检索结果-内蒙古大学图书馆

Enhancing cardiac diagnostics through semantic-driven image synthesis: a hybrid GAN approach

NEURAL COMPUTING & APPLICATIONS 2024年第14期36卷 8181-8197页

作者： Gurusubramani, S. Latha, B. Sri Sairam Engn Coll Dept Comp Sci & Engn Chennai 600044 India

Cardiac image synthesis and analysis are pivotal in modern healthcare for accurate diagnosis and treatment of cardiovascular conditions. This study introduces a pioneering approach-hybrid GAN with semantic resonance-for the generation and analysis of synthetic cardiac images. Drawing from a diverse dataset encompassing local and global views, acquired through various modalities like MRI, CT, and echocardiography, the critical need for both accuracy and clinical relevance in cardiac image synthesis is addressed. In the architectural setup, a hybrid GAN is defined, comprising both local and global components. The local generator excels in capturing intricate details, while the global generator contextualizes the overall cardiac structure. A fundamental innovation lies in the incorporation of pre-trained CNN classifiers specialized in recognizing cardiac pathologies, anatomical structures, and clinical features. These classifiers provide conditional guidance to the generators, ensuring that the synthesized images align semantically with clinical expectations. The training phase employs a pioneering approach, integrating real-time feedback from the classifiers to steer the image synthesis process. The generators, discriminators, and classifiers are optimized, with a dual emphasis on adversarial loss for authenticity and classification loss for diagnostic significance. The accuracy obtained by the proposed approach is 98.96%. Further, the SSIM and PSNR values attained by the proposed approach are 0.955 and 45.23, which is higher than the existing approaches like GAN, CNN, VAE, DenseNet, VGG19, deepCardiac, Pix2Pix GAN and Cycle-GAN, respectively. Validation on an independent test dataset underscores the generalization capabilities of the proposed hybrid GAN. Furthermore, post-processing techniques refine the generated images, elevating their clinical relevance. Results visualization presents the prowess of the proposed approach, providing a holistic view of local and glo

关键词： Heart disease Machine learning Artificial intelligence Generative adversarial network Variational autoencoders Data augmentation Denoising Convolutional neural network Upsampling and cardiac images

来源：评论

学校读者我要写书评

暂无评论

deep learning-based Visual Recognition System for Fruit-Picking Robots 11

Deep Learning-based Visual Recognition System for Fruit-Pick...

引用

11th IEEE International Conference on Cybernetics and Intelligent Systems (CIS) / 11th IEEE International Conference on Robotics, Automation and Mechatronics (RAM)

作者： Ma, Rui Liu, Yihan Wu, Qike Zhang, Shaoru Wang, Nan Zhang, Jielu Luo, Fang Lin Hebei Normal Univ Coll Engn Shijiazhuang 050024 Hebei Peoples R China Jiangsu Tailong Reducer Co LTD Hebei Prov Innovat Ctr Wireless Sensor Network Da Taizhou 225400 Peoples R China Jiangsu Tailong Reducer Co LTD Taizhou 225400 Jiangsu Peoples R China Jiangsu Tailong Reducer Co LTD Taizhou 050024 Peoples R China Nanyang Technol Univ NTU Sch Elect & Elect Engn Nanyang Ave Singapore 639798 Singapore

ISBN: (纸本)9798350364200;9798350364194

Fruit recognition plays an important role in automated picking, in order to improve the accuracy and real-time picking, this study uses deep learning methods to design a fruit-picking robot visual recognition system. First, multiple preprocessing methods are used to expand the sample data, and the images are proportionally cropped and scaled to make the image dataset more complete;subsequently, to improve the accuracy of image recognition, a multilayer Convolutional Neural Networks (CNN) is established;and the Adam algorithm is utilized to train the model parameters several times to determine the optimal hyperparameters, thus overcoming the defects of the multilayer neural network that has a local optimal search. The experimental results show that compared with the random forest method, this system has the characteristics of high-speed recognition and high accuracy in fruit picking, and can quickly and accurately recognize fruit images, with the recognition speed of a single image taking only 0.081 seconds, and the recognition accuracy reaching more than 97.35%. The method has important theoretical and application value and provides an effective means for automatic fruit recognition.

