检索结果-内蒙古大学图书馆

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Kanagaraj, R. Elakiya, E. Kumaresan, A. Selvakumar, J. Suganya, J. Shruthi, K. School of Computer Science and Engineering Vellore Institute of Technology Vellore India Vellore Institute of Technology Department of Computer Science and Engineering Chennai India Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India Mailam Engineering College Mailam India Bosch Global Software Technologies Coimbatore India

ISBN: (纸本)9798350321425

Agriculture is under tremendous pressure to produce more productivity with fewer resources as a result of the expanding global population. Decision-making along the entire supply chain needs to be improved considering competing economic, environmental, and societal demands. Data from satellites, drones, sensors, and other sources must be processed in order to make informed judgments. However, sophisticated machine learning and data analytics methods must be used due to the complexity and volume of the data. This initiative covers crucial duties in yield prediction and precision agriculture. Management zones are areas of a field that have high inter-regional variability and low intra-regional variability, dividing the field into uniform zones for which agronomic practices should be modified independently. For fertilizer optimization and post-harvest logistics, yield prediction is crucial. In order to make up for the nutrients that have been taken out of the soil, fertilizer type and quantity must be adjusted accordingly. The yield data is also essential for enhancing harvesting, shipping, storage, and sales. So, utilizing web scraping and convolution neural networks, the proposed model has been forecast yields from input satellite photos. The result of investigations is illustrated that the artificial neural network algorithm is used to predicting the agricultural data rules and powerfully decrease the error rate from crop yield data. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

DIG: Improved DINO for Graffiti Detection

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年第5期55卷 3557-3569页

作者： Wang, Bingshu Mao, Qianchen Liu, Aifei Chen, Long Chen, C. L. Philip Northwestern Polytechnical University School of Software Xi’an710129 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen518060 China University of Macao Department of Computer and Information Science China South China University of Technology School of Computer Science and Engineering Guangzhou510641 China

Graffiti detection is essential in historic building protection and urban neighborhood management. Graffiti detection has made significant progress in recent years based on the development of deep learning. However, small-scale graffiti, interference from the background, and the false detection of word parts in graffiti make it a challenging problem. This article proposes a Transformer-based high-precision graffiti detection method, namely DIG. Precisely, it consists of three modules: 1) Spatial query selection (SQS), scale-aware IoU loss (SIL);2) Denoising Task with binary contrastive denoising (BCDN);and 3) IoU-guided box denoising (IBD) modules. To detect small-scale graffiti, this paper proposes SIL to help the loss function to perceive small-scale graffiti and large-scale graffiti fairly. To reduce the false detection of word parts, this article presents the SQS module, which integrates spatial information into the query selection process of the Encoder to filter out falsely detected bounding boxes within the graffiti. To reduce the interference from the background, this article introduces a denoising task with BCDN and IBD modules, improving the model’s ability to distinguish graffiti from the background and accurately select appropriate bounding boxes. A large number of experimental results on the STORM dataset show that our method achieves state-of-the-art results with an AP50 of 87.9%. Moreover, DIG achieved competitive results on the FineFM dataset for mask detection. This indicates that DIG can also be conveniently transferred to detect other scenarios. © 2013 IEEE.

关键词： Historic preservation

来源：评论

学校读者我要写书评

暂无评论

Masked Image Self-Learning and Knowledge Distillation for Source-Free Unsupervised Domain Adaptation in Crowd Counting 2

Masked Image Self-Learning and Knowledge Distillation for So...

