Most learning-based low-light image enhancement methods typically suffer from two problems. First, they require a large amount of paired data for training, which are difficult to acquire in most cases. Second, in the process of enhancement, image noise is difficult to be removed and may even be amplified. In other words, performing denoising and illumination enhancement at the same time is difficult. As an alternative to supervised learning strategies that use a large amount of paired data, as presented in previous work, this paper presents an mixed-attention guided generative adversarial network called MAGAN for low-light image enhancement in a fully unsupervised fashion. We introduce a mixed-attention module layer, which can model the relationship between each pixel and feature of the image. In this way, our network can enhance a low-light image and remove its noise simultaneously. In addition, we conduct extensive experiments on paired and no-reference datasets to show the superiority of our method in enhancing low-light images.
{"title":"MAGAN: Unsupervised low-light image enhancement guided by mixed-attention","authors":"Renjun Wang;Bin Jiang;Chao Yang;Qiao Li;Bolin Zhang","doi":"10.26599/BDMA.2021.9020020","DOIUrl":"https://doi.org/10.26599/BDMA.2021.9020020","url":null,"abstract":"Most learning-based low-light image enhancement methods typically suffer from two problems. First, they require a large amount of paired data for training, which are difficult to acquire in most cases. Second, in the process of enhancement, image noise is difficult to be removed and may even be amplified. In other words, performing denoising and illumination enhancement at the same time is difficult. As an alternative to supervised learning strategies that use a large amount of paired data, as presented in previous work, this paper presents an mixed-attention guided generative adversarial network called MAGAN for low-light image enhancement in a fully unsupervised fashion. We introduce a mixed-attention module layer, which can model the relationship between each pixel and feature of the image. In this way, our network can enhance a low-light image and remove its noise simultaneously. In addition, we conduct extensive experiments on paired and no-reference datasets to show the superiority of our method in enhancing low-light images.","PeriodicalId":52355,"journal":{"name":"Big Data Mining and Analytics","volume":"5 2","pages":"110-119"},"PeriodicalIF":13.6,"publicationDate":"2022-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8254253/9691293/09691298.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67834094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.26599/BDMA.2022.9020001
{"title":"Call for papers: Special issue on AI-enabled Internet of medical things for medical data analytics","authors":"","doi":"10.26599/BDMA.2022.9020001","DOIUrl":"https://doi.org/10.26599/BDMA.2022.9020001","url":null,"abstract":"","PeriodicalId":52355,"journal":{"name":"Big Data Mining and Analytics","volume":"5 2","pages":""},"PeriodicalIF":13.6,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8254253/9691293/09691303.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67834074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.26599/BDMA.2021.9020029
{"title":"Call for papers: Special issue on artificial intelligence powered Internet of Healthcare Things (IoHT): Data science, emerging trends and applications","authors":"","doi":"10.26599/BDMA.2021.9020029","DOIUrl":"https://doi.org/10.26599/BDMA.2021.9020029","url":null,"abstract":"","PeriodicalId":52355,"journal":{"name":"Big Data Mining and Analytics","volume":"5 2","pages":""},"PeriodicalIF":13.6,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8254253/9691293/09691302.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67834076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.26599/BDMA.2022.9020020
{"title":"Call for Papers: Special Issue on Role & Impact of Advance Technologies AI, ML, and Big Data in Business and Society","authors":"","doi":"10.26599/BDMA.2022.9020020","DOIUrl":"https://doi.org/10.26599/BDMA.2022.9020020","url":null,"abstract":"","PeriodicalId":52355,"journal":{"name":"Big Data Mining and Analytics","volume":"5 4","pages":""},"PeriodicalIF":13.6,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8254253/9832761/09832762.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68067555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.26599/bdma.2022.9020020
{"title":"Call for Papers: Special Issue on Role & Impact of Advance Technologies AI, ML, and Big Data in Business and Society","authors":"","doi":"10.26599/bdma.2022.9020020","DOIUrl":"https://doi.org/10.26599/bdma.2022.9020020","url":null,"abstract":"","PeriodicalId":52355,"journal":{"name":"Big Data Mining and Analytics","volume":"30 1","pages":""},"PeriodicalIF":13.6,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69029454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-27DOI: 10.26599/BDMA.2021.9020014
Jiantao Zheng;Cuixiang Lin;Zhenpeng Wu;Hong-Dong Li
Intron Retention (IR) is an alternative splicing mode through which introns are retained in mature RNAs rather than being spliced in most cases. IR has been gaining increasing attention in recent years because of its recognized association with gene expression regulation and complex diseases. Continuous efforts have been dedicated to the development of IR detection methods. These methods differ in their metrics to quantify retention propensity, performance to detect IR events, functional enrichment of detected IRs, and computational speed. A systematic experimental comparison would be valuable to the selection and use of existing methods. In this work, we conduct an experimental comparison of existing IR detection methods. Considering the unavailability of a gold standard dataset of intron retention, we compare the IR detection performance on simulation datasets. Then, we compare the IR detection results with real RNA-Seq data. We also describe the use of differential analysis methods to identify disease-associated IRs and compare differential IRs along with their Gene Ontology enrichment, which is illustrated on an Alzheimer's disease RNA-Seq dataset. We discuss key principles and features of existing approaches and outline their differences. This systematic analysis provides helpful guidance for interrogating transcriptomic data from the point of view of IR.
