检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xinwei Luo Songlin Zhao Yong Chen Gui-Shuang Ying Lifang He Computer Science and Engineering Lehigh University PA USA Biostatistics Epidemiology and Informatics University of Pennsylvania PA USA Ophthalmology Scheie Eye Institute University of Pennsylvania PA USA

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The detection of Referral-Warranted Retinopathy of Prematurity (RW-ROP) is crucial for preventing severe visual impairment in premature infants. Recent studies have demonstrated that deep learning models, particularly CNNs, are effective in classifying ROP. However, the comprehensive extraction and integration of ROP-relevant features from retinal images for accurate classification remains challenging. In this paper, we propose a hybrid model based on Very Deep Convolutional Networks (VGG) and Swin Transformer (VGG-ST) for identifying RW-ROP using retinal images. The VGG-ST model first employs the VGG19 architecture to extract detailed local image features and the Swin Transformer V2 architecture to capture comprehensive global contextual information. It then introduces a novel feature enhancement module that combines these local and global features through an adaptive integration strategy, optimizing the feature representation for more accurate RW-ROP detection. Finally, the integrated features are processed through a classification module to predict the probability of RW-ROP, distinguishing between normal and RW-ROP cases. We also present customized data preprocessing techniques to address class imbalance and retinal image blur issues inherent in the e-ROP dataset. Experimental results demonstrate that the VGG-ST model offers improved classification sensitivity compared to existing methods, making it a promising tool for automated ROP screening in clinical settings. The source code is available at https://***/hawk-sudo/VGG-ST.

关键词： Adaptation models Sensitivity Accuracy Retinopathy Source coding Visual impairment Feature extraction Transformers Retina Strain

来源：评论

学校读者我要写书评

暂无评论

FEASIBILITY OF ASSESSING COGNITIVE IMPAIRMENT VIA DISTRIBUTED CAMERA NETWORK AND PRIVACY-PRESERVING EDGE COMPUTING

arXiv

引用

arXiv 2024年

作者： Hegde, Chaitra Kiarashi, Yashar Levey, Allan I. Rodriguez, Amy D. Kwon, Hyeokhyen Clifford, Gari D. Department of Biomedical Informatics Emory University School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA United States Department of Biomedical Informatics Emory University AtlantaGA United States Department of Neurology Emory University AtlantaGA United States Department of Biomedical Informatics Emory University Department of Biomedical Engineering Georgia Institute of Technology AtlantaGA United States

INTRODUCTION: Mild cognitive impairment (MCI) is characterized by a decline in cognitive functions beyond typical age and education-related expectations. Since, MCI has been linked to reduced social interactions and increased aimless movements, we aimed to automate the capture of these behaviors to enhance longitudinal monitoring. METHODS: Using a privacy-preserving distributed camera network, we collected movement and social interaction data from groups of individuals with MCI undergoing therapy within a 1700m2 space. We developed movement and social interaction features, which were then used to train a series of machine learning algorithms to distinguish between higher and lower cognitive functioning MCI groups. RESULTS: A Wilcoxon rank-sum test revealed statistically significant differences between high and low-functioning cohorts in features such as linear path length, walking speed, change in direction while walking, entropy of velocity and direction change, and number of group formations in the indoor space. Despite lacking individual identifiers to associate with specific levels of MCI, a machine learning approach using the most significant features provided a 71% accuracy. DISCUSSION: We provide evidence to show that a privacy-preserving low-cost camera network using edge computing framework has the potential to distinguish between different levels of cognitive impairment from the movements and social interactions captured during group activities. © 2024, CC BY-NC-SA.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Leveraging Resource-Aware Deep Collaborative Learning Towards Secure B5G-Driven IoT-Fog-Based Consumer Electronic Systems

引用

IEEE Transactions on Consumer Electronics 2024年 1-1页

作者： Tripathy, Subhranshu Sekhar Bebortta, Sujit Chakraborty, Chinmay Senapati, Dilip Pani, Subhendu Kumar Guduri, Manisha School of Computer Engineering KIIT Deemed to be University Bhubaneswar India Department of Computer Science Ravenshaw University Cuttack Odisha India Department of Electronics and Communication Engineering Birla Institute of Technology Jharkhand India Department of Computer Science University of Delhi Delhi India Kausalya Ganga Bhubaneswar Odisha India School of Computing and Informatics University of Louisiana at Lafayette LA USA

