检索结果-内蒙古大学图书馆

A Survey on Image Semantic Segmentation Using Deep Learning Techniques

computers, Materials & Continua 2023年第1期74卷 1941-1957页

作者： Jieren Cheng Hua Li Dengbo Li Shuai Hua Victor S.Sheng School of Computer Science and Technology Hainan UniversityHaikou570228China School of Cyberspace Security(School of Cryptology) Hainan UniversityHaikou570228China Hainan Blockchain Technology Engineering Research Center Hainan UniversityHaikou570228China Department of Computer Science Texas Tech University TX 79409USA

Image semantic segmentation is an important branch of computer vision of a wide variety of practical applications such as medical image analysis,autonomous driving,virtual or augmented reality,*** recent years,due to the remarkable performance of transformer and multilayer perceptron(MLP)in computer vision,which is equivalent to convolutional neural network(CNN),there has been a substantial amount of image semantic segmentation works aimed at developing different types of deep learning *** survey aims to provide a comprehensive overview of deep learning methods in the field of general image semantic ***,the commonly used image segmentation datasets are ***,extensive pioneering works are deeply studied from multiple perspectives(e.g.,network structures,feature fusion methods,attention mechanisms),and are divided into four categories according to different network architectures:CNN-based architectures,transformer-based architectures,MLP-based architectures,and ***,this paper presents some common evaluation metrics and compares the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value on the most widely used ***,possible future research directions and challenges are discussed for the reference of other researchers.

关键词： Deep learning semantic segmentation CNN MLP transformer

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Pseudo-Labeling for Unsupervised Meta-Learning

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5475-5488页

作者： Ouyang, Tianran Dong, Xingping Ye, Mang Du, Bo Shao, Ling Shen, Jianbing Wuhan University School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China University of Chinese Academy of Sciences UCAS-Terminus AI Lab Beijing101408 China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science 314100 China

In unsupervised meta-learning, the clustering-based pseudo-labeling approach is an attractive framework, since it is model-agnostic, allowing it to synergize with supervised algorithms to learn from unlabeled data. However, the pseudo-labels suffer from clustering noise and semantic chaos problems, further impacting the effectiveness of meta-learning. In this paper, we analyze and optimize the pseudo-labeling process, including encoding and clustering, aiming to generate semantic-like pseudo-labels to narrow the gap between unsupervised and supervised meta-learning. First, during the encoding, we observe that the embedding space of existing methods lacks clustering-friendly properties, which is the primary reason for clustering noise. To address this issue, we minimize the inter-to-intra-class similarity ratio to generate clustering-friendly embedding features and validate our approach through comprehensive experiments. Then, during the clustering, we find that the semantic quality of pseudo-labels is not adequately controlled, resulting in semantic chaos of pseudo-labels. We propose a semantic-stability index to measure the semantic quality of pseudo-labels quantitatively. Based on this index, we propose the Semantic-aware Pseudo-label Reassignment mechanism to generate semantic-like pseudo-labels for all samples. Our approach is model-agnostic and can easily be integrated into existing supervised methods. To demonstrate its generalization ability, we integrate it into two representative algorithms: MAML and EP. The results on three main few-shot benchmarks clearly show that the proposed method achieves significant improvement compared to state-of-the-art models. Notably, our approach also outperforms the corresponding supervised method in three tasks. © 1979-2012 IEEE.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Determination of Suitable Heats ink Layout for a High-Density Integrated Motor Drive Through an Effective Comparison Method

Determination of Suitable Heats ink Layout for a High-Densit...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Venkata Raghavendra, I. Lyu, Yanda Wang, Fred Chatterjee, Debanjan Cairoli, Pietro The University of Tennessee Department of Electrical Engineering and Computer Science KnoxvilleTN United States Abb Inc Us Corporate Research Center Raleigh United States

ISBN: (纸本)9798350376067

Integrated Motor Drives (IMDs), play a pivotal role in the ever-evolving landscape of technological advancements in fields such as electric transportation and industrial environments. IMDs face challenges managing heat dissipation from drive-switching devices, especially due to confined spaces and dynamic loads, intensified by elevated temperatures near motor heat sources. To overcome thermal challenges, Wideband gap devices are crucial for minimizing losses and enabling diverse heatsink layout configurations within natural cooling. This paper introduces a thermal design approach that employs an analytical thermal model to select extruded heatsinks. The heatsink lengths are then fine-tuned to limit device junction temperatures under dynamic load variations across various heatsink layout configurations. The validation of the analytical and CFD models is then demonstrated through experimental setup. Subsequently, for a 2-level VSI device placement, a comparative analysis is conducted on the heatsink designs selected across various layout configurations, with endeavours focused on identifying the layout configuration that gives out the highest power density. © 2024 IEEE.

