检索结果-内蒙古大学图书馆

5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

作者： Ma, Beier Zuo, Xin Shen, Jifeng Shu, Xin Huang, Shucheng Li, Yuanhao Jiangsu University of Science and Technology School of Computer Science and Engineering Zhenjiang China Jiangsu University School of Electronic and Informatics Engineering Zhenjiang China

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

Current sewage pipeline inspection researches focus on locating defects, with only a few studies addressing the crack fine-grained classification task. However, in engineering applications, such as Pipeline Assessment Certification Program (PACP), subcategory coding of cacks is required. Therefore, this paper studies the fine-grained classification of pipeline cracks. Algorithms based on deep learning have been widely used in the field of sewage pipeline inspection, but these models have a large number of parameters and are computationally time-consuming. Edge or embedded devices with weak GPUs cannot accept the time and storage costs of these large models. To solve the above problems, this paper introduces knowledge distillation (KD) which is one of the mainstream model compression methods. We select the large-scale network Resnet50 as the teacher model and design a lightweight network Combined MobileNetV2 & Inception (CMI) for crack detection as the student model. High-temperature distillation allows the student model to obtain dark knowledge from the pre-trained, well-performing teacher model, which is combined with ground truth (GT) for training. Experiments show that KD is effective. By adjusting the KD hyperparameters, the classification accuracy of the student model is improved by 1.41%, and the F1-score is improved by 1.12%. This demonstrates the robustness of knowledge distillation to improve the performance of small models, laying the foundation for future deployment on multi-sensor automatic detection robots. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Employee Recruitment Analysis Using the MOORA Method

Employee Recruitment Analysis Using the MOORA Method

引用

informatics engineering, Science & Technology (INCITEST), International Conference on

作者： G T Mardiani R Susanto T Harihayati Informatics Engineering Engineering and Computer Science Universitas Komputer Indonesia Bandung Indonesia

A company definitely needs employees to help in its business processes. These employees are generated from the recruitment process. Errors in the recruitment process will have an impact on the company's productivity and reputation. Therefore, when a division or part of a company that handles employee recruitment requires a technique or method that can provide recommendations for employees to be recruited as needed. One method that can be used to support the decision of which employee to accept or hire is the Multi Objective Optimization by Ratio Analysis (MOORA) method. The results of calculations using MOORA based on the criteria set by the company with prospective employees applying for administrative positions state that alternative 1 (A1) gets a preference value (Yi) of 0.40 (the highest score obtained compared to the alternatives), this shows if this method can be applied to provide recommendations on which employees should be recruited according to company needs with simple and easy-to-understand calculations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Controllable and Efficient Multi-Class Pathology Nuclei Data Augmentation using Text-Conditioned Diffusion Models

arXiv

引用

arXiv 2024年

作者： Oh, Hyun-Jic Jeong, Won-Ki College of Informatics Department of Computer Science and Engineering Korea University Seoul Korea Republic of

In the field of computational pathology, deep learning algorithms have made significant progress in tasks such as nuclei segmentation and classification. However, the potential of these advanced methods is limited by the lack of available labeled data. Although image synthesis via recent generative models has been actively explored to address this challenge, existing works have barely addressed label augmentation and are mostly limited to single-class and unconditional label generation. In this paper, we introduce a novel two-stage framework for multi-class nuclei data augmentation using text-conditional diffusion models. In the first stage, we innovate nuclei label synthesis by generating multi-class semantic labels and corresponding instance maps through a joint diffusion model conditioned by text prompts that specify the label structure information. In the second stage, we utilize a semantic and text-conditional latent diffusion model to efficiently generate high-quality pathology images that align with the generated nuclei label images. We demonstrate the effectiveness of our method on large and diverse pathology nuclei datasets, with evaluations including qualitative and quantitative analyses, as well as assessments of downstream tasks. © 2024, CC BY-NC-SA.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

What Appears Suboptimal May Surprise You: A Fixed-Rate Scheduling Policy for Geo-Distributed CoFlows 29

What Appears Suboptimal May Surprise You: A Fixed-Rate Sched...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Liu, Haoyu Ding, Feiyan Wang, Yao Xiang, Qiao Shu, Jiwu Du, Haizhou Kong, Linghe Liu, Xue Xiamen University School of Informatics Xiamen China University of Electric Power of Shanghai School of Computer Science and Technology Shanghai China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China McGill University School of Computer Science Montreal Canada

ISBN: (纸本)9798350330717

All existing coflow scheduling algorithms compute dynamic-rate schedules that change the rates of flows during transmission. In this paper, we make a crucial finding: although dynamically adjusting the rates of flows could lead to a better coflow completion time (CCT) in theory, it would introduce additional pressures on the congestion control mechanism in the underlying network, which result in poor CCT in practice. This difference between theoretical CCT and practical CCT is further exacerbated in wide-area networks, where the topology does not provide any bisection guarantee as data center networks do. To this end, we designed a fixed-rate coflow scheduling policy called FSCO. Although in theory, the best fixed-rate schedule is usually suboptimal, it keeps the in-flight traffic relatively steady, reducing the risk of triggering congestion control. The core of FSCO is an efficient scheduling algorithm based on the classic network utilization maximization (NUM) framework. We implement a prototype of FSCO and evaluate its performance extensively using real-world topologies and coflow traces. Experimental results show that the total CCT reduces up to 30% compared to baselines while yielding up to 12× speedups compared to the solver. © 2023 IEEE.

