检索结果-内蒙古大学图书馆

Supervised Machine Learning Strategy for detection of covid19 patients

Supervised Machine Learning Strategy for detection of covid1...

2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering, ICECONF 2023

作者： Punithavathi, I.S. Hephzi Deepa, K. Rao, Cheruku Poorna Venkata Srinivasa Gopal, S. Raja Rajasekar, P. Kumar, Ashok Department of Artificial Intelligence Vidya Jyothi Institute of Technology Telagana Hyderabad500075 India Department of Computer Science and Artificial Intelligence Sr University Kavaraipettai Telangana Hasanparthy India Department of Information Technology Laki Reddy Balireddy College of Engineering Andhra Pradesh Mylavaram521230 India Department of Electronics and Communication Engineering KoneruLakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522302 India Department of Data Science and Business Systems SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Computer Science Banasthali Vidyapith Rajasthan304022 India

ISBN: (纸本)9798350334357

The current severe acute respiratory syndrome corona virus 2 (SARS-CoV-2) public health catastrophe, both human lives have been lost and the economy has disrupted severely the current scenario. In this paper, we develop a detection module using a series of steps that involves pre-processing, feature extraction and detection of covid-19 patients based on the images collected from the computerized tomography (CT) images. The images are initially pre-processed and then the features are extracted using Gray Level Co-occurrence Matrix (GLCM) and then finally classified using back propagation neural network (BPNN). The simulation is conducted to test the efficacy of the model against various CT image datasets of numerous patients. The results of simulation shows that the proposed method achieves higher detection rate, and reduced mean average percentage error (MAPE) than other existing methodologies. © 2023 IEEE.

关键词： SARS

来源：评论

学校读者我要写书评

暂无评论

Basket-Enhanced Heterogenous Hypergraph for Price-Sensitive Next Basket Recommendation

Basket-Enhanced Heterogenous Hypergraph for Price-Sensitive ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhou, Yuening Wang, Yulin Cui, Qian Guan, Xinyu Cisternas, Francisco Department of Marketing The Chinese University of Hong Kong Hong Kong School of Computer Science and Technology Dalian University of Technology Dalian China The Data Intelligence Team Maoyan Beijing China The Security Platform Department Tencent Shenzhen China

ISBN: (纸本)9798350368741

Next Basket Recommendation (NBR) is a new type of recommender system that predicts combinations of items users are likely to purchase together. Existing NBR models often overlook a crucial factor, which is price, and do not fully capture item-basket-user interactions. To address these limitations, we propose a novel method called Basket-augmented Dynamic Heterogeneous Hypergraph (BDHH). BDHH utilizes a heterogeneous multi-relational graph to capture the intricate relationships among item features, with price as a critical factor. Moreover, our approach includes a basket-guided dynamic augmentation network that could dynamically enhances item-basket-user interactions. Experiments on real-world datasets demonstrate that BDHH significantly improves recommendation accuracy, providing a more comprehensive understanding of user behavior. © 2025 IEEE.

关键词： basket-augmentation heterogeneous hypergraph Next basket recommendation price-aware

来源：评论

学校读者我要写书评

暂无评论

Multi-constraint smart UAV healthcare transportation path using imperial competition algorithm for smart cities

引用

Discover Internet of Things 2025年第1期5卷 1-19页

作者： Byeon, Haewon Ramesh, Janjhyam Venkata Naga AlGhamdi, Azzah Soni, Mukesh Nimma, Divya Pothumarthi, Sridevi Shabaz, Mohammad Convergence Department Korea University of Technology and Education Cheonan Korea Republic of Department of CSE Graphic Era Hill University Dehradun248002 India Computer Information Systems Department College of Computer Science and Information Technology Imam Abdalrhman Bin Faisal University Khobar Saudi Arabia Dr. D. Y. Patil Vidyapeeth Pune Dr. D. Y. Patil School of Science & Technology Tathawade Pune India University of southern Mississippi Data Analyst in UMMC Hattiesburg United States Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur Dist. Andhra Pradesh Vaddeswaram522302 India Model Institute of Engineering and Technology J&K Jammu India Department of CSE Graphic Era Deemed To Be University Uttarakhand Dehradun248002 India Division of Research and Development Lovely Professional University Phagwara India

