检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Peng, Bo Burns, Ben Chen, Ziqi Parthasarathy, Srinivasan Ning, Xia Department of Computer Science and Engineering The Ohio State University Columbus United States Department of Biomedical Informatics The Ohio State University Columbus United States Translational Data Analytics Institute The Ohio State University Columbus United States

In recent years, with large language models (LLMs) achieving state-of-the-art performance in context understanding, increasing efforts have been dedicated to developing LLM-enhanced sequential recommendation (SR) methods. Considering that most existing LLMs are not specifically optimized for recommendation tasks, adapting them for SR becomes a critical step in LLM-enhanced SR methods. Though numerous adaptation methods have been developed, it still remains a significant challenge to adapt LLMs for SR both efficiently and effectively. To address this challenge, in this paper, we introduce a novel side sequential network adaptation method, denoted as SSNA, for LLM-enhanced SR. SSNA features three key designs to allow both efficient and effective LLM adaptation. First, SSNA learns adapters separate from LLMs, while fixing all the pre-trained parameters within LLMs to allow efficient adaptation. In addition, SSNA adapts the top-a layers of LLMs jointly, and integrates adapters sequentially for enhanced effectiveness (i.e., recommendation performance). We compare SSNA against five state-of-the-art baseline methods on five benchmark datasets using three LLMs. The experimental results demonstrate that SSNA significantly outperforms all the baseline methods in terms of recommendation performance, and achieves substantial improvement over the best-performing baseline methods at both run-time and memory efficiency during training. Our analysis shows the effectiveness of integrating adapters in a sequential manner. Our parameter study demonstrates the effectiveness of jointly adapting the top-a layers of LLMs. © 2023, CC BY.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Optical Fibre FPI End-Tip based Sensor for Protein Aggregation Detection

Optical Fibre FPI End-Tip based Sensor for Protein Aggregati...

引用

2022 IEEE International Conference on E-health Networking, Application and Services, HealthCom 2022

作者： Fatima Domingues, M. Direito, Ines Sousa, Carolina Radwan, Ayman Antunes, Paulo Andre, Paulo Helguero, Luisa Alberto, Nelia Khalifa University Department of Biomedical Engineering Abu Dhabi United Arab Emirates Instituto de Telecomunicações University of Aveiro Aveiro Portugal IBiMEd University of Aveiro Aveiro Portugal Department of Physics University of Aveiro Aveiro Portugal Department of Electronics Telecommunications and Informatics University of Aveiro Aveiro Portugal I3N Department of Physics University of Aveiro Aveiro Portugal Department of Electrical and Computer Engineering Instituto de Telecomunicações Instituto Superior Técnico University of Lisbon Lisbon Portugal

ISBN: (数字)9781665480161

ISBN: (纸本)9781665480161

The detection of protein aggregates and its concentration, plays a relevant role in several fronts, namely at the detection of neurodegenerative diseases such as Alzheimer's, and the assessment of cellular stress linked to cell death. Evaluation of protein aggregation is an essential step of quality control in all stages of biopharmaceutical synthesis and transport, in order to guarantee the activity and desired immunogenicity of their products. The detection of protein aggregates often requires the use of expensive and complex techniques. Here we propose a fast and easy implementation solution, based on an optical fibre Fabry-Perot Interferometer (FPI) end tip resonator. The solution proposed revealed to be effective on the detection of protein aggregates, providing similar results as the ones obtained using a commercial spectrometer for fluorescence detection. © 2022 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Should Users Trust Their Android Devices? A Scoring System for Assessing Security and Privacy Risks of Pre-Installed Applications

arXiv

引用

arXiv 2022年

作者： Ozbay, Abdullah Bicakci, Kemal TOBB University of Economics and Technology Ankara06520 Turkey Informatics Institute and Computer Engineering Department Istanbul Technical University Istanbul34469 Turkey

Android devices are equipped with many preinstalled applications which have the capability of tracking and monitoring users. Although applications coming pre-installed pose a great danger to user security and privacy, they have received little attention so far among researchers in the field. In this study, we collect a dataset comprising such applications and make it publicly available. Using this dataset, we analyze tracker SDKs, manifest files and the use of cloud services and report our results. We also conduct a user survey to understand concerns and perceptions of users. Last but not least, we present a risk scoring system which assigns scores for smart phones consolidating our findings based on carefully weighted criteria. With this scoring system, users could give their own trust decisions based on the available concise information about the security and privacy impacts of applications pre-installed on their Android devices. © 2022, CC BY-NC-SA.

