检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Alvarez, Miguel Jasra, Ajay Ruzayqat, Hamza Applied Mathematics and Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955 Saudi Arabia

In this article we consider the filtering problem associated to partially observed diffusions, with observations following a marked point process. In the model, the data form a point process with observation times that have its intensity driven by a diffusion, with the associated marks also depending upon the diffusion process. We assume that one must resort to time-discretizing the diffusion process and develop particle and multilevel particle filters to recursively approximate the filter. In particular, we prove that our multilevel particle filter can achieve a mean square error (MSE) of O(∈2) (∈ > 0 and arbitrary) with a cost of O(∈-2.5) versus using a particle filter which has a cost of O(∈-3) to achieve the same MSE. We then show how this methodology can be extended to give unbiased (that is with no time-discretization error) estimators of the filter, which are proved to have finite variance and with high-probability have finite cost. Finally, we extend our methodology to the problem of online static-parameter estimation. Key words: Unbiased Methods, Multilevel Monte Carlo, Non-Linear Filtering, Point Processes, Parameter *** Codes 60G55, 60G35, 62M20, 62F30 © 2023, CC BY.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Bayesian Parameter Inference for Partially Observed Stochastic Volterra Equations

arXiv

引用

arXiv 2023年

作者： Jasra, Ajay Ruzayqat, Hamza Wu, Amin Applied Mathematics & Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955 Saudi Arabia

In this article we consider Bayesian parameter inference for a type of partially observed stochastic Volterra equation (SVE). SVEs are found in many areas such as physics and mathematical finance. In the latter field they can be used to represent long memory in unobserved volatility processes. In many cases of practical interest, SVEs must be time-discretized and then parameter inference is based upon the posterior associated to this time-discretized process. Based upon recent studies on time-discretization of SVEs (e.g. [24]) we use Euler-Maruyama methods for the afore-mentioned discretization. We then show how multilevel Markov chain Monte Carlo (MCMC) methods [19] can be applied in this context. In the examples we study, we give a proof that shows that the cost to achieve a 4 mean square error (MSE) of O(ϵ2), ϵ > 0, is O(ϵ− 4/2H+1 ), where H is the Hurst parameter. If one uses a single level MCMC method then the cost is O(ϵ−2(2H+3)/ 2H+1 ) to achieve the same MSE. We illustrate these results in the context of state-space and stochastic volatility models, with the latter applied to real *** Codes 62F15, 62M20, 60J10, 60J22, 65C40 © 2023, CC BY.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Comments on a Computation-Transferable Authenticated Key Agreement Protocol for Smart Healthcare

Comments on a Computation-Transferable Authenticated Key Agr...

引用

International Conference on Applied System Innovation (ICASI)

作者： Ya-Fen Chang Chung-Yi Tsai Wei-Liang Tai Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung Taiwan Bachelor Degree Program of Artificial Intelligence National Taichung University of Science and Technology Taichung Taiwan

Recently, Wang et al. proposed a computationally transferable authenticated key agreement protocol for smart healthcare by adopting the certificateless public-key cryptography. They claimed that their protocol could ensure privacy, resist various attacks, and possess superior properties. After analyzing their protocol, we find that it suffers from some flaws. Firstly, user privacy is not ensured as claimed. Secondly, some statements are inaccurate or missing. Thirdly, it cannot resist DoS attack. In this paper, the details of how these flaws threaten Wang et al.’s protocol are shown.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Decoupling Frontend Enhancement and Backend Recognition in Monaural Robust ASR

arXiv

引用

arXiv 2024年

作者： Yang, Yufeng Pandey, Ashutosh Wang, DeLiang Department of Computer Science and Engineering The Ohio State University ColumbusOH43210 United States Center for Cognitive and Brain Sciences The Ohio State University ColumbusOH43210 United States

