检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhuang, Zeming Wen, Dingzhu Shi, Yuanming Zhu, Guangxu Wu, Sheng Niyato, Dusit Network Intelligence Center School of Information Science and Technology ShanghaiTech University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China The School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China School of Computer Science and Engineering Nanyang Technological University Singapore

Edge-device co-inference refers to deploying well-trained artificial intelligent (AI) models at the network edge under the cooperation of devices and edge servers for providing ambient intelligent services. For enhancing the utilization of limited network resources in edge-device co-inference tasks from a systematic view, we propose a task-oriented scheme of integrated sensing, computation and communication (ISCC) in this work. In this system, all devices sense a target from the same wide view to obtain homogeneous noise-corrupted sensory data, from which the local feature vectors are extracted. All local feature vectors are aggregated at the server using over-the-air computation (AirComp) in a broadband channel with the orthogonal-frequency-division-multiplexing technique for suppressing the sensing and channel noise. The aggregated denoised global feature vector is further input to a server-side AI model for completing the downstream inference task. A novel task-oriented design criterion, called maximum minimum pairwise discriminant gain, is adopted for classification tasks. It extends the distance of the closest class pair in the feature space, leading to a balanced and enhanced inference accuracy. Under this criterion, a problem of joint sensing power assignment, transmit precoding and receive beamforming is formulated. The challenge lies in three aspects: the coupling between sensing and AirComp, the joint optimization of all feature dimensions' AirComp aggregation over a broadband channel, and the complicated form of the maximum minimum pair-wise discriminant gain. To solve this problem, a task-oriented ISCC scheme with AirComp is proposed. Experiments based on a human motion recognition task are conducted to verify the advantages of the proposed scheme over the existing scheme and a baseline. Copyright © 2023, The Authors. All rights reserved.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

A distance covariance-based kernel for nonlinear causal clustering in heterogeneous populations

arXiv

引用

arXiv 2021年

作者： Markham, Alex Grosse-Wentrup, Moritz Research Group Neuroinformatics Faculty of Computer Science University of Vienna Research Group Neuroinformatics Faculty of Computer Science University of Vienna Research Platform Data Science @ Uni Vienna Vienna Cognitive Science Hub Austria

We consider the problem of causal structure learning in the setting of heterogeneous populations, i.e., populations in which a single causal structure does not adequately represent all population members, as is common in biological and social sciences. To this end, we introduce a distance covariance-based kernel designed specifically to measure the similarity between the underlying nonlinear causal structures of different samples. This kernel enables us to perform clustering to identify the homogeneous subpopulations. Indeed, we prove the corresponding feature map is a statistically consistent estimator of nonlinear independence structure, rendering the kernel itself a statistical test for the hypothesis that sets of samples come from different generating causal structures. We can then use existing methods to learn a causal structure for each of these subpopulations. We demonstrate using our kernel for causal clustering with an application in genetics, allowing us to reason about the latent transcription factor networks regulating measured gene expression levels. Copyright © 2021, The Authors. All rights reserved.

关键词： Transcription

来源：评论

学校读者我要写书评

暂无评论

Robust and Secure Federated Learning with Verifiable Differential Privacy

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Zhang, Chushan Weng, Jian Weng, Jiasi Zhong, Yijian Liu, Jia-Nan Deng, Cunle College of Cyber Security of Jinan University Guangzhou510632 China College of Cyber Security of Jinan University National Joint Engineering Research Center of Network Security Detection and Protection Technology Guangdong Key Laboratory of Data Security and Privacy Preserving Guangdong-Hong Kong-Macao Joint Laboratory of Data Security and Privacy Preserving Guangzhou510632 China Dongguan University of Technology School of Computer Science and Technology Dongguan523808 China

