检索结果-内蒙古大学图书馆

2nd IEEE National Biomedical engineering Conference, NBEC 2023

作者： Shah Ershad Bin Mohd Azrul Shazril, Mohammad Habib Mashohor, Syamsiah Amran, Mohd Effendi Fatinah Hafiz, Nur Rahman, Aishah A Ali, Azizi Rasid, M. Fadlee A. Safwan A. Kamil, A. Azilah, Nurul Farhana Universiti Putra Malaysia Systems Engineering Faculty of Engineering Dept. of Computer and Communication Selangor Serdang43400 Malaysia Biomedical Sector Engineering Service Division Ministry of Health Putrajaya62590 Malaysia Selangor Serdang43400 Malaysia

ISBN: (纸本)9798350338546

Predictive maintenance on medical equipment is to identify the equipment condition and to forecast when the maintenance is required. In this paper, the Computed Tomography scan machine is deployed with IoT sensors to monitor the environment and machine parameters such as temperature and humidity of the room, current, radiation and acceleration of X axis and Y axis. The readings are processed to ensure they are according to normal distribution and the current readings are acquired when then machine is working well. To generate data of faulty machine condition, synthetic data is created. Data synthesis is also needed to generate more data for the purpose of model's training for machine learning. An artificial neural network has been designed to predict the breakdown probability of the machine and the inputs are all the parameters from the IoT sensors. The collected readings are acquired since September 2022 until January 2023 from one of the hospitals in Klang Valley. The model produced a very good prediction accuracy of 95.91 percent which makes it an acceptable model for the prediction of machine breakdown. The prediction output is also displayed with real data monitoring on the dashboard, hosted by a dedicated server. © 2023 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Triple-Node-Upset Recoverable Radiation-Hardened by Design Latch

Triple-Node-Upset Recoverable Radiation-Hardened by Design L...

引用

Panhellenic Conference on Electronics and Telecommunications (PACET)

作者： Evangelos Paparsenos Yiorgos Tsiatouhas Dept. of Computer Science and Engineering VLSI Systems and Computer Architecture (VCAS) Lab University of Ioannina Ioannina Greece

CMOS technology evolution enhances integrated circuits (ICs) performance characteristics at the cost of their increased susceptibility to radiation and thus to the occurrence of single-event upsets (SEUs) that may lead to soft errors generation. SEUs may affect multiple nodes in a circuit (multiple node upsets - MNUs). Fortunately, these disturbances do not cause permanent damage to the circuits. Various techniques have been proposed to deal with SEUs that concurrently affect one, two or three nodes. In this paper, we propose the design of a latch that offers tolerance up to the level of triple-node upsets (TNUs). This is achieved by using redundancy in the hardware which provides the ability to store a logic value in multiple nodes within the latch as well as by using multiple feedback paths which allow it to recover its correct state in the event of an SEU. Compared to other techniques dealing with the same problem, our proposed method provides faster recovery time (higher than 16.87%) after an SEU, and at the same time reduced power consumption and higher speed performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Characterization of Printed Flexible Humidity Sensor

Design and Characterization of Printed Flexible Humidity Sen...

引用

2024 Symposium on Printed and Wearable Sensors and systems, held at the 245th ECS Meeting

作者： Banothu, Akhil Naik Budhraja, Vinay Sundaravadivel, Prabha Fletcher, Reginald Reddy, Krishna Dept. of Electrical and Computer Engineering The University of Texas at Tyler TylerTX75701 United States Crop Production Systems Research Unit USDA StonevilleMS38776 United States

ISBN: (纸本)9781623326784

The development of humidity sensors is essential for applications in the environmental, agriculture, medical and semiconductor industries. This research focused on using advanced printed board circuit (PCB) printing technology to fabricate a humidity moisture sensor. The fabrication of humidity sensor was done using two different polymers: p-HEMA and polyimide, and the performance was compared. Humidity sensors with p-HEMA showed higher capacitance value and more sensitivity than the humidity sensors with polyimide. The variation in sensitivity was higher between the relative humidity from 60% to 90% than between 45% to 60%. © The Electrochemical Society.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identification

arXiv

引用

arXiv 2024年

作者： Alehdaghi, Mahdi Shamsolmoali, Pourya Cruz, Rafael M.O. Granger, Eric LIVIA ILLS Dept. of Systems Engineering ETS Montreal Canada Dept. of Computer Science University of York United Kingdom