In response to the path planning problem of using Unmanned Aerial Vehicle (UAV) for blood transportation, with the objective of minimizing the total distance travelled by the UAV, a multi-constraint drone blood transportation path planning model is established. Taking into account the limited number of drone take-off and landing platforms and the safety time intervals for continuous drone take-off and landing, a drone take-off scheduling strategy is designed to reduce the total time spent by UAV completing transportation tasks. Additionally, an Imperial Competition Algorithm based on Imperialist Competitive Algorithm is proposed to solve this problem. This algorithm introduces a sine disturbance strategy and adds Imperial Reform stages to improve the search accuracy of the algorithm. It utilizes acceptance criteria related to solution quality to maintain the diversity of the population. Validation is conducted using benchmark examples and instances of drone blood transportation. The results indicate that the proposed algorithm can provide transportation solutions for drone blood transportation tasks that meet various constraints without any conflicts in drone take-off and landing. The drone take-off scheduling strategy effectively reduces the total time spent by UAV in completing tasks. © The Author(s) 2025.

关键词： Target drones

来源：评论

学校读者我要写书评

暂无评论

Statistical inference for association studies in the presence of binary outcome misclassification

arXiv

引用

arXiv 2023年

作者： Hochstedler Webb, Kimberly A. Wells, Martin T. Department of Statistics and Data Science Cornell University IthacaNY United States

In biomedical and public health association studies, binary outcome variables may be subject to misclassification, resulting in substantial bias in effect estimates. The feasibility of addressing binary outcome misclassification in regression models is often hindered by model identifiability issues. In this paper, we characterize the identifiability problems in this class of models as a specific case of "label switching" and leverage a pattern in the resulting parameter estimates to solve the permutation invariance of the complete data log-likelihood. Our proposed algorithm in binary outcome misclassification models does not require gold standard labels and relies only on the assumption that the sum of the sensitivity and specificity exceeds 1. A label switching correction is applied within estimation methods to recover unbiased effect estimates and to estimate misclassification rates. Open source software is provided to implement the proposed methods. We give a detailed simulation study for our proposed methodology and apply these methods to data from the 2020 Medical Expenditure Panel Survey (MEPS). Copyright © 2023, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Wave: A Dynamic Physical-Based Metaheuristic Optimizer

Wave: A Dynamic Physical-Based Metaheuristic Optimizer

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Hussam Fakhouri Sadi Alawadi Fahed Alkhabbas Feras M. Awaysheh Data Science and Artificial Intelligence Department University of Petra Amman Jordan School of Computer Science Blekinge Institute of Technology Blekinge Sweden Department of Computer Science and Media Technology Sustainable Digitalisation Research Centre Malmö University Sweden Department of Computer Science ADSLab Umeå University Umeå Sweden

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Global optimization is challenging, particularly in high-dimensional and multimodal search spaces characterized by complex landscapes and numerous local optima. This paper proposes Wave, a novel physical-Based metaheuristic optimizer, which combines wave-inspired oscillatory factors, Lévy-based random flights, and adaptive exploration and exploitation strategies to tackle global optimization problems. Inspired by the cyclical nature of wave phenomena, our approach exploits time-varying sinusoidal amplitudes that gradually reduce while maintaining oscillatory behavior, thus enhancing both population diversity and local search. However, in Wave, the random flights derived from heavy-tailed step distributions provide additional large jumps that aid in escaping local minima. Wave has been evaluated over CEC2022 benchmark functions; the results demonstrate that Wave exhibits a strong convergence performance and comparable results with several state-of-the-art metaheuristic optimizers. For example, Wave outperformed all compared optimizers in F1, F6, F11 and opined the first rank when solving the cantilver beam engineering design problem. The obtained results highlights the effectiveness of wave-driven exploration and targeted exploitation strategies, paving the way for broader applications in engineering design and other complex optimization problems.

