检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Big Data, BigData 2024

作者： Pang, Andrew Jang, Hyeju Fang, Shiaofen Horace Greeley High School ChappaquaNY United States Indiana University Indianapolis Luddy School of Informatics Computing and Engineering United States

ISBN: (纸本)9798350362480

Machine learning algorithms play a pivotal role in a wide range of Artificial Intelligence (AI) applications. Explaining the results and behavior of a machine learning model, however, remains a challenge. In this paper, we present a new approach to the explanation of machine learning models using a large language model (LLM). In this work, we seek natural language descriptions of the behavioral patterns of a machine learning model by a combination of prompting and model sampling. A subspace sampling technique is developed to generate ML model outputs using partial features in a user defined space. A projective visualization method is employed to guide the sampling process, including user-directed interactive sampling and feature-based sampling, so that an optimal amount of information can be provided to the LLM to ensure accurate and concise natural language explanations. Two public datasets, a student performance dataset and a weather dataset, were used to test our approach under various conditions. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Understanding Power Transformer Current-Voltage (I-V) Lissajous Pattern Under Different Faults 10

Understanding Power Transformer Current-Voltage (I-V) Lissaj...

引用

10th International Conference on Condition Monitoring and Diagnosis, CMD 2024

作者： Arsya, Nanda Redha Suwarno Abu-Siada, A. Bandung Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia School of Electrical Engineering Computing and Mathematical Science Curtin University Perth Australia

ISBN: (纸本)9788986510225

Condition-based maintenance (CBM) is a robust maintenance strategy suitable for high-criticality assets, including Power Transformers. Various measurements and tests are conducted by current industry practice to assess the condition of power transformers. One common method used to assess the mechanical integrity of transformers is Sweep Frequency Response Analysis (SFRA). SFRA testing is performed to detect any changes due to windings or core deformations. However, the main drawback of this method is its offline nature and the requirement for high level of expertise to analyze the results. Several studies have been conducted to address these challenges. One proposed solution in the literature is to employ Current-Voltage (I-V) Lissajous Pattern as a fingerprint for operating transformers. The method requires voltage and current measurements at both sides of each phase at the power frequency. Hence, it has the potential to be implemented online whereas, any deviation from the fingerprint raises an alarm for potential internal faults. However, the literature lacks of a comprehensive study on the detailed impact of various faults on the proposed fingerprint. This paper is aimed to investigate the impact of various fault types and levels on the transformer I-V Lissajous pattern. In this regard, simulations have been conducted on a detailed high-frequency power transformer equivalent circuit using PSIM software tool. Results are aimed to provide insights to understand power transformers I-V Lissajous patterns under different faults. With clear understanding, the I-V Lissajous method can be widely applied for other critical assets in the power grid in the future. © 2024 The Korean Institute of Electrical Engineers (KIEE).

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Empirical Study on Data Attributes Insufficiency of Evaluation Benchmarks for LLMs 31

Empirical Study on Data Attributes Insufficiency of Evaluati...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Liu, Chuang Jin, Renren Yao, Zheng Li, Tianyi Cheng, Liang Steedman, Mark Xiong, Deyi College of Intelligence and Computing Tianjin University China School of Electrical Engineering and Computer Science University of Queensland Australia School of Informatics University of Edinburgh United Kingdom

ISBN: (纸本)9798891761964

Previous benchmarks for evaluating large language models (LLMs) have primarily emphasized quantitative metrics, such as data volume. However, this focus may neglect key qualitative data attributes that can significantly impact the final rankings of LLMs, resulting in unreliable leaderboards. In this paper, we investigate whether current LLM benchmarks adequately consider these data attributes. We specifically examine three attributes: diversity, redundancy, and difficulty. To explore these attributes, we propose a framework with three separate modules, each designed to assess one of the attributes. Using a method that progressively incorporates these attributes, we analyze their influence on the benchmark. Our experimental results reveal a meaningful correlation between LLM rankings on the revised benchmark and the original benchmark when these attributes are accounted for. These findings indicate that existing benchmarks often fail to meet all three criteria, highlighting a lack of consideration for multifaceted data attributes in current evaluation datasets. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Global Inference Network for One-Stage Referring Expression Comprehension

