检索结果-内蒙古大学图书馆

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Al-Banna, Abedal-Kareem Fang, Hui Shubita, Ahmad F. Arafah, Mohammad Eqteeshat, Amani Abuaisheh, Saif B. University Of Petra Department Of Ai And Data Science Jordan Loughborough University Department Of Computer Science United Kingdom University Of Petra Department Of Software Engineering Jordan University Of Petra Department Of Computer Science Jordan Malaya University Department Of Information System Malaysia

ISBN: (纸本)9798350394962

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. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Triboelectric nanogenerator based on silanecoupled LTA/PDMS for physiological monitoring and biomechanical energy harvesting

引用

Microsystems & Nanoengineering 2024年第5期10卷 393-405页

作者： Muhammad Umair Khan Deepa Dumbre Yawar Abbas Moh'd Rezeq Anas Alazzam Nahla Alamoodi Maryam Khaleel Baker Mohammad Department of Computer and Information Engineering Khalifa University.Abu DhabiUAE System on Chip Lab Khalifa UniversityAbu DhabiUAE Department of Chemical Engineering Khalifa UniversityAbu DhabiUAE Department of Physics Khalifa UniversityAbu DhabiUAE Department of Mechanical Engineering Khalifa UniversityAbu DhabiUAE Center for Catalysis and Separations Khalifa UniversityAbu DhabiUAE Research and Innovation Center on CO_(2)and H_(2) Abu DhabiUAE

Energy harvesting from ambient sources present in the environment is essential to replace traditional energy *** strategies can diversify the energy sources,reduce maintenance,lower costs,and provide near-perpetual operation of the *** this work,a triboelectric nanogenerator(TENG)based on silane-coupled Linde type A/polydimethylsiloxane(LTA/PDMS)is developed for harsh environmental *** silane-coupled LTA/PDMS-based TENG can produce a high output power density of 42.6μW/cm^(2) at a load resistance of 10 MQ and operates at an open-circuit voltage of 120 V and a short-circuit current of 15μA under a damping frequency of 14 ***,the device shows ultra-robust and stable cyclic repeatability for more than 30 k *** fabricated TENG is used for the physiological monitoring and charging of commercial capacitors to drive low-power electronic ***,these results suggest that the silane-coupled LTA/PDMS approach can be used to fabricate ultra-robust TENGs for harsh environmental conditions and also provides an effective path toward wearable self-powered microelectronic deVices.

关键词： PDMS energy harvesting

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion 38

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent D...

引用

38th Conference on Neural information Processing systems, NeurIPS 2024

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An earlier serial lactate determination analysis of cardiac arrest patients using a medical machine learning model

An earlier serial lactate determination analysis of cardiac ...

引用

2023 International Conference on Intelligent systems for Communication, IoT and Security, ICISCoIS 2023

作者： Mohammed, Mehmood Ali Mohammed, Murtuza Ali Mohammed, Vazeer Ali Logeshwaran, J. Jiwani, Nasmin University of the Cumberlands Dept. of Information Technology WilliamsburgKY United States Lewis University Dept.of Computer Information System IL United States Sri Eshwar College of Engineering Dept. of Electronics and Communication Engineering Coimbatore India

ISBN: (纸本)9798350335835

In general, cardiac arrest results in an inability to pump enough blood for the body's needs. Through this, the organs and tissues get enough oxygen and nutrients for their metabolic needs, and excess fluid accumulates. This further increases the severity of the patient's problems. Cardiac arrest is the leading cause of hospitalization in people over 65 and is therefore considered a significant public health problem. It is a pathology linked to an increase in average life expectancy, and its incidence is increasing every year due to the general ageing of the population. In this paper, an earlier serial lactate determination analysis of cardiac arrest patients using a medical machine learning algorithm. It can occur following an episode of cardiac arrest or inadequate treatment of chronic diseases, including diabetes and hypertension. Adopting lifestyle habits that prevent the onset of these conditions is an essential strategy for preventing heart failure. The proposed approach has achieved 91.58% accuracy, 87.96% precision, 84.62% recall, and 85.23% F1-score results compared to other methods. © 2023 IEEE.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

Automatic skin lesion classification using a novel densely connected convolutional network integrated with an attention module

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第7期14卷 8943-8956页

作者： Shan, Pufang Chen, Jialei Fu, Chong Cao, Lin Tie, Ming Sham, Chiu-Wing School of Computer Science and Engineering Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China School of Information and Communication Engineering Beijing Information Science and Technology University Beijing100101 China Science and Technology on Space Physics Laboratory Beijing100076 China School of Computer Science The University of Auckland Auckland New Zealand

