检索结果-内蒙古大学图书馆

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Dhamodhar, G. Krishna, B. Vamsi Reddy, D. Sampath Reddy, A. Sameer Amutha, S. Ganesan, Kothai Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Tamilnadu Virudhnagar India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore Dist. Tamil Nadu India

ISBN: (纸本)9798331300579

The "Farmer's Crop Welfare System" is a technology that uses advanced data analytics and artificial intelligence to improve crop management and yield. It combines crop prediction, disease detection, and fertilizer recommendation. Crop prediction uses historical and real- time data, while disease detection uses image recognition and deep learning to identify early signs of diseases, promoting sustainable farming practices. © Grenze Scientific Society, 2024.

关键词： Livestock

来源：评论

学校读者我要写书评

暂无评论

From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 624-638页

作者： Chen, Yin Li, Jia Shan, Shiguang Wang, Meng Hong, Richang Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Institute of Computing Technology Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Dynamic facial expression recognition (DFER) in the wild is still hindered by data limitations, e.g., insufficient quantity and diversity of pose, occlusion and illumination, as well as the inherent ambiguity of facial expressions. In contrast, static facial expression recognition (SFER) currently shows much higher performance and can benefit from more abundant high-quality training data. Moreover, the appearance features and dynamic dependencies of DFER remain largely unexplored. Recognizing the potential in leveraging SFER knowledge for DFER, we introduce a novel Static-to-Dynamic model (S2D) that leverages existing SFER knowledge and dynamic information implicitly encoded in extracted facial landmark-aware features, thereby significantly improving DFER performance. Firstly, we build and train an image model for SFER, which incorporates a standard Vision Transformer (ViT) and Multi-View Complementary Prompters (MCPs) only. Then, we obtain our video model (i.e., S2D), for DFER, by inserting Temporal-Modeling Adapters (TMAs) into the image model. MCPs enhance facial expression features with landmark-aware features inferred by an off-the-shelf facial landmark detector. And the TMAs capture and model the relationships of dynamic changes in facial expressions, effectively extending the pre-trained image model for videos. Notably, MCPs and TMAs only increase a fraction of trainable parameters (less than +10%) to the original image model. Moreover, we present a novel Emotion-Anchors (i.e., reference samples for each emotion category) based Self-Distillation Loss to reduce the detrimental influence of ambiguous emotion labels, further enhancing our S2D. Experiments conducted on popular SFER and DFER datasets show that we have achieved a new state of the art. © 2010-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Fuzzy clustering for electric field characterization and its application to thunderstorm interpretability

引用

Digital Communications and Networks 2025年第2期11卷 299-307页

作者： Xu Yang Hongyan Xing Xinyuan Ji Wei Xu Witold Pedrycz School of Electronics and Information Engineering Nanjing University of Information Science and TechnologyNanjing 210044China Department of Electrical and Computer Engineering University of AlbertaEdmonton AB T6G 2R3Canada Systems Research Institute Polish Academy of Sciences00-901 WarsawPoland Department of Computer Engineering Faculty of Engineering and Natural SciencesIstinye University34010 IstanbulTurkey

Changes in the Atmospheric Electric Field Signal(AEFS)are highly correlated with weather changes,especially with thunderstorm ***,little attention has been paid to the ambiguous weather information implicit in AEFS *** this paper,a Fuzzy C-Means(FCM)clustering method is used for the first time to develop an innovative approach to characterize the weather attributes carried by ***,a time series dataset is created in the time domain using AEFS *** AEFS-based weather is evaluated according to the time-series Membership Degree(MD)changes obtained by inputting this dataset into the ***,thunderstorm intensities are reflected by the change in distance from a thunderstorm cloud point charge to an AEF ***,a matching relationship is established between the normalized distance and the thunderstorm dominant MD in the space ***,the rationality and reliability of the proposed method are verified by combining radar charts and expert *** results confirm that this method accurately characterizes the weather attributes and changes in the AEFS,and a negative distance-MD correlation is obtained for the first *** detection of thunderstorm activity by AEF from the perspective of fuzzy set technology provides a meaningful guidance for interpretable thunderstorms.

关键词： Atmospheric electric field(AEF) Thunderstorm Fuzzy C-means(FCM) Attribute

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Classification of River Using Machine Learning Methods 12

Remote Sensing Classification of River Using Machine Learnin...

