Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence最新文献

{"title":"Enhanced Human-Machine Interactive Learning for Multimodal Emotion Recognition in Dialogue System","authors":"C. Leung, James J. Deng, Yuanxi Li","doi":"10.1145/3579654.3579764","DOIUrl":"https://doi.org/10.1145/3579654.3579764","url":null,"abstract":"Emotion recognition has been well researched in mono-modality in the past decade. However, people express their emotion or feelings naturally via more than one modalities like voice, facial expressions, text, and behaviors. In this paper, we propose a new method to model deep interactive learning and dual modalities (e.g., speech and text) to conduct multimodal emotion recognition. An unsupervised triplet-loss objective function is constructed to learn representation of emotional information from speech audio. We extract text emotional feature representation by transfer learning of text-to-text embedding from T5 pre-trained model. Human-machine interaction like user feedback plays a vital role in improve multimodal emotion recognition in dialogue system. Deep interactive learning model is constructed by explicit and implicit feedback. Human-machine interactive learning enhanced transformer model can achieve higher levels of accuracy and precision than their non-interactive counterparts.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130653931","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}

{"title":"Fuzzy Enhanced Artificial Potential Field-based Mobile Car Path Planning","authors":"Xiaojie Tang, Chengfen Jia, Yao Liu","doi":"10.1145/3579654.3579742","DOIUrl":"https://doi.org/10.1145/3579654.3579742","url":null,"abstract":"A significant area of study in the field of autonomous driving technology is path planning. Artificial potential field approach is a popular technique to analyze local path planning, however, its conventional algorithm suffers the flaws of local optimal and unachievable goals. In this study, the artificial potential field method's repulsive force field expression is enhanced, and the fuzzy control method is integrated with the artificial potential field method. Through the design of two fuzzy controllers, the driving deflection angle and driving speed are controlled in real time, which helps the mobile car to overcome the defects of the conventional artificial potential field method in some typical position relationships, travel more safely and smoothly to its destination, and create efficient path planning. The Matlab simulation results demonstrate the improved algorithm's ability to address the issues of an unreachable objective and a local optimum in a few common path planning places, and also shows advantages in obstacle avoidance safety.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130955685","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}

{"title":"State of charge estimation for lithium battery based on Levenberg-marquardt back-propagation neural network with momentum term","authors":"Jing Wen, Guangxu Zhou, Changqing Sun, Dairong Hu, Hao Wang, Yunhai Zhu","doi":"10.1145/3579654.3579696","DOIUrl":"https://doi.org/10.1145/3579654.3579696","url":null,"abstract":"Abstract: State of charge (SOC) can reflect the residual charge of the battery, which helps the driver of a new energy vehicle to infer the battery endurance, playing a significant role. However, when using back-propagation(BP) neural network to estimate SOC, the results have some problems such as slow convergence. In this paper, the momentum term is introduced into the Levenberg-Marquardt back-propagation (LM-BP) neural network structure for the prediction of lithium battery SOC. To be specific, a momentum term with fixed momentum factor is added to the LM algorithm to replace the gradient descent method used in the standard BP neural network. The improved weight correction formula is used to update the weight to obtain a higher convergence speed of the network, and the neural network structure with double hidden layers is utilized to improve the prediction accuracy. It can be seen from the results that the mean absolute error of the proposed method is reduced by 1.422% compared with the standard BP algorithm, and the estimation performance is significantly improved.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122500302","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}

