检索结果-内蒙古大学图书馆

3rd International Conference on Machine Vision and Augmented Intelligence, MAI 2023

作者： Vinta, Surendra Reddy Dhanalaxmi, B. Lavanya, M. Thotapalli, Aruna Raju, Yeligeti School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati India Telangana Hyderabad India Telangana Hyderabad India Department of Information Technology CVR College of Engineering Telangana Hyderabad India

ISBN: (纸本)9789819743582

Banana farms are under risk from a variety of diseases, including Black Sigatoka and Panama sickness, as well as fertilizer shortages. Accurate and prompt identification of these issues is necessary to halt financial losses and promote sustainable practices. For the identification and classification of leaf diseases and their deficiencies based on the visual cues automatically, YOLOV8 is one of the latest detection models to detect the illness of banana leaves and improve the yielding capacity. Yolov8 is the state-of-the-art model to detect diseases very accurately and efficiently. It helps to prevent the illness of plants, disease detection, and improve the yielding capacity. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

RMHSForest: Relative Mass and Half-Space Tree Based Forest for Anomaly Detection

引用

Chinese Journal of Electronics 2020年第6期29卷 1093-1101页

作者： LYU Yanxia LI Wenjie WANG Yue SUN Siqi WANG Cuirong School of Computer Science and Engineering Northeastern University Information Systems Faculty of EngineeringThe University of Melbourne

Anomaly detection refers to identify the true anomalies from a given data *** present an ensemble anomaly detection method called Relative mass and half-space tree based forest(RMHSForest),which detect anomalies,including global and local anomalies,based on relative mass estimation and halfspace *** from density or distance based measure,RMHSForest utilizes a novel relative mass estimation to improve the detection of local ***,half-space tree based on augmented mass can estimate a mass distribution efficiently without density or distance calculations or *** empirical results show that RMHSForest outperforms the current popular anomaly detection algorithms in terms of AUC and processing time in the test data sets.

关键词： pattern clustering security of data trees (mathematics) AUC data set relative mass estimation popular anomaly detection algorithms mass distribution augmented mass local anomaly halfspace tree local anomalies global anomalies ensemble anomaly detection method half-space tree RMHSForest Relative mass Half-space tree Anomaly detection Ensemble methods

来源：评论

学校读者我要写书评

暂无评论

Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis 3

Hybrid Multimodal Feature Extraction, Mining and Fusion for ...

引用

3rd Multimodal Sentiment Analysis Challenge and Workshop, MuSe 2022, held in conjunction with the ACM Multimedia 2022

作者： Li, Jia Zhang, Ziyang Lang, Junjie Jiang, Yueqi An, Liuwei Zou, Peng Xu, Yangyang Gao, Sheng Lin, Jie Fan, Chunxiao Sun, Xiao Wang, Meng School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Institute of Artifcial Intelligence Hefei Comprehensive National Science Center Hefei China

ISBN: (纸本)9781450394840

In this paper, we present our solutions for the Multimodal Sentiment Analysis Challenge (MuSe) 2022, which includes MuSe-Humor, MuSe-Reaction and MuSe-Stress Sub-challenges. The MuSe 2022 focuses on humor detection, emotional reactions and multimodal emotional stress utilising different modalities and data sets. In our work, different kinds of multimodal features are extracted, including acoustic, visual, text and biological features. These features are fused by TEMMA and GRU with self-attention mechanism frameworks. In this paper, 1) several new audio features, facial expression features and paragraph-level text embeddings are extracted for accuracy improvement. 2) we substantially improve the accuracy and reliability for multimodal sentiment prediction by mining and blending the multimodal features. 3) effective data augmentation strategies are applied in model training to alleviate the problem of sample imbalance and prevent the model form learning biased subject characters. For the MuSe-Humor sub-challenge, our model obtains the AUC score of 0.8932. For the MuSe-Reaction sub-challenge, the Pearson's Correlations Coefficient of our approach on the test set is 0.3879, which outperforms all other participants. For the MuSe-Stress sub-challenge, our approach outperforms the baseline in both arousal and valence on the test dataset, reaching a final combined result of 0.5151. © 2022 ACM.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Spatial indexing and searching using parallel wavelet tree

引用

International Journal of information Technology (Singapore) 2023年第7期15卷 3583-3591页

作者： Kumar, Dharmendra Yadav, Divakar Yadav, Diwakar Singh AKTU U.P. Lucknow India School of Computer and Information Sciences IGNOU New Delhi India Department of Computer Science and Engineering IET U.P. Lucknow India

Fast retrieval through indexing from spatial databases has been considered a more challenging task for enhancing network performance in the last few decades. The wavelet tree has become a very popular and versatile data structure, used in various domains such as sequences, indexing, compression, and grid point, with surprising results. This paper presents an efficient recursive parallel wavelet tree algorithm to index and search geographical documents. The proposed method is implemented in two scenarios: Intel 4-core processor with eight threads and an Intel 8-core processor with 16 threads on real-word input data with Ubuntu operating system to make it more inspiring. The experimental results show that the proposed algorithm’s time and space complexity are less than existing wavelet tree construction algorithms. The proposed algorithm shows a good trade-off and is scalable for large input data sets. In addition, results show that the presented algorithm performs well in the scale-up of a large dataset with full utilization of cores. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Indexing information retrieval Minimum bounding rectangles Spatial search Wavelet tree

