检索结果-内蒙古大学图书馆

5th international conference on machine learning and Big Data Analytics for IoT Security and Privacy, SPIoT 2024

作者： Lin, Wei School of Economics and Business Foreign Languages Wuhan Technology and Business University Hubei Wuhan430065 China

As existing machine translation (MT) mainly uses rules or statistical models, it is not effective in dealing with complex languages and diverse contexts, and it is difficult to cope with low-resource language translation and long text context understanding. To solve these problems, this article applies deep learning algorithms into automatic MT models to improve translation quality and efficiency. In the data collection stage, in addition to using the BCC (BLCU Corpus Center) Chinese corpus, the richness of parallel corpora is also increased through crawler tools. In the preprocessing stage, Jieba is used for Chinese word segmentation, and statistics and dictionaries are combined to reduce ambiguity. the Transformer architecture is integrated with the pre-trained BERT (Bidirectional Encoder Representations from Transformers) model to more precisely capture deep semantics, and fine-tune the model to enhance its understanding of specific translation tasks and optimize the interaction between the decoder and the encoder. During training, the Adam algorithm optimization, weight decay, and Dropout strategy are used to prevent overfitting, and mixed precision training is used to improve efficiency. then, the Horovod framework is used to achieve multi-machine parallel computing. the research results show that the average scores of the MT model using deep learning algorithms on BLEU (Bilingual Evaluation Understudy) and METEOR (Metric for Evaluation of Translation with Explicit ORdering) reach 39.73% and 75.15%, respectively, which is significantly better than the traditional DNN algorithm. At the same time, the model translation takes only 0.36 seconds, which significantly improves efficiency. the model combines pre-training with self-attention mechanism and performs well in the translation of complex sentences and low-resource languages, verifying its accuracy and stability. © 2025 the Authors. Published by Elsevier B.V.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning for Dynamic Hand Gesture Recognition: Applications, Challenges and Future Scope

Deep Learning for Dynamic Hand Gesture Recognition: Applicat...

引用

international conference on Multimedia, Signal Processing and Communication Technologies, (IMPACT)

作者： Arpneek Kaur Sandhya Bansal Department of Computer Science and Engineering Maharishi Markandeshwar Engineering College Maharishi Markandeshwar (Deemed to be University) Ambala Haryana India

ISBN: (纸本)9781665476485

Hand Gesture Recognition is a very promising area of research over the last decade. It has found useful applications in touchless human-machine interaction in modern real-world problems. Dynamic Hand Gesture Recognition is an important requirement in most problems requiring recognition of moving gestures rather than a static pose. this review article provides a comprehensive survey of the recent deep learning-based systems. the articles have been selected by a systematic approach. We provide a detailed literature review and pictorial comparison of accuracies. the existing systems have been summarized concerning various aspects by using a tabular representation. From a study of the existing models, we find out the existing challenges, research gaps, and future scope in this direction.

关键词： Deep learning human computer interaction Systematics Bibliographies Gesture recognition Signal processing Communications technology

来源：评论

学校读者我要写书评

暂无评论

Gene Expression Data Analysis using Supervised machine learning Algorithm in Data Mining for Breast Cancer Prediction

Gene Expression Data Analysis using Supervised Machine Learn...

引用

Image Processing and Capsule Networks (ICIPCN), international conference on

作者： S. Nathiya J. Sumitha Department of Computer Science Dr.SNS Rajalakshmi College of Arts and Science Coimbatore Tamil Nadu India

