检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Ilayaraja, Lathika Yukthika, S.S. Prabakaran, Subramani Pavithra, S. Dept. of Computer Science and Engineering Chennai Institute of Technology Tamil Nadu Chennai600069 India

ISBN: (纸本)9798331527549

AI and EdTech are transforming education by making it more accessible, personalized, and assessable, even in low and middle income countries (LMICs) facing resource constraints. However, challenges come with unequal access, issues in data privacy, and bias in AI model creations. As AI continues to become more popular, the issue of whether the work made by the students will be original. This paper focuses on the impact of artificial intelligence on learning in both its ethical and practical dimensions while highlighting the themes of inclusivity, fairness, and authenticity. Guidelines and policies for responsible AI in integration will be proposed further, alongside teacher training. Results should depict that this moral framework, policies, and teacher education should aid in ensuring that the implications of AI are positive and fruitful for learning. Ideal AI guidelines would foster an educational system that is inclusive, transparent, and considers uniqueness and innovation. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multispectral Satellite Data Classification Using Rank Correlation Similarity Index and Automatic Labeling Technique

引用

SN computer Science 2024年第8期5卷 1073页

作者： Ain, Arindom Gogoi, Minakshi Chutia, Dibyajyoti Dept. of Computer Science and Engineering GIMT Under Assam Science and Technology University Assam Guwahati India Dept. of Computer Science and Engineering Girijananda Chowdhury University Assam Guwahati India NESAC Umium Shillong India

Multispectral satellite image classification is crucial in remote sensing and image analysis, serving various applications like water area extraction, urban region classification, and vegetation monitoring. Model-based classification, particularly supervised learning approaches, heavily relies on manually annotated training samples, which are labor-intensive and subject to human bias. However, solely depending on features derived from individual pixels may fail to capture spatial contextual information effectively and manage mixed pixels and various types of noise, resulting in classification inaccuracies. To address these challenges, this research proposes a novel unsupervised learning approach and automatic labeling technique (ALT). This approach utilizes collective information from groups of pixels instead of relying solely on individual pixels for identification and extraction of meaningful unique patterns which serves as the most significant factor for satellite image classification. A new similarity index, the patch similarity index (PSI), is generated by incorporating the rank correlation similarity index (RCSI). The PSI is used to determine the similarity factor both between the patches and within the patch. Subsequently, a clustering algorithm is employed to group pixels into four distinct classes: vegetation, water, built-ups, and open land. Additionally, ALT streamlines the post-classification process by reducing the need for manual intervention in mapping clusters to the actual class label. The proposed method offers a more accurate and reliable unsupervised classification for multispectral satellite imagery, promising enhanced efficiency and reduced manual labor. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Automatic labeling technique Frequent masking Multispectral Patch similarity index Rank Correlation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multi-label text classification using adaptive promptify concepts 15

Enhancing Multi-label text classification using adaptive pro...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Reddy, Veerababu Uppukonda, Usha Rani Veeranjaneyulu, N. Vignan's Foundation for Science Technology & Research Dept. of Computer Science & Engineering Guntur India Vignan's Lara Institute of Technology & Science College Dept. of Computer Science & Engineering Guntur India Vignan's Foundation for Science Technology & Research Dept. of Information Technology Guntur India

ISBN: (纸本)9798350370249

In present days, Multi Label Text Classification (MLTC) has become an important research area in Natural Language Processing (NLP). Existing models of MLTC have been facing domain specificity and fine-tuning challenges. Hence a model is developed to overcome the above said challenges by introducing Prompt engineering, GPT FineTuning methods and Pipeline algorithms. The experimental results are obtained based on the present Generative pre trained data produces labels for various text documents and files with an exceptional accuracy of 85%. The outcomes of the experiments reveal notable enhancements over the baseline models. © 2024 IEEE.

关键词： Fine-Tuning GPT Multi-Label Text classification NLP (Natural Language Processing) Pre-trained models Prompt engineering Transformers

来源：评论

学校读者我要写书评

暂无评论

Land Use Land Cover Classification Using Machine Learning and Remote Sensing Data: A Case Study of Karnaprayag, Uttarakhand, India 1

Land Use Land Cover Classification Using Machine Learning an...

