检索结果-内蒙古大学图书馆

Discrimination and Investigation of Cardiac Infarction gleaned from Various Machine Learning and Optimization Methods

Discrimination and Investigation of Cardiac Infarction glean...

引用

Technology, engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET), IEEE International Conference on

作者： Premananda Sahu Srikanta Kumar Mohapatra Prakash Kumar Sarangi Jayashree Mohanty School of Computer Science and Engineering Lovely Professional University Punjab India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department Of Computer Science(AI&ML) Vardhaman Colllege of Engineering Hyderabad India IIIT Bhubaneswar Odisha India

The analysis of data in medical field is frequently increasing for analyzing the diagnoses, various research methods need to be filtered, and adequate equipment need to be arranged according to the importance of the pathology that appear. In ai various classification of software are considered for presenting the data for best prediction. The basic system model made by us is pretty much capable of doing various data processing algorithms for analyzing various diseases of heart. Our model works basically on a specific category of data. This analysis basically allows us in obtaining a model prediction from training and then testing the data. Various optimizing techniques need to be used for classifying the present data which will help in predicting the best results. Our model’s main purpose is building a basic framework for exploring the cardiac infarction based on various distinct algorithms like DT, Random Forest, LR and KNN along with some data samples which we have examined both the training and testing purpose. Here for the effective diagnosis, the research is done using the dataset of heart disease which is provided by the UCI Machine Repository. After having training and testing, some optimization techniques like stochastic gradient descent method have also implemented in our model to find out the more refined outcome. As a result, we have gained as an approximation of 97.78% of classification accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Gaussian Multivariate Mixture Model and VGG19 Model for Classification and Detection of Motor Vehicle

A Gaussian Multivariate Mixture Model and VGG19 Model for Cl...

引用

Network, Multimedia and Information Technology (NMITCON) International Conference on

作者： N. Deepa Bura Vijay Kumar M Sowmya Hassan M. Al-Jawahry Yannam Bharath Bhushan Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India School of Computer Science and Artificial Intelligence SR University Warangal India Department of AI & DS Nitte Meenakshi Institute of Technology Bengaluru India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of AI&ML Gokaraju Rangaraju Institute of Engineering and Technology Bachupally Hyderabad India

ISBN: (数字)9798350372892

ISBN: (纸本)9798350372908

In daily life, the moving vehicle plays a significant part in effective system of transportation and traffic visual surveillance systems. Most critical task is to detect the vehicle image and most of the existing method, concentrated on maximizing the prediction percentage only. Also it lacks in classifying the imbalance data. To overcome this kind of problem, the Gaussian Multivariate Mixture Model (G-MMM) and VGG19 model is implemented to detect and classify the vehicle types. The proposed method contained four process namely, preprocessing performed by Flexible Histogram Equalization method (FHE), vehicle detection using G-MMM, feature extraction using Steerable Pyramid Transform (SPT) and Weber Local Descriptor (WLD) and classification using VGG19 ensemble deep learning model. G-MMM significantly improves detection sensitivity and it transformed the correlation between attributes through the training process. VGG19 is pretrained model, so it allows the fast learning recognition on new images of vehicle. The proposed method tested on Beijing Institute of Technology (BIT) dataset and MIO vision traffic camera dataset. When compared to the others methods like modified AlexNet, Deep Convolution Neural Network (DCNN), this proposed G-MMM-VGG19 gives 99.47 % of output rate in classification phase.

关键词： Deep learning Histograms Visualization Vehicle detection Computational modeling Transportation Mixture models Feature extraction Automobiles Tuning

来源：评论

学校读者我要写书评

暂无评论

Pneumonia Detection in Chest X-rays using CNN

Pneumonia Detection in Chest X-rays using CNN

引用

Innovation in Technology (INOCON), IEEE International Conference for

作者： Aaryan Chothani Bharti Khemani Sachin Malave Mit Jain Jaya Gupta Department of Computer Engineering A.P. Shah Institute of Technology Thane India Department of Computer Science & Engineering (AI & ML) A.P. Shah Institute of Technology Thane India

