检索结果-内蒙古大学图书馆

Quantitative Analysis of IITs’ Research Growth and SDG Contributions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sharma, Kiran Nagori, Akshat Manya Dubey, Mehul Khurana, Parul School of Engineering & Technology BML Munjal University Haryana Gurugram122413 India Center for Advanced Data and Computational Science BML Munjal University Haryana Gurugram122413 India School of Computer Applications Lovely Professional University Punjab Phagwara144411 India

The Indian Institutes of Technology (IITs) are vital to India’s research ecosystem, advancing technology and engineering for industrial and societal benefits. This study reviews the research performance of top IITs—Bombay, Delhi, Madras, Kharagpur, and Kanpur based on Scopus-indexed publications (1952–2024). Research output has grown exponentially, supported by increased funding and collaborations. IIT-Kanpur excels in research impact, while IIT-Bombay and IIT-Madras are highly productive but show slightly lower per-paper impact. Internationally, IITs collaborate robustly with the USA, Germany, and the UK, alongside Asian nations like Japan and South Korea, with IIT-Madras leading inter-IIT partnerships. Research priorities align with SDG 3 (Health), SDG 7 (Clean Energy), and SDG 11 (Sustainable Cities). Despite strengths in fields like energy, fluid dynamics, and materials science, challenges persist, including limited collaboration with newer IITs and gaps in emerging fields. Strengthening specialization and partnerships is crucial for addressing global challenges and advancing sustainable development. © 2024, CC BY.

关键词：

GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Jian Wei, Bifan Qi, Shihao Zhu, Haiping Liu, Jun Lin, Qika School of Computer Science and Technology Xi’an Jiaotong University Xi’an China School of Continuing Education Xi’an Jiaotong University Xi’an China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an China National University of Singapore Singapore

The construction of Generalized Knowledge Graph (GKG), including knowledge graph, event knowledge graph and commonsense knowledge graph, is fundamental for various natural language processing tasks. Current studies typically construct these types of graph separately, overlooking holistic insights and potential unification that could be beneficial in computing resources and usage perspectives. However, a key challenge in developing a unified framework for GKG is obstacles arising from task-specific differences. In this study, we propose a unified framework for constructing generalized knowledge graphs to address this challenge. First, we collect data from 15 sub-tasks in 29 datasets across the three types of graphs, categorizing them into in-sample, counter-task, and out-of-distribution (OOD) data. Then, we propose a three-stage curriculum learning fine-tuning framework, by iteratively injecting knowledge from the three types of graphs into the Large Language Models. Extensive experiments show that our proposed model improves the construction of all three graph types across in-domain, OOD and counter-task data. Copyright © 2025, The Authors. All rights reserved.

关键词： Knowledge graph

Analysis of Discovering Fraud in Master Card Based on Bidirectional GRU and CNN Based Model

学校读者我要写书评

暂无评论

Analysis of Discovering Fraud in Master Card Based on Bidire...

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： Sushma Kakkar Subha B L. Chandra Sekhar Reddy Subharun Pal Sushil Chandra Dimri Neerav Nishant Department of Electrical Electronics and Communication Engineering Sharda School of Engineering and Technology Sharda University Greater Noida Department of Management Kristu Jayanti College Bangalore India HOD-CSE(Data Science) CMR College of Engineering & Technology Kandlakoya(v) Medchal Telangana India Department of Computer Science and Engineering Indian Institute of Technology Jammu Jagti Jammu Jammu & Kashmir India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Computer Science and Engineering School of Engineering Babu Banarasi Das University Lucknow India

Detecting and confirming MasterCard fraud (also known as “master card fraud detection”) is a popular course topic amongst students due to the usefulness of data processing and machine learning strategies in combating cybercrime. The three main parts of the proposed method are preprocessing, feature extraction, and model training. Preprocessing techniques are used to mine crucial information for identifying MasterCard fraud. Only by using the most advanced and efficient algorithms, the future transactions can be predicted with any degree of certainty. By employing these techniques, the proposed approach may confirm a variety of facts, including the correctness of authentication and the regularity of dealings. To accomplish feature extraction, the proposed approach used the PCA and SKM algorithms. In order to train the models following feature extraction, the proposed approach uses CNN, BiGRU, and BiGRU-CNN. Both the CNN and the BiGRU models are outperformed by the proposed model. With an approximate 98.87 percent accuracy, the proposed method is superior to other methods such as CNN and BiGRU.

关键词：

Evaluation of Wireless Sensor Networks Module using IoT Approach

学校读者我要写书评

暂无评论

Evaluation of Wireless Sensor Networks Module using IoT Appr...