{"title":"A comparison of computational approaches for intron retention detection","authors":"Jiantao Zheng;Cuixiang Lin;Zhenpeng Wu;Hong-Dong Li","doi":"10.26599/BDMA.2021.9020014","DOIUrl":"https://doi.org/10.26599/BDMA.2021.9020014","url":null,"abstract":"Intron Retention (IR) is an alternative splicing mode through which introns are retained in mature RNAs rather than being spliced in most cases. IR has been gaining increasing attention in recent years because of its recognized association with gene expression regulation and complex diseases. Continuous efforts have been dedicated to the development of IR detection methods. These methods differ in their metrics to quantify retention propensity, performance to detect IR events, functional enrichment of detected IRs, and computational speed. A systematic experimental comparison would be valuable to the selection and use of existing methods. In this work, we conduct an experimental comparison of existing IR detection methods. Considering the unavailability of a gold standard dataset of intron retention, we compare the IR detection performance on simulation datasets. Then, we compare the IR detection results with real RNA-Seq data. We also describe the use of differential analysis methods to identify disease-associated IRs and compare differential IRs along with their Gene Ontology enrichment, which is illustrated on an Alzheimer's disease RNA-Seq dataset. We discuss key principles and features of existing approaches and outline their differences. This systematic analysis provides helpful guidance for interrogating transcriptomic data from the point of view of IR.","PeriodicalId":52355,"journal":{"name":"Big Data Mining and Analytics","volume":"5 1","pages":"15-31"},"PeriodicalIF":13.6,"publicationDate":"2021-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8254253/9663253/09663257.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68077702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-27DOI: 10.26599/BDMA.2021.9020021
Qixiang Shao;Runlong Yu;Hongke Zhao;Chunli Liu;Mengyi Zhang;Hongmei Song;Qi Liu
Intelligent Financial Advisors (IFAs) in online financial applications (apps) have brought new life to personal investment by providing appropriate and high-quality portfolios for users. In real-world scenarios, identifying potential clients is a crucial issue for IFAs, i.e., identifying users who are willing to purchase the portfolios. Thus, extracting useful information from various characteristics of users and further predicting their purchase inclination are urgent. However, two critical problems encountered in real practice make this prediction task challenging, i.e., sample selection bias and data sparsity. In this study, we formalize a potential conversion relationship, i.e., user ! activated user ! client and decompose this relationship into three related tasks. Then, we propose a Multitask Feature Extraction Model (MFEM), which can leverage useful information contained in these related tasks and learn them jointly, thereby solving the two problems simultaneously. In addition, we design a two-stage feature selection algorithm to select highly relevant user features efficiently and accurately from an incredibly huge number of user feature fields. Finally, we conduct extensive experiments on a real-world dataset provided by a famous fintech bank. Experimental results clearly demonstrate the effectiveness of MFEM.