关键词： Fruit-picking robot deep learning Object recognition image detection

来源：评论

学校读者我要写书评

暂无评论

MUTUALITY ATTRIBUTE MAKES BETTER VIDEO ANOMALY DETECTION 49

MUTUALITY ATTRIBUTE MAKES BETTER VIDEO ANOMALY DETECTION

引用

49th IEEE International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Han, Xingshuo Wang, Xiao Jiang, Kui Liu, Wei Hu, Ruimin Pan, Xuefeng Xu, Xin Wuhan Univ Sci & Technol Sch Comp Sci & Technol Wuhan Peoples R China Wuhan Qingchuan Univ Sch Comp Sci Inst Wuhan Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin Peoples R China Wuhan Univ Sch Comp Sci Wuhan Peoples R China

ISBN: (纸本)9798350344868;9798350344851

Video anomaly detection (VAD) is an essential but challenging task. Existing prevalent methods focus on analyzing the reconstruction or prediction difference between normal and abnormal patterns through multiple deep features, e.g., optic flow. However, these approaches independently use deep features to characterize attributes, ignore the mutuality among multiple deep features. Therefore, the constructed representation is limited to indirectly representing the anomaly from isolated attributes, and makes the network difficult to capture the high-level causes of anomaly. In this paper, we proposed a novel Mutuality Attribute-based Representation framework (MAR-VAD) for the VAD task, which absorbs the mutuality among deep features to characterize the mutuality attribute. Specifically, the mutuality attribute encapsulates high-level semantic information, such as the specific abnormal object or action, which mutually utilizes information from multiple deep features. In this way, the system is able to directly capture the high-level causes of anomaly, thus providing a more comprehensive perspective to accurately detect anomaly events. Following a process-transparent density estimation, we produce the final anomaly scores. Experiments show that MAR-VAD achieves state-of-the-art performance on ShanghaiTech and Avenue.

关键词： video anomaly detection mutuality attribute attribute-based unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

The Be-Hive Project-Counting Bee Traffic Based on deep learning and Pose Estimation

The Be-Hive Project-Counting Bee Traffic Based on Deep Learn...

引用

Intelligent Systems Conference (IntelliSys)

作者： Padubidri, Chirag Kamilaris, Andreas Charalambous, Alexis Lanitis, Andreas Constantinides, Marios CYENS Ctr Excellence Nicosia Cyprus Cyprus Univ Technol Limassol Cyprus Univ Twente Enschede Netherlands

ISBN: (纸本)9783031477232;9783031477249

Beekeeping is an important practice for ensuring the abundance of pollinators and for honey production. Traditionally, beekeepers inspect hives regularly to monitor their bees' populations, but this method is invasive and can cause stress to the bees. It is also impractical, for beekeepers having hundreds or thousands of beehives. In recent decades, various attempts have been made to automate the monitoring of bee colonies using emerging technologies. These technologies include sensors that collect micro-climate parameters, photos, video and audio from inside the hives and the nearby environment, which are then analyzed using automatic or manual methods. The beehive project aims a range of sensing technologies (image, sound, temperature, humidity, weight), together with state-of-the-art computer vision technologies and remote-sensing imagery to create a smart beehive system and monitor beehive on real-time. In this paper, we present the preliminary results of the BEHIVE, a smart beehive monitoring system. We present the monitoring system developed and the deep learning algorithm used to count bee traffic using the image from the camera placed at the entrance of the hive. For bee traffic estimation, we employ a counting algorithm that predicts the pose of individual bees and tracks them in subsequent frames. To reduce the annotation overhead of the key-points for pose estimation, we generate synthetic data to train our algorithm. The results show that the key-point detection model achieves an Intersection Over Union (IOU) of 86% when trained only on synthetic data and a traffic count mean absolute error of 5.7. These results indicate that the proposed approach can be used to monitor the bee activity remotely, increasing convenience and productivity.