引用

12th Academic Conference of Geology Resource Management and Sustainable Development, GRMSD 2024

作者： Cui, Hanwen Li, Cheng Tian, Xiaolin School of Computer Science Zhuhai College of Science and Technology Guangdong Zhuhai519041 China Academy of Interdisciplinary Studies Hong Kong University of Science and Technology 999077 Hong Kong School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology 999078 China

ISBN: (纸本)9798331314545

In the realm of global sustainable development, effective management of water resources and the protection of ecological environments have increasingly emerged as focal points for both governmental and international organizations. Rivers, as critical conduits of water resources, fulfill various essential functions, including transportation, irrigation, aquaculture, tourism, and climate regulation, in addition to their provision of water for human consumption and agricultural purposes. This study predominantly explores the application of remote sensing technology and machine learning methodologies to classify rivers. The research is situated in Zhuhai City, characterized by a vertically distributed river network. It employs eXtreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM), both based on gradient boosting decision trees (GBDT). The data source for this investigation consists of high spatial resolution imagery from Gaofen-2 (GF-2) remote sensing satellites. The results indicate that both models achieve an overall accuracy (OA) exceeding 96.50%, with Kappa coefficients surpassing 0.92. Notably, the LightGBM model demonstrates superior performance over XGBoost in terms of both classification accuracy and operational efficiency. The utilization of remote sensing images in conjunction with machine learning techniques for the classification and monitoring of rivers offers a robust scientific framework for enhancing water resource management. Furthermore, these methodologies can assist in the formulation of effective strategies for the sustainable utilization and protection of water resources. © 2024 Proceedings of the 12th Academic Conference of Geology Resource Management and Sustainable Development, GRMSD 2024. All rights reserved.

关键词： Rivers

来源：评论

学校读者我要写书评

暂无评论

KSRR: Knowledge Centric Semantically Driven Recipe Recommendation Framework Encompassing Collective Intelligence 15th

KSRR: Knowledge Centric Semantically Driven Recipe Recommend...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Shah, Haiya Deepak, Gerard Santhanavijayan, A. Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering National Institute of Technology Tiruchirappalli Tiruchirappalli India

ISBN: (纸本)9783031889912

In the era of Web 3.0, there is a pressing need for a knowledge-centric model to recommend recipes, as the current structure of the worldwide Web lacks specialized recommendation frameworks for recipe recommendations, even though standard search engines offer some level of recipe recommendation. This paper aims to address this gap by proposing a dedicated recommendation channel. The model utilizes user historical activity on food apps as one of the criteria for personalization, leveraging the SimRank algorithm and Grey Wolf optimization to generate a comprehensive termset. Additionally, the model incorporates semantic similarity-based reasoning, employing techniques such as SimRank, Morisita overlap index, and normalized information distance. The Grey Wolf optimization framework further refines the solution set. The topic network comprises recipe ebooks, food blogs, and crawl labels from food blogs, with the inclusion of scientific ebooks to enrich the knowledge base. A restriction classifier is employed to control the features of the data center, ensuring computational feasibility and reducing complexity. Furthermore, a lightweight decision tree classifier demonstrates strong classification performance, characterized by high precision, a lower false discovery rate (FDR), and notable expressive percentage values. Extensive evaluations reveal that the proposed framework outperforms baseline models, establishing it as the leading model for recipe recommendations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

VQARS: Visual Question Answering for Remote Sensing as a Domain of Choice Incorporating Semantic Intelligence 15th

VQARS: Visual Question Answering for Remote Sensing as a Dom...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Manoj Kumar, H.S. Deepak, Gerard Santhanavijayan, A. Department of Computer Science and Engineering PES University Bangalore India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering National Institute of Technology Tiruchirappalli Tiruchirappalli India

ISBN: (纸本)9783031889912

The need for a visual question answering framework in the era of Web 3.0 is realized by using staged addition of auxiliary knowledge in the perspective of two distinct datasets namely the dataset of documents and the images which is enriched through informative term extraction and further using structural topic modelling, Wikidata, NELL and Linked Open Data (LOD) Cloud, knowledge stores and tag generation to classify the dataset obtained informative terms. Subsequently, the image dataset terms are subjected to extraction of categories and labels to contribute to the informative terms. The random forest classifier at either ends of the two datasets helps in controlled classification of the datasets independently and assures computational inexpensiveness because of the lightweighted nature of the machine learning classifiers. The RNN to classify the tags helps in automatizing the exponentially generated tags and semantic network formulated helps in organizing the auxiliary knowledge. Semantic relevance computation using Jaccard Similarity, Morisitas Overlap Index, NPMI and SOC-PMI facilitates in semantic reasoning. The proposed VQARS model's achieves an overall precision of 94.81%;recall of 95.75%;average accuracy of 95.28%;F-measure of 95.28%;and the lowest FDR of 0.06. In comparison to the other baseline models, this model provides the best-in-class outcomes. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Smart Travel Solutions Harnessing Artificial Intelligence for Optimal Route Efficiency

Smart Travel Solutions Harnessing Artificial Intelligence fo...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Mohanapriya, D. Indumathi, R. Priyatharsini, S. Arounesh, A. Kumar, V.Kishore Kamalan, R. Manakula Vinayagar Institute of Technology Department of Computer Science and Engineering Puducherry India Karpagam Academy of Higher Education Department of Electronics and Communication Engineering Coimbatore India Manakula Vinayagar Institute of Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798331510022

This AI-based route optimizing system has put its focal point on only efficient travel routes based on real-time traffic. It focuses on calculating the shortest distance to source, along with destination and via points, distance, time-based traffic details, in order to arrive at the most optimal route for any journey. Advanced AI techniques in optimizing systems continuously adjust the route according to live traffic patterns so that users may experience the least delay possible. The system integrates with fuel consumption estimations provided the traveler through inputting vehicle mileage, enabling travelers to make better plans for their trips by considering time and fuel efficiency. This would save one time spent traveling, saves fuel, thus saving money while keeping the environment free from pollution. By such smart decisions on making routes, the system increases drivers' overall driving experience, especially in crowded areas or where there is heavy traffic. Since the system is inherently real-time, it's therefore very adaptive to the changing nature of road conditions, thus travel stream lined for the users. © 2024 IEEE.

