Financial distress prediction is an important and challenging issue in the financial field. Now, many methods have been proposed to forecast company bankruptcy and financial crisis, and many studies show that artificial intelligence is better than traditional statistical methods in prediction capacity. To overcome the imbalance class, this study employs the MetaCost algorithm to add cost-sensitive classification in the training of base classifiers, then establishes a financial crisis prediction model. In a time series and non-stationary problems, this study proposes a novel time-series financial distress model based on artificial intelligence (including attribute selection and classifiers) to predict the financial distress of a company. All in all, the proposed model has several advantages: (1) utilize the MetaCost algorithm to handle the imbalance class; (2) the proposed model is a seasonal time-series model; (3) employ attribute selection to find the core attributes and reduce data dimension; (4) the research results can be provided to investors and decision makers as reference. At last, the results show that the proposed method is better than the listed classifiers and the MetaCost algorithm is superior to the general classifier method, and the MetaCost method raises a little sensitivity, it lifts to identify the companies’ financial health when the companies are actually healthy; and type II errors are reduced by 21.6%, it denotes that the proposed method can raise the correct classification of financial distress.
{"title":"Entropy-based Time-series Financial Distress Model Based on Attribute Selection and MetaCost Methods for Imbalance Class","authors":"Chia-Pang Chan, Jun-He Yang, Wei-Hsiung Chang","doi":"10.1145/3611450.3611471","DOIUrl":"https://doi.org/10.1145/3611450.3611471","url":null,"abstract":"Financial distress prediction is an important and challenging issue in the financial field. Now, many methods have been proposed to forecast company bankruptcy and financial crisis, and many studies show that artificial intelligence is better than traditional statistical methods in prediction capacity. To overcome the imbalance class, this study employs the MetaCost algorithm to add cost-sensitive classification in the training of base classifiers, then establishes a financial crisis prediction model. In a time series and non-stationary problems, this study proposes a novel time-series financial distress model based on artificial intelligence (including attribute selection and classifiers) to predict the financial distress of a company. All in all, the proposed model has several advantages: (1) utilize the MetaCost algorithm to handle the imbalance class; (2) the proposed model is a seasonal time-series model; (3) employ attribute selection to find the core attributes and reduce data dimension; (4) the research results can be provided to investors and decision makers as reference. At last, the results show that the proposed method is better than the listed classifiers and the MetaCost algorithm is superior to the general classifier method, and the MetaCost method raises a little sensitivity, it lifts to identify the companies’ financial health when the companies are actually healthy; and type II errors are reduced by 21.6%, it denotes that the proposed method can raise the correct classification of financial distress.","PeriodicalId":289906,"journal":{"name":"Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","volume":"27 17","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113984074","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}
For speech anti-spoofing, the ability of countermeasures (CMs) to cope with unseen attacks has been under scrutiny. Since the previous LA attack was mainly for ASV, which required that the spoofed speech be clean enough to be parsed properly by the ASV and that the unseen scenario be limited to the types of synthesis algorithms. With the development of DeepFake, spoofed speech is more often used to spread fake information so that the unseen codecs channel effects needs to be considered. Based on this, we propose a channel-robust spoof detection method based on the wav2vec2.0 and a channel augmentation adversarial (AUG-ADV) strategy. Our method was experimented on the FMFCC-A dataset and achieves the best results with several evaluation metrics.