引用

2nd International Conference on Image Processing, computer Vision and Machine Learning, ICICML 2023

作者： Zeng, Jia Ma, Chaoqun Shao, Penghui Qing, Anyong Wang, Yang Southwest Jiaotong University School of Electrical Engineering Chengdu China Concordia University Department of Computer Science and Software Engineering Montreal Canada

ISBN: (纸本)9798350331417

Unsupervised Domain Adaptation (UDA) techniques leverage labeled data from a source domain to adapt to unlabeled data from a target domain, offering a primary solution for addressing cross-domain challenges in crowd counting. However, in real-world scenarios, accessing source data during the model adaptation process within the target domain can be impractical due to privacy and security concerns. This gives rise to a practical yet challenging issue known as Source-Free Unsupervised Domain Adaptation (SFUDA), where model adaptation is limited to the utilization of an existing source model and unlabeled target data. To tackle this challenge, we propose an algorithm that combines mask image self-learning and knowledge distillation to address SFUDA in crowd counting effectively. Specifically, the student model uses masked images to self-learn at both feature and output levels, exploring clues and contextual relationships around masked image blocks to predict occluded areas. Furthermore, we employ knowledge distillation to boost the model's performance within the teacher-student framework, encompassing feature extraction and density map generation stages. To mitigate cumulative errors, we stochastically recovery a subset of parameters from the source model. We conducted extensive experiments to compare our approach with a modified SFUDA algorithm, and the results demonstrate competitive performance across multiple datasets. © 2023 IEEE.

关键词： Crowd counting Domain adaptation Knowledge distillation Self-learning Source-free

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Machine Learning-Based Model for Conversational Sentiment Classification

引用

computers, Materials & Continua 2022年第8期72卷 2323-2339页

作者： Sami Ullah Muhammad Ramzan Talib Toqir A.Rana Muhammad Kashif Hanif Muhammad Awais Department of Computer Science Government College University Faisalabad38000Pakistan Department of Computer Science and IT The University of Lahore54590Pakistan School of Computer Sciences Universiti Sains Malaysia(USM)11800PenangMalaysia Department of Software Engineering Government College University Faisalabad38000Pakistan

In the current era of the internet,people use online media for conversation,discussion,chatting,and other similar *** of such material where more than one person is involved has a spate challenge as compared to other text analysis *** are several approaches to identify users’emotions fromthe conversational text for the English language,however regional or low resource languages have been *** Urdu language is one of them and despite being used by millions of users across the globe,with the best of our knowledge there exists no work on dialogue analysis in the Urdu ***,in this paper,we have proposed a model which utilizes deep learning and machine learning approaches for the classification of users’emotions from the *** accomplish this task,we have first created a dataset for the Urdu language with the help of existing English language datasets for dialogue *** that,we have preprocessed the data and selected dialogues with common *** the dataset is prepared,we have used different deep learning and machine learning techniques for the classification of *** have tuned the algorithms according to the Urdu language *** experimental evaluation has shown encouraging results with 67%accuracy for the Urdu dialogue datasets,more than 10,000 dialogues are classified into five emotions i.e.,joy,fear,anger,sadness,and *** believe that this is the first effort for emotion detection from the conversational text in the Urdu language domain.

关键词： Dialogue analysis conversational opinion mining sentiment analysis sentiment analysis in Urdu language deep learning machine learning

来源：评论

学校读者我要写书评

暂无评论

Innovating Project Management: AI Applications for Success Prediction and Resource Optimization 2nd

Innovating Project Management: AI Applications for Success P...

引用

2nd International Conference on Advances in Computing Research, ACR 2024

作者： Tarawneh, Monther AbdAlwahed, Huda AlZyoud, Faisal Computer Science Department Isra University Amman Jordan Software Engineering Department Isra University Amman Jordan Information Technology Department Tafilah Technical University Tafila Jordan

ISBN: (纸本)9783031569494

The revolution of Artificial Intelligence (AI) has made transformative changes in all industries. The field of software engineering has great benefit from AI by Automat all process. Applying Artificial intelligence (AI) technologies, particularly Deep Neural Network (DNN) models, to project management will transform traditional methodologies to new ways. This work investigates how AI can be used within project management to better allocate resources, estimate time, and predict costs. Data from many recourses used to improve accuracy in project planning, refine how risks are managed, and develop new methods. Data includes real projects portfolio, open-source data, and simulated data. The integration of AI in project management examines project success and client satisfaction. This work shows 99% accuracy for learning and 78% for testing of predicting project success and highlights the need to constantly update methods to effectively use the big potential changes AI can bring to project management. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Approach of Different Classification Algorithms to Compare in N-gram Feature Between Bangla Good and Bad Text Discourses 1