引用

1st International Conference on Electronics, Communication and Signal Processing, ICECSP 2024

作者： Saini, Rashmi Singh, Suraj Govind Ballabh Pant Institute of Engineering and Technology Dept. of Computer Science and Engineering Pauri Garhwal India

ISBN: (纸本)9798350364590

Land use and land cover (LULC) classification is crucial for planning and sustainable development, especially in mountainous regions. This study focuses on the Tehsil Karnaprayag, situated in the vicinity of the Greater Himalaya. With a total area of 1858.903 km2 and elevations ranging from 647m to 7641m. Using multispectral Sentinel-2 imagery and Machine Learning techniques i.e. Extreme gradient boosting (XGBoost) and K-nearest neighbor (KNN). This study aims to classify seven distinct land cover classes: snow, forest, water bodies, grassland, agricultural land, fallow land, and built-up areas. The classification results demonstrate the effectiveness of XGBoost classifier achieving an accuracy of 90.22% and a kappa value of 0.882, while KNN achieved an accuracy of 88.59% with a kappa value of 0.862. The analysis reveals that forest and fallow land are the predominant land cover types in the study area, constituting nearly 60% and 15% of the total area respectively. Notably, XGBoost exhibits the highest class-specific accuracy of 97.60% for the snow class, demonstrating its utility in discriminating between challenging land cover types. This research highlights the importance of LULC classification in informing land management strategies and facilitating sustainable development initiatives in mountainous regions. The findings provide valuable insights into the spatial distribution and composition of land cover in Tehsil Karnaprayag, essential for effective planning and conservation efforts in the Himalayan ecosystem. © 2024 IEEE.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection Using Multi-Modal Fusion Combined with Attention Mechanism 4

Deepfake Detection Using Multi-Modal Fusion Combined with At...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Shirley, C.P. Berin Jeba Jingle, I. Abisha, M.B. Venkatesan, R. Yashvanth Ram, R.V. Elango, Elakkiya Karunya Institute of Technology and Sciences Dept. of Computer Science and Engineering Coimbatore India Government Arts College for Woman Dept. of computer Science Sivaganga India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540364

The proliferation of deepfake technology poses a significant challenge to the authenticity of digital content. This research explores the application of multimodal fusion techniques to enhance deepfake detection accuracy. By combining visual and audio features, the proposed method leverages the complementary nature of different data types to detect discrepancies introduced by deepfake manipulation. An attention mechanism is incorporated to focus on salient regions within each modality, further improving detection accuracy. Convolutional Neural Networks (CNNs) and Mel-Frequency Cepstral Coefficients (MFCCs) are employed for feature extraction, followed by feature fusion for deepfake detection. This approach demonstrates the effectiveness of multimodal fusion in combating the evolving threat of deepfake technology. By advancing deepfake detection techniques, this research contributes to safeguarding the integrity of digital content and preserving trust in media. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Advances in Financial Sentiment Analysis:A Review of BERT,FinBert, and Large Language Models 3

Comparative Advances in Financial Sentiment Analysis:A Revie...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Mahendran, Manish Barath Gokul, Aswin Kumar Lakshmi, Poornima Pavithra, S. Dept. of Computer Science and Engineering Chennai Institute of Technology Tamil Nadu Chennai600069 India

ISBN: (纸本)9798331527549

Capturing market sentiments and supporting well-informed financial decision-making depend on the developing field of Financial Sentiment Analysis (FSA). Natural language processing (NLP) has made significant strides in comprehending and categorizing sentiment in intricate financial texts, especially with the use of Large Language Models (LLMs). The application of various LLMs, such as Bidirectional Encoder Representations form Transformers(BERT) and Financial BERT (FinBERT), as well as distilled models, such as DistilBERT and DistilRoBERTa, on a variety of financial datasets, including Financial Phrase Bank and LexisNexis news articles, was the main focus of this review article. highlighting different approaches such as model fine-tuning, zero-shot and few-shot learning, and prompt engineering. The study focuses on practical model predictions through a case study of sentimental analysis of cryptocurrencies. While FinBERT, a financial variant of BERT, exhibits high accuracy and robustness, other LLMs exhibit varying degrees of success based on the dataset and domain requirements. The analysis concentrates on the difficulties, compromises, and potential paths for improving LLMs for financial sentiment analysis. © 2025 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Music Streaming Services: A Novel Approach to Transparent Artist Control 3

Blockchain-Based Music Streaming Services: A Novel Approach ...

引用

3rd IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2024

作者： Ashtagi, Rashmi Deshmukh, Tanmay Jadhav, Swati Bidwe, Ranjeet Akkalkot, Afsha Buchade, Amar Uke, Nilesh Banerjee, Sudipta Vishwakarma Institute of Technology Dept. of Computer Engineering Pune India Symbiosis Institute of Technology Dept. of Cse Pune India Coep Technological University Dept. Name of Computer Engineering Pune India Data Science Vishwakarma Institute Technology Dept. of Artificial Intelligence Pune India Indira College of Engineering and Management Pune India Symbiosis Institute of Technology Pune India