引用

IEEE Transactions on Neural Networks and Learning Systems 2023年第1期34卷 134-143页

作者： Zhou, Yiyi Ji, Rongrong Luo, Gen Sun, Xiaoshuai Su, Jinsong Ding, Xinghao Lin, Chia-Wen Tian, Qi Xiamen University Media Analytics and Computing Laboratory Xiamen361005 China Xiamen University School of Informatics Informatics and Communication Engineering Department Xiamen361005 China School of Informatics Xiamen University Media Analytics and Computing Laboratory Department of Artificial Intelligence Xiamen361005 China Xiamen University School of Informatics Xiamen361005 China National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan Huawei Technologies Company Ltd. Cloud BU Shenzhen518129 China

Referring expression comprehension (REC) is an emerging research topic in computer vision, which refers to the detection of a target region in an image given a test description. Most existing REC methods follow a multistage pipeline, which is computationally expensive and greatly limits the applications of REC. In this article, we propose a one-stage model toward real-time REC, termed real-time global inference network (RealGIN). RealGIN addresses the issues of expression diversity and complexity of REC with two innovative designs: adaptive feature selection (AFS) and Global Attentive ReAsoNing (GARAN). Expression diversity concerns varying expression content, which includes information such as colors, attributes, locations, and fine-grained categories. To address this issue, AFS adaptively fuses features of different semantic levels to tackle the changes in expression content. In contrast, expression complexity concerns the complex relational conditions in expressions that are used to identify the referent. To this end, GARAN uses the textual feature as a pivot to collect expression-aware visual information from all regions and then diffuses this information back to each region, which provides sufficient context for modeling the relational conditions in expressions. On five benchmark datasets, i.e., RefCOCO, RefCOCO+, RefCOCOg, ReferIT, and Flickr30k, the proposed RealGIN outperforms most existing methods and achieves very competitive performances against the most advanced one, i.e., MAttNet. More importantly, under the same hardware, RealGIN can boost the processing speed by 10-20 times over the existing methods. © 2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

User-Centered Phishing Detection through Personalized Edge computing 24

User-Centered Phishing Detection through Personalized Edge C...

引用

27th ACM Conference on Computer-Supported Cooperative Work and Social computing, CSCW Companion 2024

作者： Das, Sanchari Kim, DongInn Abbott, Jacob Jean Camp, L. Ritchie School of Engineering and Computer Science University of Denver DenverCO United States Luddy School of Informatics Computing and Engineering Indiana University Bloomington BloomingtonIN United States

ISBN: (纸本)9798400711145

Ensuring user-centered phishing detection is a significant challenge due to the difficulty in distinguishing threats. To address this, we propose a personalized tool - Holistic User-Centered Identification of Threats at the Edge (HUCITE). Our system utilizes probabilistic logic to provide real-time risk estimates for local machines and employs simple cartoons as a user interface. Our approach focuses on identifying anomalies in a single machine and user browsing history for the generation of a personalized green list and global threat information for a shared red list. This approach enables blocking and identification of phishing websites, potentially malicious scripts, unfamiliar domains, and previously unencountered certificate authorities. By creating a zone of safety for a specific user and identifying departures from that zone, our approach addresses the limitations of traditional anomaly detection techniques. We present the underlying architecture and approach to local risk identification, reporting on an in-lab experiment involving 45 participants to test the effectiveness of our system in various stress conditions affecting users' phishing perception. © 2024 Owner/Author.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Approach for Commodity Market Trading Strategy 1