Pneumonia is a life-threatening condition which affects people of all ages but is mostly found in infants and older adults. It is caused by a variety of factors including bacteria, viruses and fungi and causes infections in one lung or both. The diagnosis of Pneumonia is usually facilitated using chest X-rays. This diagnosis becomes difficult in cases where access to expert radiologists or doctors to discover the disease is unavailable. Hence, using a system which makes use of powerful Machine Learning and Deep Learning techniques in order to make the diagnosis of Pneumonia in chest X-rays easier is more feasible. This problem has seen tremendous advancements in recent times with the use of various computer Vision and ml methodologies. In this work, we have showcased the use of multiple such methods in order to create a complete system based on the purpose of detecting Pneumonia in chest X-rays. The integral component of the system is a Convolutional Neural Network (CNN) model, trained on a pre-processed dataset of chest X-rays. CNN has become the most used Deep Learning algorithm for computer vision problems due to its strength of dealing with images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MOCBOA:Multi-Objective Chef-Based Optimization Algorithm Using Hybrid Dominance Relations for Solving engineering Design Problems

引用

computer Modeling in engineering & sciences 2025年第4期143卷 967-1008页

作者： Nour Elhouda Chalabi Abdelouahab Attia Abdulaziz S.Almazyad Ali Wagdy Mohamed Frank Werner Pradeep Jangir Mohammad Shokouhifar Computer Science Department University of M’silaIchebiliaM’sila28000Algeria Computer ScienceDepartment Mohamed El Bachir El IbrahimiUniversity of Bordj BouArreridjBordj BouArreridj34000Algeria Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Applied Science Research Center Applied Science Private UniversityAmman11931Jordan Faculty of Mathematics Otto-von-Guericke UniversityMagdeburg39016Germany University Centre for Research and Development Chandigarh UniversityMohali140413India Department of Electrical and Computer Engineering Shahid Beheshti UniversityTehran14399Iran DTU AI and Data Science Hub(DAIDASH) Duy Tan UniversityDa Nang550000Vietnam

Multi-objective optimization is critical for problem-solving in engineering,economics,and *** study introduces the Multi-Objective Chef-Based Optimization Algorithm(MOCBOA),an upgraded version of the Chef-Based Optimization Algorithm(CBOA)that addresses distinct *** approach is unique in systematically examining four dominance relations—Pareto,Epsilon,Cone-epsilon,and Strengthened dominance—to evaluate their influence on sustaining solution variety and driving convergence toward the Pareto *** comparison investigation,which was conducted on fifty test problems from the CEC 2021 benchmark and applied to areas such as chemical engineering,mechanical design,and power systems,reveals that the dominance approach used has a considerable impact on the key optimization measures such as the hypervolume *** paper provides a solid foundation for determining themost effective dominance approach and significant insights for both theoretical research and practical applications in multi-objective optimization.

关键词： Multi-objective optimization chef-based optimization algorithm(CBOA) pareto dominance epsilon dominance cone-epsilon dominance strengthened dominance

来源：评论

学校读者我要写书评

暂无评论

Prediction of aiDS/HIV Infection using Custom Artificial Neural Networks Model 1

Prediction of AIDS/HIV Infection using Custom Artificial Neu...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Sneha, B.J. Shriyashreshta Kodipalli, Ashwini Martis, Roshan Joy Ushasree, A. Devamane, Shridhar B. Global Academy of Technology Department of Ai & Data Science Bangalore India Manipal Institute of Technology Department of Electronics & Communication Engineering Bangalore India Gokaraju Lailavathi Engineering College Department of Computer Science & Engineering Hyderabad India Amrita Vishwavidyapeetam School of Computing Department of Cs Mysuru India

