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

筛选
英文 中文
Genetic Analysis of bHLH Family in Purple Lettuce (Lactuca sativa L.) 紫莴苣bHLH家族遗传分析
2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00076
Jian-Ming Han, Yao Chen, Yanzhao Zhang, Miaomiao Wang
{"title":"Genetic Analysis of bHLH Family in Purple Lettuce (Lactuca sativa L.)","authors":"Jian-Ming Han, Yao Chen, Yanzhao Zhang, Miaomiao Wang","doi":"10.1109/CACML55074.2022.00076","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00076","url":null,"abstract":"The bHLH family is one of the largest transcription factor families in organisms, which widely participates in various important activities during growth and development by involving many physiological and biochemical pathways, such as regulating secondary metabolism. Purple lettuce is popular for being rich in anthocyanin and other secondary metabolites which are beneficial for health. Studies in model plants showed that bHLH genes are important for the anthocyanin synthesis pathway. Now preliminary reports about the anthocyanin accumulation in purple lettuce have been made by many research teams. However, the studies in the genetic mechanism of anthocyanin biosynthesis metabolism were few, and the bHLH gene family in purple lettuce has not been characterized. Based on the genetic database of purple lettuce, we carried out the bioinformatic analysis of the bHLH gene family in purple lettuce, including analyzing the potential purple lettuce bHLH transcription factors, predicting the molecular weight, isoelectric point, the subcellular localization, and the phylogeny tree of LsbHLH family referring to AtbHLH gene family by using an online software analysis tool based on machine learning algorithms. Results suggested that Unigene 13011_All, a member of the LsbHLH gene family, plays an important role in anthocyanin synthesis. It is the first time to systematically characterize the bHLH gene family in purple lettuce. These data not only laid a foundation for further study of anthocyanin metabolism but also provided useful information for relevant research.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"12 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":"124023739","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
PV-YOLO: An Object Detection Model for Panoramic Video based on YOLOv4 PV-YOLO:基于YOLOv4的全景视频目标检测模型
2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00018
Pengfei Jia, Tie Yun, L. Qi, Fang Zhu
{"title":"PV-YOLO: An Object Detection Model for Panoramic Video based on YOLOv4","authors":"Pengfei Jia, Tie Yun, L. Qi, Fang Zhu","doi":"10.1109/CACML55074.2022.00018","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00018","url":null,"abstract":"Most existing object detection methods are applied in ordinary video of limited view. This significantly limits their usefulness and efficiency in real-world large scale deployments with the need for detecting across many views. To address this efficiency issue, we develop a novel object detection model suitable for detection in panoramic videos to achieve detection within a 360-degree panorama without the need to repeat detection in each view. Specifically, we make improvements on YOLOv4 and propose PV-YOLO, using deformable convolution in the backbone network to prevent the geometric deformation problem of targets and adding transverse skip connection in the feature fusion part of the model to enhance feature fusion. Extensive comparative evaluations validate the superiority of this new PV-YOLO model for object detection in panoramic video over a wide range of state-of-art methods on several challenging benchmarks including YOLOv4, YOLOv3, Faster-RCNN, and EfficientDet-D3, etc.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"39 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":"133899478","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 FPGA based Method of Polynomial Multiplication 一种基于FPGA的多项式乘法方法
2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00028
Xiaoyang Xiao, Wenqi Diao, Anping He, Jinzhao Wu
{"title":"An FPGA based Method of Polynomial Multiplication","authors":"Xiaoyang Xiao, Wenqi Diao, Anping He, Jinzhao Wu","doi":"10.1109/CACML55074.2022.00028","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00028","url":null,"abstract":"Polynomial multiplication is widely used in communication, signal and image processing. In practical application, the system often needs to process a large amount of data efficiently and then output the results. However, since polynomials are always multivariable and large-scale, software algorithms alone are not effective to meet the actual requestments. In addition, the key to polynomial multiplication is the operation of matrix multiplication. Nevertheless, due to the increasingly complex structure of matrix multiplication, it is challenging to realize efficient processing and calculation of large matrices. With the development of FPGA, LSI manufacturing, memory interface and EDA tools, it is possible to apply hardware to the polynomial multiplication. To solve the above problems, we have designed and implemented a polynomial multiplication platform based on FPGA, which combines hardware and software to make up for the shortcomings of current software algorithms and at the same time, it can efficiently and effectively operate polynomial multiplication.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"49 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":"132539148","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 Continuous Evaluation Method and Model of Product Storage Lifetime 产品贮存寿命的连续评价方法与模型
2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00011
Xiao-xi Liu, Yong-Seon Mo, Jia-le Lu, Zi-gang Cai, Jin Li
