检索结果-内蒙古大学图书馆

Improving Explainable Recommendations by Deep Review-Based Explanations

IEEE ACCESS 2021年 9卷 67444-67455页

作者： Ouyang, Sixun Lawlor, Aonghus Univ Coll Dublin Insight Ctr Data Analyt Dublin 4 Ireland

Many e-commerce sites encourage their users to write product reviews, in the knowledge that they exert a considerable influence on users' decision-making processes. These snippets of real-world experience provide an essential source of data for interpretable recommendations. However, current methods relying on user-generated content to make recommendations can run into problems because of well-known issues with reviews, such as noise, sparsity and irrelevant content. On the other hand, recent advances in text generation methods demonstrate significant text quality improvements and show promise in their ability to address these problems. In this paper, we develop two character-level deep neural network-based personalised review generation models, and improve recommendation accuracy by generating high-quality text which meets the input criteria of text-aware recommender systems. To make fair comparisons, we train review-aware recommender systems by human written reviews and attain advanced recommendations by feeding generated reviews at the inference step. Our experiments are conducted on four large review datasets from multiple domains. We leverage our methods' performance by comparing with non-review based recommender systems and advanced review-aware recommender systems. The results demonstrate that we beat baselines on a range of metrics and obtain state-of-the-art performance on both rating prediction and top-N ranking. Our sparsity experiments validate that our generation models can produce high-quality text to tackle the sparsity problem. We also demonstrate the generation of useful reviews so that we can achieve up to 13.53% RMSE improvements. For explanation evaluation, quantitative analyses reveal good understandable scores for our generated review-based explanations, and qualitative case studies substantiate we can capture critical aspects in generating explanations.

关键词： computing methodologies deep neural networks information systems natural language generation recommender systems

来源：评论

学校读者我要写书评

暂无评论

Unearthing Excited Hadron Resonances in Lattice QCD Using NSF XSEDE Resources

引用

computing IN SCIENCE & ENGINEERING 2015年第2期17卷 23-29页

作者： Morningstar, Colin Carnegie Mellon Univ Dept Phys Pittsburgh PA 15213 USA

The best approach to calculating hadron properties is to formulate quantum chromodynamics on a space-time lattice. Improving Monte Carlo algorithms and using high-performance computing resources have led to significant progress in understanding the lightest hadrons. A recent algorithmic advance has opened up new studies of large numbers of heavier excited hadrons.

关键词： Monte Carlo methods gluons lattice field theory neutrons protons quantum chromodynamics quarks Monte Carlo integration method NSF XSEDE resources composite objects elementary particles hadron properties high-performance computing resources lattice QCD massless gluon exchange neutrons petascale heterogeneous computing system protons quarks space-time lattice subatomic particles unearthing excited hadron resonances High performance computing Monte Carlo methods Physical sciences Quantum mechanics Scientific computing Visualization HPC Monte Carlo computer applications computing methodologies high-performance computing modeling physical sciences and engineering scientific computing simulation visualization

来源：评论

学校读者我要写书评

暂无评论

M2SKD: Multi-to-Single Knowledge Distillation of Real-Time Epileptic Seizure Detection for Low-Power Wearable Systems

引用

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY 2024年第5期15卷 1-31页

作者： Baghersalimi, Saleh Amirshahi, Alireza Forooghifar, Farnaz Teijeiro, Tomas Aminifar, Amir Atienza, David Ecole Polytech Fed Lausanne Lausanne Switzerland Basque Ctr forApplied Math BCAM Bilbao Spain Lund Univ Lund Sweden

Integrating low-power wearable systems into routine health monitoring is an ongoing challenge. Recent advances in the computation capabilities of wearables make it possible to target complex scenarios by exploiting multiple biosignals and using high-performance algorithms, such as Deep Neural Networks (DNNs). However, there is a tradeoff between the algorithms' performance and the low-power requirements of platforms with limited resources. Besides, physically larger and multi-biosignal-based wearables bring significant discomfort to the patients. Consequently, reducing power consumption and discomfort is necessary for patients to use wearable devices continuously during everyday life. To overcome these challenges, in the context of epileptic seizure detection, we propose the Multi-to-Single Knowledge Distillation (M2SKD) approach targeting singlebiosignal processing in wearable systems. The starting point is to train a highly-accurate multi-biosignal DNN, then apply M2SKD to develop a single-biosignal DNN solution for wearable systems that achieves an accuracy comparable to the original multi-biosignal DNN. To assess the practicality of our approach to real-life scenarios, we perform a comprehensive simulation experiment analysis on several edge computing platforms.

