检索结果-内蒙古大学图书馆

RAKG:Document-level Retrieval Augmented Knowledge Graph Construction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Hairong Si, Jiaheng Yan, Guohang Qi, Boyuan Cai, Pinlong Mao, Song Wang, Ding Shi, Botian Shanghai Artificial Intelligence Laboratory China School of Statistics and Data Science Nankai University Tianjin China Faculty of Computing Harbin Institute of Technology China Computer School Beijing Information Science and Technology University China

With the rise of knowledge graph based retrieval-augmented generation (RAG) techniques such as GraphRAG and Pike-RAG, the role of knowledge graphs in enhancing the reasoning capabilities of large language models (LLMs) has become increasingly prominent. However, traditional Knowledge Graph Construction (KGC) methods face challenges like complex entity disambiguation, rigid schema definition, and insufficient cross-document knowledge integration. This paper focuses on the task of automatic document-level knowledge graph construction. It proposes the Document-level Retrieval Augmented Knowledge Graph Construction (RAKG) framework. RAKG extracts pre-entities from text chunks and utilizes these pre-entities as queries for RAG, effectively addressing the issue of long-context forgetting in LLMs and reducing the complexity of Coreference Resolution. In contrast to conventional KGC methods, RAKG more effectively captures global information and the interconnections among disparate nodes, thereby enhancing the overall performance of the model. Additionally, we transfer the RAG evaluation framework to the KGC field and filter and evaluate the generated knowledge graphs, thereby avoiding incorrectly generated entities and relationships caused by hallucinations in LLMs. We further developed the MINE dataset by constructing standard knowledge graphs for each article and experimentally validated the performance of RAKG. The results show that RAKG achieves an accuracy of 95.91% on the MINE dataset, a 6.2 % point improvement over the current best baseline, GraphRAG (89.71%). The code is available at https://***/LMMApplication/RAKG. Copyright © 2025, The Authors. All rights reserved.

关键词： Graphic methods

Social network analysis (SNA) on Twitter contributes customer engagement on the cosmetic industry in Malaysia

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2024年第1期3153卷

作者： Wai Beng Tan Wan Yoke Chin Department of Information and Communication Technology Faculty of Computing and Information Technology Tunku Abdul Rahman University of Management and Technology Kuala Lumpur Malaysia Department of Mathematical and Data Science Faculty of Computing and Information Technology Tunku Abdul Rahman University of Management and Technology Kuala Lumpur Malaysia

The study shows Twitter’s analysis and visualization for a campaign organized by a cosmetic brand, Loreal Parisin Malaysia. It aimed to obtain insights into user interaction and to compare the usage of hashtags in social media campaigns, particularly focusing on the cosmetic brand L’Oreal Paris in Malaysia. They are used as part of online advocacy which can allow users to share User-Generated Content (UGC) related to the campaign. L’oreal Paris used digital activism in their campaigns to boost customer engagement and purchase intention. This suggests that the brand aimed to involve customers and increase their interest in purchasing their products. Hashtags, specifically #LorealParisMY and #Lorealista, were investigated in the study. The study employed Social Network Analysis (SNA), with the dataset from Twitter that was collected through the Gephi Tool – Twitter Streaming Importer v2. Social network analysis involves examining relationships and interactions within a network of users. The dataset was processed using the tool, Gephi. The study discovered the hashtag #Lorealista had a successful result in enhancing customer engagement compared to #LorealParisMY. Moreover, #Lorealista had better influential actors that lead to a wider audience by disseminating information on Twitter with network properties and network centrality. Overall, this study suggests that for the L’Oreal Paris campaign in Malaysia, the hashtag #Lorealista was more effective in achieving its objectives of customer engagement and influence on Twitter, as indicated by its greater success in user interaction and social network centrality.

关键词：

A residual attention-based privacy-preserving biometrics model of transcriptome prediction from genome

学校读者我要写书评

暂无评论

A residual attention-based privacy-preserving biometrics mod...