来源：评论

学校读者我要写书评

暂无评论

Incorporating the student perspective in designing a virtual team classroom environment: an elaborated action design science research approach

引用

Journal of Research in Innovative Teaching and Learning 2023年第2期16卷 153-168页

作者： Kutz, Diane Cumbie, Barry Mullarkey, Matthew Department of Management and Marketing University of North Alabama Florence AL United States Department of Computer Science and Information Systems University of North Alabama Florence AL United States School of Information Systems and Management University of South Florida Tampa FL United States

Purpose: This paper aims to address the long-standing problem of suboptimal student team experiences for instructors and students by incorporating the student voice by co-creating a virtual team collaborative environment to improve team collaboration in the online classroom. Design/methodology/approach: This paper presents a novel design science research approach and relates two elaborated action design science research (eADSR) cycles that design, implement and evaluate the student team experience in online courses requiring teamwork. Findings: The outcome is a holistic view of a virtual team classroom environment specified with technologies and practices that may be employed to optimize the student team experience. The eADSR process yields non-obvious diagnoses and actionable steps for continually incorporating the ever-changing social aspects unique to students in addition to the evolving technological landscape. Practical implications: This paper is valuable to faculty members interested in applying eADSR processes to incorporate the student voice to address pedagogical and learning challenges in the classroom. Additionally, it provides a DSR-based model that can be implemented in the classroom to improve student team collaboration as well as transparency for the instructor and the students in terms of team member contributions with the goal to alleviate student and faculty frustrations. This topic is particularly relevant in light of COVID-19 as students and faculty alike are thrust into new online classroom environments. Originality/value: Employing eADSR in the classroom is a novel and unique approach to create a replicable model for virtual team collaboration that can be added to the classroom. © 2022, Diane Kutz, Barry Cumbie and Matthew Mullarkey.

关键词： Co-create Collaboration Elaborated action design science Online classroom Virtual teams

来源：评论

学校读者我要写书评

暂无评论

The perspectives of women on telecommuting in the IT sector: A boon or a curse

The perspectives of women on telecommuting in the IT sector:...

引用

2024 International Conference on Smart Devices, ICSD 2024

作者： Sanwal, Tanushree Yadav, Sapna Tyagi, Meenakshi Avasthi, Sandhya Srivastava, Binkey Taylor, Prerana KIET Group of Institutions KIET School of Management NCR Delhi India Jaypee Institute of Information Technology J.P.Business School Noida India ABES Engineering College Computer Science and Engineering Ghaziabad India

ISBN: (纸本)9798350394412

During Covid-19, when women were allowed to work from home, it became clear that they were adept at juggling multiple jobs at once. During this time, working women faced a number of obstacles and responsibilities, including a lack of domestic help, online classes for their children, and a number of other daily routine activities and office responsibilities. However, the condition of women who work from home did not improve after the epidemic, and it still does not. Therefore, from April 2023 to July 2023, a total of 309 working women from the IT sector in Delhi-NCR were surveyed in this study to determine what factors affect working women's attitudes regarding remote work. Using analysis of variance and t-tests, we tested our predictions and found that most female professionals felt overwhelmed. Current studies show that working from home is not only more challenging for women than working in an office but also less productive. Problems with time management, communication, and reaction time, as well as technical and mental difficulties, have a negative impact on their work. The most common hiccup they experience is sluggish internet speeds. Stress, frustration, anxiety, and the pressures of the workplace are just some of the mental health concerns they face. They have a work-life imbalance due to factors including family duties and doing extra work on their own time. Nearly nine in ten women believe the government should establish guidelines for remote work. Almost half of all women hope to one day work from home, while the other half have no such plans. © 2024 IEEE.

关键词： Telecommuting

来源：评论

学校读者我要写书评

暂无评论

A verifiable and privacy-preserving framework for federated recommendation system

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第4期14卷 4273-4287页

作者： Gao, Fei Zhang, Hanlin Lin, Jie Xu, Hansong Kong, Fanyu Yang, Guoqiang College of Computer Science and Technology Qingdao University Qingdao266071 China School of Electronic and Information Engineering Xian Jiaotong University Xian710049 China School of Electronic Information and Electrical Engineering Shanghai Jiaotong University Shanghai200240 China School of Software Shandong University Jinan250100 China Sansec Technology Co. Ltd. Jinan250101 China

The data such as features involved in recommendation systems often contain private information that can cause serious security problems if leaked to other participants in the system. At present, Federated Learning (FL) combined with encryption technology is a popular privacy preserving technology. However, the distributed computing of FL threatens the credibility of calculation results. Incorrect calculation results in the recommendation system can reduce the accuracy of the recommendation. In this paper, we design a verifiable and privacy-preserving framework for the federated recommendation system (VePriRec) to ensure the privacy of data and verifiability of calculation results. For three components involved in the system, we design three privacy-preserving protocols, including a secure similarity network construction protocol, a secure gradient descent protocol and a secure aggregation protocol. We conduct experiments on real-world datasets, the results demonstrate the effectiveness and efficiency of VePriRec. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Apple Detection and Yield Estimation Based on YOLOv5 7