关键词： Coflow Scheduling Dual decomposition Network Utility Maximization

来源：评论

学校读者我要写书评

暂无评论

Classifying Upper Extremity Motor Function Using Deep Learning and Third-Person Video Data

Classifying Upper Extremity Motor Function Using Deep Learni...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Tran, Tan Chang, Lin-Ching Lum, Peter The Catholic University of America Department of Electrical Engineering and Computer Science WashingtonDC United States New Jersey Institute of Technology Department of Informatics NewarkNJ United States The Catholic University of America Department of Biomedical Engineering WashingtonDC United States

ISBN: (纸本)9798350362480

Post-stroke rehabilitation of upper extremity (UE) motor function is essential. Despite the widespread use of UE rehabilitation in clinical settings, assessing the success of these treatments is challenging. Methods for evaluating UE motor function include task performance under clinical supervision, patient self-reports, and data analysis from wearable devices equipped with accelerometers and gyroscopes. In prior research, we demonstrated that machine learning and deep learning models using data from a single wrist-worn accelerometer sensor could accurately differentiate between functional and non-functional UE movements in stroke patients. To overcome the limitations of single wrist-worn accelerometer sensors - challenges in capturing the full context of functional movements - this study presents a new deep learning (DL) based framework designed to classify functional and non-functional arm movements in videos captured from a conventional camera. The system is entirely automated and comprises two DL networks. The first network performs human pose estimation, extracting 2D pose key points of the paretic arm(s) and torso on 2-second sequences of the frames. The second network then uses these 2D pose landmarks to classify the movement sequence as functional or non-functional. This system offers two key benefits for rehabilitation. First, it can automatically generate initial annotations for video frames, significantly reducing the time needed for manual labeling. Second, analyzing the effectiveness of UE rehabilitation through third-person videos allows for objective outcome measurement of UE treatments in stroke survivors' home environments. © 2024 IEEE.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Highly-Compact Wideband High-Gain Four-Element MIMO Antenna for 5G New Radio IoT

引用

IEEE Internet of Things Journal 2025年第12期12卷 22350-22365页

作者： Khan, Shahid Khan, Owais Shah, Syed Ahson Ali Nasir, Jamal Malik, Bilal Tariq Khan, Salahuddin Koziel, Slawomir Department of Electrical and Computer Engineering COMSATS University Islamabad Abbottabad-Campus Islamabad Pakistan Gwangju Institute of Science and Technology Graduate School of Energy Convergence Gwangju Korea Republic of King Saud University College of Engineering P.O. Box 800 Riyadh11421 Saudi Arabia Gdansk University of Technology Faculty of Electronics Telecommunications and Informatics Gdansk80-233 Poland Reykjavik University Engineering Optimization and Modeling Center Reykjavik101 Iceland

Wideband millimeter-wave (mm-wave) coverage is essential for the high-speed, low-latency communication required in next-generation 5G New Radio (NR) Internet of Things (IoT) systems. This study develops a T-shaped four-element, highly compact wideband multiple-input multiple-output (MIMO) antenna covering the mm-wave n260 (37.40 GHz) and n259 (42.43.5 GHz) bands for 5G NR IoT applications. The antenna is designed on a 0.76 mm-thick Rogers RO4350B substrate with overall dimensions of 28 28 mm2 (3.3 × 3.3 λ2). For design simplicity, a T-shaped patch backed by a full-ground plane is devised to serve as the radiator of a single-element antenna with the dimensions of (Ls × Ws) mm2, optimized through a systematic three-step design process for improved performance. Moreover, the design has evolved into a 4× 4 orthogonal MIMO configuration, achieving improved gain, polarization diversity, and higher data rates, with each element exhibiting wideband characteristics across 11.5 GHz (36.5 to 48 GHz) with high gains of 9.8 dBi and 6.6 dBi at n260 and n259 5G mm-wave bands, respectively. Additionally, arc-shaped complementary split-ring resonators (CSRR) are integrated into the ground plane to significantly enhance the gain while effectively reducing mutual coupling, remarkably achieving a maximum gain of 9.8 dBi. Furthermore, the MIMO antenna exhibits an envelope correlation coefficient of less than 0.10 between any two MIMO elements encountering the required condition of © 2014 IEEE.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

Improving Power Transformer Lifetime Prediction using Hyperparameter Optimization 24

Improving Power Transformer Lifetime Prediction using Hyperp...