ISBN: (数字)9798350367171

ISBN: (纸本)9798350367188

the human body is composed of cells, and each cell has a variety of components. the human body’s cells are essential for both the construction and operation of living things. Cells in the human body are capable of dividing and self-destructing as necessary. this natural functioning can occasionally alter; for example, certain cells may grow uncontrollably or improperly, giving rise to tumors. When these tumors develop into malignant ones and spread to nearby body parts, the condition is known as cancer. Specifically, if the cells in the breast can grow uncontrollably then this condition is known as breast cancer. A gene is a piece of genetic material that is present in every human cell. the genes that code for the proteins that determine how each cell functions. Gene expression is the name given to this function that produce protein. Occasionally, variations in the genetic material, or mutated genes, produce alterations in the values of gene expression. Breast cancer is caused by these altered gene expression levels. Some diagnostic techniques are necessary to detect this altered gene expression for breast cancer, and they are highly effective in helping medical professionals to pinpoint the disease’s biomarker. thus, the goal of this research is to use gene expression data to create a model that can accurately identify breast cancer biomarkers. the suggested model in this study, a pruned neural network method, is designed to predict breast cancer while requiring less memory and execution time and offering the best accuracy. this suggested model is evaluated against current techniques, including support vector machines and decision trees, and it outperforms them with a $\mathbf{98 \%}$ accuracy rate. Having a larger number of gene characteristics and fewer samples is a drawback of using gene expression data. therefore, the wrapper approaches are employed as a preprocessing strategy in this research work to remove the undesirable genes. the gene expression data is pr

关键词： Proteins Accuracy machine learning algorithms Biological system modeling Neural networks Predictive models Breast cancer

来源：评论

学校读者我要写书评

暂无评论

VoiceSelective Sound Processing: A Design for Singular Audio Extraction 23

VoiceSelective Sound Processing: A Design for Singular Audio...

引用

Proceedings of the 5th international conference on Information Management & machine Intelligence

作者： Shikha Sharma Vijay Prakash Sharma Sandeep Gupta Department of Computer Science Poornima university India Department of IT SIT Manipal University Jaipur India Department of Artificial Intelligence and Data Science Poornima Institute of Engineering and Technology India

ISBN: (纸本)9798400709418

Voice-selective sound processing, focusing specifically on the extraction of singular audio signals from multifaceted soundscapes, has rapidly gained prominence in a diverse range of applications from health diagnostics to contemporary smart home integrations. the pressing need for such precision extraction arises from our increasingly cluttered audio environments and the escalating importance of clean, distinct voice signals for efficient processing and analysis. the present research delves deep into the intricate mechanisms that drive voice-selective sound processing. By amalgamating the nuanced understanding of human auditory models with the prowess of cutting-edge machine learning methodologies, a unique framework is proposed. this innovative model promises a marked improvement in voice extraction capabilities even in environments characterized by high ambient noise levels. this paper further elucidates the key components of this system, offering insights into its potential and effectiveness in real-world applications.

关键词： Auditory Scene Analysis (ASA) Convolution Neural Network (CNN) Recurrent Neural Network (RNN)

来源：评论

学校读者我要写书评

暂无评论

Finnish 5th and 6th graders’ misconceptions about artificial intelligence

引用

international Journal of Child-computer interaction 2024年 39卷

作者： Mertala, Pekka Fagerlund, Janne University of Jyväskylä Faculty of Education and Psychology PL 35 Jyväskylän yliopisto Jyväskylä 40014 Finland University of Jyväskylä Finnish Institute for Educational Research Alvar Aallon katu 9 Jyväskylä 40014 Finland

Research on children's initial conceptions of AI is in an emerging state, which, from a constructivist viewpoint, challenges the development of pedagogically sound AI-literacy curricula, methods, and materials. To contribute to resolving this need in the present paper, qualitative survey data from 195 children were analyzed abductively to answer the following three research questions: What kind of misconceptions do Finnish 5th and 6th graders’ have about the essence AI?;2) How do these misconceptions relate to common misconception types?;and 3) How profound are these misconceptions? As a result, three misconception categories were identified: 1) Non-technological AI, in which AI was conceptualized as peoples’ cognitive processes (factual misconception);2) Anthropomorphic AI, in which AI was conceptualized as a human-like entity (vernacular, non-scientific, and conceptual misconception);and 3) AI as a machine with a pre-installed intelligence or knowledge (factual misconception). Majority of the children evaluated their AI-knowledge low, which implies that the misconceptions are more superficial than profound. the findings suggest that context-specific linguistic features can contribute to students' AI misconceptions. Implications for future research and AI literacy education are discussed. © 2023 the Authors

关键词： AI literacy Artificial intelligence machine learning Misconceptions Student

来源：评论

学校读者我要写书评

暂无评论

Random Channel Ablation for Robust Hand Gesture Classification with Multimodal Biosignals

Random Channel Ablation for Robust Hand Gesture Classificati...