关键词： Performance evaluation Heavily-tailed distribution Metaheuristics Optimization methods Benchmark testing Oscillators Computational intelligence Convergence

来源：评论

学校读者我要写书评

暂无评论

HIGH-DIMENSIONAL SGD ALIGNS WITH EMERGING OUTLIER EIGENSPACES

arXiv

引用

arXiv 2023年

作者： Ben Arous, Gérard Gheissari, Reza Huang, Jiaoyang Jagannath, Aukosh Courant Institute New York University United States Department of Mathematics Northwestern University United States Department of Statistics and Data Science University of Pennsylvania United States Department of Statistics and Actuarial Science Department of Applied Mathematics Cheriton School of Computer Science University of Waterloo Canada

We rigorously study the joint evolution of training dynamics via stochastic gradient descent (SGD) and the spectra of empirical Hessian and gradient matrices. We prove that in two canonical classification tasks for multi-class high-dimensional mixtures and either 1 or 2-layer neural networks, the SGD trajectory rapidly aligns with emerging low-rank outlier eigenspaces of the Hessian and gradient matrices. Moreover, in multi-layer settings this alignment occurs per layer, with the final layer’s outlier eigenspace evolving over the course of training, and exhibiting rank deficiency when the SGD converges to sub-optimal classifiers. This establishes some of the rich predictions that have arisen from extensive numerical studies in the last decade about the spectra of Hessian and information matrices over the course of training in overparametrized networks. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Dimension-free private mean estimation for anisotropic distributions 24

Dimension-free private mean estimation for anisotropic distr...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yuval Dagan Michael I. Jordan Xuelin Yang Lydia Zakynthinou Nikita Zhivotovskiy School of Computer Science Tel Aviv University Department of EECS and Statistics University of California Berkeley Department of Statistics University of California Berkeley Department of EECS University of California Berkeley

ISBN: (纸本)9798331314385

We present differentially private algorithms for high-dimensional mean estimation. Previous private estimators on distributions over ℝd suffer from a curse of dimensionality, as they require Ω(d1/2) samples to achieve non-trivial error, even in cases where O(1) samples suffice without privacy. This rate is unavoidable when the distribution is isotropic, namely, when the covariance is a multiple of the identity matrix. Yet, real-world data is often highly anisotropic, with signals concentrated on a small number of principal components. We develop estimators that are appropriate for such signals—our estimators are (ε, δ)-differentially private and have sample complexity that is dimension-independent for anisotropic subgaussian distributions. Given n samples from a distribution with known covariance-proxy Σ and unknown mean μ, we present an estimator $\hat{\mu}$ that achieves error, $\|\hat{\mu}-\mu\|_2\leq \alpha$, as long as n ≳ tr(Σ)/α2 + tr(Σ1/2)/(αε). We show that this is the optimal sample complexity for this task up to logarithmic factors. Moreover, for the case of unknown covariance, we present an algorithm whose sample complexity has improved dependence on the dimension, from d1/2 to d1/4.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Characterizing overfitting in kernel ridgeless regression through the eigenspectrum 24

Characterizing overfitting in kernel ridgeless regression th...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Tin Sum Cheng Aurelien Lucchi Anastasis Kratsios David Belius Department of Mathematics and Computer Science University of Basel Switzerland Department of Mathematics and Statistics McMaster University and Vector Institute Canada Faculty of Mathematics and Computer Science UniDistance Suisse Switzerland

We derive new bounds for the condition number of kernel matrices, which we then use to enhance existing non-asymptotic test error bounds for kernel ridgeless regression (KRR) in the overparameterized regime for a fixed input dimension. For kernels with polynomial spectral decay, we recover the bound from previous work; for exponential decay, our bound is non-trivial and novel. Our contribution is two-fold: (i) we rigorously prove the phenomena of tempered overfitting and catastrophic overfitting under the sub-Gaussian design assumption, closing an existing gap in the literature; (ii) we identify that the independence of the features plays an important role in guaranteeing tempered overfitting, raising concerns about approximating KRR generalization using the Gaussian design assumption in previous literature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid Optimization Algorithm to Mitigate Phishing URL Attacks In Smart Cities 3

Hybrid Optimization Algorithm to Mitigate Phishing URL Attac...

