检索结果-内蒙古大学图书馆

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

作者： P. Sasikumar Srikanth Cherukuvada P Balmurugan P Vijay Anand S. Brindasri R. Nareshkumar Department of Artificial Intelligence and Machine Learning Sphoorthy Engineering College Nadergul Hyderabad Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Bowrampet Hyderabad Telangana Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Department of Artificial Intelligence and Data Science CMR Institute of Technology Bengaluru India Department of Computer Science Hindustan Institute of Technology and Science Padur Chennai India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

The proper detection of brain tumors as quickly as possible and the administration of efficient therapy are both necessary steps in the process of curing patients. The complexities of tumor morphology, such as size, location, and texture, as well as heteromorphic appearance in medical pictures, make tumor analysis a difficult *** three most frequent types of brain cancer are brain tumors, meningiomas, and pituitary gland tumors. The purpose of this study is to investigate a classification issue known as a triple-class problem in order to correctly identify these *** a pre-trained version of the vgg16 network, the proposed classification method pulls characteristics from brain MRI scans. Classifier models that have shown their worth in practice are given to help put the retrieved attributes into meaningful groups. The presented method is carried out on the Python platform, and its efficacy is evaluated with the use of performance *** to the results, the conventional neural network (CNN) technique was outperformed by the Transfer Learning method, which resulted in the model having a higher overall performance. This can be observed by demonstrating that the model had a stronger overall performance.

关键词： Accuracy Magnetic resonance imaging Transfer learning Brain cancer Brain modeling Feature extraction Pituitary gland

来源：评论

学校读者我要写书评

暂无评论

LLM-PS: Empowering Large Language Models for Time Series Forecasting with Temporal Patterns and Semantics

arXiv

引用

arXiv 2025年

作者： Tang, Jialiang Chen, Shuo Gong, Chen Zhang, Jing Tao, Dacheng School of Computer Science and Engineering Nanjing University of Science and Technology China College of Computing and Data Science Nanyang Technological University Singapore School of Intellgence Science and Technology Nanjing University China Department of Automation Institute of Image ProceProceedingssing and Pattern Recognition Shanghai Jiao Tong University China School of Computer Science Wuhan University China

Time Series Forecasting (TSF) is critical in many real-world domains like financial planning and health monitoring. Recent studies have revealed that Large Language Models (LLMs), with their powerful in-contextual modeling capabilities, hold significant potential for TSF. However, existing LLM-based methods usually perform suboptimally because they neglect the inherent characteristics of time series data. Unlike the textual data used in LLM pre-training, the time series data is semantically sparse and comprises distinctive temporal patterns. To address this problem, we propose LLM-PS to empower the LLM for TSF by learning the fundamental Patterns and meaningful Semantics from time series data. Our LLM-PS incorporates a new multi-scale convolutional neural network adept at capturing both short-term fluctuations and long-term trends within the time series. Meanwhile, we introduce a time-to-text module for extracting valuable semantics across continuous time intervals rather than isolated time points. By integrating these patterns and semantics, LLM-PS effectively models temporal dependencies, enabling a deep comprehension of time series and delivering accurate forecasts. Intensive experimental results demonstrate that LLM-PS achieves state-of-the-art performance in both short- and long-term forecasting tasks, as well as in few- and zero-shot settings. © 2025, CC BY.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Transforming Skin Disease Diagnosis: Harnessing Compound-Scaled AI Network for Enhanced Image Analysis and Precision Medicine

Transforming Skin Disease Diagnosis: Harnessing Compound-Sca...

引用

Disruptive Technologies (ICDT), International Conference on

作者： S. P. Santhoshkumar Torthi Ravichandra Nandipati Mounika R Ranjani S Gajalakshmi Jim Mathew Philip Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Electronics and Communication Engineering Ellenki College of Engineering and Technology Sangareddy India Department of Computer Science and Engineering Ellenki College of Engineering and Technology Sangareddy India Department of Artificial intelligence and data science Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai India Department of Computer Science and Engineering Rathinam Technical Campus Coimbatore Tamil Nadu India Department of Computer Science and Engineering Sri Ramakrishna Institute of Technology Coimbatore Tamil Nadu India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

Millions worldwide suffer from skin conditions, making prompt and precise diagnosis essential to successful treatment. However, conventional diagnostic techniques are time-consuming, dependent on physician knowledge, and frequently unavailable in low-resource locations. The compound-scaled AI network, an advanced deep-learning model, addresses these challenges by providing precise and scalable image analysis. Utilizing high-resolution imaging and compound scaling, it can accurately detect, classify, and segment various skin disorders, including benign and malignant lesions. While questions remain about whether AI matches human specialists in diagnosing all pigmented skin lesions, studies have compared AI performance against experts in identifying clinically significant cases. This research highlights the compound-scaled AI network's potential in dermatology, particularly for telemedicine, early cancer detection, and clinical workflow integration. By enhancing diagnostic accessibility and accuracy, this AI model could transform dermatology, enabling more personalized and equitable treatment worldwide. Impressively, it achieved 99.6% training accuracy and 98.4% testing accuracy, demonstrating deep learning's effectiveness in automating skin disorder detection and classification.