引用

13th National Technical Symposium on Unmanned System Technology, NUSYS 2023

作者： Wong, Pei Yuin Moung, Ervin Gubin Farzamnia, Ali Yahya, Farashazillah Obit, Joe Henry Sani, Zaidatol Haslinda Abdullah Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu Malaysia Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia School of Computing and Engineering University of Huddersfield Huddersfield United Kingdom

ISBN: (数字)9789819720279

ISBN: (纸本)9789819720262

The apparent phenomena of commodity price fluctuations significantly affect the cost of living. Most current studies utilize datasets collected before the Russo-Ukrainian War and Covid-19. Moreover, many people are focusing on fund investment, exploring avenues such as commodity trading in addition to stocks and forex investments. However, most research for price prediction in commodities does not cover the periods of Covid-19 and the Russo-Ukrainian war. The aim of this project is to develop trading strategy models to predict whether to buy or sell a commodity, and to evaluate the potential rewards and profits. The dataset used contains daily historical prices of various types of commodities from the year 2000 until March 2022. Furthermore, a real-world dataset, specifically the gold trading dataset from Nasdaq, will be used to validate the performance of the best-performing trading models. The algorithms employed are reinforcement learning-based: Advantage Actor Critic (A2C) and Proximal Policy Optimization (PPO). Evaluation performance across six rounds of experiments has shown that the A2C model in a forex environment, using 80% of the dataset for training and 20% for testing, achieved the best results, with a Sharpe ratio of 0.63, a Sortino ratio of 1.0, an Omega ratio of 1.24, and a Calmar ratio of 0.55. The best-performing trading models in Objective 2 and Objective 3 are similar but employ different window sizes. Window size specifies the timesteps that will serve as reference points for the trading model to determine the next trade. Different datasets may require different window sizes, an issue that necessitates further refinement. This refinement is crucial as it involves tailoring the window size to align with the unique characteristics and volatility patterns of each dataset, thereby ensuring that the model's predictive accuracy is optimized for varied market conditions and historical trends. In conclusion, the best-performing trading model is the Advan

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

What Makes a Technology Privacy Enhancing? Laypersons’ and Experts’ Descriptions, Uses, and Perceptions of Privacy Enhancing Technologies 18th

What Makes a Technology Privacy Enhancing? Laypersons’ and...

引用

18th International Conference on Information for a Better World: Normality, Virtuality, Physicality, Inclusivity, iConference 2023

作者： Elmimouni, Houda Shusas, Erica Skeba, Patrick Baumer, Eric P. S. Forte, Andrea Luddy School of Informatics Computing and Engineering BloomingtonIN United States College of Computing and Informatics Drexel University PhiladelphiaPA United States Computer Science and Engineering Lehigh University BethlehemPA United States

ISBN: (纸本)9783031280313

What makes a technology privacy-enhancing? In this study, we construct an explanation grounded in the technologies and practices that people report using to enhance their privacy. We conducted an online survey of privacy experts (i.e., privacy researchers and professionals who attend to privacy conferences and communication channels) and laypersons that catalogs the technologies they identify as privacy enhancing and the various privacy strategies they employ. The analysis of 123 survey responses compares not only self-reported tool use but also differences in how privacy experts and laypersons explain their privacy practices and tools use. Differences between the two samples show that privacy experts and laypersons have different styles of reasoning when considering PETs: Experts think of PETs as technologies whose primary function is enhancing privacy, whereas laypersons conceptualize privacy enhancement as a supplemental function incorporated into other technologies. The paper concludes with a discussion about potential explanations for these differences, as well as questions they raise about how technologies can best facilitate communication and collaboration while enhancing privacy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Online Conversation-Based Social engineering Detection Using Machine Learning 1

引用

13th National Technical Symposium on Unmanned System Technology, NUSYS 2023

作者： Ulaganathan, Thurairaj A/L R. Moung, Ervin Gubin Farzamnia, Ali Yahya, Farashazillah Sze, Florence Sia Fui Hung, Lai Po Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu Malaysia Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia School of Computing and Engineering University of Huddersfield Huddersfield United Kingdom