{"title":"A Continuous Evaluation Method and Model of Product Storage Lifetime","authors":"Xiao-xi Liu, Yong-Seon Mo, Jia-le Lu, Zi-gang Cai, Jin Li","doi":"10.1109/CACML55074.2022.00011","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00011","url":null,"abstract":"In order to find out the actual product storage lifetime and make the product deployment and maintenance strategy, the continuous evaluation method and model of product storage lifetime are studied by combining traditional data degradation trend prediction algorithm and intelligent algorithm. It shows a good prediction effect on both the random and the determined change trend data. Based on the lifetime evaluation model, it can continuously predict the product lifetime with high accuracy, greatly save the storage lifetime evaluation cost, and guide the manufacturer to reduce the maintenance support cost of the product.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"30 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":"123590411","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
Stock price prediction based on optimized random forest model 基于优化随机森林模型的股票价格预测
2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00134
Zi Ren, Jun Yin, Yicheng Yu, Fuxiang Ma, Rongbin Li
{"title":"Stock price prediction based on optimized random forest model","authors":"Zi Ren, Jun Yin, Yicheng Yu, Fuxiang Ma, Rongbin Li","doi":"10.1109/CACML55074.2022.00134","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00134","url":null,"abstract":"With the rapid development of Chinese financial industry, people use machine learning to effectively analyze and study the financial market and improve the expected income. The training accuracy in the random forest model is low since the decision tree has the same weight and it is difficult to select the parameters such as the decision tree and the maximum number of use features of the decision tree in the model. In order to solve the problem, a prediction model based on the weighted random forest and ant colony algorithm is proposed in this paper. The prediction error of the weighted random forest model proposed in this paper is obviously lower than the general random forest algorithm and regression algorithm, which is verified through the data of TA-lib and Baidu search index.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"28 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":"121295800","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: 1
Learning Algorithm in Two-Stage Selective Prediction 两阶段选择性预测的学习算法
2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00093
Weicheng Ye, Dangxing Chen, Ilqar Ramazanli
{"title":"Learning Algorithm in Two-Stage Selective Prediction","authors":"Weicheng Ye, Dangxing Chen, Ilqar Ramazanli","doi":"10.1109/CACML55074.2022.00093","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00093","url":null,"abstract":"Data gathered from real-world applications often suffer from corruption. The low-quality data will hinder the performance of the learning system in terms of classification accuracy, model building time, and interpretability of the classifier. Selective prediction, also known as prediction with a reject option, is to reduce the error rate by abstaining from prediction under uncertainty while keeping coverage as high as possible. Deep Neural Network (DNN) has a high capacity for fitting large-scale data. If DNNs can leverage the trade-off coverage by selective prediction, then the performance can potentially be improved. However, the current DNN embedded with the reject option requires the knowledge of the rejection threshold, and the searching of threshold is inefficient in large-scale applications. Besides, the abstention of prediction on partial datasets increases the model bias and might not be optimal. To resolve these problems, we propose innovative threshold learning algorithms integrated with the selective prediction that can estimate the intrinsic rejection rate of the dataset. Correspondingly, we provide a rigorous framework to generalize the estimation of data corruption rate. To leverage the advantage of multiple learning algorithms, we extend our learning algorithms to a hierarchical two-stage system. Our methods have the advantage of being flexible with any neural network architecture. The empirical results show that our algorithms can achieve state-of-the-art performance in challenging real-world datasets in both classification and regression problems.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"52 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":"117022346","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: 2
A Study of Mongolian Emotion Classification Incorporating Emojis 蒙古语表情符号情感分类研究
2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00021
Qian Zhang, Qing-dao-er-ji Ren, B. Saheya
{"title":"A Study of Mongolian Emotion Classification Incorporating Emojis","authors":"Qian Zhang, Qing-dao-er-ji Ren, B. Saheya","doi":"10.1109/CACML55074.2022.00021","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00021","url":null,"abstract":"A Mongolian emotion classification algorithm incorporating emojis is proposed to address the problems of small Mongolian emotion classification corpus, poor classification results, and underutilization of emoji emotion features. Firstly, we extract Mongolian text data from the corpus, vectorize it using FastText algorithm and further learn the Mongolian text features. Secondly, emojis data are extracted from the corpus, vectorized and trained in GRU network to fully learn the emotion features of emoji. Then the attention mechanism is used to adjust the attention dynamics of text and emoji features in the model. Finally, the sentiment features of text and emoji are classified with softmax layer for sentiment classification. The experimental results show that the Mongolian sentiment classification algorithm with fused emojis outperforms FastText, Word2vec_BiLSTM and Glove _ BiLSTM sentiment classification algorithms in terms of precision, recall, F1 value and accuracy. The results show the effectiveness of the proposed method and provide a reference for Mongolian sentiment analysis and opinion prediction.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"14 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":"115107245","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