引用

Annual international conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Keshav Bimbraw Jing Liu Ye Wang Toshiaki Koike-Akino Worcester Polytechnic Institute Worcester MA USA Mitsubishi Electric Research Laboratories (MERL) Cambridge MA USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Biosignal-based hand gesture classification is an important component of effective human-machine interaction. For multimodal biosignal sensing, the modalities often face data loss due to missing channels in the data which can adversely affect the gesture classification performance. To make the classifiers robust to missing channels in the data, this paper proposes using Random Channel Ablation (RChA) during the training process. Ultrasound and force myography (FMG) data were acquired from the forearm for 12 hand gestures over 2 subjects. the resulting multimodal data had 16 total channels, 8 for each modality. the proposed method was applied to convolutional neural network architecture, and compared with baseline, imputation, and oracle methods. Using 5-fold cross-validation for the two subjects, on average, 12.2% and 24.5% improvement was observed for gesture classification with up to 4 and 8 missing channels respectively compared to the baseline. Notably, the proposed method is also robust to an increase in the number of missing channels compared to other methods. these results show the efficacy of using random channel ablation to improve classifier robustness for multimodal and multi-channel biosignal-based hand gesture classification.

关键词： Hands Training Deep learning human computer interaction Ultrasonic imaging Biological system modeling Robustness Imputation Sensors Resilience

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of ChatGPT to improve experiential learning in Education 23

Exploring the Potential of ChatGPT to improve experiential l...

引用

Proceedings of the 5th international conference on Information Management & machine Intelligence

作者： Swati Rawat Sumit Mittal Deepa Nehra Chandani Sharma Dalip Kamboj M.M. Institute of Computer Technology & Business Management Maharishi Markandeshwar (Deemed to be University) India

ISBN: (纸本)9798400709418

Artificial Intelligence (AI) is revolutionizing the field of education by offering new possibilities for personalized and experiential learning along with data-driven insights. the advancement in AI to Generative Artificial Intelligence (GAI) has made the tables turn notably in the field of education. Generative AI application tool ChatGPT is emerging as a game changer offering personalized learning experiences by analyzing huge amounts of student data, generating study materials and pacing to individual needs. Intelligent educational tools powered by AI provide personalized guidance and feedback, adapting to curriculum to address knowledge gaps. GAI also automates the grading process, providing instant feedback and relieving teachers for qualitative assessments. this research paper offers a thorough examination of the potential uses, advantages, difficulties, and moral issues related to implementing ChatGPT in educational contexts. the authors closely analyze how ChatGPT can improve educational experiences, assist personalized learning, and encourage student- teacher interaction, while exploring the drawbacks of using generative AI models in education, such as concerns about bias, data privacy, and over-reliance on technology. this research article intends to offer educators & academicians useful insights into the usage of ChatGPT in the educational field through a critical analysis of the existing literature and real- world experiences.

关键词： ChatGPT

来源：评论

学校读者我要写书评

暂无评论

NLP Model for Postgraduate Research Examiner Recommendation Based on Scholarly Activity

NLP Model for Postgraduate Research Examiner Recommendation ...

引用

IEEE international conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Sadura Priscilla Akinrinwa Samuel Tolulope Ogunjo Kehinde Dennis Akinrinwa Department of Data Science Federal University of Technology Akure Akure Nigeria Department of Physics Federal University of Technology Akure Akure Nigeria Department of Computer Science Federal University of Technology Akure Akure Nigeria

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

Fairness and equity is important in postgraduate research assessment to deter malpractice, mitigate victimization of students, and protect the integrity of the process. Most universities in Africa rely on a human based system to appoint internal and external assessors for postgraduate students’ thesis. this approach is fraught with nepotism and devoid of fairness. In this study, a natural language processing model is proposed for the appointment of internal assessors for postgraduate thesis using the Federal University of Technology Akure, Nigeria as a case study. Our approach utilizes the cosine similarity function to compare students’ abstract with published abstracts of qualified examiners in SCOPUS database. Results obtained in this study showed marked difference between existing approach and the proposed method. Difference in cosine similarity scores was found to be in the range 0.0961 and 0.3345. Specifically, the algorithm showed examiners with better similarity to the students’ work. the approach proposed in this work can significantly improve the assignment of assessors for postgraduate students using a transparent, less bias, and more reliable method.