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement (SE) algorithms. However, monaural SE has not been established as an effective frontend for automatic speech recognition (ASR) in noisy conditions compared to an ASR model trained on noisy speech directly. The divide between SE and ASR impedes the progress of robust ASR systems, especially as SE has made major advances in recent years. This paper focuses on eliminating this divide with an ARN (attentive recurrent network) time-domain and a CrossNet time-frequency domain enhancement models. The proposed systems fully decouple frontend enhancement and backend ASR trained only on clean speech. Results on the WSJ, CHiME-2, LibriSpeech, and CHiME-4 corpora demonstrate that ARN and CrossNet enhanced speech both translate to improved ASR results in noisy and reverberant environments, and generalize well to real acoustic scenarios. The proposed system outperforms the baselines trained on corrupted speech directly. Furthermore, it cuts the previous best word error rate (WER) on CHiME-2 by 28.4% relatively with a 5.57% WER, and achieves 3.32/4.44% WER on single-channel CHiME-4 simulated/real test data without training on CHiME-4. Copyright © 2024, The Authors. All rights reserved.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Normality Addition via Normality Detection in Industrial Image Anomaly Detection Models

arXiv

引用

arXiv 2024年

作者： Yi, Jihun Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of School of Computer Science and Engineering Soongsil University Seoul Korea Republic of Department of Electrical and Computer Engineering and Interdisciplinary Program in AI Seoul National University Seoul Korea Republic of

The task of image anomaly detection (IAD) aims to identify deviations from normality in image data. These anomalies are patterns that deviate significantly from what the IAD model has learned from the data during training. However, in real-world scenarios, the criteria for what constitutes normality often change, necessitating the reclassification of previously anomalous instances as normal. To address this challenge, we propose a new scenario termed "normality addition," involving the post-training adjustment of decision boundaries to incorporate new normalities. To address this challenge, we propose a method called Normality Addition via Normality Detection (NAND), leveraging a vision-language model. NAND performs normality detection which detect patterns related to the intended normality within images based on textual descriptions. We then modify the results of a pre-trained IAD model to implement this normality addition. Using the benchmark dataset in IAD, MVTec AD, we establish an evaluation protocol for the normality addition task and empirically demonstrate the effectiveness of the NAND method. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Implementation and Evaluation of 0.6 µm CMOS Complex RCPF for Accurate Frequency Response Measurement

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, Information and Systems 2025年第1期145卷 25-37页

作者： Sato, Lina Fukagawa, Kanta Shouno, Kazuhiro Tanimoto, Hiroshi Muto, Cosy Moriyama, Seijiro Takahashi, Chikau Yoshino, Michitaka Graduate School of Science and Technology Degree Programs in Systems and Information Engineering Master’s Program in Computer Science University of Tsukuba Japan Division of Information Engineering University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8573 Japan Kitami Institute of Technology 165 Koen-cho Hokkaido Kitami090-8507 Japan Faculty of Education Nagasaki University 1-14 Bunkyo-machi Nagasaki852-8521 Japan Anagix Corporation 3-22-27 Numama Kanagawa Zushi249-0004 Japan Takamori Corporation Japan Research Center for Micro-Nano Technology Hosei University 3-11-15 Midori-cho Koganei Tokyo184-0003 Japan

This paper describes the implementation and evaluation of an RC polyphase filter (RCPF) and circuitry for measuring its frequency characteristics. The integrated circuit is fabricated on a 0.6 µm CMOS process and its supply voltage is 5 V. The integrated circuit includes a filter under test (FUT), a four-phase square wave generator, several analog switches and differential amplifiers to amplify the high-impedance signals of the RCPF. This FUT is a third-order complex RCPF whose passband is 8 − 40 MHz. This paper describes the design of these circuits in detail. This integrated circuit can select two measurement methods by means of external control signals. The first method uses a four-phase square wave. The frequency characteristics are measured by using an on-chip four-phase square wave generator driven by an external clock generator and by a spectrum analyzer tuned to the fundamental frequency. The second method uses an external network analyzer. Furthermore, this integrated circuit is equipped with a calibration circuit to measure the frequency characteristics of the circuitry except FUT by passing through the input / output signals of the FUT. As a result, the frequency characteristics of the FUT itself can be accurately measured. The effectiveness is confirmed through evaluation of the fabricated integrated circuit. © 2025 The Institute of Electrical Engineers of Japan.