关键词： Transportation routes

来源：评论

学校读者我要写书评

暂无评论

Analysis of Neural Machine Translation for English to Hindi using Long Short-Term Memory Model and Transformer Model 4

Analysis of Neural Machine Translation for English to Hindi ...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Naveen, Rashmi Kumar, Archana Praveen Dept. of Information Science and Engineering India Manipal Institute of Technology Manipal Academy of Higher Education Department of Computer Science & Engineering Manipal India

ISBN: (纸本)9798331540364

By providing enhanced accuracy and fluency compared to traditional approaches, Neural Machine Translation (NMT) has transformed the area of machine translation. In this research paper, the specific task of translating English to Hindi using NMT techniques is discussed. Creation and assessment of NMT systems developed for this language pair, considering the linguistic complexities and cultural aspects inherent in English and Hindi is examined. Leveraging large-scale parallel corpora and advanced neural network architectures, this work proposes novel approaches to improve translation quality and efficiency. Experimental results evaluated using standard metrics such as BLEU score, shows the efficacy of the proposed NMT models in accurately capturing the semantics and preserving the naturalness of the translated text. Additionally, this study discusses the implications of findings for cross-language communication and access to information, particularly in the context of the growing importance of Hindi in a globalized digital domain. Overall, this research contributes to develop neural machine translation for English to Hindi to a higher level and highlights the potential of NMT in facilitating multilingual communication and knowledge dissemination. © 2024 IEEE.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Malware Detection Employing Deep Neural Networks 10

Malware Detection Employing Deep Neural Networks

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Nayak, Sanjana Ganesh Kurup, Samir Andrew, J. Manipal Institue of Technology Manipal Academy of Higher Education Department of Computer Science and Engineering Karnataka Manipal India

ISBN: (纸本)9798350384369

Malware, malicious software designed to disrupt, damage, or gain unauthorized access to computer systems, poses a significant and evolving threat to cybersecurity. Malware detection is an essential component of modern cybersecurity, given the escalating complexity and diversity of malicious software threats. In this study, we present a novel approach to malware detection based on behavior-based datasets using a fully connected deep neural network. Our research is motivated by the need for robust and accurate malware detection models that can adapt to evolving threats. The behavior-based dataset, which captures the dynamic interactions of malware with the host environment, provides a rich source of information for training and evaluation. The model uses the hyperbolic tangent (tanh) activation function and the Nesterov optimizer, resulting in remarkable accuracy of 100%. This study offers a high- performing solution for malware detection using behavior- based datasets. As cybersecurity continues to evolve, our approach contributes to strengthening defenses against the ever- persistent threat of malware. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Classification of Social Anxiety Disorder Using Explainable Machine Learning and Pearson's Correlation Technique 8

Classification of Social Anxiety Disorder Using Explainable ...

引用

8th IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2024

作者： Bathula, Srivarsha Chadaga, Krishnaraj Prabhu, Srikanth Sampathila, Niranjana Manipal Institute of Technology Manipal Academy of Higher Education Manipal Department of Computer Science and Engineering Karnataka India

ISBN: (纸本)9798350350593

Social Anxiety Disorder (SAD) is a widespread mental health issue marked by significant fear or discomfort during social interactions. It can greatly affect a person's life and overall happiness, causing problems like emotional distress, low self-esteem and depression. Thorough examination by a mental health expert is often required to diagnose SAD. The diagnostic and statistical manual of mental disorders' particular criteria are used to diagnose SAD that includes clinical interviews, self-report questionnaires, and a thorough evaluation of the individual's symptoms like severe anxiety while engaging or conversing with strangers. In this work, we employ explainable artificial intelligence (XAI) and machine learning techniques to identify SAD in individuals. Critical attributes were identified using Pearson's correlation technique. Random Forest yields optimal outcomes with 88% accuracy, 93 % precision, 83 % recall, 84 % F1-score, and 94% Area Under Curve (AUC). Furthermore, XAI methods such as Shapley Additive Values (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) have been applied to improve the models' accuracy, comprehensibility, and precision. Automated SAD diagnosis helps in early detection and increased accessibility that allows for timely intervention, treatment, and facilites access to social anxiety testing and screening for an individual. © 2024 IEEE.

关键词： Adversarial machine learning

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：