{"title":"Unseen Codec Spoof Speech Detection Based on Channel-Robust Feature","authors":"Yupeng Zhu, Zuxing Zhao, Fan Li, Yanxiang Chen","doi":"10.1145/3611450.3611452","DOIUrl":"https://doi.org/10.1145/3611450.3611452","url":null,"abstract":"For speech anti-spoofing, the ability of countermeasures (CMs) to cope with unseen attacks has been under scrutiny. Since the previous LA attack was mainly for ASV, which required that the spoofed speech be clean enough to be parsed properly by the ASV and that the unseen scenario be limited to the types of synthesis algorithms. With the development of DeepFake, spoofed speech is more often used to spread fake information so that the unseen codecs channel effects needs to be considered. Based on this, we propose a channel-robust spoof detection method based on the wav2vec2.0 and a channel augmentation adversarial (AUG-ADV) strategy. Our method was experimented on the FMFCC-A dataset and achieves the best results with several evaluation metrics.","PeriodicalId":289906,"journal":{"name":"Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124054077","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}
Enhancing the utilization of computing resources is a crucial technical challenge within the realm of deep learning model deployment and application. It holds significant importance in effectively leveraging various deep learning models. However, when it comes to actual deployment and operation, deep learning models face an urgent task—processing large-scale data. This processing flow is an end-to-end procedure that typically involves three essential steps: preprocessing, model inference, and postprocessing. Presently, existing research mainly focuses on the optimization of deep learning model algorithms, and rarely considers the coordinated utilization of CPU and accelerator resources after model deployment, resulting in low resource utilization and execution efficiency. In order to solve this problem, in this study, we comprehensively analyzed the demand for computing resources and the mutual adaptation relationship between the end-to-end processing flow in the model application and designed a general algorithm based on the pipeline idea to Realize the overlapping of CPU processing and accelerator operation process. Through this scheme, the serial execution flow of the end-to-end processing can be performed in parallel, resulting in a significant reduction in accelerator latency. We extensively conducted experiments on two specific tasks, and the outcomes demonstrated that our proposed method considerably enhances the accelerator’s utilization rate and program execution efficiency. Specifically, the utilization rate of the accelerator surged from 26% to over 97%, while the program’s execution efficiency witnessed a remarkable improvement of 3.41 to 5.54 times.
{"title":"Pipeline-based Optimization Method for Large-Scale End-to-End Inference","authors":"Caili Gao, Y. Dou, P. Qiao","doi":"10.1145/3611450.3611463","DOIUrl":"https://doi.org/10.1145/3611450.3611463","url":null,"abstract":"Enhancing the utilization of computing resources is a crucial technical challenge within the realm of deep learning model deployment and application. It holds significant importance in effectively leveraging various deep learning models. However, when it comes to actual deployment and operation, deep learning models face an urgent task—processing large-scale data. This processing flow is an end-to-end procedure that typically involves three essential steps: preprocessing, model inference, and postprocessing. Presently, existing research mainly focuses on the optimization of deep learning model algorithms, and rarely considers the coordinated utilization of CPU and accelerator resources after model deployment, resulting in low resource utilization and execution efficiency. In order to solve this problem, in this study, we comprehensively analyzed the demand for computing resources and the mutual adaptation relationship between the end-to-end processing flow in the model application and designed a general algorithm based on the pipeline idea to Realize the overlapping of CPU processing and accelerator operation process. Through this scheme, the serial execution flow of the end-to-end processing can be performed in parallel, resulting in a significant reduction in accelerator latency. We extensively conducted experiments on two specific tasks, and the outcomes demonstrated that our proposed method considerably enhances the accelerator’s utilization rate and program execution efficiency. Specifically, the utilization rate of the accelerator surged from 26% to over 97%, while the program’s execution efficiency witnessed a remarkable improvement of 3.41 to 5.54 times.","PeriodicalId":289906,"journal":{"name":"Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125704923","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}
To address the problems of difficulty in determining the truncation distance, single definition of local density and low robustness of non-centroid assignment strategy and chain reaction in density peaking clustering algorithm (DPC), this paper proposes a gravitational clustering algorithm (GMNN) based on mutual K nearest neighbors. The algorithm redefines the similarity metric and local density using the mutual K-nearest neighbor approach. Based on the local gravity model, a two-step clustering strategy is designed to isolate the chain reaction to complete the clustering through the mutual gravity between points and clusters. It is marked by simulation experiments that DG-DPC algorithm is effective for both synthetic dataset and UCI dataset, and the accuracy rate is improved by 31.07%, 45.60%, 50.20%, and 35.5% on average relative to RE-DPC algorithm, DPC algorithm, GAP-DPC algorithm, and DG-DPC algorithm, respectively.
