检索结果-内蒙古大学图书馆

International IoT, Electronics and Mechatronics Conference, IEMTRONICS 2024

作者： Bhattacharya, Swarnadwip Bhattacharjee, Anindita Das Roy, Pranab Singha Samanta, Tapas Department of Computer Science and Engineering Institute of Engineering and Management Kolkata700091 India Department of CSE IEM Centre of Excellence for InnovAI Institute of Engineering and Management Kolkata700091 India Department of Computer and Informatics Variable Energy Cyclotron Centre Kolkata700064 India

ISBN: (纸本)9789819747795

This paper aims to improve Llama 2’s performance by using personalized and modified datasets. Despite the impressive capabilities of large language models (LLMs) such as Llama 2, their effectiveness may be limited in specialized domains. The proposed method entails fine-tuning Llama 2 on custom datasets to optimize performance efficiently. The study focuses on the impact of quantization-aware low-rank adapter layers (QLoRA) on a single GPU’s resource-efficient fine-tuning performance. Furthermore, the study looks into the design of instruction datasets to guide the model toward desired behaviors. When Llama 2 is fine-tuned with QLoRA, performance improves significantly across tasks such as text summarization, question answering, and natural language generation in a variety of domains. The paper concludes by highlighting the broader implications of the findings. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Custom datasets Fine-tuning Instruction datasets Large language models (LLMs) Llama 2 Personalized datasets QLoRA Quantization-aware low-rank adapter layers (QLoRA) Resource-efficient fine-tuning Specialized domains

来源：评论

学校读者我要写书评

暂无评论

A Social Robot Companion for Individuals Eating Alone 25

A Social Robot Companion for Individuals Eating Alone

引用

30th International Conference on Intelligent User Interfaces Companion, IUI 2025

作者： Soufargi, Selim Niewiadomski, Radoslaw Fong, Hunter Mancini, Maurizio Department of Computer Science Sapienza University of Rome Rome Italy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa Italy

ISBN: (纸本)9798400714092

In this paper, we present the first implementation of a social robot acting as a companion for individuals eating alone. Our system can engage in multimodal interactions with the user during meals. It conducts conversations on various topics, complemented by gestures and other nonverbal behaviors. The system comprises a NAO robot, human activity recognition modules, a speech recognition module, and a dialog management system integrated with an LLM model. In the paper, we present a technical description of the system and the interaction flow, as well as discuss the possible applications and planned validation. © 2025 Copyright held by the owner/author(s).

关键词： Social robots

来源：评论

学校读者我要写书评

暂无评论

The Threshold of Existence of δ-Temporal Cliques in Random Simple Temporal Graphs 20th

The Threshold of Existence of δ-Temporal Cliques in Rand...

引用

20th International Symposium on Algorithmics of Wireless Networks, ALGOWIN 2024

作者： Mertzios, George B. Nikoletseas, Sotiris Raptopoulos, Christoforos Spirakis, Paul G. Department of Computer Science Durham University Durham United Kingdom Computer Engineering and Informatics Department University of Patras Patras Greece Department of Mathematics University of Patras Patras Greece Department of Computer Science University of Liverpool Liverpool United Kingdom

ISBN: (纸本)9783031745799

We consider random simple temporal graphs in which every edge of the complete graph Kn appears once within the time interval [0, 1] independently and uniformly at random. Our main result is a sharp threshold on the size of any maximum δ-clique (namely a clique with edges appearing at most δ apart within [0, 1]) in random instances of this model, for any constant δ. In particular, using the probabilistic method, we prove that the size of a maximum δ-clique is approximately 2lognlog1δ with high probability (whp). We note that, even though the random simple temporal graph contains Θ(n2) overlapping δ-windows, which (when viewed separately) correspond to different random instances of the Erdős-Rényi random graphs model, the size of the maximum δ-clique in the former model and the maximum clique size of the latter are approximately the same. Furthermore, we show that the minimum interval containing a δ-clique is δ-o(δ) whp. We use this result to show that any polynomial time algorithm for δ-Temporal Clique is unlikely to have very large probability of success. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： probabilistic method Simple random temporal graph δ-temporal clique