Extra Conditional Diagnosability of Hypercubes under the Bounded PMC Model 有界PMC模型下超立方体的额外条件可诊断性
2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00072
Yongcui Tian, Qiang Zhu, Chaofeng Lv
{"title":"Extra Conditional Diagnosability of Hypercubes under the Bounded PMC Model","authors":"Yongcui Tian, Qiang Zhu, Chaofeng Lv","doi":"10.1109/CACML55074.2022.00072","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00072","url":null,"abstract":"The h-extra conditional diagnosability is different from the traditional diagnosability, which restricts that each component has no fewer than $h+1$ processors after the deletion of the faulty sets in the system. The $(f_{1}, f_{2})$ -BPMC model is a combination of the PMC model and BGM model, assuming that the upper bound number of failed processors is $f_{1}$ and no more than $f_{2}$ failed processors that can evaluate a faulty processor as non-faulty. In this paper, inspired by the $(f_{1}, f_{2})$ - BPMC model, we propose a diagnosis model called $f$ -BPMC model by relaxing the restriction of $f_{1}$. In this model, it only assumes that at most $f$ failed processors for a given system that can evaluate faulty processors as non-faulty. We then study the h-extra conditional diagnosability of interconnection networks under the $f$ -BPMC model and explore some of its properties. Finally, the h-extra conditional diagnosability is applied to hypercubes under the $f$ -BPMC model.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"17 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":"127048806","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
Time-aware Multi-layer Interest Extraction Network for Click-Through Rate Prediction 基于时间感知的多层兴趣提取网络的点击率预测
2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00136
Guoan Wang, Xingjun Wang
{"title":"Time-aware Multi-layer Interest Extraction Network for Click-Through Rate Prediction","authors":"Guoan Wang, Xingjun Wang","doi":"10.1109/CACML55074.2022.00136","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00136","url":null,"abstract":"Click-through rate (CTR) prediction, which is used to estimate the probability of a user clicking on a candidate item, acts as a core task in recommender system. Previous researchers model user's historical behaviors as a sequence and apply sequential models to extract user interests. However, user behaviors result from multiple factors, including not only their interests but also the time, especially in time-sensitive scenes. While a few researchers have considered behavior time in sequential modeling, the target predicted time is still ignored. In this paper, we propose a novel network for CTR prediction dubbed Time-aware Multi-layer Interest Extraction network (TMIE), which considers the influence imposed by user behavior time and the target predicted time along-side with modeling user interests. Specifically, we design and employ time-aware GRU as low-layer interest extractor to capture primary interests. Then simplified transformer is applied as high-layer extractor to further explore the mutual relevance among user's interests. We perform abundant comparative experiments on both public and industrial datasets and the excellent results demonstrate the rationality and effectiveness of our methods. Notably, our heuristic work is an exciting attempt to catch up the synergistic impact of behavior time and multi-layer user interests in CTR prediction.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"13 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":"126369267","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
Human Activity Recognition Based on CSI fragment with Action-value Method 基于动作值法的CSI片段人体活动识别
2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00082
Hongxin Chen, Yong Zhang, Yuqing Yin, Fei He
{"title":"Human Activity Recognition Based on CSI fragment with Action-value Method","authors":"Hongxin Chen, Yong Zhang, Yuqing Yin, Fei He","doi":"10.1109/CACML55074.2022.00082","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00082","url":null,"abstract":"The application of Human Activity Recognition (HAR) technology makes human life more convenient. As an emerging HAR technology, WiFi based wireless sensor can sense the state of the target, such as body movement, gesture, position and so on. Aiming at the problem that the current WIFi based HAR methods need more training samples and have low real-time performance, this paper proposes a novel HAR method based on action-value method. In this method, each complete Channel State Information (CSI) sample signal of each activity is sliced into piece samples, and these piece samples are trained and tested to improve the real-time performance and reduce the number of training samples. The piece sample and the sequence of piece samples are respectively regarded as the state information and environment, and the classification of each piece sample is regarded as the execution of the classification-action. A deep neural network is used to simulate the reward of classification-actions in each state, and the recognition model is established by the action-value method. We tested our approach on SignFi data set. The highest recognition accuracy rate of active is 99% and 91% respectively.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"24 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":"122207966","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: 1
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信