{"title":"Gravitational clustering algorithm based on mutual K-nearest neighbors","authors":"Zhenming Ma, Jiaqi Xu, Ruixi Li, Jinpeng Chen","doi":"10.1145/3611450.3611462","DOIUrl":"https://doi.org/10.1145/3611450.3611462","url":null,"abstract":"To address the problems of difficulty in determining the truncation distance, single definition of local density and low robustness of non-centroid assignment strategy and chain reaction in density peaking clustering algorithm (DPC), this paper proposes a gravitational clustering algorithm (GMNN) based on mutual K nearest neighbors. The algorithm redefines the similarity metric and local density using the mutual K-nearest neighbor approach. Based on the local gravity model, a two-step clustering strategy is designed to isolate the chain reaction to complete the clustering through the mutual gravity between points and clusters. It is marked by simulation experiments that DG-DPC algorithm is effective for both synthetic dataset and UCI dataset, and the accuracy rate is improved by 31.07%, 45.60%, 50.20%, and 35.5% on average relative to RE-DPC algorithm, DPC algorithm, GAP-DPC algorithm, and DG-DPC algorithm, respectively.","PeriodicalId":289906,"journal":{"name":"Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","volume":"255 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126050366","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}
China has made great progress in poverty alleviation in past 40 years. However, older Chinese rural residents, who have been identified as a doubly vulnerable group, still experience much different kinds of deprivations. This study firstly evaluated the multiple deprivations and multidimensional poverty experienced by Chinese rural older people with the Alkire and Foster (AF) measure. It then discusses the poverty alleviation based on big data. It finds that integrated multidimensional poverty declined in four components of deprivation among the aged population, but this trend was limited in a broad sense in terms of the mean poverty intensity and the poverty severity index. Although there was a 6.2 percentage point decrease in poverty incidence, the poverty intensity increased 0.7 percentage points. Deprivations in the financial insecurity, health and loneliness dimensions also increased. Based on big data, this study gives the poverty monitoring and poverty reduction path based. Also, the principles and the data collection paths will be discussed.
在过去的40年里，中国在扶贫方面取得了巨大进展。然而，被认定为双重弱势群体的中国老年农村居民，仍然经历着许多不同形式的剥夺。本研究首次采用Alkire and Foster (AF)测度对中国农村老年人的多重剥夺和多维贫困进行了评价。然后讨论了基于大数据的扶贫。研究发现，老年人口贫困的四个组成部分的综合多维贫困率有所下降，但就平均贫困强度和贫困严重程度指数而言，这种趋势在广义上是有限的。虽然贫困发生率下降了6.2个百分点，但贫困强度却增加了0.7个百分点。在经济不安全、健康和孤独方面的匮乏也有所增加。本研究基于大数据，给出了基于贫困监测和减贫的路径。此外，还将讨论原理和数据收集路径。
{"title":"Evaluating and Alleviating Multidimensional Poverty among Older People in Rural China Based on Big Data","authors":"Yan Zhang, W. Fan, Siyu Pan","doi":"10.1145/3611450.3611466","DOIUrl":"https://doi.org/10.1145/3611450.3611466","url":null,"abstract":"China has made great progress in poverty alleviation in past 40 years. However, older Chinese rural residents, who have been identified as a doubly vulnerable group, still experience much different kinds of deprivations. This study firstly evaluated the multiple deprivations and multidimensional poverty experienced by Chinese rural older people with the Alkire and Foster (AF) measure. It then discusses the poverty alleviation based on big data. It finds that integrated multidimensional poverty declined in four components of deprivation among the aged population, but this trend was limited in a broad sense in terms of the mean poverty intensity and the poverty severity index. Although there was a 6.2 percentage point decrease in poverty incidence, the poverty intensity increased 0.7 percentage points. Deprivations in the financial insecurity, health and loneliness dimensions also increased. Based on big data, this study gives the poverty monitoring and poverty reduction path based. Also, the principles and the data collection paths will be discussed.","PeriodicalId":289906,"journal":{"name":"Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","volume":"103 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131746443","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}
Anomaly detection for network attacks has always been a very important part of intrusion detection. The current research focus is anomaly detection based on deep learning, which has two main problems. One is the lack of a large amount of labeled data in model training, and the other is difficult to detect unknown network attacks or variant attacks. To solve the above problems, an unsupervised anomaly detection model is constructed in this paper. The automatic encoder is used to learn normal traffic characteristics and detect abnormal traffic. Meanwhile, time correlation features and hierarchical clustering algorithm are used for data preprocessing to reduce time and space complexity, so as to further improve the efficiency of model detection. Due to the serious lack of verification data sets for unsupervised anomaly detection, this paper collects and organizes a large amount of data and designs four types of network attack data, including new attack means, worms, system vulnerabilities and botnets. The experimental results showed that the detection accuracy of worms and system vulnerabilities reached 98%, the detection accuracy of botnets reached 89%, and the attacks of the new OriginLogger software were detected.
