检索结果-内蒙古大学图书馆

Early Diagnosis of Diabetes and Prediction Using Machine Learning Algorithm

学校读者我要写书评

暂无评论

Early Diagnosis of Diabetes and Prediction Using Machine Lea...

Intelligent Cyber Physical Systems and Internet of Things (ICoICI), International Conference on

作者： Pavithra S Ravikumar S Sreesubha S Babu R M. Kalaiselvi School of Computer Science and Engineering Vellore Institute of Technology Chennai Department of Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Department of Artificial Intelligence and Machine Learning Rajalakshmi Engineering College Chennai India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Campus Chennai India Department of Computer Science and Engineering Alagappa chettiar government college of engineering and technology

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540678

This study utilizes machine learning techniques to predict the presence of diabetes at an early stage. Diabetic complications, including kidney and heart disease, can worsen over time if not detected at an earlier stage. Making the correct changes to one's lifestyle at the right time is crucial for preventing diabetes and its complications. So, there is an increasing need for a tool that can help doctors to detect this potentially deadly disease. This study has proposed machine learning based early stage diabetes detection model. The proposed model's performance is evaluated by analyzing how well the random forest classifier, a model known for its high accuracy, and resistance to overfitting performs. Random forest is a great option for feature selection because they deal with feature-intensive datasets, even in high-dimensional settings, and give useful information regarding the importance of features.

关键词： Resistance Analytical models Accuracy Machine learning algorithms Medical services Robustness Diabetes Random forests Tuning Diseases

Deep Crowd Analysis to Spot Social Distancing Violations in Post-COVID 19 Lifestyle 7

学校读者我要写书评

暂无评论

Deep Crowd Analysis to Spot Social Distancing Violations in ...

7th IEEE International Conference on Recent Advances and Innovations in engineering, ICRAIE 2022

作者： Narayanan, S. Sankara Nesarani, A. Raghav, R.S. Robert Singh, A. Athisayamani, Suganya VelTech Rangarajan Dr.Sahunthala R&D Institute of Science and Technology Department of CSE Chennai Tamil Nadu Avadi India Koneru Lakshmaiah Education Foundation Vadeeswaram Department of Computer Science and Engineering Andra Pradesh Guntur India School of Computing Sastra Deemed to Be University Tamil Nadu Thanjavur India SRM Institute of Science and Technology Department of Computational Intelligence School of Computing Tamil Nadu Chennai India

ISBN: (纸本)9781665489102

Crowd analysis is a new field of study that involves processing a large group of people to examine one or more of their behaviors. Deep learning is an appropriate technique for crowd analysis using a convolutional neural network. To calculate the distance between crowd members and to identify social distance violations, a deep crowd analysis is proposed in this study. Pre-trained in a single class To discover the region of interest, CNN is utilised to classify people (RoI). The people in the picture are then localized using a density map. The reference point used to calculate the distance between the people is the centroid of the isolated areas in the density map. A social distance violation is reported if the estimated distance is less than the specified threshold distance (3 meters). Between the two ROIs, a distance measured in pixels is determined. © 2022 IEEE.

关键词： Convolutional neural networks

Improved Turbo Message Passing for Compressive Robust Principal Component Analysis: Algorithm Design and Asymptotic Analysis

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Zhuohang Ma, Junjie Yuan, Xiaojun The National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China Chengdu611731 China The Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100864 China

Compressive Robust Principal Component Analysis (CRPCA) naturally arises in various applications as a means to recover a low-rank matrix low-rank matrix L and a sparse matrix S from compressive measurements. In this paper, we approach the problem from a Bayesian inference perspective. We establish a probabilistic model for the problem and develop an improved turbo message passing (ITMP) algorithm based on the sum-product rule and the appropriate approximations. Additionally, we establish a state evolution framework to characterize the asymptotic behavior of the ITMP algorithm in the large-system limit. By analyzing the established state evolution, we further propose sufficient conditions for the global convergence of our algorithm. Our numerical results validate the theoretical results, demonstrating that the proposed asymptotic framework accurately characterize the dynamical behavior of the ITMP algorithm, and the phase transition curve specified by the sufficient condition agrees well with numerical simulations. © 2024, CC BY.

关键词： Asymptotic analysis

An inexact augmented lagrangian algorithm for training leaky ReLU neural network with group sparsity

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2023年第1期24卷 10097-10139页

作者： Wei Liu Xin Liu Xiaojun Chen Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China Department of Applied Mathematics The Hong Kong Polytechnic University Hung Hom Kowloon Hong Kong

The leaky ReLU network with a group sparse regularization term has been widely used in the recent years. However, training such network yields a nonsmooth nonconvex optimization problem and there exists a lack of approaches to compute a stationary point deterministically. In this paper, we first resolve the multi-layer composite term in the original optimization problem by introducing auxiliary variables and additional constraints. We show the new model has a nonempty and bounded solution set and its feasible set satisfies the Mangasarian-Fromovitz constraint qualification. Moreover, we show the relationship between the new model and the original problem. Remarkably, we propose an inexact augmented Lagrangian algorithm for solving the new model, and show the convergence of the algorithm to a KKT point. Numerical experiments demonstrate that our algorithm is more efficient for training sparse leaky ReLU neural networks than some well-known algorithms.