关键词： Smart beehive IoT deep learning Bees' traffic counting

来源：评论

学校读者我要写书评

暂无评论

Comparative Approach on Machine learning and deep learning Techniques based Diabetic Retinopathy Detection 2

Comparative Approach on Machine Learning and Deep Learning T...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Al-Farouni, Mohammed Panduri, Bharathi Alkhafaij, Mahdi Abdulkhudur Rana Veer Samara Sihman Bharattej, R. Chanti, Yerrolla The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Gokaraju Rangaraju Institute of Engineering and Technology Department of Information Technology Hyderabad India Ahl Al Bayt University College of Mlt Karbala Iraq Saint Leo University Department of Computer Science St Leo United States Sr University School of Computer Science & Artificial Intelligence Warangal India

ISBN: (纸本)9798350372892

Diabetic Retinopathy (DR) is a disease that damages retinal blood vessels and leads to blindness. The main issue involved with DR detection is that manual diagnosis process is taken maximum computational and sensitive to analysis diabetic part has been noise or overlapping. This paper discusses the taxonomy for effective performance in manual detection of DR involving three various types: deep learning (DL), Machine learning (ML) and Optimization based techniques. This survey aims to detect DR using image processing to reduces time and effort required ML based techniques such as Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) classifiers for disease detection. deep Convolutional Neural Network (DCNN) and Convolutional Neural Networks (CNNs) algorithms have demonstrated their potential as a diagnostic tool for detecting DR in deep learning (DL) methods. To enhance high-level accuracy of DR detection, utilized optimization approaches like the Grey Wolf Optimization (GWO) algorithm. The performance of the model is evaluated based on parameters such as such as accuracy, precision, F1-score, specificity and sensitivity are used in this survey compared results with various DL approaches for DR detection. © 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

Bilingual video captioning model for enhanced video retrieval

引用

JOURNAL OF BIG DATA 2024年第1期11卷 17页

作者： Alrebdi, Norah Al-Shargabi, Amal A. Qassim Univ Coll Comp Dept Informat Technol Buraydah 51452 Saudi Arabia

Many video platforms rely on the descriptions that uploaders provide for video retrieval. However, this reliance may cause inaccuracies. Although deep learning-based video captioning can resolve this problem, it has some limitations: (1) traditional keyframe extraction techniques do not consider video length/content, resulting in low accuracy, high storage requirements, and long processing times;(2) Arabic language support in video captioning is not extensive. This study proposes a new video captioning approach that uses an efficient keyframe extraction method and supports both Arabic and English. The proposed keyframe extraction technique uses time- and content-based approaches for better quality captions, fewer storage space requirements, and faster processing. The English and Arabic models use a sequence-to-sequence framework with long short-term memory in both the encoder and decoder. Both models were evaluated on caption quality using four metrics: bilingual evaluation understudy (BLEU), metric for evaluation of translation with explicit ORdering (METEOR), recall-oriented understudy of gisting evaluation (ROUGE-L), and consensus-based image description evaluation (CIDE-r). They were also evaluated using cosine similarity to determine their suitability for video retrieval. The results demonstrated that the English model performed better with regards to caption quality and video retrieval. In terms of BLEU, METEOR, ROUGE-L, and CIDE-r, the English model scored 47.18, 30.46, 62.07, and 59.98, respectively, whereas the Arabic model scored 21.65, 36.30, 44.897, and 45.52, respectively. According to the video retrieval, the English and Arabic models successfully retrieved 67% and 40% of the videos, respectively, with 20% similarity. These models have potential applications in storytelling, sports commentaries, and video surveillance.

关键词： Artificial intelligence Computer vision Natural language processing Video retrieval English video captioning Arabic video captioning

来源：评论

学校读者我要写书评

暂无评论

In-Home Gait Abnormality Detection Through Footstep-Induced Floor Vibration Sensing and Person-Invariant Contrastive learning

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第12期28卷 7054-7067页

作者： Dong, Yiwen Kim, Sung Eun Schadl, Kornel Huang, Peide Ding, Wenhao Rose, Jessica Noh, Hae Young Stanford Univ Dept Civil & Environm Engn Stanford CA 94305 USA Lucile Packard Childrens Hosp Mot & Gait Anal Lab Menlo Pk CA 94025 USA Stanford Univ Dept Orthopaed Surg Redwood City CA 94063 USA Carnegie Mellon Univ Dept Mech Engn Pittsburgh PA 15213 USA