引用

4th International Conference on Machine Intelligence and Signal Processing, MISP 2022

作者： Bitto, Abu Kowshir Bijoy, Md. Hasan Imam Khan, Saima Mahmud, Imran Biplob, Khalid Been Badruzzaman Department of Software Engineering Daffodil International University Dhaka1207 Bangladesh Department of Computer Science and Engineering Daffodil International University Dhaka1207 Bangladesh

ISBN: (数字)9789819900855

ISBN: (纸本)9789819900848

Bangla Natural Language Processing (BNLP) is a newish challenge in Artificial Intelligence. With the rapid expansion of the Bangla language, it is now adopted on a variety of platforms, including social media, communication platforms, news media, and so on. The classification of text documents becomes an important factor in resolving the challenge of information organization and knowledge management. This study uses five supervised classification methods to explore the categorization of Bangla text discourse using N-gram (unigram, bigram, and trigram) features. Bangla text discourse is collected from different platforms such as social media, personal Bangla blogs, and people's utterances in order to accomplish the research goal. After collecting data, the most difficult part of the Bangla language preprocessing is completed, which includes adding contractions, removing punctuations, encoding, and a variety of other operations. For this study, 1499 text documents were initially used, with 1459 Bangla text discourses being used after preprocessing. To convert the text into a token, N-gram feature methods utilizing TF-IDF-Vectorizer are used. During the experiment phase, unigram, bigram, and trigram feature techniques are used to apply Logistic Regression (LR), Decision Tree Classifier (DTC), Random Forest (RF), Multinomial Naive Bayes (MNB), and K-Nearest Neighbors (KNN) models to the dataset. In the unigram and bigram features, Multinomial Naive Bayes (MNB) outperformed all other classifiers, with the highest accuracy of 89.31% and 86.94%, respectively. The trigram feature of K-Nearest Neighbors (KNN) achieves a maximum accuracy of 84.25%, and the proposed model can classify the Bangla text document as Good or Bad Discourse. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

An Empirical Evaluation of the Effectiveness of Spider and Proxy Modes for Web Security Testing 10

An Empirical Evaluation of the Effectiveness of Spider and P...

引用

10th International Conference on Dependable Systems and Their Applications, DSA 2023

作者： Chiu, Kuan-Wei Yang, Shih-Sheng Lee, Shin-Jie Lee, Wen-Tin National Cheng Kung University Department of Computer Science and Information Engineering Taiwan National Kaohsiung Normal University Department of Software Engineering and Management Taiwan

ISBN: (纸本)9798350304770

Spider and proxy modes are two commonly employed methods supported by dynamic application security testing (DAST) software. Despite efforts to enhance the automated spider's efficiency, deep exploration of web applications is still constrained by the need for manual intervention in certain complex UI operations. In this regard, the proxy mode serves a crucial intermediary, intercepting and inspecting request messages exchanged between the browser and the web application during manual or scripted browsing activities. This study aims to assess the efficacy of these two modes in terms of code coverage and the number of requests, utilizing two popular PHP-based open-source web applications. The experimental findings demonstrate that employing a hybrid mode (Spider-Last) yields a significant improvement compared to using the spider or proxy mode independently. © 2023 IEEE.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

An Analysis on Cognitive Radio Adhoc Networks: Categories, Problems, and Solutions 1

引用

14th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2022, and the 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2022

