检索结果-内蒙古大学图书馆

2024 International Conference on Advances in Computing, Communication, Electrical, and Smart Systems, iCACCESS 2024

作者： Rakib Mollah, Md. Abdur Jahangir Kabir, Mir Md. Reza, Md. Sazid Kabir, Monika Rajshahi University of Engineering and Technology Department of Computer Science and Engineering Rajshahi Bangladesh Td School University of Technology Sydney Data Science and Innovation Sydney Australia Murdoch University Information Technology Perth Australia

ISBN: (纸本)9798350350289

Understanding consumer attitudes toward specific products is crucial for boosting sales in the e-commerce industry. To effectively target customers with popular products based on reviews, the classification of consumer feedback becomes imperative. However, classifying product reviews can be challenging, particularly when dealing with imbalanced data labels, which often result in suboptimal classification performance. This study builds upon previous efforts that utilized the Amazon Fine Food Reviews dataset for classification tasks. While these prior attempts showed promise, they were hindered by either poor embeddings or the prevalent class imbalance issue. In response, this research tries to solve these problems by using word embeddings with RoBERTa, a pre-trained transformer-based language model, to classify reviews. Additionally, the XGBoost classifier was implemented, along with embeddings from the language model. Losses were first calculated with equal weights for all class labels, and a re-weighted loss was subsequently adopted to balance the impact of each class on the loss function during training. The incorporation of RoBERTa and XGBoost, along with the class label re-weighting, contributed to improved capturing of intricate word relationships within reviews. As a result, this approach achieves significantly improved accuracy in both binary and multiclass classifications compared to earlier endeavors. Notably, it attained an impressive accuracy of 83.84% in multiclass classification and 93.29% in binary classification tasks, marking a substantial advancement in the field of consumer review analysis. © 2024 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Driver Drowsiness Detection using Deep Neural Networks 2

A Novel Approach for Driver Drowsiness Detection using Deep ...

引用

2nd IEEE International Conference for Women in Innovation, Technology and Entrepreneurship, ICWITE 2024

作者： Sharon, K.V. Natarajan, B. Madhumitha, P. Dhanamathi, A. Prabu, S. Saranya, S. Amrita Vishwa Vidyapeetham Amrita School of Computing Dept. of Computer Science and Engineering Chennai India VIT University School of Computer Science and Engineering Tamilnadu Chennai India Panimalar Engineering College Dept. of Artificial Intell. and Data Science Chennai India Roever Engineering College Department of Computer Science and Engineering Tamilnadu Perambalur India K. Ramakrishnan College of Engineering Dept. of Cse Tamil Nadu Tiruchirappalli621112 India

ISBN: (纸本)9798350383287

One major problem that contributes to many traffic accidents that cause injuries and fatalities all over the world is drowsy driving. This research introduces the novel approach for detecting driver drowsiness using deep networks and computer vision techniques aims to solve this issue and improve road safety. The Proposed system employs an InceptionV3-based Convolutional Neural Network (CNN) model to precisely determine whether the driver's eyes are open or closed. A sizable dataset of eye images taken in actual driving situations is used to train the CNN model. Whenever the indicators of drowsiness are detected, the proposed system will identify them in real time and promptly notify the driver. The proposed model not only has strong real-time capabilities but also exhibits superior accuracy based on stringent evaluation metrics, which makes a significant contribution to efforts aimed at promoting road safety. The performance and adaptability of the system are improved and further integrates alarm activation for drowsiness detection in a variety of driving conditions. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Dynamic prompting class distribution optimization for semi-supervised sound event detection

引用

Frontiers of Information Technology & Electronic engineering 2025年第4期26卷 556-567页

作者： Lijian GAO Qing ZHU Yaxin SHEN Qirong MAO Yongzhao ZHAN School of Computer Science and Communication Engineering Jiangsu UniversityZhenjiang 212016China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agricultural Applications Zhenjiang 212016China

Semi-supervised sound event detection(SSED)tasks typically leverage a large amount of unlabeled and synthetic data to facilitate model generalization during training,reducing overfitting on a limited set of labeled ***,the generalization training process often encounters challenges from noisy interference introduced by pseudo-labels or domain knowledge *** alleviate noisy interference in class distribution learning,we propose an efficient semi-supervised class distribution learning method through dynamic prompt tuning,named prompting class distribution optimization(PADO).Specifically,when modeling real labeled data,PADO dynamically incorporates independent learnable prompt tokens to explore prior knowledge about the true ***,the prior knowledge serves as prompt information,dynamically interacting with the posterior noisy-class distribution *** this case,PADO achieves class distribution optimization while maintaining model generalization,leading to a significant improvement in the efficiency of class distribution *** with state-of-the-art methods on the SSED datasets from DCASE 2019,2020,and 2021 challenges,PADO achieves significant performance ***,it is readily extendable to other benchmark models.

