检索结果-内蒙古大学图书馆

Sociotechnical safeguards for genomic data privacy (vol 23, pg 429, 2022)

NATURE REVIEWS GENETICS 2022年第7期23卷 453-453页

作者： Wan, Zhiyu Hazel, James W. Clayton, Ellen Wright Vorobeychik, Yevgeniy Kantarcioglu, Murat Malin, Bradley A. Center for Genetic Privacy and Identity in Community Settings Vanderbilt University Medical Center Nashville TN USA Department of Computer Science Vanderbilt University Nashville TN USA Department of Biomedical Informatics Vanderbilt University Medical Center Nashville TN USA Center for Biomedical Ethics and Society Vanderbilt University Nashville TN USA Vanderbilt University Law School Nashville TN USA Department of Biostatistics Vanderbilt University Medical Center Nashville TN USA Department of Computer Science and Engineering Washington University in St. Louis St. Louis MO USA Department of Computer Science University of Texas at Dallas Richardson TX USA

Recent developments in a variety of sectors, including health care, research and the direct-to-consumer industry, have led to a dramatic increase in the amount of genomic data that are collected, used and shared. This state of affairs raises new and challenging concerns for personal privacy, both legally and technically. This Review appraises existing and emerging threats to genomic data privacy and discusses how well current legal frameworks and technical safeguards mitigate these concerns. It concludes with a discussion of remaining and emerging challenges and illustrates possible solutions that can balance protecting privacy and realizing the benefits that result from the sharing of genetic information.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Simulation-Optimization Model for Automated Parcel Lockers Network Design in Urban Scenarios in Pamplona (Spain), Zakopane, and Krakow (Poland) 22

A Simulation-Optimization Model for Automated Parcel Lockers...

引用

Proceedings of the Winter Simulation Conference

作者： Bartosz Sawik Adrian Serrano-Hernandez Aitor Ballano Javier Faulin Department of Business Informatics and Engineering Management AGH University of Science and Technology Krakow POLAND Institute of Smart Cities Department of Statistics Computer Science and Mathematics Public University of Navarre Pamplona SPAIN

The constant rise of e-commerce coupled with extremely fast deliveries is a significant contributor to saturate city centers' mobility. To address this issue, the development of a convenient Automated Parcel Lockers (APLs) network improves last-mile distribution by reducing the number of transportation vehicles, the distances driven, and the delivery stops. This article aims to define and compare APL networks in the cities of Pamplona (Spain), Zakopane and Krakow (Poland). Thereby, a bi-criteria weighted-sum simulation optimization model is developed for a representative year for the aforementioned cities. The simulation forecasts the e-commerce demands whereas the optimal APL network is obtained with a bi-criteria maximum APL revenues and minimum network costs. Meaningful results are obtained from the multi-criteria hybrid model outcomes as well as from the cities comparison. These outcomes suggest efficient APLs networks considering cultural and demographic factors for a massive use of APLs in high-demand periods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autoregressive Attention Neural Networks for Non-Line-of-Sight User Tracking with Dynamic Metasurface Antennas

arXiv

引用

arXiv 2023年

作者： Stylianopoulos, Kyriakos Bayraktar, Murat González-Prelcic, Nuria Alexandropoulos, George C. Department of Informatics and Telecommunications National and Kapodistrian University of Athens Panepistimiopolis Ilissia Athens15784 Greece Department of Electrical and Computer Engineering North Carolina State University Raleigh27695 United States