来源：评论

学校读者我要写书评

暂无评论

Structure learning of Bayesian networks using sparrow optimization algorithm

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2025年第2期9卷 14-25页

作者： Kareem, Shahab Wahhab Awla, Hoshang Qasim Mohammed, Amin Salih Department of Technical Information Systems Engineering Erbil Technical Engineering College Erbil Polytechnic University Erbil Iraq Department of Computer Technical Engineering Al-Qalam University College Kirkuk Iraq Department of Computer Science Faculty of Science Soran University Soran Iraq Department of Software and Informatics Salahaddin University Erbil Iraq

Bayesian networks are powerful analytical models in machine learning, used to represent probabilistic relationships among variables and create learning structures. These networks are made up of parameters that show conditional probabilities and a structure that shows how random variables interact with each other. The structure is shown by a directed acyclic graph. Despite the NP-hard nature of learning Bayesian network structures, there has been significant progress in improving the accuracy of approximation solutions. The main focus is on score-based search strategies, which make use of functions to evaluate network models and identify structures with high scores. This study is significantly focused on structure learning Bayesian networks using the Bayesian Dirichlet equivalent uniform scoring function and metaheuristic search strategies. To this end, this paper presents the sparrow optimization algorithm (SOA), a new metaheuristic algorithm derived from the foraging behavior of sparrows. SOA performs a concurrent optimization in the solution space by simultaneously performing a local and global search that leads to the discovery of near-optimal structures. The results from our experiments on several benchmark datasets show that SOA yields overall better performance than SA and greedy search algorithms. In particular, it is claimed that by applying the proposed approach of SOA, the convergence speed is significantly higher compared with the existing ones;F1 score is 0.35 and 0.05 for the Hamming distance with better results. Given these results, signed operators prove to be very efficient in SOA’s Bayesian network structure learning as a concept, especially for real-world use. © (2024), (Society of Sytematic Innovation). All Rights Reserved.

关键词： Bayesian Network Global and Local Search Search and Score Sparrow Search Optimization Algorithm Structure Learning

来源：评论

学校读者我要写书评

暂无评论

A Benchmark for Multi-Speaker Anonymization

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 3819-3833页

作者： Miao, Xiaoxiao Tao, Ruijie Zeng, Chang Wang, Xin Singapore Institute of Technology Singapore567739 Singapore National University of Singapore Electrical and Computer Engineering Department Queenstown 117583 Singapore National Institute of Informatics Chiyoda-ku Tokyo101-8340 Japan

Privacy-preserving voice protection approaches primarily suppress privacy-related information derived from paralinguistic attributes while preserving the linguistic content. Existing solutions focus particularly on single-speaker scenarios. However, they lack practicality for real-world applications, i.e., multi-speaker scenarios. In this paper, we present an initial attempt to provide a multi-speaker anonymization benchmark by defining the task and evaluation protocol, proposing benchmarking solutions, and discussing the privacy leakage of overlapping conversations. The proposed benchmark solutions are based on a cascaded system that integrates spectral-clustering-based speaker diarization and disentanglement-based speaker anonymization using a selection-based anonymizer. To improve utility, the benchmark solutions are further enhanced by two conversation-level speaker vector anonymization methods. The first method minimizes the differential similarity across speaker pairs in the original and anonymized conversations, which maintains original speaker relationships in the anonymized version. The other minimizes the aggregated similarity across anonymized speakers, which achieves better differentiation between speakers. Experiments conducted on both non-overlap simulated and real-world datasets demonstrate the effectiveness of the multi-speaker anonymization system with the proposed speaker ***, we analyzed overlapping speech regarding privacy leakage and provided potential solutions © 2005-2012 IEEE.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

Sobol Sequence Optimization for Hardware-Efficient Vector Symbolic Architectures

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年第3期44卷 937-950页

作者： Aygun, Sercan Najafi, Hassan University of Louisiana at Lafayette School of Computing and Informatics LafayetteLA70503 United States Case Western Reserve University Electrical Computer and Systems Engineering Department ClevelandOH44106 United States

