检索结果-内蒙古大学图书馆

2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2024

作者： Sen, Madhura Masih, Jolly Rajasekaran, Rajkumar School of Computer Science and Engineering Vellore Institute of Technology Vellore India Bml Munjal University Gurgaon India

ISBN: (纸本)9798350372229

The rapid rise of social media usage, particularly during the COVID-19 pandemic, has amplified the prevalence of cyberbullying, necessitating effective detection and prevention measures. This research explores the application of sentiment analysis (SA) and deep learning models, specifically utilizing Bidirectional Encoder Representations from Transformers (BERT) in combination with Convolutional Neural Network (CNN) and Multi-Layer Perceptron (MLP), to automatically detect cyberbullying in Twitter posts. The study utilizes a Hate Speech and Offensive Language dataset, employing data preprocessing techniques and exploratory data analysis to address imbalances and understand the dataset's intricacies. The proposed architecture demonstrates superior performance, achieving an accuracy range of 87.2% to 92.3%, outperforming existing methods such as Naive Bayes, Support Vector Machine (SVM), Deep Neural Network (DNN), and CNN. The research contributes to the ongoing efforts to develop robust cyberbullying detection systems, emphasizing the need for proactive measures in the face of escalating online harassment incidents, especially in the COVID-19 era. © 2024 IEEE.

关键词： COVID-19 Cyberbullying Deep Learning Natural Language Processing Sentiment Analysis

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Inference of a Proposed, Improved and Efficient W Model for Software Testing 15

Evaluation and Inference of a Proposed, Improved and Efficie...

引用

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

作者： Velan, Senthil S. Velan, Sivaranjani Senthil Rubini, P. Sudhakar, K. Information Science and Engineering CMR Institute of Technology Bengaluru India Computer Science and Engineering MVJ College of Engineering Bengaluru India School of Engineering and Technology CMR University Bengaluru India Artificial Intelligence and Data Science NITTE Meenakshi Institute of Technology Bengaluru India

ISBN: (纸本)9798350370249

Software Testing is an important and measured/outcome-oriented field that requires an in-depth analysis for developing new methodologies. This enables the development of high-quality end product resulting in fewer maintenance schedules. Several models have been proposed by research teams of different companies leading to improved development and testing schedules. Even with the availability of these models, a significant allocation of the budget has been dedicated purely on the maintenance of software developed by the IT industry. In order to address this need for improved process models of testing, a new exclusive and efficient W model has been proposed and explained in this paper. This model can improve the quality of end product, namely the high-quality software and further reduce the cost involved for the maintenance. Based on the quantitative measurement the proposed W software testing model, it was found the small scale software developed by adopting this method produces high-quality software with 50% less errors/faults compared to development using classical life cycle model. ©2024 IEEE.

关键词： computer software selection and evaluation

来源：评论

学校读者我要写书评

暂无评论

CRD-CGAN:category-consistent and relativistic constraints for diverse text-to-image generation

引用

Frontiers of computer science 2024年第1期18卷 61-75页

作者： Tao HU Chengjiang LONG Chunxia XIAO College of Intelligent Systems Science and Engineering Hubei Minzu UniversityEnshi 445000China School of Computer Science Wuhan UniversityWuhan 430072China Key Laboratory of Performing Art Equipment&System Technology Ministry of Culture and TourismBeijing 100007China Meta Reality Labs BurlingameCA94010USA

Generating photo-realistic images from a text description is a challenging problem in computer *** works have shown promising performance to generate synthetic images conditional on text by Generative Adversarial Networks(GANs).In this paper,we focus on the category-consistent and relativistic diverse constraints to optimize the diversity of synthetic *** on those constraints,a category-consistent and relativistic diverse conditional GAN(CRD-CGAN)is proposed to synthesize K photo-realistic images *** use the attention loss and diversity loss to improve the sensitivity of the GAN to word attention and ***,we employ the relativistic conditional loss to estimate the probability of relatively real or fake for synthetic images,which can improve the performance of basic conditional ***,we introduce a category-consistent loss to alleviate the over-category issues between K synthetic *** evaluate our approach using the Caltech-UCSD Birds-200-2011,Oxford 102 flower and MS COCO 2014 datasets,and the extensive experiments demonstrate superiority of the proposed method in comparison with state-of-the-art methods in terms of photorealistic and diversity of the generated synthetic images.