Federated Learning (FL) has emerged as a popular paradigm for training machine learning models on data from multiple sources without the need for data to leave their respective locations. Although FL is widely used, recent research indicates its vulnerability to data privacy breaches and Byzantine attacks. Addressing both threats simultaneously remains challenging, as previous defense mechanisms struggle to balance Byzantine resilience, data privacy, and training accuracy. Although combining Differential Privacy (DP) with Byzantineresilience in FL offers potential solutions, it presents challenges due to theoretical incompatibilities that can impact the performance of large-scale models. Addressing this underexplored challenge, we propose a novel approach that enhances privacy and Byzantine-resilient in FL while maintaining training accuracy. Our method integrates DP with Byzantine-resilience techniques, overcoming the limitations of existing methods that often sacrifice accuracy or even Byzantine resistance. Our experiments carefully analyze the impact of DP noise on training accuracy and Byzantine-resilience, guiding appropriate parameter selection. The experimental results demonstrate that our approach achieves superior global model accuracy compared to previous competitive methods, even with strong privacy constraints. © 2004-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

research on Zenith Tropospheric Delay Model Based on TCN Improving HGPT2 Model

Research on Zenith Tropospheric Delay Model Based on TCN Imp...

引用

第十四届中国卫星导航年会

作者： Dengao Li Danyang Shi Jumin Zhao Fanming Wu Liangquan Yan Ran Feng Xinfang Zhang Jinhua Zhao College of Data Science Taiyuan University of Technology Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province Intelligent Perception Engineering Technology Center of Shanxi Shanxi Province Engineering Technology Research Center of Spatial Information Network College of Information and Computer Taiyuan University of Technology

The zenith tropospheric delay（ZTD） obtained by global navigation satellite system（GNSS） atmospheric sounding is a pivotal data source for water vapor monitoring. Meteorological changes in Antarctica play an important role in analysis of the global climate, but factors such as complex climatic conditions can limit the collection of meteorological data needed for ZTD retrieval. Therefore, it is necessary to establish high-precision ZTD models that do not rely on measured meteorological data. The existing global pressure and temperature 3（GPT3） model has limited ability to capture complex weather variations and cannot obtain high-precision GPT3TD. To address the above issues, this research proposes a high-precision ZTD model through using temporal convolutional network（TCN） for improving the hourly global pressure and temperature 2（HGPT2） model. The HGTP2 model based on Fourier analysis and the time-segmentation concept can consider the linear trend of climate variations, simultaneously the TCN is introduced to simulate the long-term temporal dependence of HGPT2TD, so as to achieve the goal of obtaining high-precision ZTD without relying on measured meteorological data. The experimental results show that the precision of TCNTD obtained from the proposed model is higher than GPT3TD and HGPT2TD when using the GNSSTD observations obtained from 35 stations in Antarctica as a reference, and the improvement of the model is obvious.

关键词： GNSS ZTD GPT3 HGPT2 TCN

来源：评论

学校读者我要写书评

暂无评论

MLCardiovascularPrediction: Machine Learning-Based Cardiovascular Disease Prediction

MLCardiovascularPrediction: Machine Learning-Based Cardiovas...

引用

Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), International

作者： Diaa Salama AbdElminaam Magda M. Madbouly Magdy Abd-elghany Zeid Ibrahim Abd Elatif Gomaa Laith Abualigah Faculty of Computer Science Misr International University Cairo Egypt Faculty of Computers and Artificial Intelligence Benha University Benha Egypt Faculty of Computer and Data Science Alexandria University Alexandria Egypt Computer Science Department Alobour high institute for computer and informatics Cairo Egypt Computer Science Department Al al-Bayt University Mafraq Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan MEU Research Unit Middle East University Amman Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya Malaysia

