检索结果-内蒙古大学图书馆

Effi-CNN: real-time vision-based system for interpretation of sign language using CNN and transfer learning

Multimedia Tools and Applications 2025年第6期84卷 3137-3159页

作者： Pranav Katarya, Rahul Big Data Analytics and Web Intelligence Laboratory Computer Science & Engineering Department Delhi Technological University New Delhi India

The deaf and mute population has difficulty conveying their thoughts and ideas to others. Sign language is their most expressive mode of communication, but the general public is callow of sign language;therefore, the mute and deaf have difficulty communicating with others. A system that can correctly translate sign language motions to speech and vice versa in real time is required to overcome this communication barrier. Effi-CNN, a vision-based Sign Language Recognition (SLR) system employing transfer learning with EfficientNetB2, is proposed in this paper. We have also developed a system covering sign gestures to text in real time. Our approach was evaluated on eight publicly available datasets, including the Massey University gesture dataset, the ArSL2018 dataset, the MNIST-ASL dataset, and others. When comparing our results to state-of-the-art algorithms, the experimental findings showed that our proposed work is more successful than existing models. Our proposed model delivered an accuracy of 99.90 on MNIST dataset. The results show that our Effi-CNN surpasses most currently existing solutions and can categorize many gestures with a low error rate. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques for Autism Spectrum Disorder: Current trends and future directions 4

Machine Learning Techniques for Autism Spectrum Disorder: Cu...

引用

4th International Conference on Innovative Trends in Information Technology, ICITIIT 2023

作者： Khan, Kainat Katarya, Rahul Delhi Technological University Big Data Analytics and Web Intelligence Laboratory Department of Computer Science and Engineering New Delhi India

ISBN: (纸本)9781665494144

ASD or autism spectrum disorder is a critical neuro-developmental disorder that hinders an individual's capability of social communication and interaction. This disorder has acquired considerable attention and importance due to its ubiquity among individuals covering all the countries worldwide. Individuals with ASD struggles in daily life activities. Detection of autism with the help of medical tests is a tedious and very costly task. However, detection and care of ASD still remains unfamiliar due to inadequate awareness, knowledge among the society, limited number of diagnostic devices and limited verbal therapy services for ASD patients. This paper investigates and displays reviews of various machine learning approaches on extracting useful data associated with distinctive characteristics of ASD such as brain functioning, hyperactivitperactivity, language disability, etc. Current researches reveal that analysis of biological traits by employing machine learning techniques have helped in the progress of early detection of ASD. ABIDE dataset is very much explored for the research in ASD. Additionally, numerous studies for the advancement of tools are still in progression. The presented research work can remarkably aid future studies on machine learning for ASD. © 2023 IEEE.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

DASIV: Directional Acoustic Sensing based Intelligent Vehicle Interaction System

DASIV: Directional Acoustic Sensing based Intelligent Vehicl...

引用

2024 IEEE International Performance, Computing, and Communications Conference, IPCCC 2024

作者： Zhao, Dinghua Zhou, Juntao Ding, Dian Lu, Yu Li, Yijie Yang, Hang Chen, Yi-Chao Xue, Guangtao Shanghai Jiao Tong University Department of Computer Science and Engineering China Governance and Web3 Shanghai Key Laboratory of Trusted Data Circulation China

ISBN: (纸本)9798350367942

With the increase in motor vehicles, more convenient and accurate interactions are expected while retaining a high standard of safe driving. However, complex and dynamic vehicle environments challenge sensing tasks such as breathing monitor and hand gesture recognition. In this paper, we propose DASIV, which utilizes the highly directional nature of ultrasonic signals to achieve fine-grained directional acoustic sensing in vehicle environments. Due to air nonlinearity, the system enables synchronized directional acoustic communication to transmit information (e.g., navigation) to the driver without affecting other passengers. By optimizing the frequency of the Frequency Modulated Continuous Wave (FMCW) signals, DASIV avoids mutual interference between the sensing and communication signals and achieves breathing detection and hand gesture recognition for the driver. Specifically, the system extracts breathing-induced weak thoracic bullying through the signal phase, captures and analyses breathing patterns using bandpass and Gaussian filters, and develops a breathing model. Then, the system defines 10 interaction hand gestures to meet daily interaction needs, uses spectral features to mine complex and fast hand movement features, and proposes a hand gesture recognition model. Extensive experiments in real environments show that DASIV achieves high-precision breathing monitor (Pearson correlation coefficient of 0.89) and hand gesture recognition (Precision of 91.7%). © 2024 IEEE.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

Are LLMs Aware that Some Questions are not Open-ended?