关键词： Mathematics of computing Dimensionality reduction computing methodologies Time series analysis Supervised learning by classification

来源：评论

学校读者我要写书评

暂无评论

Enhancing Lyrics Rewriting with Weak Supervision from Grammatical Error Correction Pre-training and Reference Knowledge Fusion

引用

ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING 2024年第11期23卷 1-26页

作者： Li, Jiajia Wang, Ping Li, Zuchao Parnow, Kevin Zhao, Hai Ding, Weiping Wuhan Univ Wuhan Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples R China Nantong Univ Nantong Peoples R China

Lyric rewriting involves taking the original lyrics of a song and creatively rephrasing them while preserving their core meaning and emotional essence. Sequence-to-sequence methods often face the problem of lack of annotated corpus and difficulty in understanding lyrics when dealing with the lyric rewriting task. Inspired by the language rewriting technique, grammatical error correction (GEC) and sequence-to-sequence generation techniques, and neural machine translation (NMT) methods, we propose novel self-supervised learning methods that can effectively solve the problem of the lack of a lyric rewriting corpus. In addition, we also propose a new pretrained DAE Transformer model with data prior knowledge fusion to enhance the lyric rewriting ability. The reference-as-context model (RaC-Large) constructed by us based on these two methods achieves the best results in comparison with the baseline including large language models, fully verifying the effectiveness of the new method. We also validate the effectiveness of our approach on GEC and NMT tasks, further demonstrating the potential of our approach on a broad range of sequence-to-sequence tasks.

关键词： computing methodologies Lexical semantics

来源：评论

学校读者我要写书评

暂无评论

Online URL Classification for Large-Scale Streaming Environments

引用

IEEE INTELLIGENT SYSTEMS 2017年第2期32卷 31-36页

作者： Singh, Neetu Chaudhari, Narendra S. Singh, Nidhi Cent Univ Himachal Pradesh Dept Comp Sci Shahpur Himachal Prades India Visvesvaraya Natl Inst Technol Nagpur Maharashtra India Intel Secur Duisburg Germany

Large-scale streaming URLs are the norm in many commercial software products that aim to filter URLs based on their sensitivity or risk level. In such problem scenarios, filtering is typically done by classifying a URL using either its webpage content or certain additional contextual information. However, such approaches are slow and computationally expensive, as they require gathering and processing webpage content or other contextual information for each URL. In this work, the authors propose a method for classifying URLs in large-scale streaming environments that doesn"t suffer from these drawbacks. The proposed method is based on online ensemble learning, which results in lightweight prediction models that are well-suited for classification of streaming datasets. The authors illustrate the effectiveness of the proposed approach using large-scale datasets from a live, production environment and show that the proposed method results in an increase of 5 to 8 percent in terms of precision and 3 to 5.5 percent in terms of recall.

关键词： Uniform resource locators Training Mathematical model Computational modeling Internet Predictive models Artificial intelligence Expert systems Big data INSPEC: Controlled Indexing Internet learning (artificial intelligence) pattern classification INSPEC: Non-Controlled Indexing streaming dataset classification contextual information Webpage content commercial software products large-scale streaming environments online URL classification Author Keywords computing methodologies artificial intelligence applications expert systems pattern recognition applications big data intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Knowledge Discovery in the Blogosphere Approaches and Challenges

引用

IEEE INTERNET computing 2010年第2期14卷 24-32页

作者： Lakshmanan, Geetika T. Oberhofer, Martin A. IBM T. J. Watson Research Center Cambridge

Knowledge discovery in blogs is different from knowledge discovery in areas such as databases or Web documents due to blogs' unique characteristics, which introduce additional mining challenges. Although researchers have investigated several techniques to address different aspects of blog discovery, no comparisons among key knowledge discovery techniques for blogs exist. This article examines three prominent techniques that are frequently applied to discovery in blogs - clustering, matrix decomposition, and ranking. The authors compare them in terms of effectiveness in combating present challenges and their ability to accomplish challenging tasks required for effective blog mining.

关键词： Knowledge Retrieval Knowledge Management Artificial Intelligence computing methodologies Clustering Information Search And Retrieval Information Storage And Retrieval Information Technology And Systems Interactive Data Exploration And Discovery Database Applications Database Management Mining Methods And Algorithms Blogs Trend Analysis Topic Detection Collective Wisdom

来源：评论

学校读者我要写书评

暂无评论

Web-based UMLS concept retrieval by automatic text scanning: a comparison of two methods

引用

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2001年第1期64卷 37-43页

作者： Brandt, C Nadkarni, P Yale Univ Sch Med Yale Ctr Med Informat New Haven CT 06520 USA

The Web is increasingly the medium of choice for multi-user application program delivery. Yet selection of an appropriate programming environment for rapid prototyping, code portability, and maintainability remain issues. We summarize our experience on the conversion of a LISP Web application, Search/SR to a new, functionally identical application, Search/SR-ASP using a relational database and active server pages (ASP) technology. Our results indicate that provision of easy access to database engines and external objects is almost essential for a development environment to be considered viable for rapid and robust application delivery. While LISP itself is a robust language, its use in Web applications may be hard to justify given that current vendor implementations do not provide such functionality. Alternative, currently available scripting environments for Web development appear to have most of LISP's advantages and few of its disadvantages. (C) 2001 Elsevier Science Ireland Ltd. All rights reserved.