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Cheng Tian Song Liu Jinbao Li Guangchen Wang Luyue Kong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Department of Medicine Shandong Medical College Jinan China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

Transcriptome prediction from genetic variation data is an important task in the privacy-preserving and biometrics field, which can better protect genomic data and achieve biometric recognition through transcriptome. Many transcriptome prediction methods have achieved good accuracy from genetic variation data. However, these traditional transcriptome prediction methods have the problems of linear assumption, overfitting, expose personal privacy, and extensive manual optimization. To solve these shortcomings, we propose an attention-based transcriptome prediction model from genetic variation named RATPM that improves the accuracy of transcriptome prediction and protects participant genomic data. In RATPM, we introduce and improve the deep learning model with multi-head self-attention into the transcriptome prediction stage of Predixcan, which uncovers the non-linear relationship between genetic variation and transcriptome. Moreover, we introduce a residual attention module to generate attention-aware features and extract more accurate features at different levels from genetic variation. Furthermore, we introduce the BERT pre-training module to encode genetic variation fully utilizing their contextual information. Our research enables scientific institutions to publish only predicted transcriptomic data for biometric purposes, thus protecting the genomic information of the subjects. Finally, we evaluated our model on the 1000 Genomes and Geuvadis projects datasets to compare with other baseline models.

关键词： Privacy Biometrics (access control) Biological system modeling Genomics Predictive models Feature extraction Gene expression

Evaluation of Machine Learning Techniques for Prediction of Breast Cancer

学校读者我要写书评

暂无评论

Evaluation of Machine Learning Techniques for Prediction of ...

International Colloquium on Signal Processing & Its Applications, CSPA

作者： Jared Tan Yi Hoong Samuel-Soma M. Ajibade Muhammed Basheer Jasser Anwar P.P. Abdul Majeed David Olayemi Alebiosu Bayan Issa Anthonia Oluwatosin Adediran Charis Shwu Chen Kwan Department of Data Science and Artificial Intelligence School of Engineering and Technology Sunway University No.5 Jalan Universiti Selangor Darul Ehsan Malaysia Research Centre for Nanomaterials and Energy Technology (RCNMET) Sunway University No.5 Jalan Universiti Selangor Darul Ehsan Malaysia Faculty of Informatics Engineering University of Aleppo Syria Department of Real Estate Faculty of Built Environment Universiti Malaya Kuala Lumpur Malaysia Department of Smart Computing and Cyber Resilience School of Engineering and Technology Sunway University No.5 Jalan Universiti Selangor Darul Ehsan Malaysia

ISBN: (数字)9798331522193

ISBN: (纸本)9798331522209

The prediction of breast cancer prognosis has been a significant challenge in medical research due to the complex nature of cancer progression and the variability in patient-specific factors. Machine learning techniques have emerged as powerful tools for enhancing prediction accuracy in cancer diagnosis and prognosis. This study evaluates the performance of three widely used machine learning classifiers—Artificial Neural Network (ANN), Random Forest (RF), and Support Vector Machine (SVM)—in predicting breast cancer outcomes using the Wisconsin Breast Cancer database. A robust framework was designed to preprocess the dataset, scale features, and assess the classifiers using key evaluation metrics, including accuracy, precision, recall, F1-score, and Matthews Correlation Coefficient (MCC). The results reveal that all classifiers demonstrated high predictive accuracy, with SVM achieving the highest accuracy of 97.08%, followed by RF and ANN with 96.67%. While RF recorded superior precision (95.40%), SVM outperformed others in recall (97.70%) and F1-score (96.05%), showcasing its ability to balance prediction precision and sensitivity. These findings underscore the potential of machine learning to augment traditional cancer prognosis methods, providing healthcare professionals with data-driven insights for personalized treatment strategies. This research highlights the critical role of machine learning in transforming cancer care and lays the groundwork for future studies focused on hybrid models and real-world implementation.

关键词： Support vector machines Accuracy Machine learning Medical services Artificial neural networks Breast cancer Prognostics and health management Random forests Medical diagnostic imaging Classification tree analysis

THE ANIMAL-AI ENVIRONMENT: A VIRTUAL LABORATORY FOR COMPARATIVE COGNITION AND ARTIFICIAL INTELLIGENCE RESEARCH

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Voudouris, Konstantinos Slater, Ben Cheke, Lucy G. Halina, Marta Schellaert, Wout Hernández-Orallo, José Patel, Matishalin Alhas, Ibrahim Mecattaf, Matteo G. Burden, John Holmes, Joel Chaubey, Niharika Donnelly, Niall Crosby, Matthew Department of Psychology University of Cambridge Cambridge United Kingdom Department of History and Philosophy of Science University of Cambridge Cambridge United Kingdom VRAIN ValGRAI Universitat Politècnica de València València Spain Centre for Data Science AI and Modelling University of Hull Hull United Kingdom Leverhulme Centre for the Future of Intelligence University of Cambridge Cambridge United Kingdom Faculty of Environment Science and Economy University of Exeter Exeter United Kingdom Department of Computing Imperial College London London United Kingdom