关键词： text-to-image diverse conditional GAN relativi-stic category-consistent

来源：评论

学校读者我要写书评

暂无评论

Classification of Skin Diseases in the Internet of Medical Things using Hybrid Deep Learning 2

Classification of Skin Diseases in the Internet of Medical T...

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Latha, Dandu Madhavi Anusha, Kondepati Samrin, Rafath Reddy, Pundru Chandra Shaker Sudhakar, Bolleddu Sathish, Goski Geethanjali College of Engineering and Technology Electronics and Communication Engineering Telangana Hyderabad India Marri Laxman Reddy Institute of Technology and Management Computer Science and Engineering Telangana Hyderabad India King Khalid University Department of Computer Science College of Computer Science Asir Abha Saudi Arabia Sr University School of Computer Science and Artificial Intelligence Telangana Warangal India Degree Lecturer of Computer Science Mjptbcwreis Telangana India Department of Information Technology Hyderabad India

ISBN: (纸本)9798350372892

When it comes to the IoMT, skin lesion examination is absolutely essential for making an accurate diagnosis. Skin lesion analysis relies heavily on computer-aided design(CAD) technologies to enhance accuracy and efficiency. Using hybrid deep learning approaches, this work focuses on segmenting and classifying skin lesions from dermoscopy images. Mask Region-based Convolutional Neural Network (MRCNN) for semantic separation and ResNet50 for lesion-detection are two state-of-the-art methodologies that are combined in this research's hybrid deep learning model. A skin lesion's exact location can be determined with the use of the MRCNN's border delineation capabilities. For comprehensive model training, we gather a large collection of dermoscopy photos that have been annotated. This dataset is used to train a hybrid deep-learning(DL) model that can capture images' nuanced representations. An accuracy rate of 95.49% in segmenting lesions into different groups demonstrates the model's capability to do so. Another significant improvement over older method is the high reliability and accuracy of skin lesion classification. After being tested on the ISIC2020 Challenge dataset, the model achieved an impressive 96.75% accuracy rate. Classification and segmentation models outperform the state-of-the-art in Internet-of-Medical-Things(IoMT). When it comes to segmenting and classifying skin lesions, this paper's hybrid deep learning approach works wonders. Outperforming the existing gold standards, the results demonstrate that the model can enhance diagnostic accuracy in an IoMT environment. © 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

Innovation of the Higher Education Grassroots Statistical Reports System based on Low-Code Development 7

Innovation of the Higher Education Grassroots Statistical Re...

引用

7th International Conference on Management engineering, Software engineering and Service sciences, ICMSS 2023

作者： Luo, Jinshang Hou, Mengshu Information Center University of Electronic Science and Technology of China Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781665456067

The grassroots statistical reporting of higher education is not only a critical effort for the advancement of national education, but it also serves as a prominent foundation for colleges and universities in formulating development strategies. Due to numerous statistical objects, extensive fields, and complex contents, the problems of difficult data maintenance and low filling efficiency caused by traditional manual means are prone to occur. To address these issues, the low-code software development method is utilized to design and implement a higher education grassroots statistical reports system. Initially, the characteristics of low-code development are leveraged to achieve code reusability and simplify the development process. Moreover, the method emphasizes data verification to improve data quality. To handle reported data, an automatic filling flow is eventually constructed. The system's deployment optimizes data reporting, reduces the intensity of statistical work, strengthens data verification, enhances the quality of data reporting, and effectively supports statistical reports. © 2023 IEEE.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning for Enhanced SensorPowered Green IoT with Federated Learning 15

Leveraging Machine Learning for Enhanced SensorPowered Green...