Are LLMs Aware that Some Questions are not Open-ended?

引用

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

作者： Yang, Dongjie Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

ISBN: (纸本)9798891761681

Large Language Models (LLMs) have shown the impressive capability of answering questions in a wide range of scenarios. However, when LLMs face different types of questions, it is worth exploring whether LLMs are aware that some questions have limited answers and need to respond more deterministically but some do not. We refer to this as question awareness of LLMs. The lack of question awareness in LLMs leads to two phenomena that LLMs are: (1) too casual to answer non-open-ended questions or (2) too boring to answer open-ended questions. In this paper, we first evaluate the question awareness in LLMs. The experimental results show that LLMs have the issues of lacking awareness of questions in certain domains, e.g. factual knowledge, resulting in hallucinations during the generation. To mitigate these, we propose a method called Question Awareness Temperature Sampling (QuATS). This method enhances the question awareness of LLMs by adaptively adjusting the output distributions based on question features. The automatic adjustment in QuATS eliminates the need for manual temperature tuning in text generation and consistently improves model performance in various benchmarks. © 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

Head-wise Shareable Attention for Large Language Models

Head-wise Shareable Attention for Large Language Models

引用

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

作者： Cao, Zouying Yang, Yifei Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

ISBN: (纸本)9798891761681

Large Language Models (LLMs) suffer from huge number of parameters, which restricts their deployment on edge devices. Weight sharing is one promising solution that encourages weight reuse, effectively reducing memory usage with less performance drop. However, current weight sharing techniques primarily focus on small-scale models like BERT and employ coarse-grained sharing rules, e.g., layer-wise. This becomes limiting given the prevalence of LLMs and sharing an entire layer or block obviously diminishes the flexibility of weight sharing. In this paper, we present a perspective on head-wise shareable attention for large language models. We further propose two memory-efficient methods that share parameters across attention heads, with a specific focus on LLMs. Both of them use the same dynamic strategy to select the shared weight matrices. The first method directly reuses the pre-trained weights without retraining, denoted as DirectShare. The second method first post-trains with constraint on weight matrix similarity and then shares, denoted as PostShare. Experimental results reveal our head-wise shared models still maintain satisfactory capabilities, demonstrating the feasibility of fine-grained weight sharing applied to LLMs. © 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

LaCo: Large Language Model Pruning via Layer Collapse

LaCo: Large Language Model Pruning via Layer Collapse

引用

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

作者： Yang, Yifei Cao, Zouying Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

ISBN: (纸本)9798891761681

Large language models (LLMs) based on transformer are witnessing a notable trend of size expansion, which brings considerable costs to both model training and inference. However, existing methods such as model quantization, knowledge distillation, and model pruning are constrained by various issues, including hardware support limitations, the need for extensive training, and alterations to the model internal structure. In this paper, we propose a concise layer-wise structured pruner called Layer Collapse (LaCo), in which rear model layers collapse into a prior layer, enabling a rapid reduction in model size while preserving the model structure. Comprehensive experiments show that our method maintains an average task performance of over 80% at pruning ratios of 25-30%, significantly outperforming existing state-of-the-art structured pruning methods. We also conduct post-training experiments to confirm that the LaCo effectively inherits the parameters of the original model. Additionally, we perform ablation studies on various settings of LaCo. Finally, we discuss our motivation from the perspective of layer-wise similarity and evaluate the performance of the pruned LLMs across various pruning ratios. © 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

Instruction-Driven Game Engine: A Poker Case Study

Instruction-Driven Game Engine: A Poker Case Study

引用

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

作者： Wu, Hongqiu Liu, Xingyuan Wang, Yan Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China Tencent China

ISBN: (纸本)9798891761674

The Instruction-Driven Game Engine (IDGE) project aims to democratize game development by enabling a large language model (LLM) to follow free-form game descriptions and generate game-play processes. The IDGE allows users to create games simply by natural language instructions, which significantly lowers the barrier for game development. We approach the learning process for IDGEs as a Next State Prediction task, wherein the model autoregressively predicts the game states given player actions. The computation of game states must be precise;otherwise, slight errors could corrupt the game-play experience. This is challenging because of the gap between stability and diversity. To address this, we train the IDGE in a curriculum manner that progressively increases its exposure to complex scenarios. Our initial progress lies in developing an IDGE for Poker, which not only supports a wide range of poker variants but also allows for highly individualized new poker games through natural language inputs. This work lays the groundwork for future advancements in transforming how games are created and played. © 2024 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysing the Twitter Sentiments in COVID-19 Using Machine Learning Algorithms

Analysing the Twitter Sentiments in COVID-19 Using Machine L...