关键词： Mobile security

来源：评论

学校读者我要写书评

暂无评论

A Systematic Overview on Simulation of Connected Vehicles Infrastructure in Smart Cities

A Systematic Overview on Simulation of Connected Vehicles In...

引用

Advanced Innovations in Smart Cities (ICAISC), International Conference on

作者： Manik Gupta Imed Ben Dhaou Kamal Deep Garg Bhisham Sharma Chitkara University School of Engineering and Technology Chitkara University Himachal Pradesh India Department of Computer Science Hekma School of Engineering Computing and Informatics Dar Al-Hekma University Jeddah Saudi Arabia Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

The development and use of connected vehicles are becoming increasingly important areas of study in the wireless networking and transportation research communities. These networks can provide various services such as collision warning. Unlike other types of devices, such as hand-held devices, the vehicles’ nodes are not limited by their energy consumption and storage capacity. Therefore, the development of connected networks can be carried out with minimal resources. It is necessary to run a simulation in order to determine whether they are feasible. The availability of multiple devices and protocols has led to the creation of new utilization scenarios. Due to the complexity of the task, many simulation tools were developed during the past few years. This paper systematically reviews the current state of these tools and discusses their capabilities to evaluate the various scenarios related to the development of connected vehicles network.

关键词： Wireless communication Technological innovation Connected vehicles Systematics Smart cities Vehicular ad hoc networks Transportation

来源：评论

学校读者我要写书评

暂无评论

Classes versus Communities: Outlier Detection and Removal in Tabular Datasets via Social Network Analysis (ClaCO)

Classes versus Communities: Outlier Detection and Removal in...

引用

International Conference on Advances in Social Network Analysis and Mining, ASONAM

作者： Serkan Ucer Tansel Özyer Reda Alhajj The Scientific and Technological Research Council of Turkey (TUBITAK) Ankara Türkiye Department of Computer Engineering Ankara Medipol University Ankara Turkey Department of Computer Science University of Calgary Alberta Canada Department of Computer Engineering Istanbul Medipol University Istanbul Turkey Department of Health Informatics University of Southern Denmark Odense Denmark

In this research, we introduce a model to detect inconsistent & anomalous samples in tabular labeled datasets which are used in machine learning classification tasks, frequently. Our model, abbreviated as the ClaCO (Classes vs. Communities: SNA for Outlier Detection), first converts tabular data with labels into an attributed and labeled undirected network graph. Following the enrichment of the graph, it analyses the edge structure of the individual egonets, in terms of the class and community belongings, by introducing a new SNA metric named as ‘the Consistency Score of a Node - CSoN’. Through an exhaustive analysis of the ego network of a node, CSoN tries to exhibit consistency of a node by examining the similarity of its immediate neighbors in terms of shared class and/or shared community belongings. To prove the efficiency of the proposed ClaCO, we employed it as a subsidiary method for detecting anomalous samples in the train part in the traditional ML classification task. With the help of this new consistency score, the least CSoN scored set of nodes flagged as outliers and removed from the training dataset, and remaining part fed into the ML model to see the effect on classification performance with the ‘whole’ dataset through competing outlier detection methods. We have shown this outlier detection model as an efficient method since it improves classification performance both on the whole dataset and reduced datasets with competing outlier detection methods, over several known both real-life and synthetic datasets.

关键词： Training Measurement Social networking (online) Image edge detection Machine learning Task analysis Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Analysis of a Data Set to Determine the Dependence of Airline Passenger Satisfaction 7th

Analysis of a Data Set to Determine the Dependence of Airlin...

引用

7th Computational Methods in Systems and Software, CoMeSySo 2023

作者： Tynchenko, V.S. Borodulin Kleshko, I.I. Nelyub, V.A. Rukosueva Artificial Intelligence Technology Scientific and Education Center Bauman Moscow State Technical University Moscow105005 Russia Peter the Great St. Petersburg Polytechnic University Saint Petersburg Russia Department of Information Economic System Institute of Engineering and Economics Reshetnev Siberian State University of Science and Technology Krasnoyarsk660037 Russia Department of Systems Analysis and Operations Research Institute of Informatics and Telecommunications Reshetnev Siberian State University of Science and Technology Krasnoyarsk660037 Russia Information-Control Systems Department Institute of Computer Science and Telecommunications Reshetnev Siberian State University of Science and Technology Krasnoyarsk660037 Russia Department of Technological Machines and Equipment of Oil and Gas Complex School of Petroleum and Natural Gas Engineering Siberian Federal University Krasnoyarsk660041 Russia