关键词： Prompt tuning Class distribution learning Semi-supervised learning Sound event detection

来源：评论

学校读者我要写书评

暂无评论

Quantum-Improved Weather Forecasting: Integrating Quantum Machine Learning for Precise Prediction and Disaster Mitigation

Quantum-Improved Weather Forecasting: Integrating Quantum Ma...

引用

2023 IEEE International Conference on Quantum Technologies, Communications, Computing, Hardware and Embedded Systems Security, iQ-CCHESS 2023

作者： Suhas, S. Divya, S. Vellore Institute of Technology School of Computer Science and Engineering Chennai India Vellore Institute of Technology Centre for Advanced Data Science Chennai India

ISBN: (纸本)9798350314946

In numerous industries, weather forecasting is essential for making informed decisions and mitigating the effects of extreme weather events. The complexity and chaos of weather systems, however, place restrictions on standard procedures, leading to errors and significant threats. We suggest the Quantum Improved Weather Forecast framework, which combines quantum machine learning methods with conventional methodologies, to solve these issues. By using quantum algorithms including quantum support vector machines, quantum neural networks, and quantum clustering, the QWF framework seeks to improve accuracy. Despite a few drawbacks, the QWF framework provides a method to revolutionize weather forecasting by enhancing prediction accuracy and facilitating improved catastrophe preparedness. It may prevent fatalities, safeguard critical infrastructure, and promote sustainable growth. © 2023 IEEE.

关键词： Climate change

来源：评论

学校读者我要写书评

暂无评论

Understanding Student Behavior and Learning Patterns through Video Analysis: A Comprehensive Literature Review 4

Understanding Student Behavior and Learning Patterns through...

引用

4th IEEE International Conference on Emerging Techniques in Computational Intelligence, ICETCI 2024

作者： Gadad, Jyoti Asundi, Madhu Vijayalakshmi, M. Baligar, Preethi Kle Technological University Centre for Engineering Education Research Hubballi India Data Science and Intelligent Systems Iiit Ittigatti Dharwad India School of Computer Science and Engineering Kle Technological University Hubballi India

ISBN: (纸本)9798350387063

Technology-enhanced learning (TEL) has emerged as a powerful approach to facilitate and enhance learning experiences in diverse educational settings. The integration of TEL tools enables the collection of real-time and longitudinal data. Technology-enhanced learning provides the digital infrastructure and tools that enable educators to collect and process diverse data. It is fundamental for successfully implementing Multi-modal Learning Analytics (MMLA) in understanding student learning patterns. This literature paper presents a comprehensive review of research at the intersection of MMLA, video analytics, human gesture, and their relation to behavior and learning patterns. This study explores how video analysis techniques capture and analyze human gestures, revealing insights into underlying behavioral dynamics and learning patterns. This study conducts a scoping review of relevant literature from diverse fields such as computer science, education, human-computer interaction, and medical science. The authors utilized LitMap, a comprehensive search strategy to identify pertinent literature. In education context, understanding the role of gestures in learning can inform the development of instructional strategies that optimize knowledge acquisition and retention. By studying patterns in human gestures and behavior, particularly in the education context, researchers can gain insights into students' engagement, cognitive processes, and learning strategies. This scoping review presents an in-depth survey of research encompassing video analytics, human gestures, and their interplay with behavior and learning patterns. The study delves into the behavioral factors that impact student learning and explores how educators can leverage them to enhance their teaching practices. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

DivLog: Log Parsing with Prompt Enhanced In-Context Learning 24

DivLog: Log Parsing with Prompt Enhanced In-Context Learning

引用

44th ACM/IEEE International Conference on Software engineering, ICSE 2024

作者： Xu, Junjielong Yang, Ruichun Huo, Yintong Zhang, Chengyu He, Pinjia The Chinese University of Hong Kong Dept. of Computer Science & Engineering Hong Kong Eth Zurich Switzerland School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data China