Hyperdimensional computing (HDC) is an emerging computing paradigm with significant promise for efficient and robust learning. In HDC, objects are encoded with high-dimensional vector symbolic sequences called hypervectors. The quality of hypervectors, defined by their distribution and independence, directly impacts the performance of HDC systems. Despite a large body of work on the processing parts of HDC systems, little to no attention has been paid to data encoding and the quality of hypervectors. Most prior studies have generated hypervectors using inherent random functions, such as MATLAB’s or Python’s random function. This work introduces an optimization technique for generating hypervectors by employing quasi-random sequences. These sequences have recently demonstrated their effectiveness in achieving accurate and low-discrepancy data encoding in stochastic computing systems. The study outlines the optimization steps for utilizing Sobol sequences to produce high-quality hypervectors in HDC systems. An optimization algorithm is proposed to select the most suitable Sobol sequences via indexes for generating minimally correlated hypervectors, particularly in applications related to symbol-oriented architectures. The performance of the proposed technique is evaluated in comparison to two traditional approaches of generating hypervectors based on linear-feedback shift registers and MATLAB random functions. The evaluation is conducted for three applications: 1) language;2) headline;and 3) medical image classification. Our experimental results demonstrate accuracy improvements of up to 10.79%, depending on the vector size. Additionally, the proposed encoding hardware exhibits reduced energy consumption and a superior area-delay product. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuned Attribute Weighted Naïve Bayes with Modified Partial Instances Reduction for Gaming Disorder Classification

HighTech and Innovation Journal

引用

HighTech and Innovation Journal 2025年第1期6卷 67-80页

作者： Latubessy, Anastasya Wardoyo, Retantyo Musdholifah, Aina Kusrohmaniah, Sri Doctoral Program Department of Computer Science and Electronics Faculty of Mathematics and Natural Science Universitas Gadjah Mada Yogyakarta55281 Indonesia Department of Informatics Engineering Faculty of Engineering Universitas Muria Kudus Indonesia Department of Computer Science and Electronics Faculty of Mathematics and Natural Science Universitas Gadjah Mada Yogyakarta55281 Indonesia Department of Psychology Faculty of Psychology Universitas Gadjah Mada Yogyakarta55281 Indonesia

Fine Tuning Attribute Weighted Naïve Bayes (FTAWNB) is a reliable modified Naïve Bayes model. Even though it is able to provide high accuracy on ordinal data, this model is sensitive to outliers. To improve the performance of FTAWNB, this research modified the Partial Instances Reduction (PIR) technique to make the FTAWNB more adaptive to outliers. Nevertheless, in contrast to the original PIR technique, which substitutes missing values for data values deemed outliers, the PIR technique suggested in this study replaces data values deemed outliers using a Naïve Bayes weighting approach. The attribute values from the outlier data are replaced with the highest probability values for the attributes in the actual class. This PIR technique is referred to as modified PIR. The FTAWNB model with modified PIR has been evaluated using the Gaming Disorder dataset. Replacing the four attributes with the least amount of information resulted in accuracy gains of 99.74%, an increase of 1.53% over the FTAWNB model. The experimental result shows that adding the modified PIR technique to the FTAWNB model can handle the outlier in the data, proving it by increasing the performance in terms of accuracy, precision, and recall without pruning the dataset used. © 2025, Ital Publication. All rights reserved.

关键词： Attribute Weighted Classification Fine-Tune Gaming Disorder Instances Reduction Naïve Bayes

来源：评论

学校读者我要写书评

暂无评论

Performance and Implementation Comparison of Knuth-Morris-Pratt and Boyer-Moore String Search Algorithms 2

Performance and Implementation Comparison of Knuth-Morris-Pr...

引用

2nd International Conference on Advanced Innovations in Smart Cities, ICAISC 2025

作者： Saleh, Taj Ergin, Fatma Corut Malkawi, Malek Alhajj, Reda Department of Computer Engineering Marmara University Istanbul Turkey Department of Computer Engineering Istanbul Medipol University Istanbul Turkey Department of Computer Science University of Calgary Alberta Canada Department of Heath Informatics University of Southern Denmark Odense Denmark

ISBN: (纸本)9798331506995

String search algorithms play an important role in many research areas such as data mining and bioinformatics. While there exist a number of algorithms that handles the topic, we are exploring the the Knuth-Morris-Pratt (KMP) and Boyer-Moore algorithms due to their efficiency and versatility. In this work, we compared the algorithms in terms of characteristics, performance and implementation details. We also tested both the algorithms with various patterns and texts that differs in size. We also analyzed the performance of the algorithms on 4 different processors to understand the technological advancements effects on their performance. Our findings suggest that the BM algorithm perform better with large texts and patterns, while the KMP algorithm is better suited for smaller ones. Also, while newer processor generally exhibit improved performance, the significance of these enhancements may vary. Thus, we should rather be looking specific architectural advancements within generations rather than focusing solely on the generational gap. © 2025 IEEE.