The Animal-AI Environment is a unique game-based research platform designed to facilitate collaboration between the artificial intelligence and comparative cognition research communities. In this paper, we present the latest version of the Animal-AI Environment, outlining several major features that make the game more engaging for humans and more complex for AI systems. These features include interactive buttons, reward dispensers, and player notifications, as well as an overhaul of the environment’s graphics and processing for significant improvements in agent training time and quality of the human player experience. We provide detailed guidance on how to build computational and behavioural experiments with the Animal-AI Environment. We present results from a series of agents, including the state-of-the-art deep reinforcement learning agent Dreamer-v3, on newly designed tests and the Animal-AI Testbed of 900 tasks inspired by research in the field of comparative cognition. The Animal-AI Environment offers a new approach for modelling cognition in humans and non-human animals, and for building biologically inspired artificial intelligence. © 2023, CC BY-SA.

关键词： Invertebrates

Rate-Splitting for Cell-Free Massive MIMO: Performance Analysis and Generative AI Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zheng, Jiakang Zhang, Jiayi Du, Hongyang Zhang, Ruichen Niyato, Dusit Dobre, Octavia A. Ai, Bo The School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China The Frontiers Science Center for Smart High-speed Railway System Beijing Jiaotong University Beijing100044 China The Department of Electrical and Electronic Engineering University of Hong Kong Pok Fu Lam Hong Kong The College of Computing and Data Science Nanyang Technological University Singapore Faculty of Engineering and Applied Science Memorial University Canada The State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China The Frontiers Science Center for Smart High-speed Railway System China Henan Joint International Research Laboratory of Intelligent Networking and Data Analysis Zhengzhou University Zhengzhou450001 China Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen China

Cell-free (CF) massive multiple-input multiple-output (MIMO) provides a ubiquitous coverage to user equipments (UEs) but it is also susceptible to interference. Rate-splitting (RS) effectively extracts data by decoding interference, yet its effectiveness is limited by the weakest UE. In this paper, we investigate an RS-based CF massive MIMO system, which combines strengths and mitigates weaknesses of both approaches. Considering imperfect channel state information (CSI) resulting from both pilot contamination and noise, we derive a closed-form expression for the sum spectral efficiency (SE) of the RS-based CF massive MIMO system under a spatially correlated Rician channel. Moreover, we propose low-complexity heuristic algorithms based on statistical CSI for power-splitting of common messages and power-control of private messages, and genetic algorithm is adopted as a solution for upper bound performance. Furthermore, we formulate a joint optimization problem, aiming to maximize the sum SE of the RS-based CF massive MIMO system by optimizing the power-splitting factor and power-control coefficient. Importantly, we improve a generative AI (GAI) algorithm to address this complex and non-convexity problem by using a diffusion model to obtain solutions. Simulation results demonstrate its effectiveness and practicality in mitigating interference, especially in dynamic environments. Copyright © 2024, The Authors. All rights reserved.

关键词： Genetic algorithms

Closed Shop Scheduling Optimisation using Max-Plus Automata 3

学校读者我要写书评

暂无评论

Closed Shop Scheduling Optimisation using Max-Plus Automata

3rd International Conference on science, ICOS 2019

作者： Merdekawati, Dian Ayu Subiono Faculty of Mathematics Computing and Data Science Sepuluh Nopember Institute of Technology Surabaya Indonesia

An appropriate scheduling system is needed in manufacturing activities to minimize production time and costs. Flow shop is one type of production flow that widely used in manufacturing. Based on the demand criteria, it has been known as a scheduling problem called closed shop. This scheduling emphasizes the make-to-stock (MTS) which produces a stock. We take the closed shop scheduling case studies from an existing literature and optimize scheduling using max-plus automata optimum. We compare the result with regular scheduling and the previous result in the literature. We show that the result of max-plus automata optimum scheduling are optimum compared than the existing regular scheduling and the existing previous result of the literature. © Published under licence by IOP Publishing Ltd.

关键词： Scheduling

Deep Learning Algorithms-based Object Detection and Localization Revisited

学校读者我要写书评

暂无评论

Deep Learning Algorithms-based Object Detection and Localiza...