关键词： Differential amplifiers

来源：评论

学校读者我要写书评

暂无评论

Enhanced Diagnosis of Schizophrenia Using Integrated Node Embedding and Causal Discovery on Imbalanced fMRI Data

Enhanced Diagnosis of Schizophrenia Using Integrated Node Em...

引用

International Conference of Signal Processing and Intelligent Systems (ICSPIS)

作者： Sina Sabzevar Saeed Masoudnia Babak N Araabi MohammadReza NazemZadeh Hosna Tavakoli Department of Electrical and Computer Engineering The University of Tehran Tehran Iran Department of Neuroscience Monash University Melbourne Australia Computational and Artificial Intelligence Department Institute of Cognitive Science Studies Tehran Iran

ISBN: (数字)9798331532543

ISBN: (纸本)9798331532550

This study introduces a novel diagnostic method for schizophrenia using causal discovery and node embedding techniques on resting-state fMRI data. Data from 148 subjects (27 schizophrenia patients, 121 healthy controls) were analyzed across 116 brain regions, applying several causal discovery techniques to assess directional connectivity and uncover schizophrenia-related patterns. By combining advanced causal discovery with node embedding techniques and a rigorous data-balancing pipeline, our method improves sensitivity to subtle network variations critical for schizophrenia diagnosis. Our approach addresses key challenges in the literature: the difficulty of extracting effective neurobiological markers from noisy and complex fMRI data, the limited interpretability of connectivity networks, and the imbalance in datasets that often skews classification performance. Experimental results demonstrate the pipeline's effectiveness in overcoming imbalanced data challenges and extracting features from noisy and complex data, with Regression Dynamic Causal Modeling (RDCM) achieving the highest classification metrics, including 90.06% accuracy and 89.09% sensitivity. This method identified 15 brain regions with strong diagnostic potential, offering improved sensitivity and specificity for schizophrenia diagnosis Compared to contemporary domain techniques.

关键词： Sensitivity Accuracy Pipelines Machine learning Schizophrenia Functional magnetic resonance imaging Feature extraction Brain modeling Noise measurement Data mining

来源：评论

学校读者我要写书评

暂无评论

Anomalous Behavior Identification with Visual Federated Learning in Multi-UAVs Systems

Anomalous Behavior Identification with Visual Federated Lear...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Pengfei Wang Xinrui Yu Yefei Ye Heng Qi Shuo Yu Leyou Yang Qiang Zhang School of Computer Science and Technology Dalian University of Technology Dalian China Ministry of Education Key Laboratory of Social Computing and Cognitive Intelligence (Dalian University of Technology) Dalian China School of Computer Science and Engineering Northeastern University Shenyang China

Anomaly detection aims to identify data or behav-iors that are different from the usual patterns. In traditional anomaly detection settings, edge devices collect the data and send it to a centralized server for model training, which faces two critical issues: (1) it risks data exposure during transmission; (2) it demands a large amount of network bandwidth for data transfer. To tackle these problems, we propose a Visual Federated Learning algorithm (VFLA) for anomalous behavior identification in the multi-UAVs system. To the best of our knowledge, we are the first to merge federated learning with video-based anomaly detection. VFLA consists of two phases: The initial phase is training a pseudo-label generator. UAVs collect a dataset and manually annotate it. This labeled data is then used to train the pseudo-label generator on the server, which is subsequently distributed back to the UAVs. The second phase is the federated learning-based anomaly detection model training. UAVs leverage the pseudo-label generator to automatically annotate the collected video footage. These annotated videos are fed into an anomaly detection network for training. Once the local training is completed, UAVs upload their local models to a server for federated aggregation. The global model is then redistributed to the UAVs for additional training rounds, until reach the target accuracy. Finally, we simulate the federated learning anomaly detection algorithm on the Shanghai-tech dataset, it demonstrates an average accuracy boost of 5.6% compared to baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stock Price Prediction and Recommendation Approach Based on Machine Learning 4

Stock Price Prediction and Recommendation Approach Based on ...