{"title":"Toward intelligent financial advisors for identifying potential clients: A multitask perspective","authors":"Qixiang Shao;Runlong Yu;Hongke Zhao;Chunli Liu;Mengyi Zhang;Hongmei Song;Qi Liu","doi":"10.26599/BDMA.2021.9020021","DOIUrl":"https://doi.org/10.26599/BDMA.2021.9020021","url":null,"abstract":"Intelligent Financial Advisors (IFAs) in online financial applications (apps) have brought new life to personal investment by providing appropriate and high-quality portfolios for users. In real-world scenarios, identifying potential clients is a crucial issue for IFAs, i.e., identifying users who are willing to purchase the portfolios. Thus, extracting useful information from various characteristics of users and further predicting their purchase inclination are urgent. However, two critical problems encountered in real practice make this prediction task challenging, i.e., sample selection bias and data sparsity. In this study, we formalize a potential conversion relationship, i.e., user ! activated user ! client and decompose this relationship into three related tasks. Then, we propose a Multitask Feature Extraction Model (MFEM), which can leverage useful information contained in these related tasks and learn them jointly, thereby solving the two problems simultaneously. In addition, we design a two-stage feature selection algorithm to select highly relevant user features efficiently and accurately from an incredibly huge number of user feature fields. Finally, we conduct extensive experiments on a real-world dataset provided by a famous fintech bank. Experimental results clearly demonstrate the effectiveness of MFEM.","PeriodicalId":52355,"journal":{"name":"Big Data Mining and Analytics","volume":"5 1","pages":"64-78"},"PeriodicalIF":13.6,"publicationDate":"2021-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8254253/9663253/09663261.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68077805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-27DOI: 10.26599/BDMA.2021.9020013
Hui Bai;Yan Yang;Jie Wang
Dialog State Tracking (DST) aims to extract the current state from the conversation and plays an important role in dialog systems. Existing methods usually predict the value of each slot independently and do not consider the correlations among slots, which will exacerbate the data sparsity problem because of the increased number of candidate values. In this paper, we propose a multi-domain DST model that integrates slot-relevant information. In particular, certain connections may exist among slots in different domains, and their corresponding values can be obtained through explicit or implicit reasoning. Therefore, we use the graph adjacency matrix to determine the correlation between slots, so that the slots can incorporate more slot-value transformer information. Experimental results show that our approach has performed well on the Multi-domain Wizard-Of-Oz (MultiWOZ) 2.0 and MultiWOZ2.1 datasets, demonstrating the effectiveness and necessity of incorporating slot-relevant information.
对话状态跟踪（DST）旨在从对话中提取当前状态，在对话系统中发挥着重要作用。现有的方法通常独立地预测每个时隙的值，而不考虑时隙之间的相关性，这将由于候选值的数量增加而加剧数据稀疏性问题。在本文中，我们提出了一个集成时隙相关信息的多域DST模型。特别地，不同域中的槽之间可能存在某些连接，并且可以通过显式或隐式推理来获得它们对应的值。因此，我们使用图邻接矩阵来确定槽之间的相关性，以便槽可以包含更多的槽值变换器信息。实验结果表明，我们的方法在多域Wizard Of Oz（MultiWOZ）2.0和MultiWOZ2.1数据集上表现良好，证明了引入时隙相关信息的有效性和必要性。
{"title":"Exploiting more associations between slots for multi-domain dialog state tracking","authors":"Hui Bai;Yan Yang;Jie Wang","doi":"10.26599/BDMA.2021.9020013","DOIUrl":"https://doi.org/10.26599/BDMA.2021.9020013","url":null,"abstract":"Dialog State Tracking (DST) aims to extract the current state from the conversation and plays an important role in dialog systems. Existing methods usually predict the value of each slot independently and do not consider the correlations among slots, which will exacerbate the data sparsity problem because of the increased number of candidate values. In this paper, we propose a multi-domain DST model that integrates slot-relevant information. In particular, certain connections may exist among slots in different domains, and their corresponding values can be obtained through explicit or implicit reasoning. Therefore, we use the graph adjacency matrix to determine the correlation between slots, so that the slots can incorporate more slot-value transformer information. Experimental results show that our approach has performed well on the Multi-domain Wizard-Of-Oz (MultiWOZ) 2.0 and MultiWOZ2.1 datasets, demonstrating the effectiveness and necessity of incorporating slot-relevant information.","PeriodicalId":52355,"journal":{"name":"Big Data Mining and Analytics","volume":"5 1","pages":"41-52"},"PeriodicalIF":13.6,"publicationDate":"2021-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8254253/9663253/09663259.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68077701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-27DOI: 10.26599/BDMA.2021.9020016
Amanpreet Kaur Sandhu
With the recent advancements in computer technologies, the amount of data available is increasing day by day. However, excessive amounts of data create great challenges for users. Meanwhile, cloud computing services provide a powerful environment to store large volumes of data. They eliminate various requirements, such as dedicated space and maintenance of expensive computer hardware and software. Handling big data is a time-consuming task that requires large computational clusters to ensure successful data storage and processing. In this work, the definition, classification, and characteristics of big data are discussed, along with various cloud services, such as Microsoft Azure, Google Cloud, Amazon Web Services, International Business Machine cloud, Hortonworks, and MapR. A comparative analysis of various cloud-based big data frameworks is also performed. Various research challenges are defined in terms of distributed database storage, data security, heterogeneity, and data visualization.