The integration of Fog computing and 5G communication may enhance Cyber Physical Systems (CPSs) for effective time identification of cyber attacks among consumer electronics. An unsupervised Intrusion Detection System (IDS) based on Generative Adversarial Networks (GANs) and Recurrent Neural Networks (RNNs) is presented in this study. This system is tailored to the resource limitations of consumer electronics within CPSs. By leveraging the processing power of fog nodes and the low-latency capabilities of 5G networks, cyber attacks can be swiftly identified. The use of a trained Long Short-Term Memory (LSTM) network encoder improves detection rates by enhancing reconstruction loss computation. Experimental results demonstrate that this approach, implemented through distributed fog computing infrastructure, offers better detection rates with a 15.2% reduction in detection latency and a 24.2% decrease in overall energy consumption compared to baseline methods. This innovative system could serve as an effective alternative for securing consumer electronic devices integrated into CPSs. IEEE

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Sentiment Polarity Analysis of Bangla Food Reviews Using Machine and Deep Learning Algorithms

Sentiment Polarity Analysis of Bangla Food Reviews Using Mac...

引用

International Conference on Advancement in Electrical and Electronic engineering (ICAEEE)

作者： Al Amin Anik Sarkar Md Mahamodul Islam Asif Ahammad Miazee Md Robiul Islam Md Mahmudul Hoque Department of Computer Science and Engineering Uttara University Dhaka Bangladesh National Institute of Technology Silcar India Department of Informatics University of Oslo Oslo Norway Department of Computer Science Maharishi International University Iowa USA Department of Computer Science and Engineering CCN University of Science & Technology Comilla Bangladesh

ISBN: (数字)9798350388282

ISBN: (纸本)9798350388299

The Internet has become an essential tool for people in the modern world. Humans, like all living organisms, have essential requirements for survival. These include access to atmospheric oxygen, potable water, protective shelter, and sustenance. The constant flux of the world is making our existence less complicated. A significant portion of the population utilizes online food ordering services to have meals delivered to their residences. Although there are numerous methods for ordering food, customers sometimes experience disappointment with the food they receive. Our endeavor was to establish a model that could determine if food is of good or poor quality. We compiled an extensive dataset of over 1484 online reviews from prominent food ordering platforms, including Food Panda and HungryNaki. Leveraging the collected data, a rigorous assessment of various deep learning and machine learning techniques was performed to determine the most accurate approach for predicting food quality. Out of all the algorithms evaluated, logistic regression emerged as the most accurate, achieving an impressive 90.91% accuracy. The review offers valuable insights that will guide the user in deciding whether or not to order the food.

关键词： Deep learning Logistic regression Accuracy Machine learning algorithms Reviews Sociology Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Based Deep Neural Network Model for Electrocardiogram Records Classification 7

Convolutional Neural Network Based Deep Neural Network Model...

引用

7th International Conference on Future Networks and Distributed Systems, ICFNDS 2023

作者： Khudhur, Ahmed Mahmood Alwan, Mohammed Hasan Al Omairi, Qayssar Mahmood, Omar Abdulkareem Hammadi, Yousif I Muthanna, Mohammed Saleh Ali Aziz, Ahmed Muthanna, Ammar Information Technology Department College Of Computer Science And Information Technology Kirkuk University Iraq Department Of Communications Engineering College Of Engineering University Of Diyala Baqubah32001 Iraq Department Of Computer Engineering College Of Engineering University Of Diyala Iraq Bilad Alrafidain University College Diyala32001 Iraq Institute Of Computer Technologies And Information Security Southern Federal University Taganrog344006 Russia Department Of Computer Science Faculty Of Computer And Artificial Intelligence Benha University Egypt Department Of International Business Management Tashkent State University Of Economics Tashkent Uzbekistan Department Of Telecommunication Networks And Data Transmission The Bonch Bruevich Saint Petersburg State University Of Telecommunications Russia Department Of Applied Probability And Informatics Peoples Friendship University Of Russia Russia