关键词： sparse neural network leaky ReLU group sparsity penalty method inexact augmented Lagrangian method

Scaling Laws of Graph Neural Networks for Atomistic Materials Modeling

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Chaojian Ye, Zhifan Pasini, Massimiliano Lupo Choi, Jong Youl Wan, Cheng Lin, Yingyan Balaprakash, Prasanna Computational Sciences and Engineering Division Oak Ridge National Laboratory United States Computer Science and Mathematics Division Oak Ridge National Laboratory United States Computing and Computational Sciences Directorate Oak Ridge National Laboratory United States Georgia Institute of Technology United States

Atomistic materials modeling is a critical task with wide-ranging applications, from drug discovery to materials science, where accurate predictions of the target material property can lead to significant advancements in scientific discovery. Graph Neural Networks (GNNs) represent the state-of-the-art approach for modeling atomistic material data thanks to their capacity to capture complex relational structures. While machine learning performance has historically improved with larger models and datasets, GNNs for atomistic materials modeling remain relatively small compared to large language models (LLMs), which leverage billions of parameters and terabyte-scale datasets to achieve remarkable performance in their respective domains. To address this gap, we explore the scaling limits of GNNs for atomistic materials modeling by developing a foundational model with billions of parameters, trained on extensive datasets in terabyte-scale. Our approach incorporates techniques from LLM libraries to efficiently manage large-scale data and models, enabling both effective training and deployment of these large-scale GNN models. This work addresses three fundamental questions in scaling GNNs: the potential for scaling GNN model architectures, the effect of dataset size on model accuracy, and the applicability of LLM-inspired techniques to GNN architectures. Specifically, the outcomes of this study include (1) insights into the scaling laws for GNNs, highlighting the relationship between model size, dataset volume, and accuracy, (2) a foundational GNN model optimized for atomistic materials modeling, and (3) a GNN codebase enhanced with advanced LLM-based training techniques. Our findings lay the groundwork for large-scale GNNs with billions of parameters and terabyte-scale datasets, establishing a scalable pathway for future advancements in atomistic materials modeling. Copyright © 2025, The Authors. All rights reserved.

关键词： Materials properties

Is it Nemo or Dory? Fast and accurate object detection for IoT and edge devices 21

学校读者我要写书评

暂无评论

Is it Nemo or Dory? Fast and accurate object detection for I...

Proceedings of the 11th International Conference on the Internet of Things

作者： Sudhanshu Agarwal Richard Vuduc College of Computing Georgia Institute of Technology United States School of Computational Science and Engineering Georgia Institute of Technology United States

ISBN: (纸本)9781450385664

Current state-of-the-art object detection neural networks, such as YOLO and SSD, are trained and developed on server-class GPUs. These neural networks do not scale down well to resource-constrained devices, with both accuracy and precision taking a significant hit at the expense of speed. This is particularly concerning as object detection algorithms are often used for low-powered devices, such as surveillance and smart-home cameras, where accuracy is critical. Therefore, these devices generally tend to forward data to servers for processing, which adds network latency. In other cases, algorithms developed for these devices shrink neural networks to reduce computation at the expense of accuracy, which is often not acceptable. We create an alternative object detection scheme for static-camera systems such as those used in surveillance and smart-home settings. Our model does not require positions of objects in training data, enabling us to retain only the relevant parts of a video frame for training data and reduce data storage cost while preserving privacy of other subjects in the video. When evaluated on static-camera video feeds using an NVIDIA Jetson Nano (a hybrid Arm and GPU IoT embedded device platform), our method increases throughput compared to Tiny YOLOv3. Further, it takes half of the time that Tiny YOLOv3 takes when run on OpenCV’s CUDA-optimized DNN framework per frame while having high accuracy of bounding box prediction and classification. The lessons learned from this work also suggest other strategies for tailoring the deployment of deep learning algorithms at the edge.

关键词： Background Modeling Object Detection Edge computing Parallel computing

Metaheuristic Optimization for Path Planning in UAV Networks for Long-Distance Inspection Tasks

学校读者我要写书评

暂无评论

Metaheuristic Optimization for Path Planning in UAV Networks...