随着计算机技术的进步，可用的数据量与日俱增。然而，过多的数据给用户带来了巨大的挑战。同时，云计算服务提供了一个强大的环境来存储大量数据。它们消除了各种要求，例如专用空间和维护昂贵的计算机硬件和软件。处理大数据是一项耗时的任务，需要大型计算集群来确保成功的数据存储和处理。在这项工作中，讨论了大数据的定义、分类和特征，以及各种云服务，如Microsoft Azure、Google cloud、Amazon Web services、International Business Machine cloud、Hortonworks和MapR。还对各种基于云的大数据框架进行了比较分析。从分布式数据库存储、数据安全、异构性和数据可视化等方面定义了各种研究挑战。
{"title":"Big data with cloud computing: Discussions and challenges","authors":"Amanpreet Kaur Sandhu","doi":"10.26599/BDMA.2021.9020016","DOIUrl":"https://doi.org/10.26599/BDMA.2021.9020016","url":null,"abstract":"With the recent advancements in computer technologies, the amount of data available is increasing day by day. However, excessive amounts of data create great challenges for users. Meanwhile, cloud computing services provide a powerful environment to store large volumes of data. They eliminate various requirements, such as dedicated space and maintenance of expensive computer hardware and software. Handling big data is a time-consuming task that requires large computational clusters to ensure successful data storage and processing. In this work, the definition, classification, and characteristics of big data are discussed, along with various cloud services, such as Microsoft Azure, Google Cloud, Amazon Web Services, International Business Machine cloud, Hortonworks, and MapR. A comparative analysis of various cloud-based big data frameworks is also performed. Various research challenges are defined in terms of distributed database storage, data security, heterogeneity, and data visualization.","PeriodicalId":52355,"journal":{"name":"Big Data Mining and Analytics","volume":"5 1","pages":"32-40"},"PeriodicalIF":13.6,"publicationDate":"2021-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8254253/9663253/09663258.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68077700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The blockchain, with its key characteristics of decentralization, persistence, anonymity, and auditability, has become a solution to overcome the overdependence and lack of trust for a traditional public key infrastructure on third-party institutions. Because of these characteristics, the blockchain is suitable for solving certain open problems in the service-oriented social network, where the unreliability of submitted reviews of service vendors can cause serious security problems. To solve the unreliability problems of submitted reviews, this paper first proposes a blockchain-based identity authentication scheme and a new trusted service evaluation model by introducing the scheme into a service evaluation model. The new trusted service evaluation model consists of the blockchain-based identity authentication scheme, evaluation submission module, and evaluation publicity module. In the proposed evaluation model, only users who have successfully been authenticated can submit reviews to service vendors. The registration and authentication records of users' identity and the reviews for service vendors are all stored in the blockchain network. The security analysis shows that this model can ensure the credibility of users' reviews for service vendors, and other users can obtain credible reviews of service vendors via the review publicity module. The experimental results also show that the proposed model has a lower review submission delay than other models.
{"title":"BCSE: Blockchain-based trusted service evaluation model over big data","authors":"Fengyin Li;Xinying Yu;Rui Ge;Yanli Wang;Yang Cui;Huiyu Zhou","doi":"10.26599/BDMA.2020.9020028","DOIUrl":"https://doi.org/10.26599/BDMA.2020.9020028","url":null,"abstract":"The blockchain, with its key characteristics of decentralization, persistence, anonymity, and auditability, has become a solution to overcome the overdependence and lack of trust for a traditional public key infrastructure on third-party institutions. Because of these characteristics, the blockchain is suitable for solving certain open problems in the service-oriented social network, where the unreliability of submitted reviews of service vendors can cause serious security problems. To solve the unreliability problems of submitted reviews, this paper first proposes a blockchain-based identity authentication scheme and a new trusted service evaluation model by introducing the scheme into a service evaluation model. The new trusted service evaluation model consists of the blockchain-based identity authentication scheme, evaluation submission module, and evaluation publicity module. In the proposed evaluation model, only users who have successfully been authenticated can submit reviews to service vendors. The registration and authentication records of users' identity and the reviews for service vendors are all stored in the blockchain network. The security analysis shows that this model can ensure the credibility of users' reviews for service vendors, and other users can obtain credible reviews of service vendors via the review publicity module. The experimental results also show that the proposed model has a lower review submission delay than other models.","PeriodicalId":52355,"journal":{"name":"Big Data Mining and Analytics","volume":"5 1","pages":"1-14"},"PeriodicalIF":13.6,"publicationDate":"2021-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8254253/9663253/09663256.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68077704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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：