ISBN: (纸本)9798400709036

Cardiovascular diseases, also known as CVDs, currently rank as the primary incidence of mortality. The present approach for identifying illnesses involves the analysis of the Electrocardiogram (ECG), an electronic diagnostic device utilized to capture the rhythm of the heart. Regrettably, the process of seeking out specialists to conduct analysis on a substantial volume of electrocardiogram (ECG) data results in a significant depletion of medical capabilities. Hence, the utilization of deep learning algorithms for the identification of ECG characteristics has progressively gained prominence. Nevertheless, there exist certain limitations associated with these conventional approaches, which necessitate the need for manual characteristic identification, intricate models, and extensive training duration. This study presents a novel and effective approach for categorizing the five different types of heartbeats in the MIT-BIH Arrhythmia database. The proposed method involves the utilization of a 16-layer deep one-dimensional convolutional neural network, which exhibits both robustness and efficiency in its classification performance. Thus, the designed model is consisting of five-groups, first to fourth groups are the main feature extraction and mapping blocks, while the fifth group is fully connected and classification layers. The findings indicate that the model presented in this study has superior performance in terms of accuracy, precision, and F1-score. The proper classification of medical cases has a significant impact on the conservation of medical resources, hence positively influencing clinical practice. Additionally, the model training phase is characterized by its efficiency, since it does not significantly deplete resources. © 2023 ACM.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

An AI-Driven VM Threat Prediction Model for Multi-Risks Analysis-Based Cloud Cybersecurity

arXiv

引用

arXiv 2023年

作者： Saxena, Deepika Gupta, Ishu Gupta, Rishabh Singh, Ashutosh Kumar Wen, Xiaoqing Department of Computer Science & Engineering The University of Aizu Japan Bangalore India Indian Institute of Information Technology Bhopal India The Department of Computer Applications National Institute of Technology Kurukshetra India the Department of Creative Informatics The Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka8208502 Japan

Cloud virtualization technology, ingrained with physical resource sharing, prompts cybersecurity threats on users’ virtual machines (VM)s due to the presence of inevitable vulnerabilities on the offsite servers. Contrary to the existing works which concentrated on reducing resource sharing and encryption/decryption of data before transfer for improving cybersecurity which raises computational cost overhead, the proposed model operates diversely for efficiently serving the same purpose. This paper proposes a novel Multiple Risks Analysis based VM Threat Prediction Model (MR-TPM) to secure computational data and minimize adversary breaches by proactively estimating the VMs threats. It considers multiple cybersecurity risk factors associated with the configuration and management of VMs, along with analysis of users’ behaviour. All these threat factors are quantified for the generation of respective risk score values and fed as input into a machine learning based classifier to estimate the probability of threat for each VM. The performance of MR-TPM is evaluated using benchmark Google Cluster and OpenNebula VM threat traces. The experimental results demonstrate that the proposed model efficiently computes the cybersecurity risks and learns the VM threat patterns from historical and live data samples. The deployment of MR-TPM with existing VM allocation policies reduces cybersecurity threats up to 88.9%. © 2023, CC BY.

关键词： Risk analysis

来源：评论

学校读者我要写书评

暂无评论

Image Captioning with Reinforcement Learning 2

Image Captioning with Reinforcement Learning

引用

2nd IEEE International Conference on computer Vision and Machine Intelligence, CVMI 2023

作者： Verma, Anand Agarwal, Saurabh Arya, K.V. Petrlik, Ivan Esparza, Roberto Rodriguez, Ciro ABV-IIITM Gwalior Department of Information Technology Madhya Pradesh 474015 India ABV-Indian Institute of Information Technology and Management Multimedia and Information Security Research Group Department of Computer Science and Engineering Gwalior474015 India National University Federico Villarreal Faculty of Industrial and Systems Engineering Lima Peru National University Mayor de San Marcos Faculty of Systems Engineering and Informatics Peru

ISBN: (纸本)9798350305142

Image captioning involves generating a natural language description that accurately represents the content and context of an image. To achieve this, image captioning utilises various machine learning techniques and fields, such as computer vision and natural language processing. In the field of image captioning, a lot of advances have been made with encoder-decoder models and reinforcement learning algorithms. However, there are still problems of imbalance between testing and training, as reinforcement learning only handles single comparator metrics such as CIDEr, SPICE, and BLEU and could not perform better in multiple metrics at once. Which is why a lack of diversity can be seen in generated captions. This idea proposes a general technique for collaborative updating that can bridge the gap between evaluation measures and test metrics to produce captions that are more human-like. To increase the precision of image captions, the approach involves using a compiled reward system that considers multiple evaluation metrics to compare the generated sentence with the provided sentences. We will evaluate the model's performance and the reward updating process on standard datasets like MS COCO. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Best Practices for a Handwritten Text Recognition System

arXiv

引用

arXiv 2024年

作者： Retsinas, George Sfikas, Giorgos Gatos, Basilis Nikou, Christophoros School of Electrical and Computer Engineering National Technical University of Athens Greece Computational Intelligence Laboratory Institute of Informatics and Telecommunications National Center for Scientific Research "Demokritos" Greece Department of Computer Science and Engineering University of Ioannina Greece Department of Surveying and Geoinformatics Engineering University of West Attica Greece

