检索结果-内蒙古大学图书馆

1st International Conference on AIML-Applications for engineering and technology, ICAET 2025

作者： Dixit, Jayati Rai, Anshuman Tandon, Pulak Pandey, Dhiraj JSS Academy of Technical Education Noida Information Technology Department Noida India JSS University Noida Computer Science and Engineering Department Noida India

ISBN: (纸本)9798350355611

About 17.5% of adults worldwide are infertile, which emphasizes the urgent need for cutting-edge reproductive healthcare solutions. Based on statistics from June 2023. According to the World Health Organization (WHO), 8-13% of females on earth who are in their reproductive age have PCOS, and about 70% of cases go undiagnosed. With the integration of PCOS detection, IVF success rate prediction, and a period tracking system, this work offers a comprehensive women's health application. In addition, a large percentage of women suffer from menstruation abnormalities, such as dysmenorrhea (38.1%) and irregular frequency (80.7%). This approach improves early illness detection and fertility planning by using data analysis and machine learning. The techniques used are Random Forest, K-Nearest Neighbor, Logistic Regression, Naive Bayes, Decision Tree and SVM;which provides us better accuracy than previous works. © 2025 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

DAS-COD: Depth-Aware Camouflaged Object Detection via Swin Transformer

DAS-COD: Depth-Aware Camouflaged Object Detection via Swin T...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Lu, Chenye Tan, Min Gao, Zhigang Mao, Xiaoyang Xia, Zilin School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China College of Information Engineering China Jiliang University Hangzhou China University of Yamanashi Department of Computer Science and Engineering Kofu Japan

ISBN: (纸本)9781665410205

The successful integration of depth information into salient object detection tasks has catalyzed research interest in depth-enhanced camouflaged object detection (COD) tasks. However, the challenges associated with acquiring depth information pose significant hurdles to this task, especially given the lack of RGB-D datasets tailored specifically for COD. Consequently, employing depth estimation techniques to generate pseudo-depth information emerges as a viable solution in the realm of depth-enhanced COD tasks. In this study, we propose an architecture, DAS-COD (Depth-Aware Swin Transformer COD), that integrates Swin Transformer model with depth estimation techniques for the purpose of camouflaged object detection. In particular, we use a dual-stream Swin Transformer backbone to extract feature maps from different modalities. These maps are then enhanced with a multi-modal feature enhancement module. Additionally, to address the inherent discrepancies between pseudo-depth maps and actual depth information, we incorporate an edge-aware module to significantly improve the accuracy of boundary delineation in the predicted outcomes. We tested our proposed method on three different COD datasets. Our results show that the model achieves state-of-the-art performance across these camouflaged object detection datasets. © 2024 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Transforming Business Management Practices for Increased Production through Deep Learning and Cloud Computing integration 4

Transforming Business Management Practices for Increased Pro...

引用

4th International Conference on Advancement in Electronics and Communication engineering, AECE 2024

作者： Kumar, P. Santhosh Singh, Anupam Soniya Farhana, Shaik Choudhary, Amar Biswas, Susmi Srm Institute of Science and Technology Ramapuram Faculty of Engineering and Technology Department of Information Technology Chennai India Graphic Era Hill University Department of Computer Science and Engineering India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Sanskar College of Engineering Department of Management Ghaziabad India CVR College of Engineering Department of Computer Science and Engineering Hyderabad India Alliance University Department Electronics and Communication Engineering Bengaluru India Haldia Institute of Management MAKAUT Department of Management Science India