ISBN: (纸本)9783031535512

This paper presents an analysis of a data set to determine the factors influencing airline passenger satisfaction. The study examines various criteria such as gender, customer type, age, travel type, class, and range to assess their impact on passenger satisfaction. The dataset consists of 25 columns, including attributes like Wi-Fi availability, convenience of online booking, seat comfort, in-flight entertainment, baggage handling, and overall satisfaction. The sample is relatively balanced, with equal representation of men and women, predominantly repeat customers, and a majority flying for business purposes. Key findings include a strong correlation between departure and arrival delays, higher satisfaction among passengers in business class, and positive ratings for Wi-Fi service correlating with overall satisfaction. Correlation analysis reveals interdependencies between different attributes, such as the influence of cleanliness on seat comfort and food and beverage ratings. In addition, a neural network forecasting model is used to estimate the average ratings of passengers, although with low accuracy, which was later excluded. Finally, a decision tree algorithm is utilized to identify the most significant attributes affecting passenger satisfaction words. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Baggage handling

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based real time detection for cardiac objects with fetal ultrasound video

引用

informatics in Medicine Unlocked 2023年 36卷

作者： Iriani Sapitri, Ade Nurmaini, Siti Naufal Rachmatullah, Muhammad Tutuko, Bambang Darmawahyuni, Annisa Firdaus, Firdaus Rini, Dian Palupi Islami, Anggun Intelligent System Research Group Faculty of Computer Science Universitas Sriwijaya Palembang 30139 Indonesia Doctoral Program Faculty of Engineering Universitas Sriwijaya Palembang 30139 Indonesia Department of Informatics Engineering Faculty of Computer Science Universitas Sriwijaya Palembang 30139 Indonesia

Fetal cardiac anatomical structure interpretation by ultrasound (US) is a key part of prenatal assessment. Unfortunately, the numerous speckles in US video, the small size of fetal cardiac structures, and unfixed fetal positions make manual detection processes difficult. To alleviate such problems, a deep learning model was developed to fully automate the processing of fetal echocardiographs with 2-dimensional cross-sectional images. The weakness of such an approach is that a physician immediately interprets US video with 3-dimensional objects to diagnose patients in clinical practice. To improve fetal cardiac anatomical structure interpretation via US for accurate and real time diagnosis, this paper proposes a real-time fetal cardiac substructure detection using US video with the You Only Look Once (YOLO) framework. In YOLO, an end-to-end neural network makes predictions for cardiac substructure objects, boxes, and class probabilities simultaneously. To achieve reliable performance, 40 fetal echocardiography videos were trained with the new YOLOv7 architecture and fine-tuned to work optimally and run efficiently. We conducted with nine fetal cardiac substructure objects such as the left atrium, right atrium, left ventricle, right ventricle, tricuspid valve, pulmonary valve, mitral valve, aortic valve, and aorta. The results yielded the highest mean average precision of 82.10%, reaching 17 frames per second (FPS) for nine cardiac substructure objects in 0.3 ms. The main finding of our study is that with even a limited number of US videos, YOLOv7 can detect fetal cardiac substructure objects in real-time. Such a network can work efficiently to detect small fetal cardiac objects automatically in a rapid phase with the help of proper fine-tuning. This work mainly assists medical experts in the fetal cardiac anatomy diagnostic process. © 2022 The Authors

关键词： computer vision Fetal echocardiography Object detection YOLOv7

来源：评论

学校读者我要写书评

暂无评论

Geoelectric Sounding for Identification of Aquifer Layer in East Turatea Village South Sulawesi Province

Geoelectric Sounding for Identification of Aquifer Layer in ...

