检索结果-内蒙古大学图书馆

2nd International Conference on Intelligent Perception and Computer Vision, CIPCV 2024

作者： Addo, Daniel Al-Antari, Mugahed A. Zhou, Shijie Ashalley, Eric Muoka, Gladys Wavinya Nartey, Obed T. University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China Sejong University Seoul AISSLab Department of Artificial Intelligence and Data Science Korea Republic of University of Electronic Science and Technology of China Institute of Fundamental and Frontier Science Chengdu610054 China ChengduUniversity of Technology of China Sino-British Collaborations Erxianqiao Campus Chengdu610059 China

ISBN: (纸本)9798350360097

Alzheimer's disease (AD) presents a formidable challenge in healthcare, characterized by its progressive nature and the absence of definitive diagnostic markers. This study introduces an innovative method to enhance AD detection by integrating advanced technology with established techniques. We have developed a hybrid model that combines Gabor Convolutional Neural Networks (GCNN) with traditional Convolutional Neural Networks (CNNs) to improve feature extraction from MRI images, thereby achieving a more precise diagnosis of AD. The efficacy of our model is evidenced by its high-performance metrics: an accuracy of 98.58%, a sensitivity of 98.17%, a precision of 97.11%, and robust empirical support. This approach benefits from the use of augmented data and the unique capabilities of GCNN. Comprehensive evaluations, including confusion matrix analysis and ROC curve assessments, confirm the model's proficiency in accurately classifying various stages of dementia. By enhancing diagnostic accuracy, this innovative approach holds the potential to improve patient outcomes, facilitate better care, and enable more timely interventions in the treatment of Alzheimer's disease. © 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

VAE Latent Space Quantization Methods for UAVs Video Stream 8

VAE Latent Space Quantization Methods for UAVs Video Stream

引用

8th International Conference on Information, Control, and Communication Technologies, ICCT 2024

作者： Chenskiy, Alexander Berezkin, Alexander Vivchar, Roman Kirichek, Ruslan Kukunin, Dmitry Bonch-Bruevich Saint-Petersburg University of Telecommunications Advanced Projects and Developments Department Saint-Petersburg Russia Bonch-Bruevich Saint-Petersburg University of Telecommunications Software Engineering and Computer Science Department Saint-Petersburg Russia Bonch-Bruevich Saint-Petersburg University of Telecommunications Communication Networks and Data Transmission Department Saint-Petersburg Russia

ISBN: (纸本)9798331517564

In FPV control of unmanned aerial vehicles, video frames are transmitted to the external pilot's station via a down link. Down links utilize mobile and hybrid orbital-terrestrial communication networks. The efficiency increase in their utilization is achieved by reducing the required bandwidth for each FPV-controlled unmanned aircraft. This requires ensuring a high compression rate of video stream frames, for which methods based on the application of variational autoencoders can be used. The principle of their operation is as follows: encoding frames into latent space, quantization and lossless compression. This paper presents new quantization algorithms and investigates the effect of applying different quantization algorithms to compression rate of latent space of VQ-D6 variational autoencoder from Stable Diffusion during further lossless compression using LZMA algorithm. In the result, the most effective quantization is selected to be used together with lossless compression. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Detection of Toxic Content on Social Networking Platforms Using Fine Tuned ULMFiT Model

引用

Intelligent Automation & Soft Computing 2023年第1期35卷 15-30页

作者： Hafsa Naveed Abid Sohail Jasni Mohamad Zain Noman Saleem Rao Faizan Ali Shahid Anwar Department of Software Engineering Faculty of ScienceUniversity of LahorePakistan Department of Computer Science COMSATS University IslamabadLahore CampusPakistan Institute for Big Data Analyics and Artifcial Intelligence(IBDAAI) Kompleks Al-KhawarizmiUniversii Tekoogi MARA40450Shah AlamSelangorMalaysia TechnoGenics SMC PVT LTD LahorePakistan Department of Computer and Infomation Science Universiti Teknologi PETRONASBandar Ser IskandarTronohPerakMalaysia Depatment of Information Engineering Technology National Skils University IslamabadSector H-8/1Faiz AhmedFaiz RoadIslamabadPakistan

Question and answer websites such as Quora,Stack Overflow,Yahoo Answers and Answer Bag are used by *** users post questions on these websites to get the answers from domain specific *** websites are multilingual meaning they are available in many different *** problem for these types of websites is to handle meaningless and irrelevant *** this paper we have worked on the Quora insincere questions(questions which are based on false assumptions or questions which are trying to make a statement rather than seeking for helpful answers)dataset in order to identify user insincere questions,so that Quora can eliminate those questions from their platform and ultimately improve the communication among users over the ***,a research was carried out with recurrent neural network and pretrained glove word embeddings,that achieved the F1 score of *** proposed study has used a pre-trained ULMFiT *** model has outperformed the previous model with an F1 score of 0.91,which is much higher than the previous studies.

