2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)最新文献_第6页

Few-shot Learning for Human Activity Recognition Based on CSI 基于CSI的少镜头学习人体活动识别

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00074

Sipeng Huang, Yang Chen, Dingchao Wu, Guangwei Yu, Yong Zhang

{"title":"Few-shot Learning for Human Activity Recognition Based on CSI","authors":"Sipeng Huang, Yang Chen, Dingchao Wu, Guangwei Yu, Yong Zhang","doi":"10.1109/CACML55074.2022.00074","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00074","url":null,"abstract":"Human Activity Recognition(HAR) based on Channel State Information(Csi)plays an increasingly impor-tant role in human-computer interaction. Traditional research requires a large amount of activity sample to train network model. However, collecting a great many of data causes waste of time and manpower. Some models can well identify the categories of activities in this scene, but when another scene is tested, the identification accuracy of the model will be reduced. Therefore it needs to re-collect data to retrain the model. We proposed a method which can transfer the knowledge learned from a scenario to a new scenario. It can also facilitate the model's knowledge learning from the source domain and quickly generalize to new tasks that contain only a small number of samples. Through this method, the model that maintains high accuracy and scalability to identify new category, we added attention mechanism can automatically extract features that are useful to the model and ignore some noise that negatively affects the model, meanwhile improve system stability and the effectiveness of activity recognition. We also performed the scaling and shifting(SS) transformation on the network, which could reduce the parameters of the model, improve the training speed, and avoid overfitting.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117197996","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}

引用次数: 0

Cryptocurrency Price forecasting: A Comparative Study of Machine Learning Model in Short-Term Trading 加密货币价格预测:短期交易中机器学习模型的比较研究

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00054

Haoran Lyu

{"title":"Cryptocurrency Price forecasting: A Comparative Study of Machine Learning Model in Short-Term Trading","authors":"Haoran Lyu","doi":"10.1109/CACML55074.2022.00054","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00054","url":null,"abstract":"In recent years, the expansion of the cryptocurrency market has received significant attention among investors, studies of cryptocurrency price predictions have been conducted in various fields. With the enhancement of machine learning algorithms and increased computational capabilities, machine learning has proved one of the most efficient cryptocurrency prediction methods. However, most studies focused on single digital currency prediction or small-scale algorithm comparison for multiple currencies. This study aims to present a comparative performance of large-scale selected Machine Learning algorithms for cryptocurrency forecasting. Specifically, this paper concentrates on forecasting time series data for a short-term trading period in ten cryptocurrencies (BTC, ETH, ADA, BNB, XRP, DOGE, LUNA, LINK, LTC, and BCH) with ten selected machine learning algorithms (Decision Tree, Linear Regression, Ridge Regression, Lasso Regression, Bayesian Regression, Random Forest, K-Nearest Neighbors, Neural Networks, Gradient Boosting, and Support Vector Machine). Our experiment results show that the Gradient Boosting with the mean square error criterion is superior in predicting most major cryptocurrencies by performing statistical analysis and data visualizations. Additionally, the Random Forest and Decision Tree model built by the Classification and Regression Tree algorithm also shows outstanding performance in certain currencies such as ETH, XRP, LUNA, and LTC. Thus, all three algorithms can help anticipate the short-term evolutions of the cryptocurrency market.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128893838","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}

引用次数: 0

Comparison of Hyperbox Granular Computing Classification Algorithms by Positive Valuation Functions 基于正评价函数的Hyperbox颗粒计算分类算法比较

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00047

Baoduo Su, Yinhao Zhang, Meiyao Zhu, Hongbing Liu

{"title":"Comparison of Hyperbox Granular Computing Classification Algorithms by Positive Valuation Functions","authors":"Baoduo Su, Yinhao Zhang, Meiyao Zhu, Hongbing Liu","doi":"10.1109/CACML55074.2022.00047","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00047","url":null,"abstract":"Granular Computing (GrC) is a computing paradigm derived from the human congiton of the real world, by which different granularity spaces can be converted to each other. For GrC, we have to face two issues, such as the operation between two granules and inclusion relation between two granules. In the paper, we proposed the hyperbox granular computing classification algorithms based on the fuzzy inclusion relation between granules in terms of the different positive valuation functions. The proposed positive valuation functions keep the consistency of the partial order relation between two vectors in the vector space and the partial order relation between two hyperbox granules in the granule space. The fuzzy lattice is constructed by the hyperbox granule set and the fuzzy inclusion relation induced by the proposed positive valuation functions, and used to design the algorithms which realize the transformation from the training set to the sparse granule space. Experimental results on the benchmark data set show superiority of the proposed hyperbox granular computing classification algorithms.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129000214","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}

引用次数: 0

Modeling of air quality prediction for PM2.5 concentration in Chengdu area based on measured data 基于实测数据的成都地区PM2.5浓度空气质量预测模型

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00097

Chenglin Yu, Ming Zhu, Hongyuan Zhang, Ke Liu, YongQiang Liu, He Zhou, Qian Yang

引用次数: 0

Using Big Data and Empirical Analysis to Optimize The Decision-Making of Smart City Tourism Logistics Service System 基于大数据和实证分析的智慧城市旅游物流服务系统决策优化