A key challenge in visible-infrared person re-identification (V-I ReID) is training a backbone model capable of effectively addressing the significant discrepancies across modalities. State-of-the-art methods that generate a single intermediate bridging domain are often less effective, as this generated domain may not adequately capture sufficient common discriminant information. This paper introduces Bidirectional Multi-step Domain Generalization (BMDG), a novel approach for unifying feature representations across diverse modalities. BMDG creates multiple virtual intermediate domains by learning and aligning body part features extracted from both I and V modalities. In particular, our method aims to minimize the cross-modal gap in two steps. First, BMDG aligns modalities in the feature space by learning shared and modality-invariant body part prototypes from V and I images. Then, it generalizes the feature representation by applying bidirectional multi-step learning, which progressively refines feature representations in each step and incorporates more prototypes from both modalities. Based on these prototypes, multiple bridging steps enhance the feature representation. Experiments1 conducted on V-I ReID datasets indicate that our BMDG approach can outperform state-of-the-art part-based and intermediate generation methods, and can be integrated into other part-based methods to enhance their V-I ReID performance. © 2024, CC BY.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Explainable Long-Term Forecasting of Air Pollution

Explainable Long-Term Forecasting of Air Pollution

引用

IEEE International Conference on Big Data

作者： Abdul Mutakabbir Samuel A. Ajila Dept. of Systems and Computer Engineering Carleton University Ottawa ON Canada

Long-term air pollution forecasting is essential for making public policies and issuing warnings. This will reduce the impact of pollution on the environment and human health. This research focuses on achieving long-term forecasting of air pollution attributes $(PM 2.5, PM_{10}, SO_{2}$, $NO_{2}, CO$, and $O_{3})$ by providing minimal historical data as input to the model. The best-performing models in this research produced between a 1% increase in RMSE for certain pollutants to a 50% decrease in RMSE for other air pollution attributes (except $CO)$ compared to the initial research on compositional learning, while being able to forecast the trend and seasonality accurately for more than one year into the future. The training time for each pollution attribute model dropped to 4 seconds compared to 1800 seconds in the case of the compositional learning method. This paper also delves into the challenges with long-term forecasting for the Beijing air quality dataset and discusses approaches to overcome these challenges.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RAN Explainable Anomaly Prediction for 6G Networks 29

RAN Explainable Anomaly Prediction for 6G Networks

引用

29th IEEE International Workshop on computer Aided Modeling and Design of Communication Links and Networks, CAMAD 2024

作者： Marantis, Panagiotis Ramantas, Kostas Verikoukis, Christos Universitat Politècnica de Catalunya Dept. of Signal Theory and Communications Barcelona Spain Iquadrat Informatica S.L. Barcelona Spain University of Patras Dept. of Computer Engineering and Informatics Patras Greece Athena Research Center Athens Greece Industrial Systems Institute Patras Greece

ISBN: (纸本)9798350377644

Machine Learning (ML) models integrated into future 6G network architectures are anticipated to address the demanding task of Anomaly Detection (AD) at the Radio Access Network (RAN). A challenging but essential aspect of this task is forecasting anomalies ahead of time, aiming to enable automated interventions to proactively prevent or mitigate service degradation. To address this challenge, we propose an Explainable Anomaly Prediction (XAP) framework, that combines a time series forecasting Long Short-Term Memory Encoder- Decoder (LSTM-ED) model, and an Isolation Forest (IF) anomaly detector whose output is interpreted using the SHAP algorithm. The framework is evaluated using a real- world dataset containing RAN Key Performance Indicators (KPIs) collected from a User Equipment (UE) device. The results validate the effectiveness of our framework in predicting RAN anomalies and identifying the specific KPIs linked to each predicted anomaly. © 2024 IEEE.

关键词： Radio access networks

来源：评论

学校读者我要写书评

暂无评论

Designing and Developing a Mobile Application for Monitoring & Visualizing Blood Pressure Data

Designing and Developing a Mobile Application for Monitoring...

引用

IEEE Sensors Applications Symposium, SAS

作者： Mahsa Sinaei Hamed Laura Reid Alice Olorunnife David Casciano Fateme Rajabiyazdi dept. Systems and Computer Engineering Carleton University Ottawa Canada

High blood pressure is one of the major causes of cardiovascular diseases, renal failure, and even sudden death. To avoid developing these health issues, it is important to consistently monitor blood pressure levels. Monitoring blood pressure levels regularly allows people to observe changes in their blood pressure measurements and contact their healthcare providers for guidance if needed. The aim of this paper is designing and developing a mobile application that can assist individuals to better understand the changes in their blood pressure levels by introducing a novel approach to visualizing blood pressure data and managing missing data. Employing a user-centered design approach, we designed and developed an app. To complete this study, we conducted a literature review to identify key design requirements for such apps and then, designed our low-fidelity prototype based on these design requirements. Next, we consulted with two experts to obtain their feedback on the content, presentation, and usability of our initial low-fidelity prototype. Based on these experts' feedback we designed our mid-fidelity and high-fidelity prototype. Eventually, we conducted a user evaluation study to evaluate our high-fidelity prototype. The results demonstrated this app provides a clear visual representation of blood pressure measurements over time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Service Function Chaining Implementation using VNFs and CNFs