ISBN: (纸本)9798350354348

Artists have historically used music as a form of personal expression. However, due to the centralized nature of music streaming services, artists receive only a small percentage of the revenue generated and have no control over their content produced. To address these issues, a revolutionary technique is needed that provides artists with greater control and transparency over their output. This paper focuses on a decentralized strategy that utilizes blockchain technology to facilitate direct interaction between artists and users, enabling artists to upload their music, sell songs, and receive royalties. The implementation of blockchain technology could potentially revolutionize the music industry by ensuring that rightful owners receive payment for their music while reducing the waste of paying intermediaries. Without intermediaries involved in the distribution process, the music industry could pay out more royalties to rights holders automatically and instantaneously. The proposed solution also addresses piracy concerns through the use of encryption and watermarking techniques. Blockchains provide security, confidentiality, tamper-proofing, traceability, control, and oversight over information. By developing a secure, self-installing, cross-platform reader positioned on the header of the digital content file, The research empowers data owners to manage the flow of information even after it has been made available. The suggested approach enables content owners to control their digital content and monitor its most popular components after distribution. The blockchain-based system also benefits from token distribution among the content's owner, distributor, and consumer. The simulation results demonstrate that our approach is capable of overcoming the flaws of the existing system. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Techniques Optimised LSTM Network for Improved Weather Prediction 2

Metaheuristic Techniques Optimised LSTM Network for Improved...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in technology and Management for Social Innovation, IATMSI 2024

作者： Mittal, Shweta Sangwan, Om Prakash Guru Jambheshwar University of Science and Technology Dept. of Computer Science and Engineering Hisar India

ISBN: (纸本)9798350360523

Tremendous amount of meteorological data is being generated on a daily basis from a number of sources such as weather stations, balloons, satellites, sensors etc. Timely weather prediction helps people plan everyday life events. Long Short Term Memory (LSTM) networks perform extremely well for capturing dependencies in time series datasets. Number of neurons in hidden layer highly impacts the performance of the LSTM network. The hit and Trial method for selecting the neurons consumes a lot of time and resources and might not lead to a global optimum solution. In this research work, two techniques, i.e. Genetic Algorithm optimized LSTM (LSTM-GA) and Artificial Bee Colony optimized LSTM (LSTM-ABC) have been proposed and implemented to automate the selection of the hidden layer's neurons for improved weather prediction. Proposed techniques have been implemented using DeepLearning4j library making the techniques scalable on clusters of machines. For evaluating the performance of proposed techniques, 15 years Brazil's weather dataset has been used. The experimental results proved that the proposed LSTM-GA and LSTM-ABC techniques have the reduced MAE value of 0.0074 and 0.0075 respectively while the LSTM network without any optimization has a relatively higher MAE value of 0.0086. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Emotion Classification to Augment the Emotional Intelligence of Autistic Individuals 5

Emotion Classification to Augment the Emotional Intelligence...

引用

5th IEEE International Conference on Communication, Computing and Industry 6.0, C2I6 2024

作者： Guruvammal, S. Kesavamoorthy, R. Anju, M.I. Chellatamilan, T. Jegatha Deborah, L. Jain University Dept. of Cse Kanakapura India Cmr Institute of Technology Dept. of Cse Bengaluru India Srm Institute of Science and Technology Dept. of Ece Chennai India Vellore Institute of Technology School of Computer Science and Engineering Vellore India University College of Engineering Computer Science and Engineering Tindivanam India

ISBN: (数字)9798350379884

ISBN: (纸本)9798350379884

The collaboration of machine learning (ML) algorithms and cognitive psychological frameworks supports the enhancement of emotional intelligence. In light of Plutchik's emotional wheel, this study investigates how to identify human emotions. By utilizing 24 different emotions, 8 high-intensive (secondary) emotions are identified. We employed 9 different classification algorithms K-nearest neighbors (KNN), decision trees (DT), naïve bayes (NB), support vector machine (SVM), Logistic regression, random forest (RF), artificial neural network (ANN), gradient boosting machines (GBM), and bagging classifier (BC) to identify the emotions accurately and the performance of them are compared. This research uses the labelled dataset consisting of 11 columns as similar word 1, similar word 2, typical sensation 1, typical sensation 2, opposite intensity low, opposite intensity medium, opposite intensity high, tells, helps, emotion and cluster. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Resume Parser and Job Description Matcher 8

Resume Parser and Job Description Matcher

引用

8th IEEE International Conference on Computational System and Information technology for Sustainable Solutions, CSITSS 2024

作者： Kamkar, Spandana Anilkumar Sanjay, Srushti Vaishnavi, P.S. Chaitra, M. Bnm Institute of Technology Affiliated to Vtu Dept. of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331505462

Resume Parser and Job Description Matcher is an innovative project aimed at enhancing the efficiency and accuracy of job candidate screening and matching processes. Leveraging natural language processing (NLP) techniques, particularly using SpaCy and machine learning models, the system parses resumes and job descriptions to extract relevant skills, experience, and qualifications. By analyzing textual data and applying advanced algorithms, such as Support Vector Machines (SVM), the system learns to match candidates with job postings based on keyword relevance and contextual understanding. Our paper demonstrates improved matching results compared to traditional methods, facilitating streamlined recruitment processes, and enhancing workforce management strategies. © 2024 IEEE.

关键词： Support vector machines

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：