关键词： Training Accuracy Image analysis Precision medicine Computational modeling Dermatology Transforms Skin Lesions Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Speech-to-text Emotion Detection System using SVM, CNN, and BERT

Speech-to-text Emotion Detection System using SVM, CNN, and ...

引用

Smart Power Control and Renewable Energy (ICSPCRE), IEEE International Conference on

作者： Uma Yadav Shweta Bondre Bhakti Thakre Kiran Likhar Computer Science & Engineering (Data Science) Shri Ramdeobaba College of Engineering and Management Nagpur India Information Technology Department Shri Ramdeobaba College of Engineering and Management Nagpur India Cyber Security Department St. Vincent Pallotti College of Engineering and Technology Nagpur India Computer Science & Engineering G H Raisoni Institute of Engineering and Technology Nagpur India

ISBN: (数字)9798350377002

ISBN: (纸本)9798350377019

Emotions have a tremendous impact on human experiences and decision-making processes. People are frequently motivated to repeat happy behaviors while avoiding depressing ones. Emotions may spread like wildfire in the modern digital era due to the quick broadcast of information and the heavy use of emotive language in communication. The identification of these emotional undercurrents in a variety of literary forms has been made easier by the analysis of indigenous languages, allowing for prompt interventions when needed. This study presents an algorithm that can analyze statements and then categorize them into sentiments in order to determine a person's emotional state. An analysis of the algorithm's performance shows that BERT performs better than SVM and CNN in a variety of emotional categories, showing better recall, accuracy, and F1-scores in the identification of emotions including Joy, Sadness, Fear, and Anger. For example, BERT outperforms SVM and CNN by large margins, achieving an average F1-score of 0.85 across all emotions. CNN performs competitively, especially when it comes to identifying emotions such as Fear and Sadness, but SVM performs somewhat worse overall than BERT and CNN. Interestingly, all models are good at recognizing Neutral emotions, with BERT and CNN doing somewhat better than SVM. As a result, BERT stands out as the best model for classifying emotions, demonstrating its effectiveness in identifying complex emotional states.

关键词： Support vector machines Emotion recognition Renewable energy sources Wildfires Accuracy Power control Decision making

来源：评论

学校读者我要写书评

暂无评论

Almost minimax optimal best arm identification in piecewise stationary linear bandits 24

Almost minimax optimal best arm identification in piecewise ...

引用

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

作者： Yunlong Hou Vincent Y. F. Tan Zixin Zhong Department of Mathematics National University of Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore Data Science and Analytics Thrust Hong Kong University of Science and Technology (Guangzhou)

ISBN: (纸本)9798331314385

We propose a novel piecewise stationary linear bandit (PSLB) model, where the environment randomly samples a context from an unknown probability distribution at each changepoint, and the quality of an arm is measured by its return averaged over all contexts. The contexts and their distribution, as well as the changepoints are unknown to the agent. We design Piecewise-Stationary ε-Best Arm Identification+ (PSεBAI+), an algorithm that is guaranteed to identify an ε-optimal arm with probability ≥ 1 - δ and with a minimal number of samples. PSεBAI+ consists of two subroutines, PSεBAI and NAÏVE ε-BAI(NεBAI), which are executed in parallel. PSεBAI actively detects changepoints and aligns contexts to facilitate the arm identification process. When PSεBAI and NεBAI are utilized judiciously in parallel, PSεBAI+ is shown to have a finite expected sample complexity. By proving a lower bound, we show the expected sample complexity of PSεBAI+ is optimal up to a logarithmic factor. We compare PSεBAI+ to baseline algorithms using numerical experiments which demonstrate its efficiency. Both our analytical and numerical results corroborate that the efficacy of PSεBAI+ is due to the delicate change detection and context alignment procedures embedded in PSεBAI.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BRAINOOD: OUT-OF-DISTRIBUTION GENERALIZABLE BRAIN NETWORK ANALYSIS

arXiv

引用

arXiv 2025年

作者： Xu, Jiaxing Chen, Yongqiang Dong, Xia Lan, Mengcheng Huang, Tiancheng Bian, Qingtian Cheng, James Ke, Yiping College of Computing and Data Science Nanyang Technological University Singapore Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong S-Lab Nanyang Technological University Singapore