Service Function Chaining Implementation using VNFs and CNFs

引用

IEEE International Conference on Cloud engineering (IC2E)

作者： Abdullah Bittar Ziqiang Wang Changcheng Huang Dept. of Systems and Computer Engineering Carleton University Ottawa Canada

The increasing popularity of cloud-based platforms has led to the emergence of two prominent open-source solutions: OpenStack and Kubernetes. OpenStack facilitates computing and networking resources through virtual machine instances, while Kubernetes excels in container orchestration, managing containerized workloads and services. This paper explores the implementation of Service Function Chaining (SFC) using a combination of virtual machines in OpenStack and containers in Kubernetes. The primary focus of our study is to analyze the performance of containers within the context of chain deployment in Kubernetes. Our experimentation reveals compelling insights into container bootup times, showcasing their efficiency when compared to virtual machines. Additionally, we meticulously evaluate the impact of integrating SFC-related interfaces into pods forming a chain, particularly assessing CPU, memory, and bandwidth utilization. Our findings underline the advantages of utilizing containers in SFC deployment scenarios and shed light on the potential overhead that arises during interface integration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Applying Deep Learning Methods on Spam Review Detection

Applying Deep Learning Methods on Spam Review Detection

引用

International Conference on Computing Methodologies and Communication (ICCMC)

作者： M. Ramu Chinnakotla Jayanth Raj Apthiri Nithish Chandhu Boggula Ganesh Babu G Srikanth K.I Goud Dept. of computer science and systems engineering SVEC Tirupati andhrapradesh

In today's environment, a reliable and effective technique for identifying spam reviews is essential if you want to purchase things online without being taken advantage of. There are possibilities for publishing reviews in many internet locations, which opens the door for sponsored or deceptive fake reviews. These fabricated evaluations may mislead the general audience and leave them unsure of whether or not to believe them. The issue of spam review finding has been solved by the introduction of prominent deep literacy methods. The focus of recent research has been on supervised literacy practices that contain labelled data, which is inadequate for online review. This initiative aims to expose any dishonest textbook reviews. To do this, we've used both labelled and unlabeled data and suggested deep learning techniques for spam review detection, including Multi-Layer Perceptron (MLP), Convolutional Neural Networks (CNN), and a Long Short-Term Memory (LSTM) variation of Recurrent Neural Networks (RNN). We also used standard machine learning classifiers to identify spam reviews, including Naive Bayes (NB), K Nearest Neighbor (KNN), and Support Vector Machine (SVM). Finally, we compared the effectiveness of traditional and deep literacy classifiers. We'll use deep literacy classifiers to boost the finesse and efficiency.

关键词： Support vector machines Deep learning Recurrent neural networks Publishing Manuals programming Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CLIP-IT: CLIP-based Pairing for Histology Images Classification

arXiv

引用

arXiv 2025年

作者： Karimian, Banafsheh Avanzato, Giulia Belharbi, Soufian McCaffrey, Luke Shateri, Mohammadhadi Granger, Eric LIVIA ILLS Dept. of Systems Engineering ETS Montreal Canada Dept. of Computer Engineering University of Cagliari Italy Goodman Cancer Research Centre Dept. of Oncology McGill University Canada

Multimodal learning has shown significant promise for improving medical image analysis by integrating information from complementary data sources. This is widely employed for training vision-language models (VLMs) for cancer detection based on histology images and text reports. However, one of the main limitations in training these VLMs is the requirement for large paired datasets, raising concerns over privacy, and data collection, annotation, and maintenance costs. To address this challenge, we introduce CLIP-IT method to train a vision backbone model to classify histology images by pairing them with privileged textual information from an external source. At first, the modality pairing step relies on a CLIP-based model to match histology images with semantically relevant textual report data from external sources, creating an augmented multimodal dataset without the need for manually paired samples. Then, we propose a multimodal training procedure that distills the knowledge from the paired text modality to the unimodal image classifier for enhanced performance without the need for the textual data during inference. A parameter-efficient fine-tuning method is used to efficiently address the misalignment between the main (image) and paired (text) modalities. During inference, the improved unimodal histology classifier is used, with only minimal additional computational complexity. Our experiments4 on challenging PCAM, CRC, and BACH histology image datasets show that CLIP-IT can provide a cost-effective approach to leverage privileged textual information and outperform unimodal classifiers for histology. © 2025, CC BY.

关键词： Taxonomies

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：