关键词： Thermal modeling

来源：评论

学校读者我要写书评

暂无评论

Real-time deep learning-assisted mechano-acoustic system for respiratory diagnosis and multifunctional classification

引用

npj Flexible Electronics 2024年第1期8卷 192-203页

作者： Hee Kyu Lee Sang Uk Park Sunga Kong Heyin Ryu Hyun Bin Kim SangHoon Lee Danbee Kang Sun Hye Shin Ki Jun Yu Juhee Cho Joohoon Kang Il Yong Chun Hye Yun Park Sang Min Won Department of Electrical and Computer Engineering Sungkyunkwan UniversitySuwonRepublic of Korea Department of Clinical Research Design and Evaluation SAIHSTSungkyunkwan UniversitySeoulRepublic of Korea Patient-Centered Outcomes Research Institute Samsung Medical CenterSeoulRepublic of Korea Center for Clinical Epidemiology Samsung Medical CenterSeoulRepublic of Korea Division of Pulmonary and Critical Care Medicine Department of MedicineSamsung Medical CenterSungkyunkwan University School of MedicineSeoulRepublic of Korea School of Electrical and Electronic Engineering Yonsei UniversitySeoulRepublic of Korea School of Advanced Materials Science and Engineering Sungkyunkwan UniversitySuwonRepublic of Korea Center for Neuroscience Imaging Research Institute for Basic ScienceSuwonRepublic of Korea

Epidermally mounted sensors using triaxial accelerometers have been previously used to monitor physiological processes with the implementation of machine learning(ML)algorithm *** findings from these previous studies have established a strong foundation for the analysis of highresolution,intricate signals,typically through frequency domain *** this study we integrate a wireless mechano-acoustic sensor with a multi-modal deep learning system for the real-time analysis of signals emitted by the laryngeal prominence area of the thyroid cartilage at frequency ranges up to 1 *** interface provides real-time data visualization and communication with the ML server,creating a system that assesses severity of chronic obstructive pulmonary disease and analyzes the user’s speech patterns.

关键词： system diagnosis mounted

来源：评论

学校读者我要写书评

暂无评论

A Dual-Core Dual-Mode Class-F VCO With Wide Frequency Tuning Range Using Wide Inductance-Switching-Range Inductor

引用

IEEE Microwave and Wireless Technology Letters 2025年第4期35卷 460-463页

作者： Hou, Yaru Li, Runlong Chi, Pei-Ling Yang, Tao University of electronic Science and Technology of China Chengdu610036 China Sichuan Province Engineering Research Center for Broadband Microwave Circuit High Density Integration Chengdu610036 China University of Electronic Science and Technology of China School of Electronic Science and Engineering Sichuan Chengdu610054 China National Yang Ming Chiao Tung University Department of Electrical and Computer Engineering Hsinchu300 Taiwan

A novel dual-core dual-mode class-F voltage-controlled oscillator (VCO) with wide frequency tuning range (TR) is proposed in this letter. It consists of two coupled parallel "8"-shaped inductor and two crossed-coupled VCO cores. To increase the TR of the proposed VCO without adding additional footprint size, a single-turn common-mode inductor is embedded inside the "8"-shaped inductor. By controlling the mode switches, the inductor can work in different modes with large inductance difference, realizing large VCO TR consequently. Then, the two coupled inductors were engineered to form the fundamental and third harmonic resonances, respectively, thereby producing a pseudo-square wave output waveform and realizing class-F operation. With the proposed configuration, the phase noise (PN) of the proposed VCO can be significantly reduced without increasing VCO core size. To demonstrate the proposed idea, a VCO prototype is fabricated in a 65-nm CMOS process with a core size of 1.235×0.8mm. It achieves a wide frequency TR from 2.84 to 7.04 GHz. The measured PN at 1-MHz offset is from -123.9 to -113.1 dBc/Hz, demonstrating an FOMT of 196.0-201.3 dBc/Hz. © 2023 IEEE.