ISBN: (纸本)9798350364729

This research is vital to meet the need for improved predictive maintenance in manufacturing, thus enabling predictive operations and minimizing expensive downtime. The aim is to assess and compare different machine learning models like Artificial Neural Networks (ANN), Support Vector Machines (SVM) and Decision Trees( DT ) with respect to predicting maintenance requirements using historical sales data, social media trends, and machinery sensor readings. The methodology included gathering a dataset of 3,200 records from the industry and then the pre-processing phase to compute the preprocessing operations like data cleaning, normalization and feature selection. The various models were then trained and tested, using 70% of the data for training to generalise the model, with the rest of the unseen test set consisting of the remaining 30%. The models were evaluated based on performance metrics (accuracy, precision, recall, F1 score and Dice Similarity Coefficient or DSC). Results showed the proposed ANN model as the most accurate and efficient prediction mechanism in comparison with precision, recall and F1 score for remaining useful life (RUL) predictions. The SVM model also worked well, with an accuracy of 95.45% but low rates of false positives and negatives. Although the DT model was informative, its performance (93.34% accuracy) was less robust than that of our RF ensemble trainer. This research demonstrates the use of these findings to be applied in real-time maintenance prediction by ANN. This research would help industries and other manufacturing sectors to reduce downtime, achieve optimal planned maintenance scheduling and improve production efficiency. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Comparing Boosting and Bagging Algorithms for Image Classification

Comparing Boosting and Bagging Algorithms for Image Classifi...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Chaudhary, Chetan Gupta, Arun Murugan, R. Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India College of Engineering Teetthanker Mahaveer University Uttar Pradesh Moradabad India Department of Computer Science and Information Technology Bangalore India

ISBN: (纸本)9798350383348

Boosting and bagging are famous ensembles gaining knowledge of algorithms for photo classes. Each algorithm depends upon combining a couple of classifiers to enhance generalization accuracy, at the same time as using specific techniques to generate a final model and boosting works by using training more than one vulnerable classifier iteratively, deciding on new classifiers that concentrate on miscategorized examples from earlier rounds. Bagging then uses the same classifier with extraordinary subsets of the education dataset to generate more than one classifiers that are then blended. In phrases of generalization accuracy, boosting algorithms outperform bagging due to their capability to focus more on tough-to-classify examples. However, boosting can be more computationally intensive in phrases of education time than bagging because it continually updates and trains new vulnerable classifiers. Furthermore, boosting algorithms can also be afflicted by low bias and low variance problems, making them vulnerable to overfitting. In conclusion, boosting and bagging are effective strategies for picture type, with boosting algorithms presenting superior generalization accuracy and bagging algorithms being computationally greener. Relying on the task, the perfect method may be determined. © 2024 IEEE.

关键词： algorithm computationally generalization miscategorized vulnerable

来源：评论

学校读者我要写书评

暂无评论

Improving Online Job Authenticity Detection Using Deep Learning and Focal Loss 2

Improving Online Job Authenticity Detection Using Deep Learn...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Akhila, K. Sofi, Mukhtar Ahmad Reddy, Ch. Likitha Sarayu, A. Sannitya, M. Bvrit Hyderabad College of Engineering for Women Department of Information Technology Hyderabad India Bvrit Hyderabad College of Engineering for Women Department of Computer Science Hyderabad India

ISBN: (纸本)9798350373110

The rise of fake job postings in online job marketplaces presents a significant challenge for job seekers, necessitating robust detection methods. Existing methods often struggle to adapt to evolving fraudulent tactics, leading to suboptimal accuracy. This project introduces a novel Deep Learning approaches which are Recurrent Neural Network (RNN) variants leveraging Bi-LSTM and Bi-GRU architectures to enhance fake job detection and used a loss function for removing the imbalanced class distribution which is called 'Focal Loss'. Using the EMSCAD dataset, we trained and evaluated the performance of the proposed model against state-of-the-art methods, aiming for broader accessibility through integration into a user-friendly webserver for real-time job posting analysis which will help jobseekers to identify whether the job posting is Genuine/Fake. In this project we got accuracy of value 98.6% with precision of 85%, recall of 84% and f1-score of 85%. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Query Optimization Framework for Graph Database in Cloud Dew Environment

