检索结果-内蒙古大学图书馆

Data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： Leo Prasanth L Susi E Selvin Ebenezer S Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder considered by challenges in communication, social interaction, and behavior. Early and accurate detection remains a challenge due to subjective clinical assessments. This work presents an innovative hybrid framework that incorporates sentiment analysis from social media data with deep learning techniques applied to clinical data to enhance ASD prediction. Leveraging Twitter sentiment, a Long Short-Term Memory (LSTM) model captures public emotional and behavioral patterns, while clinical data undergoes deep learning-based character-level embedding using a Convolutional Neural Network (CNN) with transfer learning. The fusion of these models through a weighted sum mechanism results in a comprehensive ASD detection system. Experimental outcomes demonstrate an accuracy of 99.3% with a loss of 1.45%, significantly outperforming traditional diagnostic approaches. Visual analyses further validate key correlations between assessment scores and ASD diagnoses. Despite limitations such as misinformation in social media and the need for larger clinical datasets, the proposed approach highlights the potential of integrating social and clinical perspectives for improved ASD diagnosis. Future work will explore broader social media sources and advanced deep learning architectures to refine the model, ultimately contributing to early intervention and progressed results for individuals with ASD.

关键词： Deep learning Sentiment analysis Autism Visualization Accuracy Social networking (online) Transfer learning Data models Fake news Long short term memory

来源：评论

学校读者我要写书评

暂无评论

IMPACT: an interactive multi-disease prevention and counterfactual treatment system using explainable AI and a multimodal LLM

引用

PeerJ computer science 2025年 11卷

作者： Mohanty, Prasant Kumar Francis, Sharmila Anand John Barik, Rabindra Kumar Reddy, K. Hemant Kumar Roy, Diptendu Sinha Saikia, Manob Jyoti Department of Computer Science and Engineering National Institute of Technology Meghalaya Shillong India Department of Computer Science Rijal Alma’a King Khalid University Abha Saudi Arabia School of Computer Applications KIIT Deemed to be University Odisha Bhubaneswar India Department of Computer Science and Engineering VIT-AP University Beside AP Secretariat Amaravati Andhra Pradesh India Biomedical Sensors & Systems Lab The University of Memphis MemphisTN United States Electrical and Computer Engineering Department The University of Memphis MemphisTN United States

Multi-disease conditions strain the body’s defenses, complicating recovery and increasing mortality risk. Therefore, effective concurrent prevention of multiple diseases is essential for mitigating complications and improving overall well-being. Explainable artificial intelligence (XAI) with an advanced multimodal large language model (LLM) can create an interactive system enabling the general public to engage in natural language without any specialized knowledge prerequisites. Counterfactual explanation, an XAI method, offers valuable insights by suggesting adjustments to patient features to minimize disease risks. However, addressing multiple diseases simultaneously poses challenging barriers. This article proposes an interactive multi-disease prevention system that uses Google Gemini Pro, a multimodal LLM, and a non-dominated sorting genetic algorithm, namely NSGA-II, to overcome such problems. This system recommends changes in feature values to concurrently minimize the risk of diseases such as heart attacks and diabetes. The system facilitates personalized feature value selection, significantly reducing disease attack probabilities to as low as possible. Such an approach holds the potential to simultaneously address the unresolved issue of preventing and managing multiple diseases for the general public. © 2025 Mohanty et al.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Speaker Verification with Batch-scale Pseudo-labels Correction

Self-supervised Speaker Verification with Batch-scale Pseudo...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Junxu Wang Zhihua Fang Liang He School of Computer Science and Technology Xinjiang University Urumqi China Department of Electronic Engineering Tsinghua University Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Self-supervised learning has shown outstanding performance on speaker verification, and the 2-stage frameworks have more comprehensive training schemes, which typically exhibit better performance. They utilize clustering to obtain pseudo-labels, which are then used as the supervision signal in stage 2. However, these pseudo-labels often contain a significant amount of noisy labels, severely impacting speaker verification performance. In this paper, we propose a dynamic self-supervised pseudo-label correction method based on batch-scale training. By filtering and correcting samples based on the loss and prediction distribution, our method better aligns with the dynamic training process and achieves EER(%) of 1.33, 1.56 and 2.78 on the test sets of Voxceleb-O, E, H.

关键词： Training Filtering Self-supervised learning Signal processing Acoustics Noise measurement Speech processing

来源：评论

学校读者我要写书评

暂无评论

Human Action Recognition Using Mediapipe Holistic Keypoints: A Deep Learning Approach 4th

Human Action Recognition Using Mediapipe Holistic Keypoints:...