Artificial Intelligence and Smart Systems (ICAIS), International Conference on

作者： L. Anand Padmalal S J. Seetha R. Juliana PS Naveen Kumar Gayatri Parasa Department of Networking and Communications School of Computing SRM Institute of Science and Technology Kattanguluthur Department of Computer Science and Engineering Mangalam College of Engg Kerala Department of Computer Science and Business Systems Panimalar Engineering College Chennai Department of Information Technology Loyola-ICAM College of Engineering and Technology Chennai India Department of CSE-DATA SCIENCE St. Ann's College Of Engineering And Technology Chirala AP Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur Andhra Pradesh India

Microcomputers and medical devices with signal transceivers that operate on a specific radio display constitute the backbone of wireless sensor networks (WS Ns) that monitor environmental conditions (temperature, pressure, light, vibration levels, location). It is widely used in WAN sensor networks because of its flexible design and low setup fees. The u200b touch network allows for the connection of up to 65,000 devices, while the Intelligent sensors on other wireless networks are used to transfer data ports and assign wireless networks. Since the price of wireless solutions has been decreasing, and their functional capabilities have been growing, they are gradually replacing wired ones in telemetry data gathering systems and long- distance detecting communication. A deep learning model was used in this investigation to prevent the sensor nodes from manipulating data. Sensor nodes include a lot of parameters and estimations. If these projected data values are altered, network performance will suffer, and the node's lifetime will be reduced. data security became a priority when the sensor nodes were distributed. This new method is 98.82% more efficient than the previous one.

关键词： Temperature sensors Wide area networks Vibrations Temperature measurement Wireless sensor networks Wireless networks Transceivers

Tutorial on Using Machine Learning and Deep Learning Models for Mental Illness Detection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Yeyubei Wang, Zhongyan Ding, Zhanyi Tian, Yexin Dai, Jianglai Shen, Xiaorui Liu, Yunchong Cao, Yuchen University of Pennsylvania School of Engineering and Applied Science United States New York University Center for Data Science United States Georgia Institute of Technology College of Computing United States University of California Department of EECS Berkeley United States Northeastern University Khoury College of Computer Science United States

Social media has become an important source for understanding mental health, providing researchers a way to detect conditions like depression from user-generated posts. This tutorial provides practical guidance to address common challenges in applying machine learning and deep learning methods for mental health detection on these platforms. It focuses on strategies for working with diverse datasets, improving text preprocessing, and addressing issues such as imbalanced data and model evaluation. Real-world examples and step-by-step instructions demonstrate how to apply these techniques effectively, with an emphasis on transparency, reproducibility, and ethical considerations. By sharing these approaches, this tutorial aims to help researchers build more reliable and widely applicable models for mental health research, contributing to better tools for early detection and intervention. © 2025, CC BY.

关键词： Adversarial machine learning

Optimal vintage factor analysis with deflation varimax

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bing, Xin He, Xin Jin, Dian Zhang, Yuqian Department of Statistical Sciences University of Toronto Canada School of Statistics and Data Science Shanghai University of Finance and Economics China Department of Electrical and Computer Engineering Rutgers University NB Canada

Vintage factor analysis is one important type of factor analysis that aims to first find a low-dimensional representation of the original data, and then to seek a rotation such that the rotated low-dimensional representation is scientifically meaningful. Perhaps the most widely used vintage factor analysis is the Principal Component Analysis (PCA) followed by the varimax rotation. Despite its popularity, little theoretical guarantee can be provided mainly because varimax rotation requires to solve a non-convex optimization over the set of orthogonal matrices. In this paper, we propose a deflation varimax procedure that solves each row of an orthogonal matrix sequentially. In addition to its net computational gain and flexibility, we are able to fully establish theoretical guarantees for the proposed procedure in a broad context. Adopting this new varimax approach as the second step after PCA, we further analyze this two step procedure under a general class of factor models. Our results show that it estimates the factor loading matrix in the optimal rate when the signal-to-noise-ratio (SNR) is moderate or large. In the low SNR regime, we offer possible improvement over using PCA and the deflation procedure when the additive noise under the factor model is structured. The modified procedure is shown to be optimal in all SNR regimes. Our theory is valid for finite sample and allows the number of the latent factors to grow with the sample size as well as the ambient dimension to grow with, or even exceed, the sample size. Extensive simulation and real data analysis further corroborate our theoretical findings. © 2023, CC BY.