User localization and tracking in the upcoming generation of wireless networks have the potential to be revolutionized by technologies such as the Dynamic Metasurface Antennas (DMAs). Commonly proposed algorithmic approaches rely on assumptions about relatively dominant Line-of-Sight (LoS) paths, or require pilot transmission sequences whose length is comparable to the number of DMA elements, thus, leading to limited effectiveness and considerable measurement overheads in blocked LoS and dynamic multipath environments. In this paper, we present a two-stage machine-learning-based approach for user tracking, specifically designed for non-LoS multipath settings. A newly proposed attention-based Neural Network (NN) is first trained to map noisy channel responses to potential user positions, regardless of user mobility patterns. This architecture constitutes a modification of the prominent vision transformer, specifically modified for extracting information from high-dimensional frequency response signals. As a second stage, the NN’s predictions for the past user positions are passed through a learnable autoregressive model to exploit the time-correlated channel information and obtain the final position predictions. The channel estimation procedure leverages a DMA receive architecture with partially-connected radio frequency chains, which results to reduced numbers of pilots. The numerical evaluation over an outdoor ray-tracing scenario illustrates that despite LoS blockage, this methodology is capable of achieving high position accuracy across various multipath settings. © 2023, CC BY-SA.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

IDA: Informed Domain Adaptive Semantic Segmentation

arXiv

引用

arXiv 2023年

作者： Chen, Zheng Ding, Zhengming Gregory, Jason M. Liu, Lantao Luddy School of Informatics Computing and Engineering Indiana University BloomingtonIN47408 United States The Department of Computer Science Tulane University United States DEVCOM Army Research Laboratory United States

Mixup-based data augmentation has been validated to be a critical stage in the self-training framework for unsupervised domain adaptive semantic segmentation (UDA-SS), which aims to transfer knowledge from a well-annotated (source) domain to an unlabeled (target) domain. Existing self-training methods usually adopt the popular region-based mixup techniques with a random sampling strategy, which unfortunately ignores the dynamic evolution of different semantics across various domains as training proceeds. To improve the UDA-SS performance, we propose an Informed Domain Adaptation (IDA) model, a self-training framework that mixes the data based on class-level segmentation performance, which aims to emphasize small-region semantics during mixup. In our IDA model, the class-level performance is tracked by an expected confidence score (ECS). We then use a dynamic schedule to determine the mixing ratio for data in different domains. Extensive experimental results reveal that our proposed method is able to outperform the state-of-the-art UDA-SS method by a margin of 1.1 mIoU in the adaptation of GTA-V to Cityscapes and of 0.9 mIoU in the adaptation of SYNTHIA to Cityscapes. Code link: https://***/ArlenCHEN/*** Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Comparison of Parallel and Serial Execution of Shortest Path Algorithms

Comparison of Parallel and Serial Execution of Shortest Path...

引用

International Conference on Computational Intelligence and Knowledge Economy (ICCIKE)

作者： Ahmed Taha Ameen Ahmed M. Fouad Emil Mourad Matta Rawan Abdelkhalek Elkhishen Shorouk Abdelfattah Alalem Aya Mohamed Safan Islam Tharwat Abdel Halim School of Engineering and Applied Sciences Nile University Giza Egypt School of Information Technology and Computer Science Nile University Giza Egypt Center of Informatics (CIS) Nile University Giza Egypt

Shortest Path Algorithms are an important set of algorithms in today’s world. It has many applications like Traffic Consultation, Route Finding, and Network Design. It is essential for these applications to be fast and efficient as they mostly require real-time execution. Sequential execution of shortest path algorithms for large graphs with many nodes is time-consuming. On the other hand, parallel execution can make these applications faster. In this paper, three popular shortest path algorithms - Dijkstra, Bellman-Ford, and Floyd Warshall - are both implemented as serial and parallel programs and tested on various problem sizes. The performance of these algorithms is evaluated by comparing their execution times. To achieve parallelization, the OpenMP (Open multiprocessing) framework is employed.

关键词： Real-time systems Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Leveraging the Pre-Trained Whisper Model and Levenshtein Distance for Audio Buginesse Transcription

Leveraging the Pre-Trained Whisper Model and Levenshtein Dis...