Automated skin lesion classification in dermoscopy images remains challenging due to the existence of artefacts and intrinsic cutaneous features, diversity of lesion morphology, insufficiency of training data, and class imbalance problem. To address these challenges, we propose a new densely connected convolutional network termed AttDenseNet-121, which is obtained by integrating the convolutional block attention module (CBAM) into DenseNet-121. CBAM is a simple yet efficient attention module, which is further improved by adding a novel pooling layer (multiscale-pooling) to effectively enhance its attention capability. The optimized CBAM strengthens the representation power of DenseNet-121 by emphasizing meaningful features and suppressing unnecessary ones, thus significantly enhancing the classification performance. Besides, to handle the imbalanced dataset, we employ an improved focal loss function rather than the traditional cross-entropy loss function to train AttDenseNet-121. The improved focal loss is calculated from a different perspective compared with the original focal loss. It makes the distribution of positive samples and negative samples in each batch the same as that in the original data, successfully mitigating the negative influence of class imbalance on this multi-class classification task. We conduct extensive experiments on the public benchmark dataset (HAM10000) and the results indicate that our proposed method achieves superior performance compared with that of the baselines and state-of-the-art algorithms. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Genre Classification of Bangla Poem Using Machine Learning and Deep Learning Techniques

Genre Classification of Bangla Poem Using Machine Learning a...

引用

2023 IEEE World AI IoT Congress, AIIoT 2023

作者： Pasha, Syed Tangim Islam, Ashraful Rahman, Mohammed Masudur Ahmed, Eshtiak Ahmed Foysal, Md. Ferdouse Zahangir Alam, Md Daffodil International University Department of Computing and Information System Bangladesh Independent University Center for Computational and Data Sciences Bangladesh Independent University Department of Computer Science and Engineering Bangladesh International Standard University Department of Computer Science and Engineering Bangladesh Daffodil International University Department of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798350337617

The computational analysis of the Bangla poems is a challenging task due to the diverse linguistic, stylistic, and semantic features of the Bangla language. In this work, we prepared a dataset of 1311 Bangla poems of two separate categories: Love and Miscellaneous poem, which contain 500 and 811 poems respectively. We used word or semantic-based features to classify Bangla poems using the TF-IDF feature techniques. We used Logistic Regression, Naïve Bayes (NB), and Support Vector Machine (SVM) models for classification through machine learning, and we used Bayesian optimization techniques for hyperparameters tuning of these three models. We also used LSTM, CNN, and transformer models for this research. For the performance evaluation of the classification models, we used four evaluation metrics of precision, recall, F1-score, and accuracy. We also used the ROC-AUC curve to distinguish between all the machine learning and deep learning models. The experimental results expressed that, the transformer model achieved the highest accuracy compared to all the typical machine learning and deep learning models with an accuracy of 87%. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Unveiling Ethical Challenges and Malpractice in Academic Research and Integrity 3

Unveiling Ethical Challenges and Malpractice in Academic Res...

引用

3rd International Conference on Creative Communication and Innovative Technology, ICCIT 2024

作者： Singh Bist, Ankur Rawat, Bhupesh Rahardja, Untung Hardini, Marviola Kamal, Mustofa Graphic Era Hill University Faculty of Computer Science & Engineering Uttarakhand India Graphic Era Hill University Faculty of Computing Uttarakhand India University of Raharja Faculty of Information Technology Tangerang Indonesia University of Raharja Faculty of Computer System Tangerang Indonesia

ISBN: (纸本)9798350367492

In the pursuit of knowledge and innovation, academic research stands as a cornerstone of intellectual progress. However, the integrity of this process is susceptible to malpractice, raising profound ethical concerns. This research paper delves into the nuanced landscape of malpractice and ethical considerations within the realm of academic research, aiming to shed light on the challenges that undermine the credibility and reliability of scholarly endeavours. The study explores various forms of malpractice, including plagiarism, data fabrication, and authorship disputes, which have the potential to erode the foundations of academic integrity. Through a combination of literature reviews, case studies, and expert interviews, the research seeks to identify patterns and motivations behind such malpractices. The findings reveal that systematic solutions are necessary to address these issues, and propose the integration of advanced technological tools to enhance ethical oversight. This study contributes to the ongoing discourse on ethics in academic research by providing comprehensive insights and recommendations to uphold ethical standards. © 2024 IEEE.

关键词： Confidentiality Ethics Informed Consent Plagiarism Professional Misconduct

来源：评论

学校读者我要写书评

暂无评论

Decision-Making Method for Sound Volume Control in the 'Smart House' system 19

Decision-Making Method for Sound Volume Control in the 'Smar...