引用

4th International Conference on Advanced Network Technologies and Intelligent Computing, ANTIC 2024

作者： Shandilya, Utkarsh Sharma, Vijeta Mishra, Deepti Department of Computer Science and Engineering Central University of Haryana Haryana India NTNU-Norwegian University of Science and Technology Gjøvik2815 Norway

ISBN: (纸本)9783031837951

Human action recognition (HAR) is a crucial field in computer vision with applications ranging from video surveillance to human-computer interaction. This study explores an efficient framework for HAR by leveraging human keypoint extraction using Google’s Mediapipe and Long Short-Term Memory (LSTM) networks. The Mediapipe framework provides accurate and real-time human keypoint extraction, significantly reducing the computational complexity associated with raw video data processing. These keypoints, representing skeletal movements, are utilised as input to LSTM networks, which capture the temporal dependencies vital for action classification. The proposed method is evaluated on two benchmark datasets: UCF101 and Kinetics 400. UCF101 contains 13,320 video clips across 101 action classes, while Kinetics 400 features 400 human action categories. The combination of Mediapipe for feature extraction and LSTM for temporal modelling achieves 92.40% and 86.8% accuracy on UCF101 and Kinetics400, respectively. The results demonstrate the effectiveness of keypoint-based approaches for HAR. This study highlights the potential of lightweight, real-time human action recognition frameworks suitable for resource-constrained environments, especially for edgeAI and edge Robotics. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Tiny Objects Classification on Remote Sensing Image by Using Multi-Scale Crop

Tiny Objects Classification on Remote Sensing Image by Using...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Rou-Ying Su Pei-Jun Lee Electronic and Computer Engineering Department National Taiwan University of Science and Technology Taipei Taiwan R.O.C

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Classifying tiny objects in remote sensing images (e.g., a 20x20 pixels target within a resolution 1000x1000 image) is a significant challenge. This paper adopts a fused FPN (Feature Pyramid Network) to enhance the feature extraction capability for tiny objects. Additionally, the proposed multi-scale crop method can more effectively focus on the target objects. This network architecture improves overall accuracy by 14.4%.

关键词： Image resolution Accuracy Crops Network architecture Feature extraction Remote sensing Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

I Can’t Share Code, but I need Translation - An Empirical Study on Code Translation through Federated LLM

arXiv

引用

arXiv 2025年

作者： Kumar, Jahnavi Janapati, Venkata Lakshmana Sasaank Tanguturi, Mokshith Reddy Chimalakonda, Sridhar Research in Intelligent Software & Human Analytics Lab Department of Computer Science and Engineering Indian Institute of Technology Tirupati India

Owing to the rapid evolution of technologies and project requirements, organizations need to upgrade the code base in their software projects to a new version of the programming language or even translating to an entirely new one. However, code translation is resource-intensive and requires expertise in both the source and target languages. While researchers have made progress in automating translations between legacy and modern languages, recent work has increasingly turned to pre-trained Large Language Models (LLMs) to translate efficiently. Given the proprietary nature of code, organizations prefer finetuning LLMs locally rather than relying on external APIs. This is one of the first empirical studies that proposes a Federated LLM-based approach for code translation. The proposed approach enables clients to jointly train a code translator without sharing sensitive data. This study demonstrates that participants can collaboratively develop a FedLLM for efficient code translation (particularly C# to Java and vice-versa) with superior results (more than 40% improvement in CodeLLaMA’s CodeBLEU score) compared to individual client models. Our findings indicate that FedLLM offers a collaborative approach to code translation and could serve as a promising direction for future research in this field. © 2025, CC BY.

关键词： Program translators

来源：评论

学校读者我要写书评

暂无评论

Environmental Temperature Monitoring System Featuring Printed Temperature Sensor and a Flexible, Printed WiFi Antenna

Environmental Temperature Monitoring System Featuring Printe...

引用

Microwave, Antennas & Circuits (ICMAC), International Conference on

作者： Rana muhammad Bilal Firas Fatani Mohammad Vaseem Sakandar Rauf Atif Shamim Department of Electrical and Computer Engineering CEMSE Division King Abdullah University of Science and Technology (KAUST) Kingdom of Saudi Arabia

ISBN: (数字)9798331518424

ISBN: (纸本)9798331518431

With the increasing need for scalable, energy-efficient sensing solutions in smart cities and buildings, traditional temperature monitoring systems face limitations due to higher manufacturing costs and rigid designs. Printed fabrication offers a flexible and economical alternative that enhances potential for volume deployment, ubiquitous integration and the increased spatial resolution of monitoring. In this work, we present a novel environmental temperature monitoring system that leverages printed fabrication for antenna and sensor for such applications. A high measured sensitivity (i.e. 3.1% Temperature coefficient of resistance) is shown for the designed printed temperature sensor. A measured 93MHz bandwidth coverage is shown for the designed printed, flexible dual-patch array WiFi antenna.