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： J. Akshya M. Manochitra R. Indu Poornima T. Jeevitha M. Saravanakumar M. Sundarrajan Mani Deepak Choudhry Department of Computational Intelligence SRM Institute of Science and Technology Chennai Computer Science and Engineering (Cyber Security) Dr. N.G.P. Institute of Technology Coimbatore Department of Information Technology KGiSL Institute of Technology Coimbatore Department of Artificial Intelligence and Data Science Nehru Institute of Engineering and Technology Coimbatore Department of Networking and Communications SRM Institute of Science and Technology Chennai Deportment of Computing Technologies SRM Institute of Science and Technology Chennai

ISBN: (数字)9798350380583

ISBN: (纸本)9798350380590

With broad applicability in surveillance, delivery, and environmental monitoring, multi-drone path planning has received a great deal of attention recently. So far, wide applicability has been explored by various applications of Genetic Algorithms, Particle Swarm Optimization, and Ant Colony Optimization, which have already established reliable solutions to navigation and coverage through drone path optimization. However, in dynamic, obstacle-dense environments, these algorithms fail to adapt in real-time with energy efficiency. Traditional GA and PSO approaches can be effective for generating an initial path but fail to respond to collision avoidance and efficient resource management. In complex and unpredictable conditions, ACO fails to converge rapidly, which leads to suboptimal paths and increased energy consumption. To overcome such barriers, we present here an HGARL for enhanced multi-drone path optimization. The proposed algorithm thus combines the population-based search capability of GA with RL's adaptive learning ability, therefore providing an algorithm that in addition to finding optimal paths adjusts the paths according to changing environmental situations. HGARL presents better performance compared to existing methods. In path convergence, it reaches up to 15%, and in energy consumption, it reduces up to 20% with safe collision-free navigation. The strong potential of HGARL for robust, efficient, and adaptive solutions of real-time multi-drone operation in complex and dynamic environments has set a new benchmark for UAV path planning.

关键词： Energy consumption Navigation Heuristic algorithms Reinforcement learning Path planning Real-time systems Reliability Genetic algorithms Drones Convergence

SCIAGENTS: AUTOMATING SCIENTIFIC DISCOVERY THROUGH MULTI-AGENT INTELLIGENT GRAPH REASONING

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ghafarollahi, Alireza Buehler, Markus J. Massachusetts Institute of Technology 77 Massachusetts Ave CambridgeMA02139 United States Center for Computational Science and Engineering Schwarzman College of Computing Massachusetts Institute of Technology 77 Massachusetts Ave CambridgeMA02139 United States

A key challenge in artificial intelligence is the creation of systems capable of autonomously advancing scientific understanding by exploring novel domains, identifying complex patterns, and uncovering previously unseen connections in vast scientific data. In this work, we present SciAgents, an approach that leverages three core concepts: (1) the use of large-scale ontological knowledge graphs to organize and interconnect diverse scientific concepts, (2) a suite of large language models (LLMs) and data retrieval tools, and (3) multi-agent systems with in-situ learning capabilities. Applied to biologically inspired materials, SciAgents reveals hidden interdisciplinary relationships that were previously considered unrelated, achieving a scale, precision, and exploratory power that surpasses traditional human-driven research methods. The framework autonomously generates and refines research hypotheses, elucidating underlying mechanisms, design principles, and unexpected material properties. By integrating these capabilities in a modular fashion, the intelligent system yields material discoveries, critique and improve existing hypotheses, retrieve up-to-date data about existing research, and highlights their strengths and limitations. Our case studies demonstrate scalable capabilities to combine generative AI, ontological representations, and multi-agent modeling, harnessing a ‘swarm of intelligence’ similar to biological systems. This provides new avenues for materials discovery and accelerates the development of advanced materials by unlocking Nature’s design principles. © 2024, CC BY-NC-ND.

关键词： Ontology

AtomAgents: Alloy design and discovery through physics-aware multi-modal multi-agent artificial intelligence

学校读者我要写书评

暂无评论

arXiv 2024年

The design of new alloys is a multi-scale problem that requires a holistic approach that involves retrieving relevant knowledge, applying advanced computational methods, conducting experimental validations, and analyzing the results, a process that is typically slow and reserved for human experts. Machine learning (ML) can help accelerate this process, for instance, through the use of deep surrogate models that connect structural and chemical features to material properties, or vice versa. However, existing data-driven models often target specific material objectives, offering limited flexibility to integrate out-of-domain knowledge and cannot adapt to new, unforeseen challenges. Here, we overcome these limitations by leveraging the distinct capabilities of multiple AI agents that collaborate autonomously within a dynamic environment to solve complex materials design tasks. The proposed physics-aware generative AI platform, AtomAgents, synergizes the intelligence of large language models (LLM) the dynamic collaboration among AI agents with expertise in various domains, including knowledge retrieval, multi-modal data integration, physics-based simulations, and comprehensive results analysis across modalities that includes numerical data and images of physical simulation results. The concerted effort of the multi-agent system allows for addressing complex materials design problems, as demonstrated by examples that include autonomously designing metallic alloys with enhanced properties compared to their pure counterparts. Our results enable accurate prediction of key characteristics across alloys and highlight the crucial role of solid solution alloying to steer the development of advanced metallic alloys. Our framework enhances the efficiency of complex multi-objective design tasks and opens new avenues in fields such as biomedical materials engineering, renewable energy, and environmental sustainability. © 2024, CC BY-NC-ND.

关键词： Multi agent systems