ISBN: (纸本)9798331529246

HIV is a serious disease that impairs immunity. Without treatment, the infection may progress through three stages, which might drastically shorten a person's life. Artificial neural networks (ANNs) are utilized to detect the HIV infection and even to find treatments for it. The aiDS viral infection is predicted in this review. The aim of ANN is to precisely classify patients according to whether or not they have HIV/aiDS. We have formed a custom ANN model and applied it to the Kaggle dataset that is accessible to the public, compared which optimizers offer the best accuracy and whether employing dropouts yields improved accuracy. With Gradient Descent, we achieved the maximum accuracy of 86.92% it is also one of the most commonly used optimizers due to its simplicity and effectiveness, followed by SGD with 86.45% it is a variation of gradient descent in which a random subset of data as opposed to the complete dataset is used to update the parameter and RMSprop with 86.21% uses the average of recent gradient magnitudes to modify the learning rate for each parameter. This aids with training stabilization, particularly when dealing with sparse or noisy data. The accuracy increased to 87.62% after we introduced dropouts to the hidden layer with optimizer as gradient descent, which produced the best results. Loss vs. Accuracy graphs and ROC curve have been plotted. With dropouts, the custom ANN model performed even better on the Gradient Descent optimizer. © 2025 IEEE.

关键词： ANN dropouts HIV/aiDS optimizers

来源：评论

学校读者我要写书评

暂无评论

Towards a Personalized LLM-Based Daily Edge Memory aid 15

Towards a Personalized LLM-Based Daily Edge Memory Aid

引用

15th International Conference on Information and Communication Technology Convergence, ICTC 2024

作者： Ha, Sangil Ko, Dongbeom Lim, Joon-Ho Kang, Sungjoo Kim, Hyeon Soo Ai Lab Tutorus Labs Inc. Deajeon Korea Republic of Deajeon Korea Republic of Department of Computer Science and Engineering Deajeon Korea Republic of

ISBN: (纸本)9798350364637

This paper introduces a personalized memory aid system that combines a high-performance cloud-based large language model (LLM) with a low-power edge device running a small language model (sLM) to enhance user productivity by processing and summarizing daily conversations in real-time. The system optimizes efficiency and user experience while ensuring privacy through localized data handling. By combining cloud and edge resources, the system provides scalable, real-time memory support without compromising data security. The research highlights the system's architecture, its role in protecting user data, and its potential to seamlessly integrate into daily life, offering a sustainable and efficient approach to personalized artificial intelligence applications. © 2024 IEEE.

关键词： Cloud computing architecture

来源：评论

学校读者我要写书评

暂无评论

On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm 41

On the Emergence of Cross-Task Linearity in Pretraining-Fine...

引用

41st International Conference on Machine Learning, ICml 2024

作者： Zhou, Zhanpeng Chen, Zijun Chen, Yilan Zhang, Bo Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University Shanghai China Shanghai Artificial Intelligence Laboratory China Computer Science and Engineering University of California San Diego United States

The pretraining-finetuning paradigm has become the prevailing trend in modern deep *** this work, we discover an intriguing linear phenomenon in models that are initialized from a common pretrained checkpoint and finetuned on different tasks1, termed as Cross-Task Linearity (CTL).Specifically, we show that if we linearly interpolate the weights of two finetuned models, the features in the weight-interpolated model are often approximately equal to the linear interpolation of features in two finetuned models at each *** provide comprehensive empirical evidence supporting that CTL consistently occurs for finetuned models that start from the same pretrained *** conjecture that in the pretraining-finetuning paradigm, neural networks approximately function as linear maps, mapping from the parameter space to the feature *** on this viewpoint, our study unveils novel insights into explaining model merging/editing, particularly by translating operations from the parameter space to the feature ***, we delve deeper into the root cause for the emergence of CTL, highlighting the role of *** released our source code at https://***/zzp1012/Cross-Task-Linearity. Copyright 2024 by the author(s)

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models

An Empirical Analysis on Spatial Reasoning Capabilities of L...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Shiri, Fatemeh Guo, Xiao-Yu Far, Mona Golestan Yu, Xin Haffari, Gholamreza Li, Yuan-Fang Department of Data Science & AI Monash University Australia Australian Institute for Machine Learning University of Adelaide Australia School of Electrical Engineering and Computer Science University of Queensland Australia