关键词： Variable frequency oscillators

来源：评论

学校读者我要写书评

暂无评论

Explainable AI for Healthcare: An Approach Towards Interpretable Healthcare Models 24

Explainable AI for Healthcare: An Approach Towards Interpret...

引用

24th International Arab Conference on Information Technology, ACIT 2023

作者： Zahoor, Kanwal Bawany, Narmeen Zakaria Ghani, Usman Jinnah University for Women Institute of Business Administration Center for Computing Research Department of Computer Science and Software Engineering Karachi Pakistan

ISBN: (纸本)9798350384307

Artificial intelligence (AI) along with deep learning techniques has become an integral part of almost all aspects of life. One of the domains significantly impacted by this technological revolution is healthcare. Deep learning-based AI systems assist clinicians and medical professionals in disease diagnosis, personalized treatment, and monitoring through wearables, among other applications. Despite its expedient integration in healthcare, the trustworthiness of deep learning models remains a concern, primarily due to a lack of understanding of their underlying processes. However, Explainable AI (XAI) offers explanations through various methods, including Local Interpretable Model-agnostic Explanations (LIME), Shapley Additive explanation (SHAP), and GRAD-CAM. XAI is utilized to enhance transparency, allowing users to understand and trust AI decisions. In this study, we present deep learning models for the classification of pneumonia disease in Chest X-ray Images followed by their explanations. Convolutional Neural Networks (CNNs) and other pre-trained models, including VGG16, MobileNetV3, and ResNet50, were used for classification of images as 'normal' or 'pneumonia'. The VGG16 model, known for its exceptional image understanding capabilities, achieved the highest accuracy, with an impressive 93% score. Further, we used XAI techniques including SHAP, LIME, and Grad-CAM for explanation of models. LIME and Grad-CAM provided more accurate results than SHAP in our experiments. This approach was taken to evaluate the fairness and transparency of the model. The insights gained from XAI can be used to refine and improve machine learning models by identifying areas of weakness or misinterpretation which increases overall model robustness. © 2023 IEEE.

关键词： Deep learning Explainable AI Grad-CAM Healthcare LIME SHAP Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Android Malware Detection and Classification using Stacked Machine Learning 4

Android Malware Detection and Classification using Stacked M...

引用

4th International Conference on Distributed Sensing and Intelligent Systems, ICDSIS 2023

作者： Nawshin, Faria Gad, Radwa Unal, Devrim Suganthan, Ponnuthurai Nagaratnam KINDI Center for Computing Research College of Engineering Qatar University Doha Qatar Department of Computer Science & Engineering College of Engineering Qatar University Doha Qatar

ISBN: (纸本)9781839539954

The widespread use of Android smartphones in daily life can be attributed to the extensive prevalence stemming from the Android OS and the availability of open-source applications. People have become accustomed to performing various tasks, such as online banking transactions, scheduling appointments, attending virtual meetings and classes, and online shopping, on their mobile devices instead of computers. However, the significant use of mobile phones also presents opportunities for attackers to access sensitive and confidential information without the user’s knowledge. Intruders often use malicious applications found on the Google Play Store and other third-party app markets. The increased volume of Android malware in recent years has severely threatened human privacy and security. In this paper, we present a novel solution that utilizes a stacking ensemble machine learning approach to detect whether an application is malware or benign, which achieved 98% accuracy and F1-Score, and to identify the malware category with 96% accuracy and F1-Score. We conducted the experiment on the CCCS-CIC-AndMal-2020 dataset, which comprises 27,125 samples. Static features such as permissions, meta-data, and intents were analyzed, and the performance of standard machine learning algorithms was compared to our proposed model. Our results demonstrate that the stacked ensemble model shows promising results for malware detection (binary classification) and malware type classification (multi-class classification). © 2024 The Author(s).