引用

4th International Conference on Mathematics, Science, Education and Technology, ICOMSET 2020, in Conjunction with the 2nd International Conference on Biology, Science and Education, ICoBioSE 2020

作者： Nurfalaq, Aryadi Jumardi, Andi Manrulu, Rahma Hi Nawir, Alfian Prasetyawati Umar, Emi Informatics Department Faculty of Computer Engineering Universitas Cokroaminoto Palopo Palopo Indonesia Physics Department Faculty of Science Universitas Cokroaminoto Palopo Palopo Indonesia Mining Engineering Department Faculty of Industrial Technology Universitas Muslim Indonesia Makassar Indonesia

East Turatea Village farmers still depend on rainwater for irrigating their rice fields. This study aims to identify groundwater aquifers in the village of East Turatea which can be used as water sources in irrigating rice fields. The method used is the correlation of well data and Vertical Electric Sounding (VES). Well data is result of water table mapping at three measuring stations. Measure the resistivity of rock using a resistivity meter with a length of 200 m with two Vertical Electric Sounding (VES) points. The measurement results are then processed using Progress software to produce a Vertical Electric Sounding (VES) with a resistivity variation to depth. The result this study found that East Turatea Village's groundwater system in the form of shallow groundwater aquifer has a resistivity value of 0.84-5.5 Ohm.m at a depth of 6.04-31.88 m. Meanwhile, deep groundwater aquifers are at a depth of more than 53.8 m with a resistivity value of 1.94 - 2.75 Ohm.m. East Turatea Village groundwater aquifer is estimated to consist of permeable layer such as sand which is in a saturated zone. © Published under licence by IOP Publishing Ltd.

关键词： Aquifers

来源：评论

学校读者我要写书评

暂无评论

Action Localization and Recognition through Unsupervised I3D and TSN

Action Localization and Recognition through Unsupervised I3D...

引用

Computing and Information Technology (ICCIT-1441), 2020 International Conference on

作者： Munzir Umran Kahlil Muchtar Taufik Fuadi Abidin Fitri Arnia Dept. of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh Indonesia Dept. of Electrical and Computer Engineering Telematics Research Center (TRC) Universitas Syiah Kuala Banda Aceh Indonesia Department of Informatics Faculty of Mathematics and Natural Sciences Universitas Syiah Kuala Banda Aceh Indonesia

Since CCTV technology was widely introduced as a video surveillance system, it has become very popular due to increased security concerns. However, detecting suspicious behavior is still done manually by humans, which is inefficient in terms of accuracy and manpower (prone to distraction and fatigue). Many studies use the entire frame of a video to recognize human action, whereas in this study first localize the area of object movement using the unsupervised inflated 3D (I3D) network which produces several frames that have been determined as the region of interest (ROI) from the total frames in the video. Then the collection of ROI frames is generated into a video which will then be classified to recognize human action through the Temporal Segment Networks (TSN). For efficiency purposes, the proposed pipeline can be run separately in the edge (for localization), and cloud environment (for recognition), respectively. The results show that there are 54 classes of ROI video data sets that have an average human action recognition prediction similarity rate above 84.6% which is the average of the prediction similarity rate of the entire ROI video data. In terms of prediction accuracy, 37 classes of data (36.63%) are better than the original class, including 25 classes of data (24.75%) above the threshold, and the processing speed of classification with ROI video data is on average 5 times faster than full-frame video data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Age-of-Information and Energy Optimization in Digital Twin Edge Networks

arXiv

引用

arXiv 2024年

作者： Guo, Yongna Fu, Yaru Zhang, Yan Quek, Tony Q.S. School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden School of Science and Technology Hong Kong Metropolitan University Hong Kong Department of Informatics University of Oslo Oslo Norway Singapore University of Technology and Design Singapore

In this paper, we study the intricate realm of digital twin synchronization and deployment in multi-access edge computing (MEC) networks, with the aim of optimizing and balancing the two performance metrics Age of Information (AoI) and energy efficiency. We jointly consider the problems of edge association, power allocation, and digital twin deployment. However, the inherent randomness of the problem presents a significant challenge in identifying an optimal solution. To address this, we first analyze the feasibility conditions of the optimization problem. We then examine a specific scenario involving a static channel and propose a cyclic scheduling scheme. This enables us to derive the sum AoI in closed form. As a result, the joint optimization problem of edge association and power control is solved optimally by finding a minimum weight perfect matching. Moreover, we examine the one-shot optimization problem in the contexts of both frequent digital twin migrations and fixed digital twin deployments, and propose an efficient online algorithm to address the general optimization problem. This algorithm effectively reduces system costs by balancing frequent migrations and fixed deployments. Numerical results demonstrate the effectiveness of our proposed scheme in terms of low cost and high efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Energy utilization

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：