引用

computers, Materials & Continua 2023年第1期74卷 2317-2330页

作者： Tahir Alyas Ali Alzahrani Yazed Alsaawy Khalid Alissa Qaiser Abbas Nadia Tabassum Department of Computer Science Lahore Garrison UniversityLahorePakistan Faculty of Computer Science and Information Systems Islamic University Madinah Madinah42351Saudi Arabia Networks and Communications Department College of Computer Science and Information TechnologyImam Abdulrahman Bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia Department of Computer Science Virtual University of PakistanLahorePakistan

The query optimizer uses cost-based optimization to create an execution plan with the least cost,which also consumes the least amount of *** challenge of query optimization for relational database systems is a combinatorial optimization problem,which renders exhaustive search impossible as query sizes *** in CPU performance have surpassed main memory,and disk access speeds in recent decades,allowing data compression to be used—strategies for improving database performance *** performance enhancement,compression and query optimization are the two most *** reduces the volume of data,whereas query optimization minimizes execution *** the database reduces memory requirement,data takes less time to load into memory,fewer buffer missing occur,and the size of intermediate results is more *** paper performed query optimization on the graph database in a cloud dew environment by considering,which requires less time to execute a *** factors compression and query optimization improve the performance of the *** research compares the performance of MySQL and Neo4j databases in terms of memory usage and execution time running on cloud dew servers.

关键词： Query optimization compression cloud dew decompression graph database

来源：评论

学校读者我要写书评

暂无评论

DBNLP: detecting bias in natural language processing system for India-centric languages

引用

International Journal of information technology (Singapore) 2025年 1-16页

作者： T. G, Keerthan Kumar Mendke, Saish Parihar, Rohit Mayya, Samarth Venkatesh, Spoorthy Koolagudi, Shashidhar G. Department of Information Science and Engineering Siddaganga Institute of Technology Karnataka Tumkur 572102 India Department of Computer Science and Engineering National Institute of Technology Karnataka Surathkal Karnataka Mangalore 575025 India Department of Artificial Intelligence and Machine Learning CSPIT CHARUSAT Gujarat Anand 388421 India

Natural language processing (NLP) is gaining widespread interest and seeing advancements rapidly due to its attractive and exhilarating applications. NLP models are being developed in search engines for real-world scenarios such as language translation, sentiment analysis, chat-bots such as ChatGPT, and auto-completion. These models are trained on a vast corpus of online data, exposing them to harmful biases and stereotypes towards various communities. The models learn these biases, making harmful and undesirable predictions about particular genders, religions, races, and professions. Biases in NLP systems can perpetuate societal biases and discrimination, leading to unfair and unequal treatment of individuals or groups. It is crucial to identify these biases, which will help mitigate them. Most of the literary works in this area have been primarily Western-centric, focusing on the English language, making it tough to use them for Indian models and languages. In this work, we propose a model called Detecting Bias in Natural Language Processing System for India-Centric Languages (DBNLP), which aims to identify the biases relevant to the Indian context present in the text-based language models, particularly for the English and Hindi languages. The DBNLP presents three techniques for bias identification based on (1) a Context Association Test (CAT), (2) a template-based perturbation technique for various co-domain associations, and (3) a co-occurrence count-based corpus analysis technique. Further, this work showcases how India-centric models such as IndicBERT, MuRIL, and datasets such as IndicCorp are biased toward various demographic categories. Detecting bias in natural language processing systems for India-centric languages is essential to creating fair, diverse, and inclusive models that benefit society. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Diverse and Inclusive models Harmful biases and stereotypes India-centric models Indian context Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Text recognition using improved dual attention based on textual double embedding network with aquila optimization algorithm

引用

International Journal of information technology (Singapore) 2024年 1-15页

作者： Singhdev, Harsiddhi Gupta, Shruti Srivastava, Vivek Saxena, Apoorva Department of Computer Science and Engineering ABES Engineering College Uttar Pradesh Ghaziabad India Department of Computer Science and Engineering Axis Institute of Technology & amp Management Uttar Pradesh Kanpur India