关键词： Machine learning text mining quora mining artificial intelligence natural language processing

来源：评论

学校读者我要写书评

暂无评论

Multiobjective Many-Tasking Evolutionary Optimization using Diversified Gaussian-Based Knowledge Transfer

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Lin, Qiuzhen Wang, Qianhui Chen, Baihao Ye, Yulong Ma, Lijia Tan, Kay Chen Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The Hong Kong Polytechnic University Department of Data Science and Artificial Intelligence Hong Kong Hong Kong

Multiobjective multitasking evolutionary algorithms have shown promising performance for tackling a set of multiobjective optimization tasks simultaneously, as the optimization experience gained within one task can be transferred to accelerate the solving of others. However, most studies only select similar transfer tasks based on their designed metrics, which become less efficient when tackling a large number of optimization tasks, as their transferred knowledge may be insufficiently diversified. To alleviate this issue, this article proposes a Multiobjective Many-Tasking Evolutionary Algorithm using Diversified Gaussian-based knowledge Transfer, named MMaTEA-DGT. In this algorithm, a diversified transfer selection strategy is presented to choose a number of similar and complementary source tasks for knowledge transfer. Then, based on the above diversified source tasks, a Gaussian-based transfer strategy is designed to transfer their various optimization knowledge. In this way, MMaTEA-DGT is more effective in transferring optimization knowledge to speed up the solving of many tasks. Experimental studies on both the benchmark suites and a real-world dynamic vaccine prioritization problem have indicated the superiority of MMaTEA-DGT over some recently proposed multiobjective many-tasking evolutionary algorithms. © 1997-2012 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Predicting Pre-Owned Bike Values with Machine Learning Techniques in Bangladesh

Predicting Pre-Owned Bike Values with Machine Learning Techn...

引用

data science and Network Security (ICDSNS), International Conference on

作者： Kazi Hassanul Ferdous Md.Shohel Arman Kazi Rifat Ahmed Nusrat Tasnim Imran Mahmud P. Revathi Department of Software Engineering DIU Data Science Lab Daffodil International University Dhaka Bangladesh Department of Computer Science Holy Cross College Tiruchirapalli Tamilnadu India

ISBN: (数字)9798350373110

ISBN: (纸本)9798350373127

As the importance of sustainable practices in the automobile sector grows, it's critical to anticipate motorcycle prices and offerings. With so many variables to consider when buying a secondhand motorcycle-condition, mileage, brand reputation, model characteristics, etc.-accurate pricing prediction is essential for both customers looking for good values and sellers hoping to maximize profits. This study investigates the effectiveness of four machine learning techniques Decision Tree models, Support Vector Regression (SVR), K-Nearest Neighbors (KNN), and Stochastic Gradient Descent (SGD) Regressions-in predicting motorcycle prices using a dataset obtained from motorcycle merchants. It's noteworthy that these methods are used with a hybrid architecture to improve prediction accuracy. Different approaches are compared and contrasted to find the best fit for the given dataset, and the difficulties and roadblocks that come with them are also discussed. After extensive testing, the decision tree model's effectiveness is shown with an amazing 97% accuracy rate, providing accurate price estimates that are essential for encouraging sustainable habits in the ever-changing Internet of Things environment. With an impressive accuracy rate, this methodology provides precise pricing estimations, which are critical for supporting sustainable practices in the automotive industry.

关键词： Support vector machines Industries Accuracy Motorcycles Stochastic processes Pricing Predictive models Nearest neighbor methods data models Regression tree analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Multilabel Hateful Speech Text Comments Recognition and Classification Model for Resource Scarce Ethiopian Language: The case of Afaan Oromo

Deep Learning based Multilabel Hateful Speech Text Comments ...