Like most diseases that affect a human's life, car-diovascular disease is dangerous and unwanted for anyone who has heard of it as it brings a high risk of death. In today's world, most deaths are caused by heart disease as it could come from age, heritage, smoking, and many factors that could seem normal, and it doesn't matter what part of the world you are in. There must be a way to know or predict if this person is at high risk of cardiovascular disease. This paper and project talk about six algorithms: K-Nearest-Neighbour (KNN), Decision Tree (DT), Naive Bayes, Neural network, Logistic Regression, and Support Vector Machine (SVM). The results came between 60% to 70% in one dataset and from 80 % to 90 % in the second. Still, they mostly favor the Neural network algorithm as it can learn and model around complex relationships. The SVM showed different outputs between the two datasets as one is significantly larger than the other, possibly due to the outliers in both datasets being different and more complex in the larger one. Cardiovascular disease can be very dangerous, but finding and discovering it soon can be a lifesaver. These algorithms also can help find and predict it, as it was shown with not just decent, but good and respectable success rates for each one.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ML_Alzheimer: Alzheimer Disease Prediction Using Machine Learning

ML_Alzheimer: Alzheimer Disease Prediction Using Machine Lea...

引用

Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), International

作者： Diaa Salama AbdElminaam Magda M. Madbouly Mohamed S Farag Ibrahim A Gomaa Magdy Abd-Elghany Zeid Laith Abualigah Faculty of Computer Science Misr International University Cairo Egypt Faculty of Computers and Artificial Intelligence Benha University Benha Egypt Faculty of Computer and Data Science Alexandria University Alexandria Egypt Computer Science Department Alobour high institute for computer and informatics Cairo Egypt Computer Science Department Al al-Bayt University Mafraq Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan MEU Research Unit Middle East University Amman Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya Malaysia

Alzheimer's disease is a fatal brain disorder that impacts predominantly the elderly. The early identification of Alzheimer's illness requires the use of efficient automated methods. For the categorization of Alzheimer's disease, researchers have proposed several distinct methods. To create more effective learning strategies, however, a deeper comprehension of Alzheimer's research is necessary. The condition is diagnosed but not until a later stage. As a consequence, the disease's progression or its symptoms' onset can be slowed if detected earlier. This article uses two datasets and machine learning techniques to predict Alzheimer's disease based on psychological characteristics such as age, gender, number of visits, and Mini-Mental State Examination (MMSE). We ultimately focused on the masculine gender and characteristics. The following results (accuracy) were discovered: SVM: 84%, KNN: 79%, and Random forest: 86%. Neural network: 86%; Naive Bayes: 83%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ML_BrainDetection: An Intelligent Model for Brain Tumor Identification Using Machine Learning

ML_BrainDetection: An Intelligent Model for Brain Tumor Iden...

引用

Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), International

Brain tumors are one of the greatest causes of death worldwide. Due to that, early diagnosis and classification of the tumor would surely help increase the chance of survival for patients worldwide. However, classifying and identifying brain tumors requires certain tools, including using Magnetic Resonance Imaging (MRI) to detect brain tumors. Moreover, many researchers in the past have also built up computer-Aided Diagnosis (CAD) systems to aid radiologists in their purpose of detecting brain abnormalities and tumors effectively. In this research, extracted multi-modal features like texture, morphological, entropy-based, Scale Invariant Features are proposed, and consequently, certain robust machine learning techniques, which are k-nearest neighbors (KNN), Decision Tree (DT), Support Vector Machine (SVM), Naive Bayes, as well as the Logistic Regression classifier were used to analyze the two data-sets included in the paper, detect tumors found in the brain, not to mention, examining their results, which have then shown the highest accuracy when using the Logistic regression classifier in both data sets, with the Support Vector Machine (SVM) classifier following it, which further support the argument made in the paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification of Breast Thermal Images into Healthy/Cancer Group Using Pre-Trained Deep Learning Schemes

Classification of Breast Thermal Images into Healthy/Cancer ...