关键词： String searching algorithms

来源：评论

学校读者我要写书评

暂无评论

A fusion of machine learning and cryptography for fast data encryption through the encoding of high and moderate plaintext information blocks

引用

Multimedia Tools and Applications 2025年第8期84卷 5349-5375页

作者： Shafique, Arslan Mehmood, Abid Alawida, Moatsum Elhadef, Mourad Rehman, Mujeeb Ur School of Biomedical Engineering University of Glasgow Glasgow United Kingdom Department of Computer Sciences Abu Dhabi University Abu Dhabi United Arab Emirates Cyber Technology Institute School of Computer Science and Informatics De Montfort University Leicester United Kingdom

Within the domain of image encryption, an intrinsic trade-off emerges between computational complexity and the integrity of data transmission security. Protecting digital images often requires extensive mathematical operations for robust security. However, this computational burden makes real-time applications unfeasible. The proposed research addresses this challenge by leveraging machine learning algorithms to optimize efficiency while maintaining high security. This methodology involves categorizing image pixel blocks into three classes: high-information, moderate-information, and low-information blocks using a support vector machine (SVM). Encryption is selectively applied to high and moderate information blocks, leaving low-information blocks untouched, significantly reducing computational time. To evaluate the proposed methodology, parameters like precision, recall, and F1-score are used for the machine learning component, and security is assessed using metrics like correlation, peak signal-to-noise ratio, mean square error, entropy, energy, and contrast. The results are exceptional, with accuracy, entropy, correlation, and energy values all at 97.4%, 7.9991, 0.0001, and 0.0153, respectively. Furthermore, this encryption scheme is highly efficient, completed in less than one second, as validated by a MATLAB tool. These findings emphasize the potential for efficient and secure image encryption, crucial for secure data transmission in rea-time applications. © The Author(s) 2024.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Fingerprint Matching for Noisy and Distorted Patterns using a Siamese Network with ResNet50 and Multihead Attention

引用

IEEE Access 2025年 13卷 88047-88064页

作者： Sawhney, Tinny Sharma, Ashu Abrol, Pawanesh Lehana, Parveen Kumar Chaahat Yadav, Vaishali Scherer, Rafal Kulakov, Oleksii AlZubi, Ahmad Ali University of Jammu DSP Lab Department of Electronics India University of Jammu Department of Computer Science and IT India Chitkara University Institute of Engineering and Technology Chitkara University Department of Computer Science and Engineering Punjab India Manipal University Jaipur Jaipur India Czestochowa University of Technology Department of Artificial Intelligence Częstochowa Poland National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute" Faculty of Informatics and Software Engineering Kyiv Ukraine King Saud University Community College Department of Computer Science Riyadh Saudi Arabia

Dermatoglyphics, the study of unique ridge patterns on fingertips, plays a crucial role in fingerprint-based identification. However, skin conditions such as psoriasis, eczema, and verruca vulgaris can distort these patterns. This distortion creates challenges for fingerprint matching systems in forensic science and biometric authentication. This paper proposes a Siamese network with a modified ResNet50 architecture and multihead attention mechanisms to improve fingerprint matching under such distortions. The Siamese network enables the system to compare fingerprint pairs effectively, even under distortions. The modified ResNet50 architecture captures intricate ridge patterns, while the multihead attention mechanisms focus on critical fingerprint regions. Overall, the proposed approach enhances the system’s ability to learn discriminative features. As a result, it can effectively differentiate between matched and unmatched fingerprint pairs, even in the presence of moderate to extreme noise. The proposed system was trained on the Sokoto coventry fingerprint dataset (SOCOFing) and a custom dataset. Experimental results demonstrate high accuracy, with the system achieving 99.47% accuracy under low noise conditions and 90% under moderate noise. However, performance declined to 55.56% under extreme distortions. A comparative analysis highlighted the superiority of the proposed system over widely used minutiae-based methods. The latter exhibited a significant drop in matching scores, falling below 15% for highly distorted fingerprints. These findings underscore the limitations of traditional fingerprint recognition techniques and highlight the effectiveness of proposed approach in handling dermatoglyphic distortions. © 2013 IEEE.

关键词： Feature Selection

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：