Detecting gait abnormalities is crucial for assessing fall risks and early identification of neuromusculoskeletal disorders such as Parkinson's and stroke. Traditional assessments in gait clinics are infrequent and pose barriers, particularly for disadvantaged populations. Previous efforts have explored sensor-based approaches for in-home gait assessments, yet they face limitations such as visual obstructions (cameras), limited coverage (pressure mats), and the need for device carrying (wearables and insoles). To overcome these limitations, we introduce an in-home gait abnormality detection system using footstep-induced floor vibrations, enabling low-cost, non-intrusive, device-free gait health monitoring. The main research challenge is the high uncertainty in floor vibrations due to gait variations among people, making it challenging to develop a generalizable model for new patients. To address this, we analyze time-frequency-domain features of floor vibration data during specific gait phases and develop a feature transformation method through contrastive learning to address the between-people gait variation challenge. Our method transforms the features from vibrations to an embedding space where samples from different people stay close to each other (robust to people variation) while normal and abnormal gait samples are far apart (sensitive to gait abnormalities). Then, gait abnormalities are detected by a downstream classifier after feature transformation. We evaluated our approach through a real-world walking experiment with 21 participants and achieved an 85% to 95% mean accuracy in detecting various gait abnormalities. This novel method overcomes prior limitations in in-home gait assessments, offering accessible gait abnormality detection without the need for intrusive devices or labels for new patients.

关键词： gait disorders Gait assessment sensors sensors vibrations vibrations vibrations contras- tive learning contras- tive learning contras- tive learning contras- tive learning contras- tive learning sensors vibrations

来源：评论

学校读者我要写书评

暂无评论

Alternative deep learning method for fast spatial-frequency shift imaging microscopy

引用

OPTICS EXPRESS 2023年第3期31卷 3719-3730页

作者： Zhang, Qianwei Liang, Chenhui Tang, Mingwei Yang, Xiaoyu Lin, Muchun Han, Yubing Liu, Xu Yang, Qing Zhejiang Univ Coll Opt Sci & Engn Int Res Ctr Adv Photon State Key Lab Modern Opt Instrumentat Hangzhou 310027 Peoples R China Zhejiang Lab Res Ctr Sensing Mat & Devices Hangzhou 311121 Zhejiang Peoples R China Zhejiang Lab Res Ctr Humanoid Sensing Hangzhou 311100 Peoples R China Shanxi Univ Collaborat Innovat Ctr Extreme Opt Taiyuan 030006 Peoples R China

Spatial-frequency shift (SFS) imaging microscopy can break the diffraction limit of fluorescently labeled and label-free samples by transferring the high spatial-frequency information into the passband of microscope. However, the resolution improvement is at the cost of decreasing temporal resolution since dozens of raw SFS images are needed to expand the frequency spectrum. Although some deep learning methods have been proposed to solve this problem, no neural network that is compatible to both labeled and label-free SFS imaging has been proposed. Here, we propose the joint spatial-Fourier channel attention network (JSFCAN), which learns the general connection between the spatial domain and Fourier frequency domain from complex samples. We demonstrate that JSFCAN can achieve a resolution similar to the traditional algorithm using nearly 1/4 raw images and increase the reconstruction speed by two orders of magnitude. Subsequently, we prove that JSFCAN can be applied to both fluorescently labeled and label-free samples without architecture changes. We also demonstrate that compared with the typical spatial domain optimization network U-net, JSFCAN is more robust to deal with deep-SFS images and noisy images. The proposed JSFCAN provides an alternative route for fast SFS imaging reconstruction, enabling future applications for real-time living cell research.(c) 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Diffraction limit image metrics image processing Neural networks Spatial resolution Temporal resolution

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Intelligent Condition Adaptation of Feature Extraction for Bearing Fault Detection Using deep Responsible Active learning