关键词： Text mining humanities machine learning algorithms Databases Reviews Ecosystems Natural language processing Recycling Reliability Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Review on Deep learning Network Architectures for Image Reconstruction

Review on Deep Learning Network Architectures for Image Reco...

引用

Image Processing and Capsule Networks (ICIPCN), international conference on

作者： Babitha Lokula L.V Narasimha Prasad Ramakrishna Tirumuri department of ECE K L deemed to be university Institute of Aeronautical Engineering Vaddeshwaram India department of ECE Institute of Aeronautical Engineering Hyderabad India department of ECE K L deemed to be university Vaddeshwaram India

ISBN: (数字)9798350367171

ISBN: (纸本)9798350367188

In order to obtain the low resolution(LR) image’s detailed information, super resolution(SR) image reconstruction is essential. From 1D projections, we can reconstruct images in 2D and 3D. the LR images attained have different details of the same scene for which the super resolution reconstruction is possible. In the field of computer vision, image reconstruction is used in a variety of applications including robotics, entertainment, reverse engineering, augmented reality, human-computer interaction, and animation. In addition, applications in the medical field like Magnetic Resonance Imaging (MRI), Computed Tomography (CT), X-rays, and ultrasound, among others, make use of image reconstruction. We may encounter limitations while reconstructing the image, such as noise, missing information, a low signal to noise ratio, and a low contrast to noise ratio. We even come across different issues and challenges in application of SR techniques like image registration, computational efficiency, robustness and performance limitations. To address the above-mentioned issues, we study numerous SISR architectures. In this paper, we’ll talk about various techniques, their benefits, drawbacks, and Single Image Super Resolution (SISR) architectures that can help improve super resolution image reconstruction in a variety of applications.

关键词： Image registration Magnetic resonance imaging Computed tomography Superresolution computer architecture X-rays Robustness

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection and Diagnosis

Plant Disease Detection and Diagnosis

引用

Emerging Technology (INCET), international conference for

作者： Pedapudi. Nagababu Shaik. Nageena Veeranki. Dharani Darsi. Naveen Department of Computer Science and Engineering Lakireddy Bali Reddy College of Engineering (Autonomous) Mylavaram India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

One of the most major occupations and a key contributor to the GDP of our country is agriculture. Food crops have a vital role in the ecosystem and for human health, and plant diseases can result in large losses in food supply. Plant leaves can become infected with a variety of diseases, including blights, leaf spots, and other bacterial and fungal infections. It's critical to identify plant diseases in order to minimise yield losses. Disease identification and plant monitoring are essential to sustainable agriculture. Manually observing plant diseases is a challenging task. We therefore present a novel solution to these issues. We are going to talk about a method that uses photos of the plants' leaves to identify plant illnesses. these flaws have a severe detrimental impact on both the quantity and quality of crop yield. In this research, a review is carried out to examine the outcomes of studies based on the machine learning model for plant leaf disease identification. Many plants die as a result of improper diagnosis of these illnesses, ignorance of the symptoms, and lack of knowledge about treatment options. Image processing, which can extract important information and features from images, is the primary component employed in this research. To achieve the maximum level of precision, leaf colour, leaf damage, leaf area, and leaf texture are all classified qualities. CNN algorithm is used to examine various image parameters or features for the purpose of recognising various plant leaf diseases. this plant disease diagnostics can assist farmers in creating defence systems that lead to robust and fruitful food crops.

关键词： Productivity Plant diseases Microorganisms Reviews Plants (biology) machine learning Feature extraction

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：