In neuroscience, identifying distinct patterns linked to neurological disorders, such as Alzheimer’s and Autism, is critical for early diagnosis and effective intervention. Graph Neural Networks (GNNs) have shown promising in analyzing brain networks, but there are two major challenges in using GNNs: (1) distribution shifts in multi-site brain network data, leading to poor Out-of-Distribution (OOD) generalization, and (2) limited interpretability in identifying key brain regions critical to neurological disorders. Existing graph OOD methods, while effective in other domains, struggle with the unique characteristics of brain networks. To bridge these gaps, we introduce BrainOOD, a novel framework tailored for brain networks that enhances GNNs’ OOD generalization and interpretability. BrainOOD framework consists of a feature selector and a structure extractor, which incorporates various auxiliary losses including an improved Graph Information Bottleneck (GIB) objective to recover causal subgraphs. By aligning structure selection across brain networks and filtering noisy features, BrainOOD offers reliable interpretations of critical brain regions. Our approach outperforms 16 existing methods and improves generalization to OOD subjects by up to 8.5%. Case studies highlight the scientific validity of the patterns extracted, which aligns with the findings in known neuroscience literature. We also propose the first OOD brain network benchmark, which provides a foundation for future research in this field. Our code is available at https://***/AngusMonroe/BrainOOD. © 2025, CC BY-NC-SA.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars

arXiv

引用

arXiv 2025年

作者： Hua, Yuncheng Qu, Lizhen Li, Zhuang Xue, Hao Salim, Flora D. Haffari, Gholamreza Department of Data Science & AI Monash University Australia School of Computer Science Engineering University of New South Wales Australia School of Computing Technologies Royal Melbourne Institute of Technology Australia

Alignment tuning is crucial for ensuring large language models (LLMs) behave ethically and helpfully. Current alignment approaches require high-quality annotations and significant training resources. This paper proposes a low-cost, tuning-free method using in-context learning (ICL) to enhance LLM alignment. Through an analysis of high-quality ICL demos, we identified style as a key factor influencing LLM alignment capabilities and explicitly restyled ICL exemplars based on this stylistic framework. Additionally, we combined the restyled demos to achieve a balance between the two conflicting aspects of LLM alignment—factuality and safety. We packaged the restyled examples as prompts to trigger few-shot learning, improving LLM alignment. Compared to the best baseline approach, with an average score of 5.00 as the maximum, our method achieves a maximum 0.10 increase on the Alpaca-eval task (from 4.50 → 4.60), a 0.22 enhancement on the just-eval-instruct benchmark (from 4.34 → 4.56), and a maximum improvement of 0.32 (from 3.53 → 3.85) on the MT-Bench dataset. We release the code and data at https://***/AnonymousCode-computerscience/RIDE. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Dual-Channel Convolutional Neural Network with Attention Pooling and Sand Cat Swarm Optimization for Incremental Land-Cover Classification in Satellite Image Patches 4

Dual-Channel Convolutional Neural Network with Attention Poo...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Anushkannan, N.K. Karpagavalli, C. Jagadesan, A. Kavya, R.V. Geetha, K. Devi, S. Rukmani Kathir College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Coimbatore641062 India Ramco Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Rajapalayam626117 India R.M.K Engineering College Department of Physics Tamil Nadu Thiruvallur601206 India J J College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Tiruchirappalli620009 India Srm Institute of Science and Technology Department of Computing Technologies Tamil Nadu Kattankulathur603203 India Saveetha College of Liberal Arts and Sciences Simats Deemed to Be University Department of Computer Science Tamil Nadu Chennai602105 India