{"title":"An Unsupervised Network Anomaly Detection Model and Implementation","authors":"Yingdan Zhang, Kun Wen, Xingyu Wang","doi":"10.1145/3611450.3611468","DOIUrl":"https://doi.org/10.1145/3611450.3611468","url":null,"abstract":"Anomaly detection for network attacks has always been a very important part of intrusion detection. The current research focus is anomaly detection based on deep learning, which has two main problems. One is the lack of a large amount of labeled data in model training, and the other is difficult to detect unknown network attacks or variant attacks. To solve the above problems, an unsupervised anomaly detection model is constructed in this paper. The automatic encoder is used to learn normal traffic characteristics and detect abnormal traffic. Meanwhile, time correlation features and hierarchical clustering algorithm are used for data preprocessing to reduce time and space complexity, so as to further improve the efficiency of model detection. Due to the serious lack of verification data sets for unsupervised anomaly detection, this paper collects and organizes a large amount of data and designs four types of network attack data, including new attack means, worms, system vulnerabilities and botnets. The experimental results showed that the detection accuracy of worms and system vulnerabilities reached 98%, the detection accuracy of botnets reached 89%, and the attacks of the new OriginLogger software were detected.","PeriodicalId":289906,"journal":{"name":"Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133769767","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}
Jiale Jiang, K. Zhao, Jiasheng Zhou, X. Cao, Zhuang Yuan
Due to severe signal obstruction, the global navigation satellite system is unable to work indoors. Visible light positioning, as an alternative technology for indoor positioning, has gained widespread attention in recent years due to its low cost and environmental friendliness. Among these, the visible light single anchor positioning method based on light-emitting diode arrays has shown great potential as it can simultaneously provide lighting and positioning. The rise of artificial intelligence has provided new methods for indoor positioning.This article focuses on the single anchor visible light fingerprinting-based positioning technology and uses a multi-layer perceptron-based method to maximize its performance. In addition, in terms of hardware design, we focus on improving the receiver's integration, making it applicable to a wider range of scenarios through size reduction and cost control. Finally, the designed hardware and the proposed method are evaluated in the space range of 320 cm* 560 cm* 270 cm. When compared with the traditional nearest neighbor, k-nearest neighbor, and weighted k-nearest neighbor methods, the experimental results show that the proposed method exhibits significant advantages in performance. The average positioning accuracy in the real scene can reach 34cm.
{"title":"A Single-Anchor Visible Light Positioning System Based on Fingerprinting and Deep Learning","authors":"Jiale Jiang, K. Zhao, Jiasheng Zhou, X. Cao, Zhuang Yuan","doi":"10.1145/3611450.3611475","DOIUrl":"https://doi.org/10.1145/3611450.3611475","url":null,"abstract":"Due to severe signal obstruction, the global navigation satellite system is unable to work indoors. Visible light positioning, as an alternative technology for indoor positioning, has gained widespread attention in recent years due to its low cost and environmental friendliness. Among these, the visible light single anchor positioning method based on light-emitting diode arrays has shown great potential as it can simultaneously provide lighting and positioning. The rise of artificial intelligence has provided new methods for indoor positioning.This article focuses on the single anchor visible light fingerprinting-based positioning technology and uses a multi-layer perceptron-based method to maximize its performance. In addition, in terms of hardware design, we focus on improving the receiver's integration, making it applicable to a wider range of scenarios through size reduction and cost control. Finally, the designed hardware and the proposed method are evaluated in the space range of 320 cm* 560 cm* 270 cm. When compared with the traditional nearest neighbor, k-nearest neighbor, and weighted k-nearest neighbor methods, the experimental results show that the proposed method exhibits significant advantages in performance. The average positioning accuracy in the real scene can reach 34cm.","PeriodicalId":289906,"journal":{"name":"Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134500442","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 conductor is responsible for controlling speed, emotion, instruments, and other musical information in music performances. Using hand gestures, facial expressions, and body movements, the conductor communicates with each member of the band; the conductor primarily uses hand movements to reflect the different beats of different music pieces. In this study, Kinect was used to capture the gestural trajectory of the conductor. Additionally, the three-dimensional spatial data of the obtained motion trajectory were adaptively smoothed. The motion timing data were subsequently segmented, and a dynamic time-warping algorithm was used to match the timing data of the template library with the to-be-classified data.