引用

informatics International Conference (BTS-I2C), Beyond Technology Summit on

作者： Amirul Mukmin Adnan Abdul Jalil Mahabintang Pallawabonang Esa Prakasa Yuyun Dept. of informatics engineering Handayani University of Makassar Makassar Indonesia Dept. of computer system Handayani University of Makassar Makassar Indonesia Research center for data and information science National Research and Innovation Agency Bandung Indonesian

ISBN: (数字)9798331508579

ISBN: (纸本)9798331508586

This research aims to transcribe audio into text using the pre-trained Whisper model, focusing on Bugis, a low-resource language. A key challenge in transcribing local languages like Bugis is the limited availability of language model. To address this, we implemented an algorithmic correction approach that does not require extensive datasets or computationally demanding customizations. The Whisper model provides an initial transcription, serving as a foundation; however, the output often lacks accuracy due to the absence of specific adjustments for Bugis. To enhance accuracy, we applied the Levenshtein distance algorithm to correct word errors by comparing transcription results with entries in a Bugis language dataset based on similarity. Although this method is not fully precise and depends on the completeness of the reference dataset, evaluation results indicate that it effectively lowers the word error rate (WER) and improves transcription accuracy. This research produces SRT files containing transcripts that have been corrected using the Levenhstein distance algorithm, which not only improves accessibility but also contributes to the preservation of Bugis language through digital media. This approach is expected to provide a practical solution to improve transcription accuracy and support more accurate documentation in Bugis language preservation efforts.

关键词： Accuracy Error analysis Computational modeling Focusing Speech recognition Documentation Media Linguistics Synchronization informatics

来源：评论

学校读者我要写书评

暂无评论

Stock Price Forecasting in Finance with Artificial Neural Networks

Stock Price Forecasting in Finance with Artificial Neural Ne...

引用

Information engineering (ACIE), IEEE Asia Conference on

作者： Turgut Daloğlu Garibe Osi Murat Aslan Mehmet Beşkirli Cizre District Directorate of National Education Şırnak University Şırnak Türkiye Department of Computer Engineering Şırnak University Şırnak Türkiye Departmen of Medical Education and Informatics Faculty of Medicine Karamanoğlu Mehmetbey University Karaman Türkiye

ISBN: (数字)9798331528409

ISBN: (纸本)9798331528416

This paper examines the applications of Artificial Neural Networks (ANNs) in the field of finance, particularly in stock price forecasting. Artificial neural networks are mathematical models that mimic biological nervous systems and are used to solve complex problems such as financial data analysis. Stock price forecasting is an important topic for investors and finance professionals. Artificial neural networks have been widely used in this field due to their ability to process large amounts of financial data, learn complex relationships and predict future price movements. This study deals with stock price forecasting with artificial neural networks using historical stock prices, economic indicators and other financial data. Neural networks attempt to predict future price movements by learning the complex relationships between these data. Stock price forecasting with artificial neural networks can offer a more flexible and adaptive approach than traditional statistical methods. However, the success of the model depends on factors such as the quality of the data set used, network architecture and training parameters. This study was conducted to understand the potential of artificial neural networks in finance and to evaluate their effectiveness in stock price forecasting. The purpose of this study is to explore how artificial neural networks can be used in financial data analysis, and in particular their potential in stock price forecasting. The study is designed to understand the advantages of applying ANN in finance, to evaluate the stock price forecasting performance of this technology and to provide a new perspective that can influence future investment strategies.

关键词： Training Accuracy Statistical analysis Finance Training data Predictive models Data models Forecasting Long short term memory Testing

来源：评论

学校读者我要写书评

暂无评论

Robustness Evaluation of Machine Learning Models for Robot Arm Action Recognition in Noisy Environments

Robustness Evaluation of Machine Learning Models for Robot A...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Elaheh Motamedi Kian Behzad Rojin Zandi Hojjat Salehinejad Milad Siami Department of Electrical & Computer Engineering Northeastern University Boston MA USA Kern Center for the Science of Health Care Delivery Mayo Clinic Rochester MN USA Department of Artificial Intelligence and Informatics Mayo Clinic Rochester MN USA