引用

3rd International Conference on Innovative Practices in Technology and Management, ICIPTM 2023

作者： Sujatha, G. Ayyannan, Manimuthu Priya, S. Gayathri Arun, V. Arularasan, A.N. Kumar, M Jogendra Sri Venkateswara College of Engineering Department of Electronics and Communication Andhra Pradesh Tirupati India AI/ML and Data Expert San FranciscoCA United States R. M. D. Engineering College Department of Electronics and Communication Tamil Nadu Kavaraipettai India Madanapalle Institute of Technology Department of Computer Science &engineering Andhra Pradesh Madanapalle India Panimalar Engineering College Department of Artificial Intelligence &data Science Tamil Nadu Chennai India Koneru Lakshmaiah Education Foundation Department of Computer Science Andhra Pradesh Vaddeswaram India

ISBN: (纸本)9798350336238

To improve the detection of phishing sites, this proposal introduces feature weights for intelligent phishing site detection based on hybrid bio-inspired algorithms. The proposed approach uses Gray Wolf Optimization (GWO) and Firefly Algorithm (FF), which examines a wide range of website attributes, to more precisely identify phishing sites. Then employs Artificial Neural Network (ANN) to classify different website elements according to the importance of each component in differentiating between legitimate and phishing websites using bioinspired-based recommended site feature weights. According to experimental findings, the suggested hybrid bioinspired-based feature weighting greatly improved classification accuracy, true positive (TPR), and negative rates (TNR), as well as precision and F1 score. Phishing is an online crime that entails the gathering of private information like passwords, account numbers, and credit card numbers. Attackers use alluring URLs to entice phony website visitors. Recently, Artificial Intelligence-based phishing detection has seen some success, and in this study, ANN was used to detect phishing. This ANN classifier may make phishing websites simpler to spot. However, it has been shown that the effectiveness of detection can be increased by applying a genetic algorithm to improve feature selection. © 2023 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Product Quality Enhancement in Social Media using Emotion-Enhanced Bert (EE-BERT) Model

Product Quality Enhancement in Social Media using Emotion-En...

引用

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

作者： V S Raj Kumar T Kumaresan V Mythily N Raghavendran Department of Artificial Intelligence and Data science Bannari Amman Institute of Technology Sathyamangalam India Department of Computer Science and Engineering Bannari Amman Institute of Technology Sathyamangalam India Department of Computer Science and Engineering Nandha Engineering College Erode India Department of Artificial Intelligence and Data science RMK college of Engineering and Technology Chennai India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

Twitter plays an important role in understanding the consumer sentiment about the products. The advanced analytics and Natural Language Processing (NLP) are used to extract actionable insights from this data and useful for a business to improve features and address issues on time for better customer satisfaction and brand loyalty. Most of the current models suffer from a lack of effective ways to handle subtle sentiment analysis because of a lack of contextual understanding and proper feature extraction. Most traditional models cannot combine and optimize features that lead to obtaining sentiments. This leads to overfitting and problems caused by local minima. The proposed Emotion-Enhanced BERT (EE-BERT) model is an extension of the standard BERT to learn contextual embeddings in user sentiment. In this work, data preprocessing includes text cleaning, tokenization, dealing with emojis and emoticons, and lemmatization with the best quality data. The proposed work is basically a dual-stream architecture extended with butterfly optimizer. First, the advanced tokenization and semantic understanding techniques is used for extracting textual features. Second, the emotion-enhanced features extracted through emotion-hash vectorization to enhance the model’s contextual awareness in social media data. This provides a unified framework that combines the feature extraction methods to enhance the accuracy in sentiment analysis. It demonstrated with an impressive accuracy of ${9 8. 2 \%}$ on sentiment in posts and comments with 0.15 losses. The proposed work is free from overfitting and local minima in product quality enhancement.

关键词： Accuracy Social networking (online) Computational modeling Blogs Feature extraction Product design Encoding data models Quality assessment Context modeling

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：