关键词： Temperature sensors Temperature measurement Antenna measurements Fabrication Smart cities Sensors Electrical resistance measurement Monitoring Wireless fidelity Antenna arrays

来源：评论

学校读者我要写书评

暂无评论

SimpleRNN Based Human Emotion Recognition Using EEG Signals 6th

SimpleRNN Based Human Emotion Recognition Using EEG Signals

引用

6th International Conference on Computational Intelligence in Communications and Business Analytics, CICBA 2024

作者： Sonwani, Harsh Banoth, Earu Jain, Puneet Kumar Department of Computer Science and Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India Department of Biotechnology and Biomedical Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India

ISBN: (纸本)9783031813382

The research focuses on developing an electroencephalography (EEG) based emotion recognition system to identify happy, neutral, and negative emotions. The suggested framework uses Simple Recurrent Neural Networks (SimpleRNN) networks to capture the temporal information of the EEG data. Identifying prominent EEG bands for emotion classification and the ensemble of Simple RNN based on these bands are significant contributions of this research. The proposed model achieved 83.39% on a publicly available dataset SJTU Emotion EEG Dataset (SEED). The dual-tree Complex Wavelet Transform (DT-CWT) is used to decompose the signal into five bands, and then the features are extracted from each. By drawing parallels between the capabilities of shallow, deep, and ensemble models, the authors show how their suggested emotion detection system may provide adequate identification performance at a reasonable computational cost. The results indicate that higher frequency bands of EEG signals are more effective in identifying emotions. The study contributes particularly to addressing the time-dependence trait of emotion processing. The proposed method has the potential for practical applications in various fields, such as psychology and human-computer interaction, where identifying emotional states is crucial. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

On de Bruijn Array Codes, Part II: Linear Codes

arXiv

引用

arXiv 2025年

作者： Chee, Yeow Meng Etzion, Tuvi Lao, Huimin Department of Industrial Systems Engineering and Management National University of Singapore Singapore Computer Science Department Technion Israel Institute of Technology Haifa3200003 Israel Department of Electrical and Computer Engineering National University of Singapore Singapore

An M-sequence generated by a primitive polynomial has many interesting and desirable properties. A pseudorandom array is the two-dimensional generalization of an M-sequence. Similarly to primitive polynomials, there are irreducible and reducible polynomials whose all nonzero sequences have the same length. In this paper, a two-dimensional generalization for such sequences is given. This generalization is for a pseudo-random array code which is a set of r1×r2 arrays in which each n1×n2 nonzero matrix is contained exactly once as a window in one of the arrays. Moreover, these arrays have the shift-and-add property, i.e., the bitwise addition of two arrays (or a nontrivial shift of such arrays) is another array (or a shift of another array) from the code. All the known arrays can be formed by folding sequences generated from an irreducible polynomial or a reducible polynomial whose factors have the same degree and the same exponent. Two proof techniques are used to prove the parameters of the constructed arrays. The first one is based on another method for constructing some of these arrays. The second one is a generalization of a known proof technique. This generalization enables to present pseudo-random arrays with parameters not known before and also a variety of pseudo-random array codes which cannot be generated by the first method. The two techniques also suggest two different hierarchies between pseudo-random array codes. Finally, a method to verify whether a folding of sequences, generated by these polynomials, yields a pseudo-random array or a pseudo-random array code, will be presented. © 2025, CC BY.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Noise Supervised Contrastive Learning and Feature-Perturbed for Anomalous Sound Detection

Noise Supervised Contrastive Learning and Feature-Perturbed ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shun Huang Zhihua Fang Liang He School of Computer Science and Technology Xinjiang University Urumqi China Department of Electronic Engineering Tsinghua University Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Unsupervised anomalous sound detection aims to detect unknown anomalous sounds by training a model using only normal audio data. Despite advancements in self-supervised methods, the issue of frequent false alarms when handling samples of the same type from different machines remains unresolved. This paper introduces a novel training technique called one-stage supervised contrastive learning (OS-SCL), which significantly addresses this problem by perturbing features in the embedding space and employing a one-stage noisy supervised contrastive learning approach. On the DCASE 2020 Challenge Task 2, it achieved 94.64% AUC, 88.42% pAUC, and 89.24% mAUC using only Log-Mel features. Additionally, a time-frequency feature named TFgram is proposed, which is extracted from raw audio. This feature effectively captures critical information for anomalous sound detection, ultimately achieving 95.71% AUC, 90.23% pAUC, and 91.23% mAUC. The source code is available at: ***/huangswt/OS-SCL.

关键词： Training Time-frequency analysis Source coding Perturbation methods Contrastive learning Production Feature extraction Stability analysis Noise measurement Speech processing

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：