关键词： computing methodologies internet programming languages LISP active server pages VBScript

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Consent Platform for Active Assisted Living: Modeling Study and Conceptual Framework

引用

JOURNAL OF MEDICAL INTERNET RESEARCH 2020年第12期22卷 e20832页

作者： Velmovitsky, Pedro Elkind Da Silva E Souza Miranda, Pedro Augusto Vaillancourt, Helene Donovska, Tania Teague, Jennifer Morita, Plinio Pelegrini Univ Waterloo Sch Publ Hlth & Hlth Syst 200 Univ Ave W Waterloo ON N2L 3G1 Canada CSA Grp Toronto ON Canada Univ Waterloo Res Inst Aging Waterloo ON Canada Univ Waterloo Dept Syst Design Engn Waterloo ON Canada Univ Hlth Network Techna Inst eHlth Innovat Toronto ON Canada Univ Toronto Dalla Lana Sch Publ Hlth Inst Hlth Policy Management & Evaluat Toronto ON Canada

Background: Recent advancements in active assisted living (AAL) technologies allow older adults to age well in place. However, sensing technologies increase the complexity of data collection points, making it difficult for users to consent to data collection. One possible solution for improving transparency in the consent management process is the use of blockchain, an immutable and timestamped ledger. Objective: This study aims to provide a conceptual framework based on technology aimed at mitigating trust issues in the consent management process. Methods: The consent management process was modeled using established methodologies to obtain a mapping of trust issues. This mapping was then used to develop a conceptual framework based on previous monitoring and surveillance architectures for connected devices. Results: In this paper, we present a model that maps trust issues in the informed consent process;a conceptual framework capable of providing all the necessary underlining technologies, components, and functionalities required to develop applications capable of managing the process of informed consent for AAL, powered by blockchain technology to ensure transparency;and a diagram showing an instantiation of the framework with entities comprising the participants in the blockchain network, suggesting possible technologies that can be used. Conclusions: Our conceptual framework provides all the components and technologies that are required to enhance the informed consent process. Blockchain technology can help overcome several privacy challenges and mitigate trust issues that are currently present in the consent management process of data collection involving AAL technologies.

关键词： health care blockchain Internet of Things aging informed consent mobile phone computing methodologies computer security

来源：评论

学校读者我要写书评

暂无评论

Expression imbalance map: a new visualization method for detection of mRNA expression imbalance regions

引用

PHYSIOLOGICAL GENOMICS 2003年第1期13卷 31-46页

作者： Kano, M Nishimura, K Ishikawa, S Tsutsumi, S Hirota, K Hirose, M Aburatani, H Univ Tokyo Sch Engn Tokyo 1138655 Japan Univ Tokyo Sch Informat Sci & Technol Tokyo 1138655 Japan Univ Tokyo Adv Sci & Technol Res Ctr Dept Informat Syst Tokyo 1538904 Japan Univ Tokyo Genome Sci Div Tokyo 1538904 Japan

We describe the development of a new visualization method, called the expression imbalance map (EIM), for detecting mRNA expression imbalance regions, reflecting genomic losses and gains at a much higher resolution than conventional technologies such as comparative genomic hybridization (CGH). Simple spatial mapping of the microarray expression profiles on chromosomal location provides little information about genomic structure, because mRNA expression levels do not completely reflect genomic copy number and some microarray probes would be of low quality. The EIM, which does not employ arbitrary selection of thresholds in conjunction with hypergeometric distribution-based algorithm, has a high tolerance of these complex factors. The EIM could detect regionally underexpressed or overexpressed genes (called, here, an expression imbalance region) in lung cancer specimens from their gene expression data of oligonucleotide microarray. Many known as well as potential loci with frequent genomic losses or gains were detected as expression imbalance regions by the EIM. Therefore, the EIM should provide the user with further insight into genomic structure through mRNA expression.

关键词： gene expression profiling allelic imbalance chromosome mapping hypergeometric distribution computing methodologies

来源：评论

学校读者我要写书评

暂无评论

Detecting Fall Risk Factors for Toddlers

引用

IEEE PERVASIVE computing 2011年第1期10卷 82-89页

作者： Na, Hana Qin, Sheng-Feng Wright, David K. Brunel Univ Sch Engn & Design Uxbridge UB8 3PH Middx England

Preventing accidental injuries of toddlers requires thorough, consistent supervision, but this isn't always practical. A proposed vision-based system detects three fall risk factors in the home environment to help caregivers supervise nearby toddlers when they can't give continuous attention to the toddlers. The crucial technical challenge is to differentiate a human from other foreground objects in the images. Unlike previous systems, this one uses multiple dynamic motion cues for human detection, employing cues related to human appearance.

关键词： computer applications computing methodologies health image processing and computer vision implementation life and medical sciences pattern recognition pervasive computing real-time systems Accidental Injury Ubiquitous computing transistor diode logic real-time systems computing methodologies health APPLIED COMPUTER SCIENCE Medicine home environment toddler Pattern recognition fall risk

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：