function are taken into consideration.","PeriodicalId":44265,"journal":{"name":"International Journal of Swarm Intelligence Research","volume":"1 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41351137","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 electric grid is being increasingly integrated with renewable energy sources whose output is mostly fluctuating in nature. The load demand is also increasing day by day, mainly due to the increased interest in electric vehicles and other automated devices. An energy management system helps in maintaining the balance between the available generation and the load demand and thus optimizes the energy usage. It also helps in reducing the peak load, green-house gas emissions, and the operational cost. Energy management can be performed at different levels and is essential for realizing smart homes, smart buildings, and even smart grid. The different objectives considered for designing energy management systems are reduction of emissions, energy cost, operational cost, peak demand, etc. Many traditional and hybrid nature-inspired algorithms are used for optimizing these various objectives. This paper intends to give an overview about the various nature-inspired algorithms used for optimizing energy management systems in homes, buildings, and micro grid.
{"title":"Nature-Inspired Algorithms for Energy Management Systems","authors":"Meera P. S., Lavanya V.","doi":"10.4018/ijsir.319310","DOIUrl":"https://doi.org/10.4018/ijsir.319310","url":null,"abstract":"The electric grid is being increasingly integrated with renewable energy sources whose output is mostly fluctuating in nature. The load demand is also increasing day by day, mainly due to the increased interest in electric vehicles and other automated devices. An energy management system helps in maintaining the balance between the available generation and the load demand and thus optimizes the energy usage. It also helps in reducing the peak load, green-house gas emissions, and the operational cost. Energy management can be performed at different levels and is essential for realizing smart homes, smart buildings, and even smart grid. The different objectives considered for designing energy management systems are reduction of emissions, energy cost, operational cost, peak demand, etc. Many traditional and hybrid nature-inspired algorithms are used for optimizing these various objectives. This paper intends to give an overview about the various nature-inspired algorithms used for optimizing energy management systems in homes, buildings, and micro grid.","PeriodicalId":44265,"journal":{"name":"International Journal of Swarm Intelligence Research","volume":" ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46465869","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}
Mutation testing is devised for measuring test suite adequacy by identifying the artificially induced faults in software. This paper presents a novel approach by considering multiobjectives-based optimization. Here, the optimal test suite generation is performed using the proposed water cycle water wave optimization (WCWWO). The best test suites are generated by satisfying the multi-objective factors, such as time of execution, test suite size, mutant score, and mutant reduction rate. The WCWWO is devised by a combination of the water cycle algorithm (WCA) and water wave optimization (WWO). The hierarchical attention network (HAN) is used for classifying the equivalent mutants by utilizing the MutPy tool. Furthermore, the performance of the developed WCWWO+HAN is evaluated in terms of three metrics—mutant score (MS), mutant reduction rate (MRR), and fitness—with the maximal MS of 0.585, higher MRR of 0.397, and maximum fitness of 0.652.
{"title":"Multi-Objective Optimization Model and Hierarchical Attention Networks for Mutation Testing","authors":"S. Sugave, Yogesh R. Kulkarni, Balaso","doi":"10.4018/ijsir.319714","DOIUrl":"https://doi.org/10.4018/ijsir.319714","url":null,"abstract":"Mutation testing is devised for measuring test suite adequacy by identifying the artificially induced faults in software. This paper presents a novel approach by considering multiobjectives-based optimization. Here, the optimal test suite generation is performed using the proposed water cycle water wave optimization (WCWWO). The best test suites are generated by satisfying the multi-objective factors, such as time of execution, test suite size, mutant score, and mutant reduction rate. The WCWWO is devised by a combination of the water cycle algorithm (WCA) and water wave optimization (WWO). The hierarchical attention network (HAN) is used for classifying the equivalent mutants by utilizing the MutPy tool. Furthermore, the performance of the developed WCWWO+HAN is evaluated in terms of three metrics—mutant score (MS), mutant reduction rate (MRR), and fitness—with the maximal MS of 0.585, higher MRR of 0.397, and maximum fitness of 0.652.","PeriodicalId":44265,"journal":{"name":"International Journal of Swarm Intelligence Research","volume":" ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47299266","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}
Breast cancer is one of the most common and dangerous cancer types in women worldwide. Since it is generally a genetic disease, microarray technology-based cancer prediction is technically significant among lot of diagnosis methods. The microarray gene expression data contains fewer samples with many redundant and noisy genes. It leads to inaccurate diagnose and low prediction accuracy. To overcome these difficulties, this paper proposes an Improved Whale Optimization Algorithm (IWOA) for wrapper based feature selection in gene expression data. The proposed IWOA incorporates modified cross over and mutation operations to enhance the exploration and exploitation of classical WOA. The proposed IWOA adapts multiobjective fitness function, which simultaneously balance between minimization of error rate and feature selection. The experimental analysis demonstrated that, the proposed IWOA with Gradient Boost Classifier (GBC) achieves high classification accuracy of 97.7% with minimum subset of features and also converges quickly for the breast cancer dataset.
{"title":"Breast Cancer Classification With Microarray Gene Expression Data Based on Improved Whale Optimization Algorithm","authors":"S. Devi, Prithiviraj K.","doi":"10.4018/ijsir.317091","DOIUrl":"https://doi.org/10.4018/ijsir.317091","url":null,"abstract":"Breast cancer is one of the most common and dangerous cancer types in women worldwide. Since it is generally a genetic disease, microarray technology-based cancer prediction is technically significant among lot of diagnosis methods. The microarray gene expression data contains fewer samples with many redundant and noisy genes. It leads to inaccurate diagnose and low prediction accuracy. To overcome these difficulties, this paper proposes an Improved Whale Optimization Algorithm (IWOA) for wrapper based feature selection in gene expression data. The proposed IWOA incorporates modified cross over and mutation operations to enhance the exploration and exploitation of classical WOA. The proposed IWOA adapts multiobjective fitness function, which simultaneously balance between minimization of error rate and feature selection. The experimental analysis demonstrated that, the proposed IWOA with Gradient Boost Classifier (GBC) achieves high classification accuracy of 97.7% with minimum subset of features and also converges quickly for the breast cancer dataset.","PeriodicalId":44265,"journal":{"name":"International Journal of Swarm Intelligence Research","volume":" ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45323520","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：