Text recognition is the process that changes an image of text into a system readable text format. Different approaches were suggested related to text detection but the existing methods accuracy is low and error rate is high. Therefore, a text recognition using Improved Dual-attention based on Textual Double Embedding (IDTDE) with aquila optimization algorithm is proposed in this manuscript for effective text recognition. In this method the input image is taken from several datasets. Usually, the images have some kind of noise in it, and to eliminate that, the Structural interval gradient filtering preprocessing technique is used. Then, the ternary pattern and discrete wavelet technique is use to extract best features. Next, residual-based temporal attention convolutional neural network is utilized for the text classification and character identification are effectively attained by and IDTDE network. The Aquila optimization algorithm is used to optimize the network for best extracted text as output. Experimental outcomes demonstrate that the introduced approach accomplishes the high accuracy rates of 98.14%, 98.89%, and 90.47% on the IIIT5K, ICDAR 2013, and ICDAR 2015 datasets, respectively, surpassing the performance of existing frameworks. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Aquila optimizer Character recognition Gradient filtering Improved self-attention Text recognition

来源：评论

学校读者我要写书评

暂无评论

The Threat of Quantum Computing to the Cryptographic Security of Blockchain 2

The Threat of Quantum Computing to the Cryptographic Securit...

引用

2nd International Conference on Emerging Trends in information technology and engineering, ic-ETITE 2024

作者： Modi, Pranit Asgola, Abhishek Mishra, Hiya Charanya, R. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore Vellore India

ISBN: (纸本)9798350328202

Blockchain technology, born as the backbone of cryptocurrencies like Bitcoin, has rapidly expanded into a versatile platform spanning various industries. This review paper delves into the critical aspects of security and anonymity within blockchain applications. It simplifies complex technical concepts while exploring the foundation of blockchain security, including cryptography, decentralization, consensus mechanisms, and the challenges posed by smart contracts. Additionally, it examines the pseudonymous nature of blockchain addresses, privacy-enhancing cryptocurrencies, and the delicate balance between transparency and anonymity. As we navigate these intricacies, we address challenges such as scalability, regulatory concerns, and potential threats from quantum computing. This paper aims to provide a comprehensive yet easily digestible understanding of the security and anonymity dimensions in blockchain applications. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Twin attention based multi-task convolutional bidirectional long short term memory for facial expression recognition

引用

Multimedia Tools and Applications 2025年第10期84卷 8037-8070页

作者： Sreenivas, Velagapudi Sivaneasan, B. Vani, K. Suvarna Chakrabarti, Prasun Singapore Institute of Technology Singapore138683 Singapore Engineering Cluster Singapore Institute of Technology Singapore138683 Singapore Department of Computer Science and Engineering AI/ML Research Group Head VR Siddhartha Engineering College Andhra Pradesh Vijayawada520007 India Department of Computer Science and Engineering Sir Padampat Singhania University Rajasthan Udaipur313601 India

Facial Expression Recognition (FER) aims to detect the emotional state of facial images. It is playing an increasingly important role in several application areas, including human–computer interaction (HCI), video transcriptions, and social communications. This article provides an adequate attention-based multi-task deep learning method for facial expression recognition. First, the input videos are collected from the RAVDESS and MELD datasets. Then, the input videos are converted using a threshold-based keyframe extraction algorithm. Next, the input data is pre-processed using the Adaptive Pixel Density Median Filtering (A-PDMF) method. Key features such as shape, color and texture are extracted from the pre-processed images. Finally, the facial expressions are recognized by proposing a novel twin attention-based multi-task convolutional bidirectional long-short-term memory method (TA-MC-BiLSTM). In addition, the classification parameters are optimally tuned using the EX-AHA method (Extended Artificial Hummingbird Algorithm). The proposed model reduces the size of facial features while accurately identifying the wide range of facial expressions. For simulation, the proposed method prefers python tool and results are analyzed using RAVDESS and MELD datasets. The simulation results show that the proposed model provides better results than other existing models in terms of accuracy of 99.6% for RAVEDESS and 99.4% for MELD. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Pixels

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：