{"title":"Recognition of Beat-Motion Gestures of Orchestra Conductor using DTW and Nearest Neighbor Method","authors":"Gen-Fang Chen","doi":"10.1145/3611450.3611459","DOIUrl":"https://doi.org/10.1145/3611450.3611459","url":null,"abstract":"The conductor is responsible for controlling speed, emotion, instruments, and other musical information in music performances. Using hand gestures, facial expressions, and body movements, the conductor communicates with each member of the band; the conductor primarily uses hand movements to reflect the different beats of different music pieces. In this study, Kinect was used to capture the gestural trajectory of the conductor. Additionally, the three-dimensional spatial data of the obtained motion trajectory were adaptively smoothed. The motion timing data were subsequently segmented, and a dynamic time-warping algorithm was used to match the timing data of the template library with the to-be-classified data.","PeriodicalId":289906,"journal":{"name":"Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124924898","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}
Abstract: Molecular property prediction is a fundamental research problem in the fields of drug discovery, chemical synthesis prediction. To establish a universal molecular property prediction model, this study proposed six molecular properties prediction models. For capture molecular features, this study combines the representational ability of molecular graphs and the advantage of attention mechanism. Based on three different molecular graph representation of MPNN, DMPNN, dyMPN, to combine two different kinds of deep learning algorithm with the attention mechanism of Transformer and Bert. The results were compared with MPNN and DMPNN. The evaluation indexes of ROC-AUC, RMSE and MAE are applied in this paper. Ten benchmark datasets were used to test the performance of eight models. The results based on the proposed DMPNN combine Bert (DMPNN-Bert) achieves in seven of ten benchmark datasets, which illustrate that the prediction performance of the proposed model.
{"title":"DMPNN-Bert: a deep learning architecture for molecular property prediction","authors":"Mengmeng Fan, Qing Liu, Zeyu Cui, Hao Wang, Mingkai Chen, Dakuo He, Yue Hou","doi":"10.1145/3611450.3611472","DOIUrl":"https://doi.org/10.1145/3611450.3611472","url":null,"abstract":"Abstract: Molecular property prediction is a fundamental research problem in the fields of drug discovery, chemical synthesis prediction. To establish a universal molecular property prediction model, this study proposed six molecular properties prediction models. For capture molecular features, this study combines the representational ability of molecular graphs and the advantage of attention mechanism. Based on three different molecular graph representation of MPNN, DMPNN, dyMPN, to combine two different kinds of deep learning algorithm with the attention mechanism of Transformer and Bert. The results were compared with MPNN and DMPNN. The evaluation indexes of ROC-AUC, RMSE and MAE are applied in this paper. Ten benchmark datasets were used to test the performance of eight models. The results based on the proposed DMPNN combine Bert (DMPNN-Bert) achieves in seven of ten benchmark datasets, which illustrate that the prediction performance of the proposed model.","PeriodicalId":289906,"journal":{"name":"Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131976944","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}
This paper first mathematically models the UAV swarm online cooperative path planning problem based on the prerequisite assumptions of transparent posture and dynamic mission environment. Then the receding horizon control (RHC) and 2D-equal-step path generation method are briefly introduced and combined with the improved firefly optimization algorithm to solve the UAV swarm online cooperative path planning problem modeled in the previous. Simulations show that the improved firefly algorithm combining the RHC and 2D-equal-step path generation methods can be used to optimally solve the UAV swarm online cooperative path planning problem for moving mission targets in dynamic environments, and the improved firefly algorithm is more powerful and more efficient than the original algorithm in this process of application.
{"title":"RHC Method Based 2D-equal-step Path Generation for UAV Swarm Online Cooperative Path Planning in Dynamic Mission Environment","authors":"Yue Shen, Guoliang Fan","doi":"10.1145/3611450.3611451","DOIUrl":"https://doi.org/10.1145/3611450.3611451","url":null,"abstract":"This paper first mathematically models the UAV swarm online cooperative path planning problem based on the prerequisite assumptions of transparent posture and dynamic mission environment. Then the receding horizon control (RHC) and 2D-equal-step path generation method are briefly introduced and combined with the improved firefly optimization algorithm to solve the UAV swarm online cooperative path planning problem modeled in the previous. Simulations show that the improved firefly algorithm combining the RHC and 2D-equal-step path generation methods can be used to optimally solve the UAV swarm online cooperative path planning problem for moving mission targets in dynamic environments, and the improved firefly algorithm is more powerful and more efficient than the original algorithm in this process of application.","PeriodicalId":289906,"journal":{"name":"Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116693711","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：