International Laser Technology and Optics Symposium in Conjunction with Photonics Meeting 2020, ILATOSPM 2020

作者： Waheed, Safa Riyadh Suaib, Norhaida Mohd Mohd Rahim, Mohd Shafry Mundher Adnan, Myasar Salim, A.A. Big Data Center and Faculty of Engineering School of Computing Universiti Teknologi Malaysia Johor Bahru81310 Malaysia Computer Techniques Engineering Department Faculty of Information Technology Imam Jaafar Al-Sadiq University Baghdad Iraq UTM-IRDA Digital Media Institute of Human-Centred Engineering Universiti Teknologi Malaysia Johor Bahru81310 Malaysia Islamic University Najaf Iraq Laser Center and Physics Department Faculty of Science Universiti Teknologi Malaysia Johor Bahru81310 Malaysia

The computer vision (CV) is an emerging area with sundry promises. This communication encompasses the past development, recent trends and future directions of the CV in the context of deep learning (DL) algorithms-based object detections and localizations techniques. To identify the object location inside an image and recognize it by a computer program as fast as the human brain the machine learning and DL techniques have been evolved. However, the main limitations of the machine are related to the prolonged time consumption to handle vast amount of data to perform the same task as the human brain. To overcome these shortcomings, the convolution neural networks (NNs)-based deep NN has been developed, which detects and classifies the object with high precision. To train the deep NNs, massive amount of data (in the form of images and videos) and time is needed, making the computational cost of the CV very high. Thus, transfer learning techniques have been proposed wherein a model trained on one task can be reused on another linked task, thereby producing excellent outcomes. In this spirit, diverse DL-based algorithms have been introduced to detect and classify the object. These algorithms include the region-based convolutional NN (R-CNN), fast R-CNN, Faster R-CNN, mask E-CNN and You Only Look Once. A comparative evaluation among these techniques has been made to reveal their merits and demerits in the CV. © Published under licence by IOP Publishing Ltd.

关键词： Learning algorithms

HARDC : A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention based dual structured RNN with dilated CNN

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Islam, Md Shofiqul Hasan, Khondokar Fida Sultana, Sunjida Uddin, Shahadat Lio', Pietro Quinn, Julian M.W. Moni, Mohammad Ali Faculty of Computing Universiti Malaysia Pahang Gambang Pahang Kuantan26300 Malaysia Lebuhraya Tun Razak Gambang Pahang Kuantan26300 Malaysia 2 George Street Brisbane4000 Australia Department of Computer Science and Engineering Islamic University Kushtia7600 Bangladesh School of Project Management Faculty of Engineering The University of Sydney Sydney Australia Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom Bone Research Group The Garvan Institute of Medical Research DarlinghurstNSW Australia Artificial Intelligence & Data Science School of Health and Rehabilitation Sciences Faculty of Health and Behavioural Sciences The University of Queensland St LuciaQLD4072 Australia

Deep learning-based models have achieved significant success in detecting cardiac arrhythmia by analyzing ECG signals to categorize patient heartbeats. To improve the performance of such models, we have developed a novel hybrid hierarchical attention-based bidirectional recurrent neural network with dilated CNN (HARDC) method for arrhythmia classification. This solves problems that arise when traditional dilated convolutional neural network (CNN) models disregard the correlation between contexts and gradient dispersion. The proposed HARDC fully exploits the dilated CNN and bidirectional recurrent neural network unit (BiGRU-BiLSTM) architecture to generate fusion features. As a result of incorporating both local and global feature information and an attention mechanism, the model's performance for prediction is improved. By combining the fusion features with a dilated CNN and a hierarchical attention mechanism, the trained HARDC model showed significantly improved classification results and interpretability of feature extraction on the PhysioNet 2017 challenge dataset. Sequential Z-Score normalization, filtering, denoising, and segmentation are used to prepare the raw data for analysis. CGAN (Conditional Generative Adversarial Network) is then used to generate synthetic signals from the processed data. The experimental results demonstrate that the proposed HARDC model significantly outperforms other existing models, achieving an accuracy of 99.60%, F1 score of 98.21%, a precision of 97.66%, and recall of 99.60% using MIT-BIH generated ECG. In addition, this approach substantially reduces run time when using dilated CNN compared to normal convolution. Overall, this hybrid model demonstrates an innovative and cost-effective strategy for ECG signal compression and high-performance ECG recognition. Our results indicate that an automated and highly computed method to classify multiple types of arrhythmia signals holds considerable promise. © 2023, CC BY.

关键词： Electrocardiograms