引用

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

作者： Devrani, Rekha Premkumar, R. Kumar, Shyam Vivekananda Global University Department of Computer Science & Engineering Jaipur India School of Engineering and Technology Department of Electronics and Communication Engineering Karnataka Bangalore India Arka Jain University Department of Computer Science & It Jharkhand Jamshedpur India

ISBN: (纸本)9798350370249

Federated getting to know (FL) is a gadget studying generation which allows a user to train a single model across more than one dispensed system, with none of the person systems having to transfer the statistics sets, nor the version, to a vital device for education. It allows disbursed schooling of an unmarried model throughout more than one disbursed net of things (IoT) gadgets or users. It makes it feasible to improve the accuracy and scalability of our Sensor-Powered inexperienced IoT applications. FL can consequently be instrumental in taking inexperienced IoT answers towards the character sources of environmental records, like air firstclass sensors, as opposed to amassing facts *** permits us to leverage powerful gadget learning models to enhance the accuracy and scalability of our Sensor-Powered green IoT systems. By using federated models throughout education, we will grow the accuracy of our predictions and decrease the amount of effort and time we have to acquire and store sensor facts centrally. Moreover, FL lets us improve the version overall performance of green IoT packages by dispensing schooling and predictions to a disbursed community of sensor-based totally IoT devices. We also can, in addition, reduce the reliance on central systems with the aid of transferring the middle of our Sensor-Powered inexperienced IoT packages from the cloud to allotted nodes. © 2024 IEEE.

关键词： Generation Predictions Scalability Sensor Statistics Throughout Unmarried

来源：评论

学校读者我要写书评

暂无评论

Leveraging Packet Cloning to Achieve Fast Flow-Transmission for Data Center Load Balancing 22

Leveraging Packet Cloning to Achieve Fast Flow-Transmission ...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Wang, Yuchen Li, Zhenbo Jing, Haotian Zhang, Tao Zou, Shaojun Luan, Xidao Yin, Hui Li, Fangmin Changsha University School of Computer Science and Engineering ChangSha410022 China Hunan Province Key Laboratory of Industrial Internet Technology and Security ChangSha410022 China Hainan University School of Computer Science and Technology Haikou570228 China

ISBN: (纸本)9798331509712

Modern data center network often possesses multiple end-to-end parallel paths, which undertake the crucial task of transmitting vast heterogeneous data traffic generated by a wide variety of applications. To fully utilize the offered super high bisection network bandwidth thus benefiting application performance, many data center load balancing schemes are proposed to improve path utilization for avoiding network congestion hot-spot. However, these schemes are naturally agnostic to data center traffic pattern and the diverse requirements on flow-transmission, leading to the sub-optimal network transmission performance. To address this issue, this paper presents a new data center load balancing scheme, called PCLB, which selectively generates Clone Packets by considering both flow-transmission phases and path states, thereby helping different types of flows choose more appropriate paths for speeding up their data transmission. Experimental results of numerous NS2 simulations show that PCLB significantly reduces the average and tail flow completion time for delay-sensitive flows, while the performance of throughput-oriented flows can be always maintained at high level. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Optimizing Supply Chain Management with Neural Network and Machine Learning Techniques 3

Optimizing Supply Chain Management with Neural Network and M...