ISBN: (数字)9789819720279

ISBN: (纸本)9789819720262

Social engineering through online conversations can occur via phone calls, Skype, or Google Meet, among others. This paper presents a machine learning-based classifier for detecting scam conversations in various online formats, including live call conversations. However, selecting an appropriate dataset and the optimal vectorization technique for the algorithm remains challenging, and many fraudulent scams remain undetectable in online conversations. Consequently, six experiments were conducted to apply a machine learning classifier, resulting in 108 outcomes. All six experiments demonstrate that different classifiers possess unique strengths and weaknesses when applied to different scenarios. When compared to Doc2Vec, the vectorization techniques of Universal Sentence Encoder yield excellent results. Among various clustering methods, K-Means and the EM algorithm perform exceptionally well. The results reveal that Random Forest and CatBoost classifiers outperform others in terms of accuracy, precision, recall, and F1-score across all cases. These findings can contribute to enhancing the detection of scam attempts in live call conversations, thus helping protect individuals from falling victim to scams. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Automated Sleep Staging Classification System Based on Convolutional Neural Network Using Polysomnography Signals 1

引用

13th National Technical Symposium on Unmanned System Technology, NUSYS 2023

作者： Azrin, Muhd Luqman Bin Farzamnia, Ali Fan, Liau Chung Moung, Ervin Gubin Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu Malaysia School of Computing and Engineering University of Huddersfield Huddersfield United Kingdom

ISBN: (数字)9789819720279

ISBN: (纸本)9789819720262

Sleep is a crucial bodily process that plays a vital role in maintaining overall health and well-being. When diagnosing and treating sleep disorders, the initial step is sleep staging. However, manual sleep staging by physicians can be complicated, leading to a growing interest in computer-aided sleep stage classification algorithms. In this research, a method was introduced for automatically classifying sleep stages by extracting distinctive representations from single-channel EEG signals. PSG signals are selected exclusively for the project because they directly capture the essential physiological changes needed for sleep staging, ensuring both data relevance and quality. This choice also aligns with the project’s goal of feasibility and computational efficiency while avoiding potential ethical and privacy issues linked to audio and video data. Furthermore, it conforms to established practises in the field, ensuring consistency in benchmarking. A filterbank is applied by dividing the range of the frequency signal into two 15 sub epochs. The activity of the signal within distinct frequency ranges during different sleep stages was fully comprehended by computing the standard deviation as a single characteristic from different frequency subbands of the EEG. These characteristics served as the input for a two-stream convolutional neural network (CNN) that was trained using a two-stage learning methodology for classification. These characteristics served as the input for a two-stream convolutional neural network (CNN) that was trained using a two-stage learning methodology for classification. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

A Cocoa Ripeness Detection and Classification Model Based on Improved YOLOv5s 10

A Cocoa Ripeness Detection and Classification Model Based on...

引用

10th International Conference on Advanced informatics: Concept, Theory and Application, ICAICTA 2023

作者： Ayubi, Aula Faiz, Muhammad Situmorang, George B. Ramadhani, Kurniawan Nur Utama, Nugraha P. School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Telkom University of School of Computing Bandung Indonesia

ISBN: (纸本)9798350329919

The present study introduces a novel approach to identifying the maturity of cacao fruits, utilizing YOLOv5s in tandem with the Convolutional Block Attention Module (CBAM). The efficacy of this method was evaluated on two distinct datasets, namely the Cocoa Maturity Dataset TCS 01 and the dataset from PT. Cargill Indonesia. The integration of CBAM into the network is aimed at enhancing the feature representation of the model, leading to an improvement in detection accuracy. The method under consideration demonstrated efficacy in attaining elevated levels of precision while concurrently maintaining a condensed model magnitude, thereby conferring benefits for real-world applications. The results indicate that the suggested approach holds promise for enhancing the cacao industry by increasing the level of cocoa cultivation productivity. © 2023 IEEE.

关键词： Object detection

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：