关键词： Convex optimization

Artificial Intelligence enabled Employee Performance Prediction using Comprehensive Learning Metrics

学校读者我要写书评

暂无评论

Artificial Intelligence enabled Employee Performance Predict...

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： P. GururamaSenthilvel N. Duraimutharasan Hannah Rose Esther T P. N. Periyasamy Rajesh Kumar. K Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai Department of Information Technology AMET University Kanathur Tamil Nadu Department of Artificial Intelligence and Data Science Velammal Engineering College Department of Computer Science and Engineering Hindusthan Institute of Technology Coimbatore Tamil Nadu Department of Electronics and Communication Engineering Chendu College of Engineering Madurantakam Tamil Nadu India

Human capital is crucial to the success of businesses in the new knowledge economy. There is a compelling financial justification for developing a system to assess and enhance employee performance, making performance measurement at the level of the individual worker a must. With data Mining, HR professionals may find new and relevant information (HRM). The success of an employee is not dependent on a single trait. Humans vary greatly in their innate talents and the traits that define their personalities. Hence, data from many sectors must be collected for performance monitoring. The purpose of this article is to present an overall grade of an employee's performance taking into account a number of criteria. We begin by contrasting many popular Machine Learning algorithmsagainst one another. We then recommend an ensemble method that draws from the aforementioned methods. The empirical findings show that the suggested model outperforms the state-of-the-art models in terms of precision, recall, F1-score, and accuracy, as compared to the more conventional models.

关键词：

Multi-modal Underwater Acoustic Target Recognition

学校读者我要写书评

暂无评论

Multi-modal Underwater Acoustic Target Recognition

computer, Big data and Artificial Intelligence (ICCBD+AI), International Conference on

作者： Tianxiang He Rui Xiang Junlin Zhou Duanbing Chen Sheng Feng Jie Yang Chengdu Union Big Data Technology Inc. Chengdu China School of Computer Science and Engineering UESTC Chengdu China Dept. 804 Sichuan Jiuzhou Electric Co. Ltd. Mianyang China

ISBN: (数字)9798331533991

ISBN: (纸本)9798331534004

Underwater acoustic target recognition (UATR) has gained significant attention across various fields in recent years. However, traditional UATR methods, which primarily rely on data from a single sensor, have limitations in fully capturing target characteristics. This constraint ultimately impacts the accuracy and robustness of recognition. This paper presents a multi-modal UATR method that fuses data from two different sensors, thereby improving underwater target recognition accuracy. Additionally, a new training framework is proposed to facilitate the learning of consistent feature representations across diverse data sources, allowing for more effective capture of the intrinsic characteristics of acoustic data. Experimental results demonstrate that the method has positive effectiveness under various Signal-to-Noise Ratio (SNR) conditions and achieves an improvement in recognition accuracy ranging from 0.95% to 8.33%.

关键词： Training Accuracy Target recognition Fuses Soft sensors Self-supervised learning data models Robustness Underwater acoustics Signal to noise ratio

Global Graph Counterfactual Explanation: A Subgraph Mapping Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Yinhan Zheng, Wendy Zhu, Yaochen Ma, Jing Mishra, Saumitra Raman, Natraj Liu, Ninghao Li, Jundong Department of Electrical and Computer Engineering University of Virginia United States Department of Computer Science University of Virginia United States Department of Computer & Data Sciences Case Western Reserve University United States JP Morgan Chase & Co. United States School of Computing University of Georgia United States

Graph Neural Networks (GNNs) have been widely deployed in various real-world applications. However, most GNNs are black-box models that lack explanations. One strategy to explain GNNs is through counterfactual explanation, which aims to find minimum perturbations on input graphs that change the GNN predictions. Existing works on GNN counterfactual explanations primarily concentrate on the local-level perspective (i.e., generating counterfactuals for each individual graph), which suffers from information overload and lacks insights into the broader cross-graph relationships. To address such issues, we propose GlobalGCE, a novel global-level graph counterfactual explanation method. GlobalGCE aims to identify a collection of subgraph mapping rules as counterfactual explanations for the target GNN. According to these rules, substituting certain significant subgraphs with their counterfactual subgraphs will change the GNN prediction to the desired class for most graphs (i.e., maximum coverage). Methodologically, we design a significant subgraph generator and a counterfactual subgraph autoencoder in our GlobalGCE, where the subgraphs and the rules can be effectively generated. Extensive experiments demonstrate the superiority of our GlobalGCE compared to existing baselines. Our code can be found at https://***/r/GlobalGCE-92E8. © 2024, CC BY-NC-ND.

关键词： Graph neural networks