引用

4th IEEE Eurasia Conference on IoT, Communication and engineering, ECICE 2022

作者： Chang, Chin-Chih Luo, Kei-Wen Hsiao, Sean Chung Hua University Bachelor's Program in Applied Foreign Language and Smart Commerce Hsinchu Taiwan Chung Hua University Department of Computer Science and Information Engineering Hsinchu Taiwan

ISBN: (纸本)9781665482080

Investment is a lifetime work. Investing in stocks is a popular measure. However, investing in stocks is not easy, and losing money is not uncommon. We investigate if there is a systematic way to find buyable stocks and more importantly when to buy and sell them. Nowadays, with the progress of hardwarel, artificial intelligence (AI) has become a feasible solution to many issues. Machine learning and deep learning are two widely adopted methods in AI. In this study, we show how to apply machine learning to stock prediction and recommendation. After trials, we found that LightGBM shows its potential to predict and recommend stocks. We used the data of the Taiwan stock market to validate the method. We compared the prediction and recommendation with the wellknown Taiwan ETFs 0050 and 0056. The results show that the method is feasible, effective, efficient, and has better performance than Taiwan ETFs 0050 and 0056. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review of Knowledge Sharing Practices in Academic Institutions 3

A Systematic Literature Review of Knowledge Sharing Practice...

引用

3rd International Conference on Informatics, Multimedia, Cyber, and Information System, ICIMCIS 2021

作者： Purba, Mariana Ermatita, Ermatita Abdiansah, Abdiansah Ayumi, Vina Noprisson, Handrie Ratnasari, Anita Universitas Sriwijaya Doctoral Program in Engineering Palembang Indonesia Universitas Sriwijaya Faculty of Computer Science Palembang Indonesia Universitas Sriwijaya Faculty of Computer Science South Sumatera Indonesia Universitas Mercu Buana Faculty of Computer Science Jakarta Indonesia

ISBN: (纸本)9781665427333

Many knowledge-sharing activities take place in educational institutions, both formally and informally. If this activity is organized with good knowledge management, then this will support a faster knowledge sharing process to get quality and innovative ideas. This paper aims to obtain a summary of existing research, issues, and opportunities for further analysis on knowledge-sharing (KS) practices in academic institutions. The phases of the systematic literature review (SLR) method are described based on Kitchenham (2009) guideline. We found 21 articles, seven articles from IEEE, nine articles from science Direct, and five articles from Springer. The collection of research data on knowledge sharing has been carried out in the United States, Australia, China, Cyprus, United Kingdom, Ghana, Hungary, Indonesia, Iran, Israel, Italy, Jordanian, Malaysia, and Saudi Arabia, with the most research locations being Malaysia (14%) and Saudi Arabia (19%). We also attempted to identify the research topic trend of knowledge sharing research in academic institutions. We found two types of research trends of knowledge sharing research in university, including factor analysis and architecture development. Of the two categories of research trends, 76% discussed factor analysis, and 24% discussed architectural development. We also identified six methods in KS research including Partial Least Square Structure Equation Modeling (PLS-SEM), questionnaire, data triangulation, focus groups discussion, observation and interview. Moreover, the most used method in related research is questionnaire, because it is a relatively inexpensive, fast and efficient way of collecting large amounts of information. © 2021 IEEE.

关键词： Factor analysis

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：