{"title":"A method for accelerating relations search over big data scenario","authors":"Lihua Liu, Mao Wang, Kaiming Xiao, Haiwen Chen","doi":"10.1145/3579654.3579686","DOIUrl":"https://doi.org/10.1145/3579654.3579686","url":null,"abstract":"We propose an acceleration method for relations search over big data scenario. The relations search is in essence an induced subgraph search of graph data model, which is to search all edges with all adjacent vertices falling into a given vertex set. For example, in the risk-control scenario for anti-fraud, for a swindling gang of highly similar fraud behaviors, figuring out all relations between these swindlers can be greatly beneficial to precisely attack all similar gangs. In-memory induced subgraph search requires lots of random accesses, while in big data scenario, relations data tend to be stored on disk when the memory is limited, and the corresponding random lookups over disk incorporate huge overhead. Also, even a singleton disk access could be costly since there are usually many properties data in a relation. Hence, existing methods would suffer considerable performance bottlenecks when applied over data on disk. We build graph over disk-based edge index, and propose multiple BFS (Bread First Search) level gaps based induces subgraph acceleration method, with efficient performance guarantee when the memory is limited. We avoid imbalance in performance for query evaluation with edge index based data organization, with which we further reduce redundant I/O accesses. We filter most invalid no-result edge queries based our BFS level gaps framework. We find that, for each BFS, we can confirm the no edge status between a pair of vertices if their BFS accessing level are of distance more than 1, which indicates the nonexistence of edge. Extensive experiments over real world graph datasets confirm the effectiveness of our method. We find that more than 97% invalid edge queries are filtered by our method, which greatly improve the system performance. Hence, our method with multiple BFS level gap encoding over vertices could greatly filter no-result edge queries and improve the relation search performance. Out method also reduce the redundant I/O access over disk with performance stability guarantee.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"371 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115948465","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}

{"title":"Dynamic Multi-skill Knowledge Tracing for Intelligent Educational System","authors":"Han Shi, Yuqing Yang, Zian Chen, Peng Fu","doi":"10.1145/3579654.3579740","DOIUrl":"https://doi.org/10.1145/3579654.3579740","url":null,"abstract":"Knowledge tracing (KT) is the task of tracing students’ evolving knowledge proficiency in learning interactions. In KT research, the modeling of exercise-student relations always plays a key role. How to construct the exercise and student representation is still a pending problem. To solve this problem, we propose a novel Dynamic Multi-skill Knowledge Tracing (DMKT) method in this paper. First, the Res-embedding layer is exploited to make the exercise representation more complete. Then, a new approach is proposed for simulating students’ learning process. Furthermore, a Learning Absorption Indicator (LAI) is designed to effectively model the student's knowledge mastery. To verify the performance of our method, we implement DMKT with several baselines on three real-world datasets. Experimental results demonstrate the superiority and effectiveness of the proposed method.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125382135","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}

{"title":"Analysis of tissue specificity of alternative polyadenylation sites","authors":"W. Qin","doi":"10.1145/3579654.3579722","DOIUrl":"https://doi.org/10.1145/3579654.3579722","url":null,"abstract":"The study of gene expression has become an effective way to explore complex life phenomena, and messenger RNA polyadenylation is a very important step in the process of eukaryotic gene expression. In this session, there is an important biological process called polyadenylation, in which polyadenylation sites (poly(A) sites) are formed, which usually mark the end of the transcript and the end of the gene. Some genes have multiple poly(A) sites. In this case, we call these polyadenylation sites Alternative polyadenylation sites (APA sites). APA sites play an important role in the study of eukaryotic transcription process and biological complexity. APA sites are used differently in different tissues, and the analysis of tissue specificity can also help us further explore biological functions. Therefore, this paper mainly conducts tissue-specific analysis on APA sites, obtains tissue-specific sites through information entropy and generalized linear mixed effect models, and further analyzes these sites. We have effectively screened tissue-specific APA sites through the method in this paper, and these APA sites are of great help to the study of polyadenylation.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116264500","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}

{"title":"A Privacy Preserving Energy Trading Platform Based on Smart Contract","authors":"JingJing Wang, Fei Long, Bo Jin, Dangdang Dai, Fen Liu","doi":"10.1145/3579731.3579804","DOIUrl":"https://doi.org/10.1145/3579731.3579804","url":null,"abstract":"The smart grid has provided a fascinating opportunity to move the energy industry into a new era of reliability, availability and efficiency that contributes to both energy saving and environment protection. Besides, the smart grid has abandoned the single power supply paradigm in traditional power grid, and it can promote information and resource exchange through peer-to-peer transactions. For example, electricity can be traded effectively in real-time, so that all users can be benefited from cost saving. However, the energy trading data may contain sensitive information of the participating parties. If this information is leaked, user privacy might be violated. Moreover, the trading information should be enforced with fine-grained access control. To fulfil these security requirements, we propose a privacy preserving energy trading platform based on smart contract. First, ElGamal encryption is used to protect the privacy of exchanged messages. Second, proxy re-encryption is employed to achieve fine-grained access control, and it is more efficient than attribute based encryption that is widely used in existing solutions. Third, smart contract is used as the arbitrator, and thanks to its attractive characteristics, such as transparency and trustworthy execution, it can replace the trusted third parties in many existing schemes. Security analyses prove that our scheme satisfies all the desirable security requirements, such as correctness, privacy, fine-grained access control, robustness. And performance analyses demonstrate that it is practical for large-scale applications.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127612604","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}