引用

2022 IEEE International Conference on Current Development in engineering and Technology, CCET 2022

作者： Defersha, Naol Bakala Abawajy, Jemal Kekeba, Kula College of Electrical and Mechanical Engineering Centre of Excellence for Hpc & Big Data Analytics Addis Ababa Science and Technology Software Engineering Department 16417 Ethiopia School of Information Technology Deakin University Faculty of Science Engineering and Built Environment GeelongVIC3220 Australia Centre of Excellence College of Electrical and Mechanical Engineering Addis Ababa Science and Technology Department of Software Engineering Technology 16417 Ethiopia

ISBN: (纸本)9781665454155

In response to the phenomenon of hate speech on popular social media such as Facebook, a number of researchers have investigated and developed different automated techniques in order to detect and moderate hate speech. Reliable hate speech detection tools ranging from traditional machine learning models to deep neural network models have been developed and deployed for resource rich languages such as English, French and Arabic. On the Other hand, the topic of building automated techniques for hate speech detection in Afaan Oromo is still the subject of very limited studies. In this study, we have used pretrained word embedding approaches such as word2vec and fast text, and assessed their effectiveness for hateful speech recognition and classification in Afaan Oromo text comments on Facebook. By using the proposed model, the effectiveness of deep learning algorithms like CNN and LSTM was also assessed. Moreover, the significance of one of the recent topic modeling approaches, i.e., BERTopic, has been investigated to in extracting topics that can help the categorization of Afaan Oromo hate speech. Afaan Oromo Multilabel Hateful Speech Detection and dataset (AOMLHSDD), which contains 30728 text comments, was created after we employed the BERTopic to extract relevant topics. Accordingly, Then, we have conducted different experiments to test the effectiveness of CNN and LSTM models by using word2vec and fast text. The result of our experiments has shown showed that LSTM has outperformed the CNN approach by achieving the accuracy of 98.32%. © 2022 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

The Impact of Stuttering Event Representation on Detection Performance

The Impact of Stuttering Event Representation on Detection P...

引用

Cyber Resilience (ICCR), International Conference on

作者： Abedal-Kareem Al-Banna Hui Fang Ahmad F Shubita Mohammad Arafah Amani Eqteeshat Saif B Abuaisheh Department of AI and Data Science University of Petra Department of Computer Science Loughborough University Department of Software Engineering University of Petra Department of Computer Science University of Petra Department of Information System Malaya University

ISBN: (数字)9798350394962

ISBN: (纸本)9798350394979

Stuttering or stammering is a common neurogenic, psychogenic fluency disorder wherein people have uncontrolled blocks on the natural flow of speech. Automatic Stuttering Event Detection (SED) is a widely recognised challenge due to the heterogenic and overlapped nature of stuttering speech. Therefore, this comparative study investigates the impact of stuttering event representation on detection performance. The paper evaluates the performance of SED and shows the impact of employing ASR pre-trained feature extractions on each stuttering event. Moreover, the paper provides different groups of experiments that evaluate the impact of three acoustic features, the Zero Crossing Rate (ZCR), the Spectral Flux Onset Strength Envelope (SFO), and Fundamental Frequency (FF) features, on SED performance. The paper demonstrates that the fusion of spectral and ASR features improves SED performance across all stuttering events by 8%. The F1 score of the Block class increased by approximately 10%, from 15% to 25%, while the word repetition and interjection increased by 8%. In addition, our experiments proved that the fusion of temporal features increased the average F1 score of SED by 2% across all stuttering events. The F1 score of the prolongation and sound repetition classes increased by 6% and 3%, respectively.

关键词： Event detection Speech recognition Feature extraction Acoustics Robustness Time-domain analysis Mel frequency cepstral coefficient

来源：评论

学校读者我要写书评

暂无评论

Federated privacy computing based on oblivious transfer in financial applications: A case study in credit risk management 3

Federated privacy computing based on oblivious transfer in f...