引用

IEEE ACCESS 2024年 12卷 45381-45397页

作者： Mahesh, T. R. Chandrasekaran, Saravanan Ram, V. Ashwin Kumar, V. Vinoth Vivek, V. Guluwadi, Suresh Deemed Univ Fac Engn & Technol Dept Comp Sci & Engn JAIN Bengaluru 562112 India SRM Inst Sci & Technol Dept Comp Sci & Engn Ramapuram Campus Chennai 600089 Tamil Nadu India Vellore Inst Technol Sch Comp Sci Engn & Informat Syst SCORE Vellore 632014 India Adama Sci & Technol Univ Dept Mech Engn Adama 302120 Ethiopia

The detection of faulty bearings is an essential step in guaranteeing the safe and efficient operation of rotating machinery. Bearings, which also transmit the loads and pressures generated by the machinery, support the rotating shafts. A common method for bearing fault diagnostics is using signal processing techniques. In terms of accuracy, dependability, and sensitivity to various fault types and severity levels, these techniques do, however, have significant limits. To address these limitations, practitioners often integrate signal processing with advanced techniques like machine learning and data analytics to enhance diagnostic accuracy, reliability, and overall effectiveness in bearing fault detection and predictive maintenance. Exploration of various models has demonstrated enhanced results in managing nonlinear data to a certain degree;however, these models face challenges when dealing with intricately complex patterns. Moreover, CNNs can automatically learn relevant features from raw sensor data, capturing intricate patterns and relationships in the data without the need for manual feature engineering. CNNs can be optimized for scalability and real-time processing, essential for applications requiring quick decisions and computationally less expensive for large datasets compared to other models. An optimized one-dimensional Convolutional Neural Network (1D CNN) using different kernel sizes is proposed for predicting and finding bearing problems to overcome these constraints. This method creates a feature vector by applying many filters of various sizes to the input signal. Using the created feature vector, the input signal can be divided into many categories, such as healthy or unhealthy. In comparison to other methods, the proposed technology performs better and offers a high accuracy of 99.52% in bearing fault identification. The 1D CNN model with multiple kernel sizes excels in preserving data structure during dimensionality reduction, as confirmed by com

关键词： Convolutional neural network bearings accuracy performance classification bearing fault detection

来源：评论

学校读者我要写书评

暂无评论

NedgeSIM-RL: Simulating Smart Offloading in NOMA-VEC Environments 20

NedgeSIM-RL: Simulating Smart Offloading in NOMA-VEC Environ...

引用

2024 International Conference on Wireless and Mobile Computing Networking and Communications

作者： Dulout, Romain Ariouich, Yassine Mendiboure, Leo Pousset, Yannis Deniau, Virginie Univ Poitiers XLIM UMR CNRS 7252 F-86000 Poitiers France Univ Gustave Eiffel COSYS ERENA F-77454 Marne La Vallee France Univ Gustave Eiffel COSYS LEOST F-59666 Villeneuve Dascq France

ISBN: (纸本)9798350387452;9798350387445

The advent of cooperative intelligent transport systems (C-ITS) and connected vehicles has brought with it a raft of novel services, including autonomous driving and dynamic traffic management, which necessitate both real-time processing and substantial data processing capacity. These technological advancements have imposed significant network constraints, requiring the development of robust network infrastructures to guarantee the reliable transmission of critical information in real time. In consequence, numerous studies have concentrated on NOMA-assisted Multi-Access Edge Computing (NOMA-MEC) to facilitate the provision of new services and, in particular, on their management through the utilisation of Multi-Agent deep Reinforcement learning (MADRL) algorithms. Nevertheless, the absence of a unified framework for the rigorous evaluation and comparison of these different approaches represents a significant issue. For this reason, we have established a unified, adaptable, and extensible framework, NedgeSIM-RL, with the objective of evaluating decentralised offloading strategies within the context of NOMA-VEC architectures. In this paper, we illustrate the functionality of the framework, the potential configurations, and the areas of research that can be pursued. We also present a basic simulation that can be executed on the framework to manage decentralised offloading via NOMA on a single MEC server by multiple vehicles.

关键词： Vehicular Edge Computing NOMA Offloading Reinforcement learning Simulation Evaluation

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：