引用

2022 International Conference on Machine Learning and data Engineering, ICMLDE 2022

作者： Kadry, Seifedine Crespo, Rubén González Herrera-Viedma, Enrique Krishnamoorthy, Sujatha Rajinikanth, Venkatesan Faculty of Applied Computing and Technology Noroff University College Kristiansand94612 Norway Computer Science Department School of Engineering and Technology Universidad Internacional de la Rioja Andalusia26006 Spain Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Tamil Nadu Chennai602105 India

In the women's community, Breast Cancer (BC) is a severe disease. The World Health Organization reported in 2020 that 2.26 million deaths occur due to BC. BC is curable if detected early. Since thermal imaging is non-invasive and supports disease detection, it is commonly used in clinics. Compared to other methods, it keeps BC early and accurate. The proposed work aims to evaluate the performance of the Pretrained Deep-Learning Methods (PDLM) in detecting BC using the thermal images collected from the benchmark dataset. It includes the following stages: primary image processing, deep feature mining, handcrafted feature mining, feature optimization using Firefly-Algorithm (FA), classification and validation. Visual Lab thermal images were used in the study. The investigational outcome of this study authenticates that the VGG16, along with the DT, provides better detection accuracy (95.5%) compared to other classifiers used in this study. To justify the significance of the implemented technique, the proposed work not only improved accuracy, but also improved precision, sensitivity, specificity, and F1-Scores. © 2023 The Authors. Published by Elsevier B.V.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

SKIN_ML: An Efficient Approach for Skin Cancer Detection Using Soft Computing Methods

SKIN_ML: An Efficient Approach for Skin Cancer Detection Usi...

引用

Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), International

In today's environment, cancer is a fatal disease. Skin cancer has become a fairly common malignancy due to the spread of several forms of cancer. Skin cancer is divided into two types: melanoma and non-melanoma. Melanoma is one of the most fatal tumors on the planet, and it can spread to other parts of the body if not diagnosed early enough. Our proposed system uses Five alternative methods to predict a skin lesion's borders, texture, and color: a neural network and four standard machine learning classifiers. To enhance their performance, the outputs of these systems are merged using majority voting. Experiments have demonstrated that combining the five strategies yields the maximum level of accuracy. Pre-processing, Segmentation, Feature Extraction, and Classification are four critical phases in skin cancer identification. Skin lesion images were collected for this research from the International Skin Imaging Collaboration (ISIC), which contains over 3297 photos. The accuracy of the NN classifier is 91.9%, compared to 87.2% for the KNN classifier, 81.5% for the Naive Bayes classifier, 72.5% for the SVM classifier, and 68.3% for the DT classifier.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ML_Recognition: A Robust Model for Handwritten Digit Recognition Using Machine Learning Classifiers

ML_Recognition: A Robust Model for Handwritten Digit Recogni...

引用

Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), International

作者： Diaa Salama AbdElminaam Magda M. Madbouly Magdy Abd-Elghany Zeid Laith Abualigah Faculty of Computer Science Misr International University Cairo Egypt Faculty of Computers and Artificial Intelligence Benha University Benha Egypt Faculty of Computer and Data Science Alexandria University Alexandria Egypt Ibrahim Abd Elatif Gomaa Computer Science Department Alobour high institute for computer and informatics Cairo Egypt Computer Science Department Al al-Bayt University Mafraq Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan MEU Research Unit Middle East University Amman Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya Malaysia

Handwritten digit recognition is a branch of machine learning in which a computer is taught to recognize hand-written numbers. Classification and regression are applied using deep learning and machine learning algorithms. In this paper, we discussed the efficiency of different algorithms: Random Forest, KNN, Naive Bayes, SVM, CNN, and Decision Tree Algorithm. Those algorithms were applied in the handwritten digit recognition process using the MINIST data set. By comparing each algorithm by training every one of them on the data set, then by testing, we got the best algorithm to get the optimal results with the highest accuracy. After comparing the results of each algorithm, it has shown that the neural network has the best results with 97.3% classification accuracy followed by K- the nearest neighbor with 97.2%.

关键词：

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：