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00140

Chuling Chen, Qin Xue

引用次数: 0

Approximating Permutations with Neural Network Components for Travelling Photographer Problem 用神经网络分量逼近旅行摄影师问题的排列

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00036

C. Sin

{"title":"Approximating Permutations with Neural Network Components for Travelling Photographer Problem","authors":"C. Sin","doi":"10.1109/CACML55074.2022.00036","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00036","url":null,"abstract":"Most of current inference techniques rely upon Bayesian inference on Probabilistic Graphical Models of observations, and does prediction and classification on observations rather well. Event understanding of machines with observation inputs needs to deal with understanding of the relationship between sets of observations, and thus there is a crucial need to build models and come up with effective data structures to accumulate and organize relationships between observations. Given a set of states probabilisitcally-related with observations, this paper attempts to fit a permutation of states to a sequence of observation tokens (The Travelling Photographer Problem). We have devised a machine learning inspired architecture for randomized approximation of state permutation, facilitating parallelization of heuristic search of permutations. Our algorithm is able to solve The Travelling Photographer Problem with very small error. We demonstrate that by mimicking components of machine learning such as normalization, dropout, lambda layer with randomized algorithm, we are able to devise an architecture which solves TPP, a permutation NP-Hard problem. Other than TPP, we are also able to provide a 2-Local improvement heuristic for the Travelling Salesman Problem (TSP) with similar ideas.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129990087","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}

引用次数: 0

An Electronic Contract Management System Based on Blockchain A case study of technology framework with improved algorithms 基于区块链的电子合同管理系统基于改进算法的技术框架案例研究

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00027

Sheng Guo

{"title":"An Electronic Contract Management System Based on Blockchain A case study of technology framework with improved algorithms","authors":"Sheng Guo","doi":"10.1109/CACML55074.2022.00027","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00027","url":null,"abstract":"Contract management is the core of management business that implements enterprise risk management and internal control. The quality of contract management directly affects the success or failure of the company's operations. However, the contract approval process of manual management is not clear: the level of information utilization is not high, resulting in low business processing efficiency with wasting huge man-power and material resources. Hence, many companies have been working on finding a simple and practical software to manage contracts. The article advances an electronic contract management software. The existing electronic contract system is not secure enough in encryption because of the shortcoming of easily forgetting and pretending. The new system adds a private key login through a coin-free open chain technology which is used in hospital, government, military, university and other special scenes, achieved perfect security guarantee. This paper discusses several crucial mechanisms implemented for the goals of designing the system, and gives out relevant methods and process of the implementation. Guided by system engineering theory, this thesis also discusses the modeling and optimization problems of consensus mechanism. The article finally makes analysis on the research process and results, discusses the advantages and prospects of the technology, and points out problems remaining to be solved.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131179230","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}

引用次数: 0

The research of the optimized solutions to Raft consensus algorithm based on a weighted PageRank algorithm 基于加权PageRank算法的Raft共识算法优化解的研究

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00135

Yu-shi Wu, Yuansai Wu, Yiran Liu, Tingjun Shi

引用次数: 5

Bayesian Optimization Based on Pseudo Labels 基于伪标签的贝叶斯优化

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00043

Waner Chen, Zhongwei Wu, Jiewen Xu, Yuehai Wang

{"title":"Bayesian Optimization Based on Pseudo Labels","authors":"Waner Chen, Zhongwei Wu, Jiewen Xu, Yuehai Wang","doi":"10.1109/CACML55074.2022.00043","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00043","url":null,"abstract":"The performance of a machine learning or deep learning algorithm is heavily influenced by its hyperparameters. The selection of the hyperparameters is of great significance. To automatically find a superior-performing set of hyperparameters, Bayesian optimization is a common and effective hyperparameter optimization method. And an early stopping strategy is usually employed in the optimization algorithm to improve efficiency. The early stopped trials cannot run to the end, so their final performance metrics are unavailable. Therefore, the existing Bayesian optimization algorithms fail to use the trials terminated early as samples for modeling. This may result in less information participating in the modeling, which leads to high model uncertainty. In this paper, we propose Bayesian optimization based on pseudo labels (BOPL). We apply the extrapolation of learning curves as the early stopping strategy and the pseudo labels obtainment method. We use the pseudo labels of all trials to model the surrogate model in Bayesian optimization, thereby avoiding the waste of information contained in the early stopped trials. Experiments on the ResNet-18 on the CIFAR-100 dataset show that the proposed BOPL consistently outperforms vanilla Bayesian and Bayesian with early stopping. It proves the effectiveness of the proposed method, which finds better-performing hyperparameters at a faster rate. The proposed method is versatile, conceptually simple, and easy to implement.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121270671","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}

引用次数: 0

A Multi-Objective Topology Optimization Method Used in Simultaneous Constraints of Natural Frequency and Static Stiffness 一种同时约束固有频率和静刚度的多目标拓扑优化方法

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00010

Wen Wang, Tian Qingguo, Wang Fengbin, Fan Yesen, Zheng Shikun, Zhang Wenhui

引用次数: 0