{"title":"Evaluating Quality of DIBR-synthesized Views based on Texture and Perceptual Hashing Similarity","authors":"Dongsheng Zheng, Huan Zhang, Jiangzhong Cao, Xu Zhang, Ximei Yao, Wing-Kuen Ling","doi":"10.1145/3579654.3579687","DOIUrl":"https://doi.org/10.1145/3579654.3579687","url":null,"abstract":"Depth-Image-Based Rendering (DIBR) technology is widely used in 3D video systems to synthesize virtual views. However, the DIBR rendering process tends to introduce local and global distortions, especially local geometric distortion, that will severely affect the perception. In addition, traditional 2D quality metrics may fail to handle this issue since only global distortion is considered. Therefore, in order to evaluate the quality of virtual views more accurately, we propose a full reference DIBR-synthesized views quality assessment model that considers both local and global aspects. Local standard deviation texture images of the reference and distorted images are used to detect local distortions due to local distortions in the virtual view result in a large degree of variation in texture information. The intensity similarity and gradient similarity of the texture images are fused to obtain the final local distortion map. The perceptual hash similarity between the reference and the distorted image is used to quantify the global sharpness due to its powerful frequency domain analysis capability. Depending on the experimental results on the IRCCyN/IVC and IETR databases, the performance of our metric is competitive with the state-of-the-art methods.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129490585","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}

{"title":"Robust Image Matching for Camera Pose Estimation Using Oriented Fast and Rotated Brief","authors":"Junqi Bao, Xiaochen Yuan, C. Lam","doi":"10.1145/3579654.3579720","DOIUrl":"https://doi.org/10.1145/3579654.3579720","url":null,"abstract":"This paper presents a novel image matching method for camera pose estimation based on point cloud segmentation. The Oriented Fast and Rotated Brief (ORB) is employed to extract the key points, which are then extracted based on matched point cloud planes. The point cloud planes are segmented based on the depth image, and then matched by the distance of the centroid between planes. The putative corresponding key points on the planes are generated based on the distance of their 3-D coordinates and the descriptors of the key points are further matched based on the putative corresponding key points. As an additional constraint, the spatial relative position in 3-D spaces solves the problem that the descriptors of each key point in some scenarios are too similar which may lead to a mismatch. According to the experimental results, the superiority of the proposed approach is illustrated by comparing with the existing matching methods.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131820735","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}

{"title":"A transmission line fault identification method based on long short-term memory network and random matrix principle","authors":"Xu Lin, Xinlei Cai, Jinzhou Zhu, Yanlin Cui, Naixiao Wang","doi":"10.1145/3579654.3579662","DOIUrl":"https://doi.org/10.1145/3579654.3579662","url":null,"abstract":"In the past decade, driven by the policy of maximizing the consumption of renewable energy, renewable energy is being integrated into the power grid in the form of centralized power generation or decentralized power generation. The volatility and randomness of renewable energy generation lead to great uncertainty in the power flow of transmission lines, which leads to the increasing diversity of the types and characteristics of transmission line faults. This paper presents an intelligent fault identification method for transmission lines based on long short-term memory network and stochastic matrix principle. Firstly, a method to determine the fault time of transmission lines in stochastic matrix theory is proposed. Secondly, on this basis, a learning and training method of large sample fault random matrix is given. Furthermore, the fault types of transmission lines are further identified based on long short-term memory network. Finally, an actual transmission line is taken as an example to demonstrate the effectiveness of the proposed method.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"664 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131856055","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}