Apple Detection and Yield Estimation Based on YOLOv5

引用

7th International Conference on Advanced Algorithms and Control engineering, ICAACE 2024

作者： Li, Zhaoyang Bai, Xue He, Chao Jiang, Pengfei School Of Earth And Space Science University Of Science And Technology Of China Hefei230026 China School Of Electrical And Information Engineering Zhengzhou University Zhengzhou450001 China College Of Computer Science And Engineering Shandong University Of Science And Technology Qingdao266590 China College Of Geodesy And Geomatics Shandong University Of Science And Technology Qingdao266590 China

ISBN: (纸本)9798350361445

With the continuous advancement of modernization and intelligence in agricultural production, precise orchard management is crucial for enhancing the efficiency of apple production. This study focuses on apple orchards, introducing the YOLOv5 deep learning model to address the issues of apple detection and quantity estimation in traditional orchard management. Through effective feature extraction and learning from orchard images, the model accurately detects and estimates the quantity of fruits, providing reliable data support for orchard management. Firstly, this research delves into the background of the apple detection problem, highlighting the limitations of traditional methods in dealing with complex lighting, shadows, and other environmental factors. Subsequently, leveraging the YOLOv5 model, a deep learning-based orchard image processing method is proposed. This method fully exploits the efficiency and accuracy of the YOLOv5 model in object detection, training the model to recognize apples and providing a more intelligent tool for orchard management. In the model-solving phase, the structure and training process of the YOLOv5 model are detailed. Through training on a large number of orchard images, the model successfully learns the feature representation of apples, demonstrating strong generalization capabilities. The results indicate the model's outstanding performance in apple detection and quantity estimation tasks. Finally, the study summarizes the advantages and innovations of the apple detection and quantity estimation method based on YOLOv5, and provides prospects for future research directions. This research offers an efficient and accurate tool for orchard management, contributing new ideas and methods to the development of agricultural intelligence. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

3D-EX: A Unified Dataset of Definitions and Dictionary Examples

3D-EX: A Unified Dataset of Definitions and Dictionary Examp...

引用

2023 International Conference Recent Advances in Natural Language Processing: Large Language Models for Natural Language Processing, RANLP 2023

作者： Almeman, Fatemah Sheikhi, Hadi Espinosa-Anke, Luis CardiffNLP School of Computer Science and Informatics Cardiff University United Kingdom College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Saudi Arabia School of Computer Engineering Iran University of Science and Technology Iran AMPLYFI United Kingdom

ISBN: (纸本)9789544520922

Definitions are a fundamental building block in lexicography, linguistics and computational semantics. In NLP, they have been used for retrofitting word embeddings or augmenting contextual representations in language models. However, lexical resources containing definitions exhibit a wide range of properties, which has implications in the behaviour of models trained and evaluated on them. In this paper, we introduce 3D-EX, a dataset that aims to fill this gap by combining well-known English resources into one centralized knowledge repository in the form of triples. 3D-EX is a unified evaluation framework with carefully pre-computed train/validation/test splits to prevent memorization. We report experimental results that suggest that this dataset could be effectively leveraged in downstream NLP tasks. Code and data are available at https://***/F-Almeman/3D-EX. © 2023 Incoma Ltd. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Identification of Damaged Date Palm Tree in a Farm using IoT-based Thermal Image Analysis

Identification of Damaged Date Palm Tree in a Farm using IoT...

引用

2023 IEEE International Conference on computer, information, and Telecommunication systems, CITS 2023

作者： Nadeem, Adnan Ashraf, Muhammad Mehmood, Amir Siddiqui, Muhammad Shoaib Almoamari, Hani Abbasi, Qammer H. Islamic University of Madinah Faculty of Computer and Information Systems Madinah42351 Saudi Arabia Federal Urdu University of Arts Science and Technology Department of Physics Karachi75300 Pakistan Sir Syed University of Engineering and Technology Department of Computer Science and Information Technology Karachi75300 Pakistan James Watt School of Engineering University of Glasgow Glasgow United Kingdom

ISBN: (纸本)9798350336092

The Kingdom of Saudi Arabia is one of the world's leading fresh date producers. Identifying damaged date palm trees on the farm is important for saving water and stopping the spread of pest which has caused the damage. In this paper, we aim to evaluate the performance of IoT-based thermal image camera input for the automatic detection of damaged trees in a Date Tree farm. The thermal images will be obtained by an IoTbased thermal camera attached to UAV. Then the temperature histogram vector will be generated which will be fed to the SVM for identification of the damaged tree. The system will raise the alarm along with the coordinates of the damaged tree for the farmer to proactively deal with the issue. The initial results of the tested scenario are encouraging for its detailed implementation in the future. © 2023 IEEE.

关键词： Cameras

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：