Handwritten text recognition has been developed rapidly in the recent years, following the rise of deep learning and its applications. Though deep learning methods provide notable boost in performance concerning text recognition, non-trivial deviation in performance can be detected even when small pre-processing or architectural/optimization elements are changed. This work follows a "best practice" rationale;highlight simple yet effective empirical practices that can further help training and provide well-performing handwritten text recognition systems. Specifically, we considered three basic aspects of a deep HTR system and we proposed simple yet effective solutions: 1) retain the aspect ratio of the images in the preprocessing step, 2) use max-pooling for converting the 3D feature map of CNN output into a sequence of features and 3) assist the training procedure via an additional CTC loss which acts as a shortcut on the max-pooled sequential features. Using these proposed simple modifications, one can attain close to state-of-the-art results, while considering a basic convolutional-recurrent (CNN+LSTM) architecture, for both IAM and RIMES datasets. Code is available at https://***/georgeretsi/HTR-best-practices/. © 2024, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Machine Speech Chain with Emotion Recognition

Machine Speech Chain with Emotion Recognition

引用

International Conference of Advanced informatics: Concept, Theory and Application (ICAICTA)

作者： Akeyla Pradia Naufal Dessi Puji Lestari Ayu Purwarianti Kurniawati Azizah Dipta Tanaya Sakriani Sakti School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Faculty of Computer Science University of Indonesia Depok Indonesia Graduate School of Information Science Nara Institute of Science and Technology Nara Japan

ISBN: (数字)9798331520311

ISBN: (纸本)9798331520328

Developing natural speech recognition and speech synthesis systems requires speech data that authentically represents real emotions. However, this type of data is often challenging to obtain. Machine speech chain offers a solution to this challenge by using unpaired data to continue training models initially trained with paired data. Given the relative abundance of unpaired data compared to paired data, machine speech chain can be instrumental in recognizing emotions in speech where training data is limited. This study investigates the application of machine speech chain in speech emotion recognition and speech recognition of emotional speech. Our findings indicate that a model trained with 50% paired neutral emotion speech data and 22% paired non-neutral emotional speech data shows a reduction in Character Error Rate (CER) from 37.55% to 34.52% when further trained with unpaired neutral emotion speech data. The CER further decreases to 33.75% when additionally trained with combined unpaired speech data. The accuracy of recognizing non-neutral emotions ranged from 2.18% to 53.51 %, though the F1 score fluctuated, increasing by up to 20.6% and decreasing by up to 23.4%. These results suggest that the model demonstrates a bias towards the majority class, as reflected by the values of the two metrics.

关键词： Training Emotion recognition Accuracy Error analysis Natural languages Training data Speech recognition Speech enhancement Data models Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Detection of Dead Victims at Volcanic Disaster Location based on Drone and LoRa

Detection of Dead Victims at Volcanic Disaster Location base...

引用

International Conference on computer engineering, Network and Intelligent Multimedia (CENIM)

作者： Moch. Zen Samsono Hadi Achmad Abie Dafa Prima Kristalina Department of Informatics and Computer Engineering Electronic Engineering Polythecnic Institute of Surabaya (EEPIS) Surabaya East Java Indonesia

ISBN: (纸本)9781665476515

When a natural disaster occurs, the process of evacuating victims after a disaster must be carried out immediately to reduce the risk due to the late evacuation process. In this evacuation process, the Search and Rescue (SAR) team played a big role in addition to focusing on the safety of victims and also paying attention to their own safety. Meanwhile, due to the large area of the disaster the search took quite a long time. In this paper, research was carried out to facilitate the evacuation process at the location of volcanic disasters by using drones carrying electronic devices to find the whereabouts of victims on the surface. This process of detecting and classifying is based on the Convolutional Neural Network (CNN) method with the MobileNetV2 model. We train the data set of disaster victims using batch sizes 16 and 32 with epochs of 40, 80 and 100. The resulting model has the greatest accuracy of 0.81 and f1-score of 0.86.

关键词： Computational modeling Simulation Neural networks Training data Focusing Safety Convolutional neural networks

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：