引用

3rd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2024

作者： Mathur, Anubhav Yadav, Dipti Singh, Jagendra Ikra, Km Abbas, Haider Mohammed Agarwal, Nishi Bennett University School of Media Greater Noida India Pranveer Singh Institute of Technology Department of Cse Kanpur India Bennett University School of Computer Science Engineering and Technology Greater Noida India Galgotias University School of Computer Science & Engineering Department of Computer Science Engineering Greater Noida India The Islamic University Najaf Iraq Dev Bhoomi Uttrakhand University Department of Cse Dehradun India

ISBN: (纸本)9798350364569

This study focused on identifying the possible reduction in holding costs and minimizing stockout risk through utilizing machine learning models as;Long Short-Term Memory (LSTM), Artificial Neural Network (ANN) and Random Forest (RF) to improve supply chain management in textile sector. The research is based on rich data assets like historical sales information, weather factors and economic indexes, lead times (time intervals between emergence of need for a product until it becomes available in the store) along with supplier reliability and transportation details. However, the LSTM model that is capable of learning temporal dependencies performed with precision at the top with 97.76% accuracy which effectively learn elaborate patterns in our dataset. The ANN also accurately predicted at 94.50% accuracy that can capture complex relationships between different parameters of the supply chains. Although with slightly more false positive rate, RF showed highly robust performance using its ensemble approach (91.23% of accuracy). Every model will be trained and evaluated stringently where some performance metrics (accuracy, precision, recall, and F1 score) every epoch are considered. A comparative analysis of the different approaches used in this work show that LSTM scores higher precision and recall, essential for making forecasting over time where arithmetic predictions become harmful. ANN and RF offer stable across short terms prediction adjusting to operating context Businesses can improve their overall operational performance in dynamic and competitive market environments by incorporating these models to supply chain decision-making processes which result in efficient operations, lower inventory holding costs and reduce the risk of stockouts. © 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

LEARNING UNCERTAINTY FOR UNKNOWN DOMAINS WITH ZERO-TARGET-ASSUMPTION 11

LEARNING UNCERTAINTY FOR UNKNOWN DOMAINS WITH ZERO-TARGET-AS...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Yu, Yu Sajjad, Hassan Xu, Jia School of Engineering and Science Stevens Institute of Technology United States Faculty of Computer Science Dalhousie University Canada

We introduce our Maximum-Entropy Rewarded Reinforcement Learning (MERRL) framework that selects training data for more accurate Natural Language Processing (NLP).Because conventional data selection methods select training samples based on the test domain knowledge and not on real life data, they frequently fail in unknown domains like patent and *** approach selects training samples that maximize information uncertainty measured by entropy, including observation entropy like empirical Shannon entropy, Min-entropy, Rényi entropy, and prediction entropy using mutual information, to cover more possible queries that may appear in unknown *** MERRL using regularized A2C and SAC achieves up to -99.7 perplexity decrease (-43.4% relatively) in language modeling, +25.0 accuracy increase (+40.0% relatively) in sentiment analysis, and +5.0 F1 score increase (+30.8% relatively) in named entity recognition over various domains, demonstrating strong generalization power on unknown test sets. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Harmonizing Ensemble Learning Strategies for Enhanced Coronary Artery Disease Prediction 1

Harmonizing Ensemble Learning Strategies for Enhanced Corona...

引用

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Upadhyay, Sachin Sagar, Anil Kumar Roy, Nihar Ranjan School of Engineering and Technology Sharda University Department of Computer Science and Engineering Greater Noida India VIPS-TC Delhi India

ISBN: (纸本)9798350353648

Coronary artery disease (CAD) is a common health issue today that can lead to financial loss, disability, and even death for those with heart problems. In addition to increasing the chances of curing patients, early diagnosis could lead to a reduction in their impermanence as well. Machine learning algorithms are now often employed in medicine and have proven to be reliable, saving both time and lives. In order to enhance precision, Machine Learning models are trained using diverse datasets to attain more accurate results. In this research, our goal is to improve the accuracy of predicting heart disease by training different machine learning models with the aid of these datasets. Rather than having costly medical examinations, we want to cut down on time and money spent. In this way, patients will not have to wait long for multiple tests of this type. This paper demonstrates how advanced machine learning algorithms can help predict CVD using simple medical tests. © 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：