ISBN: (纸本)9798331523923

Incremental Land-Cover Classification in satellite image patches concerns the categorization of different types of land cover in satellite images. Land cover mapping from satellite imagery has applications in environmental observation, planning and resource management, and disaster response. Current land cover change classification paradigms involve heavily sampled and trained state vector data models, which do not have provisions for dynamic updates consequent upon variation in the cover density sizes, seasonal changes, incremental growth of urban sprawl, deforestation, and other natural calamities. Since new satellite images become available often, retraining your models from the very beginning is both time-consuming and computationally expensive. To tackle these issues, we propose a Dual-Channel Convolutional Neural Network with Attention Pooling and Sand Cat Swarm Optimization (DualCCNNet-AP+SCSO) for incremental classification of land cover in satellite imagery patches. This methodology utilizes satellite image patches from the So2Sat image patch dataset, where images are initially preprocessed with Iterative Self-Guided Image Filtering (ISGIF). After preprocessing, the Spike-Driven Transformer (SDT) method extracts key features, which are then classified through the Dual-Channel Convolutional Neural Network with Attention Pooling (DualCCNNet-AP), fine-tuned by Sand Cat Swarm Optimization (SCSO) for accurate incremental land-cover classification. The DualCCNNet-AP+SCSO method is implemented in Python. The effectiveness of the proposed method was assessed on the So2Sat image patch dataset, where it achieved an impressive 99.9% accuracy and 99.5% recall, outperforming current techniques. Based on these conclusions about classification accuracy, it demonstrated that the proposed approach enables the effective classification of the change, especially in the smallest class of the land cover in the satellite image patches. The results of the proposed method were bett

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Diversified Sequential Recommendation via Evolutionary Multi-Objective Transfer Optimization

Diversified Sequential Recommendation via Evolutionary Multi...

引用

Artificial Intelligence (CAI), IEEE Conference on

作者： Wei Zhou Xiaolong Luo Hongyue Bao Zexuan Zhu National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

Sequential Recommendation (SR) intends to model user interests based on historical behavior sequences and suggest the next item. Most existing sequential models primarily focus on learning users’ preferences on the relevance objective of the target item. However, the investigation of personalized preferences on the diversity objective of SR results is usually ignored. Evolutionary algorithms have amply demonstrated effectiveness in solving multi-objective problems but encounter efficiency bottlenecks when applied to multi-objective recommendation tasks due to the limited scalability at the user level. To address the problem, this study proposes to facilitate diversified SR via a multi-objective transfer optimization algorithm, in which each optimization task corresponds to the recommendation for a target user. With the optimization knowledge of user preference transferred within and across tasks, the diversified SR of a set of users can synchronously proceed. The novelty of our proposed algorithm is fully utilizing the outstanding global search capability of evolutionary multi-objective optimization without hindering the efficiency of sequential models.

关键词： Scalability Evolutionary computation Task analysis Artificial intelligence Optimization

来源：评论

学校读者我要写书评

暂无评论

Feature Enhancement for Multi-modal Entity Alignment Transformer

Feature Enhancement for Multi-modal Entity Alignment Transfo...

引用

IEEE International Conference on Big Knowledge (ICBK)

作者： Zewen Deng Zan Zhang Bingbing Dong Xiulin Zheng Xindong Wu Key Laboratory of Knowledge Engineering With Big Data (the Ministry of Education of China) School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (数字)9798331508821

ISBN: (纸本)9798331508838

Multi-modal entity alignment (MMEA) aims to identify equivalent entities across different multi-modal knowledge graphs. In these graphs, entities are enriched with information from various modalities, such as text, images, and numerical data, making the alignment task both challenging and crucial for improving knowledge graph quality. Current MMEA algorithms typically encode entity information separately for each modality using corresponding encoders, and then integrate these representations through various modal fusion strategies. However, these methods often fail to fully exploit the multi-modal information of entities. To address this issue, we propose a feature-enhanced multi-modal entity alignment transformer (FEMEAT). FEMEAT enhances entity attribute information by incorporating modal distribution data, which captures the inherent distribution of different modalities for each entity. This inclusion allows the model to have a richer understanding of entity characteristics across modalities. Additionally, FEMEAT utilizes an Optical Character Recognition (OCR) model to extract and incorporate textual information from images. By integrating this text extracted from images, the model can better utilize the visual modality, enhancing its ability to understand and process multi-modal information. Furthermore, FEMEAT employs a multi-head cross-modal attention (MHCA) mechanism for modal fusion to achieve comprehensive multi-modal entity representation. This mechanism enables the model to attend to different modalities simultaneously and learn a detailed representation of entities by considering the interactions between modalities. The multi-head cross-modal attention mechanism facilitates a nuanced understanding and integration of multi-modal data. Experimental results demonstrate that our model achieves state-of-the-art (SOTA) performance across various training scenarios. The code and datasets used in this study can be accessed at https://***/zewenD/FEMEAT.

关键词： Training Visualization Attention mechanisms Optical character recognition Noise Knowledge graphs Transformers Robustness Numerical models data mining

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：