引用

2022 IEEE International Conference on Advances in Computing, Communication and Applied Informatics, ACCAI 2022

作者： Katarya, Rahul Nath, G Amar Singhal, Divit Shukla, Aryaman Delhi Technological University Big Data Analytics and Web Intelligence Laboratory Department of Computer Science Engineering New Delhi India

ISBN: (纸本)9781665495295

The coronavirus emanated in Wuhan city of China, in the last month of 2019 and was even announced as a global threat. Social media could be an utterly noteworthy supply of facts during a time of crisis. User-generated texts yield perception into users' minds withinside the direction of such times, giving us insights into their critiques in addition to moods. This venture examines Twitter messages (tweets) regarding people's sentiment on the unconventional coronavirus. The essential aim of sentiment evaluation is the origin of human emotion from messages or tweets. This venture is geared toward using numerous gadgets studying type algorithms to expect the people's reception of the worldwide pandemic by reading their tweets on Twitter. In the course of this paper, we are testing our dataset on five different classifiers, namely Random Forest, Logistic regression, Multinomial naive Bayes, K-nearest neighbor, and Support vector machines classifiers. Together with precision rankings and balanced accuracy rankings, metrics are offered to gauge the fulfilment of the numerous algorithms implemented. The K-Nearest Neighbor classifier has given the highest precision score while the Logistic Regression classifier gives the highest recall, F1, accuracy and balanced accuracy scores. © 2022 IEEE.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning 27th

SecureCut: Federated Gradient Boosting Decision Trees with ...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Li, Bowen Zhang, Jian Li, Jie Wu, Chentao Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Yancheng Blockchain Research Institute Yancheng China Blockchain Advanced Research Center Shanghai China Shanghai Key Laboratory of Trusted Data Circulation and Governance and Web3 Shanghai China

ISBN: (纸本)9783031781681

In response to legislation, companies are now mandated to honor the right to be forgotten by erasing user data. Consequently, it has become imperative to enable data removal in Vertical Federated Learning (VFL), where multiple parties provide private features for model training. In VFL, data removal, i.e., machine unlearning, requires removing specific features across all samples, ensuring privacy in federated learning. To address this challenge, we propose SecureCut, a novel Gradient Boosting Decision Tree (GBDT) framework that effectively enables both instance unlearning and feature unlearning without the need for retraining from scratch. Leveraging a robust GBDT structure, we enable effective data deletion while reducing degradation of model performance. Extensive experimental results on popular datasets demonstrate that our method achieves superior model utility and forgetfulness compared to the state-of-the-art methods. To the best of our knowledge, this is the first work that investigates machine unlearning in VFL scenarios. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

On the Robustness of Editing Large Language Models

On the Robustness of Editing Large Language Models

引用

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

作者： Ma, Xinbei Ju, Tianjie Qiu, Jiyang Zhang, Zhuosheng Zhao, Hai Liu, Lifeng Wang, Yulong School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China Baichuan Intelligent Technology China

ISBN: (纸本)9798891761643

Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. Model editing enables the manipulation of specific knowledge memories and the behavior of language generation without retraining. However, the robustness of model editing remains an open question. This work seeks to understand the strengths and limitations of editing methods, facilitating practical applications of communicative AI. We focus on three key research questions. RQ1: Can edited LLMs behave consistently resembling communicative AI in realistic situations? RQ2: To what extent does the rephrasing of prompts lead LLMs to deviate from the edited knowledge memory? RQ3: Which knowledge features are correlated with the performance and robustness of editing? Our empirical studies uncover a substantial disparity between existing editing methods and the practical application of LLMs. On rephrased prompts that are flexible but common in realistic applications, the performance of editing experiences a significant decline. Further analysis shows that more popular knowledge is memorized better, easier to recall, and more challenging to edit effectively. © 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

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：