In the realm of robot action recognition, identifying distinct but spatially proximate arm movements using vision systems in noisy environments poses a significant challenge. This paper studies robot arm action recognition in noisy environments using machine learning techniques. Specifically, a vision system is used to track the robot's movements followed by a deep learning model to extract the arm's key points. Through a comparative analysis of machine learning methods, the effectiveness and robustness of this model are assessed in noisy environments. A case study was conducted using the Tic-Tac-Toe game in a 3-by-3 grid environment, where the focus is to accurately identify the actions of the arms in selecting specific locations within this constrained environment. Experimental results show that our approach can achieve precise key point detection and action classification despite the addition of noise and uncertainties to the dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI Based Prediction for Heart Disease: A Comparative Analysis and an Improved Machine Learning Approach

AI Based Prediction for Heart Disease: A Comparative Analysi...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Jay Raval Jai Prakash Verma Sardar N. M. Islam Rachna Jain Narina Thakur Computer Science Engineering Department Institute of Technology Nirma University Ahmedabad India Applied Informatics Research Victoria University Melbourne Australia Department of Computer Science and Engineering Bhagwan Parshuram Institute of Technology Delhi India

Heart disease problems are growing day by day in the world. Many factors are responsible for increasing the chance of heart attack and any other disease. Many countries have a low level of cardiovascular competence in predicting heart disease-related issues. Finding the best accurate machine learning classifiers for various diagnostic uses by data mining and machine learning techniques aids in predicting whether or not the heart disease-related issue will occur. To predict heart disease, a number of supervised machine-learning algorithms are used and their effectiveness are evaluated. With the exceptionof MLP and KNN, all applied algorithms had their estimated feature significance scores for each feature. This helps to find the main factors affecting heart disease and the accuracy of the model, which helps to get the best prediction. At the end of the research the support vector machine gives us 87.91 % highest testing accuracy compare with all applied machine learning algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Auto-Handover Gateway LoRaWAN based on Autonomous Vehicles

Auto-Handover Gateway LoRaWAN based on Autonomous Vehicles

引用

Information Technology International Seminar (ITIS)

作者： Iwan Purnama Rahmadani Pane Adri Gabriel Sooai Firman Edi Ahmad Abdul Chamid Puput Dani Prasetyo Adi Department of Information Technology Faculty of Science and Technology Universitas Labuhanbatu Labuhanbatu Indonesia Department of Computer Engineering Faculty of Computer Science Universitas Katolik Widya Mandira Kupang NTT Indonesia Department of Engineering Management Faculty of Industrial Technology Batam Institute of Technology Batam City Indonesia Department of Informatics Engineering Muria Kudus University Kudus Indonesia Department of Telecommunication National Research and Innovation Agency (BRIN) Bandung Indonesia

ISBN: (数字)9798331521295

ISBN: (纸本)9798331521301

This article presents a simulation study on the use of LoRaWAN technology in autonomous vehicles. The research focuses on developing an Auto-Handover Gateway for Autonomous Vehicles, utilizing LoRaWAN parameters such as bit rates, spreading factor (SF), packet loss, and received signal strength. These parameters are tested in simulations of autonomous vehicle movements, which include both regular and random motion patterns. The aim is to assess the performance of LoRaWAN in different scenarios and its impact on communication in autonomous vehicle systems. The simulation results show several key trends. As the vehicle moves further, the spreading factor (SF) increases, and bit rates tend to decrease, indicating a drop in communication performance over longer distances. The research also identifies that the gateway with the closest proximity to the vehicle is selected, both in random and non-random movement scenarios. Additionally, packet loss increases as the distance between the vehicle and the gateway grows, highlighting the challenges of maintaining reliable communication over long distances. These findings provide insights into optimizing LoRaWAN parameters for real-time communication in autonomous vehicles, contributing to the development of intelligent vehicle networks.

关键词： Seminars Simulation Bit rate LoRaWAN Packet loss Logic gates Market research Real-time systems Reliability Autonomous vehicles

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：