作者： Vinya, Viyyapu Lokeshwari Sahithi, G. Gopal, S. Venu Rao, G. Venkateswara Shaikh, Mehwish Department of Computer Science and Engineering Vardhaman College of Engineering Telangana Shamshabad India Department of Computer Science and Engineering CVR College of Engineering Telangana Ibrahimpatnam India Department of Artificial Intelligenceand Data Science Vardhaman College of Engineering Telangana Shamshabad India Department of Computer Science and Engineering GIT GITAM-Deemed to be University A.P. Visakhapatnam India Department of Software Engineering Mehran University of Engineering and Technology Jamshoro Pakistan

ISBN: (数字)9783031275241

ISBN: (纸本)9783031275234

The exploitation of finite spectrum resources is being addressed by the new technology known as Cognitive Radio (CR). It has emerged as a potential remedy for the spectrum shortage problem in the following generation of cellular networks by utilizing opportunities in the time, frequency, and spatial domains. Many group-oriented applications that are created for CRAHN deployment have grown significantly in relevance in recent years. Multicasting is a more effective method for enabling applications that rely on group communication. In contrast to traditional wired multicast routing protocols, multicast routing for CRNs must manage a range of challenges, because of the characteristics of CRNs, such as low bandwidth, mobility, and low power. In this paper, we discussed about various types, issues and solutions for CRAHN routing, Multicast Routing, Channel Assignment and Load balancing. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Multicasting

来源：评论

学校读者我要写书评

暂无评论

Secret Sharing Based Key Agreement Protocol for Body Area Networks 18th

Secret Sharing Based Key Agreement Protocol for Body Area N...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Sheng, Weihong Cai, Bin Hu, Chunqiang Li, Ruinian School of Big Data and Software Engineering Chongqing University Chongqing China Computer Science Department Bowling Green State University Bowling Green United States

ISBN: (纸本)9783031714634

In order to provide more comprehensive medical services and personalized health monitoring according to individual needs, Body Area Networks (BANs) have been extensively studied by many researchers. As BANs involve the transmission of personal private data, the security of the communication is of utmost importance. Unfortunately, existing encryption techniques cannot be directly applied with the limited power or computation ability of the sensors in BANs. An alternative direction is to use physiological signals for key agreement. However, many of the current physiological signal-based key agreement schemes either have high overheads or are vulnerable to certain security issues. In this paper, we proposed a novel secret sharing and Bloom filter based key agreement scheme that balances overhead and security for BANs. Also, we use an approximate hash table to free ourselves from the problem of dependence on the ordering of features, which has been neglected by previous researchers. We validate the security of our scheme with based on real datasets and compare overheads with other solutions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Tumor-TL: A Transfer Learning Approach for Classifying Brain Tumors from MRI Images 1st

Tumor-TL: A Transfer Learning Approach for Classifying Brain...

引用

1st International Conference on Machine Intelligence and Emerging Technologies, MIET 2022

作者： Bitto, Abu Kowshir Bijoy, Md. Hasan Imam Yesmin, Sabina Mia, Md. Jueal Department of Software Engineering Daffodil International University Dhaka1341 Bangladesh Department of Computer Science and Engineering Daffodil International University Dhaka1341 Bangladesh

ISBN: (纸本)9783031346187

An intracranial tumor is another name for a brain tumor, is a fast cell proliferation and uncontrolled bulk of tissue, and seems unaffected by the mechanisms that normally govern normal cells. The identification and segmentation of brain tumors are among the most common difficult and time-consuming tasks when processing medical images. MRI is a medical imaging technique that allows radiologists to see within body structures without requiring surgery. The information provided by MRI regarding human soft tissue contributes to the diagnosis of brain tumors. In this paper, we use several Convolutional Neural Network architectures to identify brain tumor MRI. We use a variety of pre-trained models such as VGG16, VGG19, and ResNet50, which we have found to be critical for reaching competitive performance. ResNet50 performs with an accuracy of 96.76% among all the models. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Network architecture

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：