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Audio-guided implicit neural representation for local imagestylization

引用

Computational Visual Media 2024年第6期10卷 1185-1204页

作者： Seung Hyun Lee Sieun Kim Wonmin Byeon Gyeongrok Oh Sumin In Hyeongcheol Park Sang Ho Yoon Sung-Hee Hong Jinkyu Kim Sangpil Kim Department of Artificial Intelligence Korea UniversitySeoul 02841Republic of Korea NVIDIA Research Nvidia CorporationSanta ClaraCA 95051USA Graduate School of Culture Technology KAISTSeoul 34141Republic of Korea Hologram Research Center Korea Electronics Technology InstituteSeoul 03924Republic of Korea Department of Computer Science and Engineering Korea UniversitySeoul 02841Republic of Korea

We present a novel framework for audio-guided localized image *** often provides information about the specific context of a scene and is closely related to a certain part of the scene or ***,existing image stylization works have focused on stylizing the entire image using an image or text *** a particular part of the image based on audio input is natural but *** work proposes a framework in which a user provides an audio input to localize the target in the input image and another to locally stylize the target object or *** first produce a fine localization map using an audio-visual localization network leveraging CLIP embedding *** then utilize an implicit neural representation(INR)along with the predicted localization map to stylize the target based on sound *** INR manipulates local pixel values to be semantically consistent with the provided audio *** experiments show that the proposed framework outperforms other audio-guided stylization ***,we observe that our method constructs concise localization maps and naturally manipulates the target object or scene in accordance with the given audio input.

关键词： audio guidance image style transfer implicit neural representations(INR)

来源：评论

学校读者我要写书评

暂无评论

Synergistic Design and Analysis of a Multi-Tasking Robot Enabling Artificial Intelligence for Hazard Response 23

Synergistic Design and Analysis of a Multi-Tasking Robot Ena...

引用

23rd International Conference on Control, Automation and Systems, ICCAS 2023

作者： Rahman, Md Hasibur Al Monir, Md Fayed Shihab, Rahat Hasan Ahammed, Fatin Ishraq Uddin, Mohammad Faisal Hasan, Mahady Islam, Rubaiyat Alam, Saadia Binte Independent University Department of Computer Science & Engineering Dhaka Bangladesh RIoT Research Center Independent University of Bangladesh Dhaka Bangladesh

ISBN: (纸本)9788993215274

This research paper presents a comprehensive study on designing and implementing a hyper-multifunctional robot tailored for hazard response and surveillance tasks. The development of the robot involved a meticulously planned and executed methodology, encompassing the design and construction of a sophisticated machine composed of 25 individual parts. The robot had cutting-edge sensing capabilities and mechanisms to perform multiple tasks simultaneously. Key components integrated into the robot included an image recognition camera, a water pump controller, and a servo controller, enabling three degrees of freedom. The primary control hub was based on an Atmega328p AVR microcontroller and esp32, and the control units were interconnected via a low-cost Bluetooth communication system. The prototype successfully demonstrated the significance of meticulous design and thoughtful consideration of each component, resulting in seamless interaction and the creation of a highly functional robot. Object detection was achieved using Yolo NAS, while HSV color space was employed for fire detection. The project's prospects encompass the utilization of more accurate servos, the installation of sensors for automated firefighting capabilities, and the reduction of latency by adopting wireless protocols like Esp32 radio frequencies. © 2023 ICROS.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

AcLGB: A Lightweight DDoS Attack Detection Method 7th

AcLGB: A Lightweight DDoS Attack Detection Method

引用

7th International Conference on Information science, Communication and Computing, ISCC 2023

作者： Zeng, Fantao Cheng, Jieren Cao, Zhuyun Yang, Yue Sheng, Victor S. School of Computer Science and Technology Hainan University Haikou570228 China Hainan Blockchain Technology Engineering Research Center Haikou570228 China Department of Computer Science Texas Tech University TX79409 United States

ISBN: (纸本)9789819971602

With the development of Internet technology, distributed denial of service(DDoS) attack has always been a hot and difficult point in network *** network infrastructure and information security is also becoming more and more ***, cyber security is an arms race, as attacks develop and network traffic surges, intelligent solutions face the challenge of detecting sensitive changes in traffic *** this paper, we propose a lightweight Adaptive Clustering-based LightGBM(AcLGB) detection *** is a new DDoS traffic classification method and an effective lightweight detection *** introduce a new clustering technique to learn the clustering centers that can be used to extend the characteristics of a given *** solves the challenge of difficult detection when traffic characteristics change *** model separates the samples of different categories in the best way, and outperforms the current detection method with 99.98% detection accuracy. In the CIC-DDoS2019 data set, the detection time of 802s is better than other detection methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Denial-of-service attack

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：