引用

19th IEEE International Conference on computer Science and information Technologies, CSIT 2024

作者： Hovorushchenko, Tetiana Aleksov, Serhii Boyarchuk, Artem Khmelnytskyi National University (KhNU) Computer Engineering and Information System Department Khmelnytskyi Ukraine Law School Tallinna Tehhnikaülikool (TalTech) Tallinn Estonia

ISBN: (纸本)9798331542627

The developed in this paper decision-making method for sound volume control in the 'Smart House' system provides automatic control of sound volume in the 'Smart House' system in order to prevent exceeding sound volume standards depending on the type of room and time of day, as well as to ensure a comfortable noise (sound volume) level in the appropriate room. The results of the experiment have shown that the developed decision-making method for sound volume control in the 'Smart House' system provides for the recognition of situations (optimal sound volume, high sound volume, unacceptable high sound volume) and automatic decision-making on sound volume control in a room of a certain type (automatic reduction of the sound volume of multimedia devices in the room to the maximum permissible level for it). © 2024 IEEE.

关键词： 'Smart House' system Cyberphysical system Decision-Making Noise Level Sound Volume Control

来源：评论

学校读者我要写书评

暂无评论

Significance of Internet-of-Things Edge and Fog Computing in Education Sector

Significance of Internet-of-Things Edge and Fog Computing in...

引用

2023 International Conference on Smart Computing and Application, ICSCA 2023

作者： Siddiqui, Shams Tabrez Khan, Mohammad Rafeek Khan, Zeba Rana, Nadim Khan, Haneef Alam, Md Imran College of Cs It Jazan University Department of Computer Science Jazan Saudi Arabia College of Cs It Jazan University Department of Computer and Network Engineering Jazan Saudi Arabia Computer and Information System Applied College Jazan University Jazan Saudi Arabia College of Computer Science and Information Technology Jazan University Jazan Saudi Arabia

ISBN: (纸本)9798350347050

IoT gadgets include smart lights, ovens, and industrial data-collecting equipment. IDC expects 41.6 billion connected IoT devices to generate 79.4 ZB of data by 2025. Early IoT devices sent data to the cloud for analysis. When sending trillions of gigabytes to the cloud, the data pipeline clogs. Edge computing enables IoT devices to handle data locally instead of sending it to the cloud. Data is processed at the 'edge' of your local network, rather than transferred away. Technology's versatility makes it valuable in education. IoT edge computing has different requirements than non-IoT edge computing. IoT devices have limited data processing and storage capabilities, thus processing must occur off the device. The edge offers an environment to manage huge numbers of IoT devices and data. Many functions can be off-loaded to the edge, reducing device cost. In education, IoT edge computing architecture has gained importance due to real-time applications. In order to facilitate the analysis of educational system architecture, this paper seeks to provide an IoT Edge computing framework in the field of education. The framework will identify IoT-related issues and concerns. This study discusses IoT Edge computing in education, identifies limits, and makes recommendations. As well as the paper evaluates IoT Edge computing's performance in educational systems. © 2023 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Impact of Advanced Innovations on Solar Panel Efficiency and Adoption 3

Impact of Advanced Innovations on Solar Panel Efficiency and...

引用

3rd International Conference on Creative Communication and Innovative Technology, ICCIT 2024

作者： Supriyono, Ignatius Agus Sudaryono Azizah, Nur Zakaria, Noor Azura Madani, Muchlishina University of Raharja Department of Computer System Tangerang Indonesia University of Raharja Department of Informatic Engineering Tangerang Indonesia University of Raharja Department of Information Systems Tangerang Indonesia International Islamic University Malaysia Department of Computer Science Selangor Kuala Lumpur Malaysia

ISBN: (纸本)9798350367492

The rapid advancement of new technologies has significantly impacted the solar energy industry. This study explores how innovative technologies such as artificial intelligence (AI), the Internet of Things (IoT), and advanced materials affect the performance and adoption of solar panels. Using data from global solar panel manufacturers and adoption rates from 2010 to 2023, we aim to show how these technologies improve efficiency, reduce costs, and drive widespread adoption. Our findings indicate that integrating AI and IoT into solar panel systems significantly boosts efficiency by optimizing energy output and predictive maintenance. Advanced materials, especially in photovoltaic cells, have greatly improved energy conversion rates. These advancements lower production and maintenance costs and enhance the reliability and lifespan of solar panels, making them more attractive to consumers and investors. Regions with supportive regulations and financial incentives see higher adoption rates and better performance improvements. This research provides valuable insights for policymakers, industry stakeholders, and researchers, highlighting the importance of technological innovation in achieving sustainable energy goals. By addressing key factors that influence solar panel performance and adoption, this study contributes to the broader discussion on renewable energy development and the transition to a low carbon economy. Future research should focus on long-term studies to assess the lasting impacts of these technologies on the solar energy market. © 2024 IEEE.

关键词： Adoption Rates Advanced Materials Cost Reduction Efficiency Impact Innovative Technologies Regulatory Frameworks

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：