ISBN: (纸本)9798400702174

Log parsing, which involves log template extraction from semi-structured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for two reasons. First, traditional data-driven log parsers solely rely on heuristics or handcrafted features designed by domain experts, which may not consistently perform well on logs from diverse systems. Second, existing super-vised log parsers require model tuning, which is often limited to fixed training samples and causes sub-optimal performance across the entire log source. To address this limitation, we propose Di-vLog, an effective log parsing framework based on the in-context learning (ICL) ability of large language models (LLMs). Specifically, before log parsing, DivLog samples a small amount of offline logs as candidates by maximizing their diversity. Then, during log parsing, DivLog selects five appropriate labeled candidates as examples for each target log and constructs them into a prompt. By mining the semantics of examples in the prompt, DivLog generates a target log template in a training-free manner. In addition, we design a straightforward yet effective prompt format to extract the output and enhance the quality of the generated log templates. We conducted experiments on 16 widely-used public datasets. The results show that DivLog achieves (1) 98.1% Parsing Accuracy, (2) 92.1% Precision Template Accuracy, and (3) 92.9% Recall Template Accuracy on average, exhibiting state-of-the-art performance. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Piccolo: Large-Scale Graph Processing with Fine-Grained in-Memory Scatter-Gather 31

Piccolo: Large-Scale Graph Processing with Fine-Grained in-M...

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Shin, Changmin Song, Jaeyong Jang, Hongsun Kim, Dogeun Sung, Jun Kwon, Taehee Ju, Jae Hyung Liu, Frank Choi, Yeonkyu Lee, Jinho Seoul National University Department of Electrical and Computer Engineering Korea Republic of Old Dominion Univeristy School of Data Science United States Samsung Electronics Korea Republic of

ISBN: (纸本)9798331506476

Graph processing requires irregular, fine-grained random access patterns incompatible with contemporary off-chip memory architecture, leading to inefficient data access. This inefficiency makes graph processing an extremely memory-bound application. Because of this, existing graph processing accelerators typically employ a graph tiling-based or processing-in-memory (PIM) approach to relieve the memory bottleneck. In the tiling-based approach, a graph is split into chunks that fit within the on-chip cache to maximize data reuse. In the PIM approach, arithmetic units are placed within memory to perform operations such as reduction or atomic addition. However, both approaches have several limitations, especially when implemented on current memory standards (i.e., DDR). Because the access granularity provided by DDR is much larger than that of the graph vertex property data, much of the bandwidth and cache capacity are wasted. PIM is meant to alleviate such issues, but it is difficult to use in conjunction with the tiling-based approach, resulting in a significant disadvantage. Furthermore, placing arithmetic units inside a memory chip is expensive, thereby supporting multiple types of operation is thought to be impractical. To address the above limitations, we present Piccolo, an end-to-end efficient graph processing accelerator with fine-grained in-memory random scatter-gather. Instead of placing expensive arithmetic units in off-chip memory, Piccolo focuses on reducing the off-chip traffic with non-arithmetic function-in-memory of random scatter-gather. To fully benefit from in-memory scatter-gather, Piccolo redesigns the cache and miss-handling architecture (MHA) of the accelerator such that it can enjoy both the advantage of tiling and in-memory operations. Piccolo achieves a maximum speedup of 3.28 × and a geometric mean speedup of 1.62 ×, along with up to 59.7% reduction in energy consumption across various and extensive benchmarks. © 2025 IEEE.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Based Clustering with Deep Learning Model for Big data Classification

引用

computer Systems science & engineering 2023年第1期44卷 391-406页

作者： R.Krishnaswamy Kamalraj Subramaniam V.Nandini K.Vijayalakshmi Seifedine Kadry Yunyoung Nam Department of Electronics and Communication Engineering University College of Engineering AriyalurAriyalur621704India Department of Biomedical Engineering Faculty of EngineeringKarpagam Academy of Higher EducationCoimbatore641021India Department of Computer Science and Engineering Sona College of TechnologySalem636005India Department of Electronics and Communication Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai600077India Deparmtent of Applied Data Science Noroff University CollegeKristiansandNorway Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea

Recently,a massive quantity of data is being produced from a distinct number of sources and the size of the daily created on the Internet has crossed two *** the same time,clustering is one of the efficient techniques for mining big data to extract the useful and hidden patterns that exist in ***-based clustering techniques have gained significant attention owing to the fact that it helps to effectively recognize complex patterns in spatial *** data clustering is a trivial process owing to the increasing quantity of data which can be solved by the use of Map Reduce *** this motivation,this paper presents an efficient Map Reduce based hybrid density based clustering and classification algorithm for big data analytics(MR-HDBCC).The proposed MR-HDBCC technique is executed on Map Reduce tool for handling the big *** addition,the MR-HDBCC technique involves three distinct processes namely pre-processing,clustering,and *** proposed model utilizes the Density-Based Spatial Clustering of Applications with Noise(DBSCAN)techni-que which is capable of detecting random shapes and diverse clusters with noisy *** improving the performance of the DBSCAN technique,a hybrid model using cockroach swarm optimization(CSO)algorithm is developed for the exploration of the search space and determine the optimal parameters for density based ***,bidirectional gated recurrent neural network(BGRNN)is employed for the classification of big *** experimental validation of the proposed MR-HDBCC technique takes place using the benchmark dataset and the simulation outcomes demonstrate the promising performance of the proposed model interms of different measures.

关键词： Big data data classification clustering mapreduce dbscan algorithm

来源：评论

学校读者我要写书评

暂无评论

Preliminary analysis of traffic related pollution factors around primary and secondary schools during commuting in winter: A case study in Jinan city

Preliminary analysis of traffic related pollution factors ar...

引用

Healthy Buildings 2023: Asia and Pacific Rim

作者： Ren, Lulu Fu, Sifang Sun, Teng Liu, Jiying School of Thermal Engineering Shandong Jianzhu University Jinan China School of Data and Computer Science Shandong Women's University Jinan China

ISBN: (纸本)9781713890850

In recent years, the rapid development of urbanization and the increase in vehicle emissions have exacerbated urban air pollution. During commuting, the number of vehicles around primary and secondary schools has increased, and students' exposure to pollutants emitted by motor vehicles has also increased significantly. Traffic related pollutants around schools are affected by the layout of buildings, street characteristics, traffic volume, and traffic planning around schools, but there is less research on related aspects. This study selected 20 typical primary and secondary schools in Jinan to comprehensively analyze factors such as the architectural layout, street characteristics, traffic volume, and traffic planning around the school. Then, the method of fixed-point testing is used to test the traffic pollutants in different time periods and spatial locations around the school to obtain the exposure level of traffic pollutants. The results show that the concentration of pollutants around primary and secondary schools is related to traffic flow, road congestion, and the characteristics of surrounding buildings. The main time period during commuting time when the concentration of particulate matter increases due to traffic is 7:00-7:40 a.m. This study proposes methods to effectively alleviate the exposure level of air pollutants around schools, mitigate the impact of motor vehicle emissions on student health, and ensure the health and quality of life of primary and secondary school students, providing a reference for school site selection and planning and design. © 2023 Healthy Buildings 2023: Asia and Pacific Rim. All rights reserved.

关键词： Site selection

来源：评论

学校读者我要写书评

暂无评论

Predicting Cervical Cancer Using Deep Learning Mutation-based Atom Search Optimization (MASO) Algorithm 2

Predicting Cervical Cancer Using Deep Learning Mutation-base...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Mayuri, A.V.R. Selvekumar Subash, K. Aeron, Anurag Vit Bhopal University School of Computing Science and Engineering Madhya Pradesh Sehore India Bahir Dar University Bahir Dar Institute of Technology Department of Electrical and Computer Engineering Ethiopia Department of Data Science Trichy India Miet Meerut Department of Computer Science and Engineering Uttar Pradesh India

ISBN: (纸本)9798350384277

Worldwide, women are compressed by cervical cancer, which is a prevalent malignancy. This disease, which is currently the fourth leading cause of death for women, shows no symptoms when it first arises. Cells that cause cervical cancer multiply gradually at the cervix. If this cancer is detected early enough, treatment can be effective. Presently, it is difficult for medical workers to detect this kind of cancer before it spreads rapidly. This study used a number of machine learning classification algorithms with risk markers to predict cervical cancer. These study suggestions mutation-based Atom Search Optimization (MASO) with a Deep Convolutional Neural Network (DCNN) to offer a original method for automated diagnosis of uterine cervical cancer. Though DCNN is used to extract features from medical imaging data, MASO is used to increase the optimization of the diagnostic model. Composed, these technologies have the potential to rise cervical cancer diagnosis accuracy and efficiency, offering an automated approach for early detection and prompt intervention. Our proposed model established a strong 95% accuracy rate for generalization. This study explores the difficulties caused by missing values and class imbalance in the specific dataset with the goal of assisting medical professionals in the early detection of cervical cancer and improving treatment for people that are impacted by the illness. © 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

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：