引用

3rd International Symposium on Computer Applications and Information Systems, ISCAIS 2024

作者： Liang, Jian Quan, Fan Yang, Suyi Tao, Ping Ge, Fei Li, Hualin School of Software and Artificial Intelligence Chongqing Institute of Engineering Chongqing China Intelligent Application of Financial Big Data Chongqing Colleges Universities Engineering Research Center Chongqing China Shu Yi Xin Credit Management Co LTD Chongqing China School of Information and Communication Studies University College Dublin Dublin Ireland Department of Statistics and Data Science University of California Los Angeles United States

ISBN: (纸本)9781510681316

Invoice data is critical and highly sensitive for enterprises, yet it stands as one of the most extensively used data categories in the financial credit sector. Participants in the credit market, engaged in corporate lending activities, face the dual challenge of ensuring the security of enterprise invoice data and safeguarding the integrity of institutional rules. Traditional data computation and encryption present a dilemma, as two encrypted datasets cannot directly engage in calculations, and two datasets participating in calculations must be in plaintext. This necessitates the convergence of enterprise data and institutional rules for computation. Consequently, two sets of data must be exposed to one of the parties or a mutually trusted third party. In practice, identifying a genuinely trusted third party proves to be a formidable task. This paper introduces a federated privacy computing method based on an oblivious transfer algorithm in the context of risk control admission rules within the credit risk management field. This approach enables both parties holding data to determine admission rules without disclosing their own data. © 2024 SPIE.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

A Multiform Many-objective Evolutionary Algorithm for Multi-label Feature Selection in Classification

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Hancer, Emrah Xue, Bing Zhang, Mengjie Victoria University of Wellington Center for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Burdur Mehmet Akif Ersoy University Department of Software Engineering Burdur15039 Turkey

Multi-label classification (MLC) deals with instances associated with multiple labels simultaneously and often includes high dimensional data with noisy, irrelevant, and redundant features. Feature selection for MLC is crucial for achieving successful classification performance. However, no unified metric exists for evaluating learning performance in MLC tasks. Instead, multiple metrics exist, each assessing a different aspect of the classification process, and these metrics are often inconsistent with one another. Consequently, multi-label feature selection (MLFS) becomes a many-objective optimization problem (MaOP) when optimizing three or more classification metrics and the number of selected features simultaneously. Evolutionary computation (EC) techniques have shown great promise in addressing many-objective tasks due to their ability to effectively explore large and complex search spaces. EC techniques can handle multiple objectives concurrently, making them well-suited for the challenges posed by MLFS. Despite this potential, research on EC-based MLFS methods remains limited, with few studies treating it as a MaOP. To address this gap, this paper proposes a new many-objective evolutionary algorithm within a multiform framework. The proposed algorithm leverages distinct sub-populations to address specific MLFS tasks, incorporates a strategy to exchange information between MLFS tasks, employs a local density-based selection mechanism to maintain diverse high-quality solutions, and uses an adaptive parameter scheme inspired by stochastic gradient descent to guide the search towards new regions in the objective space. Experimental results demonstrate the superiority of the proposed algorithm across a diverse range of high-dimensional datasets, outperforming both recently introduced many-objective and conventional MLFS algorithms. © 1997-2012 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Communication-Efficient Federated Learning in Mobile Edge Environments

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Jia, Ninghui Qu, Zhihao Ye, Baoliu Wang, Yanyan Hu, Shihong Guo, Song Hohai University Key Laboratory of Water Big Data Technology of Ministry of Water Resources College of Computer Science and Software Engineering Nanjing211100 China Nanjing University State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing210023 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Kowloon Hong Kong

In traditional centralized machine learning, transmitting raw data to a cloud center incurs high communication costs and raises privacy concerns. This is particularly challenging in mobile edge environments, where devices are dynamic and resource-constrained. Federated Learning (FL) addresses these issues by allowing devices to train models locally and upload parameters to a central server without sharing local data. However, limited wireless channel resources and dynamic transmission performance make communication overhead a major bottleneck of FL in mobile edge environments. Concerning this challenge, this survey provides a comprehensive summary of methods to improve communication efficiency in FL, focusing on: 1) minimizing communication complexity to reduce total transmission volume, 2) scheduling resources appropriately to improve training efficiency, 3) utilizing over-the-air computation (OTA) to integrate computation into communication for accommodating the computation/communication characteristics of FL in mobile edge environments. Thus, this work analyzes research from the perspective of convergence and data heterogeneity to reduce communication rounds by optimizing algorithm performance. We hope that this survey could offer insights into communication-efficient FL for future research. © 2025 IEEE.

关键词： Federated 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：