ISBN: (纸本)9798891761643

Large Multimodal Models (LMMs) have achieved strong performance across a range of vision and language tasks. However, their spatial reasoning capabilities are under-investigated. In this paper, we construct a novel VQA dataset, Spatial-MM, to comprehensively study LMMs' spatial understanding and reasoning capabilities. Our analyses on object-relationship and multi-hop reasoning reveal several important findings. Firstly, bounding boxes and scene graphs, even synthetic ones, can significantly enhance LMMs' spatial reasoning. Secondly, LMMs struggle more with questions posed from the human perspective than the camera perspective about the image. Thirdly, chain of thought (CoT) prompting does not improve model performance on complex multi-hop questions involving spatial relations. Lastly, our perturbation analysis on GQA-spatial reveals that LMMs are much stronger at basic object detection than complex spatial reasoning. We believe our new benchmark dataset and in-depth analyses can spark further research on LMMs spatial reasoning. © 2024 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

Edge-SAN: An Edge-Prompted Foundation Model for Accurate Nuclei Instance Segmentation in Histology Images

Edge-SAN: An Edge-Prompted Foundation Model for Accurate Nuc...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wu, Xuening Shen, Yiqing Zhao, Qing Kang, Yanlan Hu, Ruiqi Zhang, Wenqiang Fudan University Shanghai Engineering Research Center of Ai & Robotics Academy for Engineering & Technology Shanghai China Johns Hopkins University Department of Computer Science BaltimoreMD United States Hong Kong Polytechnic University Department of Applied Mathematics Hong Kong Fudan University Engineering Research Center of Ai & Robotics Ministry of Education Academy for Engineering & Technology School of Computer Science Shanghai China

ISBN: (纸本)9798350386226

Accurate nuclei segmentation is fundamental in histology image analysis, playing an essential role in cancer grading and diagnosis. However, this task remains challenging due to variations in staining protocols, heterogeneity among nuclei types, and the densely clustered nature of nuclei. While SAM exhibits zero-shot generalization capabilities in natural image segmentation, its performance degrades when applied to nuclei segmentation in histology images. Existing adaptations of SAM for medical imaging primarily focus on organ or lesion segmentation, which differs substantially from nuclei segmentation due to the unique characteristics of nuclei - specifically, their sparse distribution combined with dense clustering. To address these challenges, we propose Edge-SAN (Segment Any Nuclei with Edge Prompting), an interactive segmentation foundation model specifically designed for nuclei segmentation. Edge-SAN introduces a novel edge prompting method that enhances the delineation of nuclei boundaries, particularly among densely clustered nuclei, by leveraging edge information to improve segmentation accuracy. We evaluate Edge-SAN on 12 diverse datasets in both few-shot and zero-shot scenarios, demonstrating its effectiveness as a foundation model for nuclei segmentation, achieving 66.81% AJI and 73.13% DSC - improvements of 16.33% and 15.48% over SAM-Med2D, respectively. The code is available at https://***/deep-geo/Edge-SAN. © 2024 IEEE.

关键词： Deep Learning Digital Pathology Foundation Model Nuclei Segmentation Segment Anything Model

来源：评论

学校读者我要写书评

暂无评论

Robust Calibration For Improved Weather Prediction Under Distributional Shift

arXiv

引用

arXiv 2024年

作者： Gilda, Sankalp Bhandari, Neel Mak, Wendy Panizza, Andrea ML Collective Department of Computer Science and Engineering RV College of Engineering India

In this paper, we present results on improving out-of-domain weather prediction and uncertainty estimation as part of the Shifts Challenge on Robustness and Uncertainty under Real-World Distributional Shift challenge. We find that by leveraging a mixture of experts in conjunction with an advanced data augmentation technique borrowed from the computer vision domain, in conjunction with robust post-hoc calibration of predictive uncertainties, we can potentially achieve more accurate and better-calibrated results with deep neural networks than with boosted tree models for tabular data. We quantify our predictions using several metrics and propose several future lines of inquiry and experimentation to boost performance. © 2024, CC BY-NC-SA.

关键词： Deep neural networks

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：