引用

24th International Electronics Symposium, IES 2022

作者： Ningrum, Ayu Ahadi Maulida, Ihdalhubbi Ansari, Rudy Syarif, Iwan Universitas Muhammadiyah Banjarmasin Department of Informatics Banjarmasin Indonesia Electronic Engineering Polytechnic Institute of Surabaya Department of Informatic and Computer Engineering Surabaya Indonesia

ISBN: (数字)9781665489713

ISBN: (纸本)9781665489713

Since the global pandemic has significantly impacted human life, technology has become a vital role in various sectors. The more technology used, the more we need the electricity supply. The stability of the electricity supply is an absolute thing to customers. Power Transformer is essential equipment for delivering electricity to customers. So the condition of the power transformers should be an essential thing that must be considered. Deep Learning is part of artificial intelligence that is widely applied to facilitate the human need. Based on its role, accuracy in the prediction results will be absolute. Hyperparameter optimization is the essential methods in the machine learning process. Errors in assigning hypermeter values can harm producing predictive values. This study discusses how to optimize the prediction results of the lifetime prediction on a power transformer. With optimal prediction results, it can help electricity management companies monitor conditions. Thereby minimizing the risk of disruption of electricity supply to customers. Models are tested and verified using a real dataset from a power transformer in several locations. The best hyper-parameter for this dataset is Bayesian Search, producing 0,001343 for Mean Absolute Error (MAE). © 2022 IEEE.

关键词： Power transformers

来源：评论

学校读者我要写书评

暂无评论

Machine Speech Chain with Emotion Recognition 11

Machine Speech Chain with Emotion Recognition

引用

11th International Conference on Advanced informatics: Concept, Theory and Application, ICAICTA 2024

作者： Naufal, Akeyla Pradia Lestari, Dessi Puji Purwarianti, Ayu Azizah, Kurniawati Tanaya, Dipta Sakti, Sakriani School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia University of Indonesia Faculty of Computer Science Depok Indonesia Graduate School of Information Science Nara Institute of Science and Technology Nara Japan

ISBN: (纸本)9798331520311

Developing natural speech recognition and speech synthesis systems requires speech data that authentically represents real emotions. However, this type of data is often challenging to obtain. Machine speech chain offers a solution to this challenge by using unpaired data to continue training models initially trained with paired data. Given the relative abundance of unpaired data compared to paired data, machine speech chain can be instrumental in recognizing emotions in speech where training data is limited. This study investigates the application of machine speech chain in speech emotion recognition and speech recognition of emotional speech. Our findings indicate that a model trained with 50% paired neutral emotion speech data and 22% paired non-neutral emotional speech data shows a reduction in Character Error Rate (CER) from 37.55% to 34.52% when further trained with unpaired neutral emotion speech data. The CER further decreases to 33.75% when additionally trained with combined unpaired speech data. The accuracy of recognizing non-neutral emotions ranged from 2.18% to 53.51 %, though the F1 score fluctuated, increasing by up to 20.6% and decreasing by up to 23.4%. These results suggest that the model demonstrates a bias towards the majority class, as reflected by the values of the two metrics. © 2024 IEEE.

关键词： Chains

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Thesis Policy by Instagram Users Using Logistic Regression

Sentiment Analysis of Thesis Policy by Instagram Users Using...

引用

International Conference on Electrical engineering, computer Science and informatics (EECSI)

作者： Fathia Dwi Astuti Widodo Bambang Prasetya Adhi Dept. of Informatics and Computer Engineering Education Universitas Negeri Jakarta Jakarta Indonesia

ISBN: (数字)9798350355314

ISBN: (纸本)9798350355321

The requirements for university graduation were changed by the Minister of Education, Culture, Research and Technology in August 2023, where a thesis is no longer required and can be replaced with another form. The existence of this regulation has caused discussion in the community with various responses visible through social media Instagram. Instagram has become a forum for sharing the latest topics for the public, causing the emergence of online media accounts such as Folkative. This research aims to analyze sentiment regarding the policy of eliminating thesis obligations at universities through data collected from comments on Folkative's Instagram account posts. Sentiment analysis was carried out using Logistic Regression for classification, K-Fold Cross Validation for data validation, Confusion Matrix for evaluation, and ADASYN to resolve data imbalances. The data collected from the scraping process was 4,172 comments. After carrying out the classification and performance evaluation process, the best method produced was a combination of Logistic Regression and ADASYN achieving results of 89.6% accuracy, 91.5% precision, 87.7% recall, and f-1 score 89.5%. This shows that the performance of the Logistic Regression method is good and suitable for use as a classification model in this research.

关键词： Support vector machines Performance evaluation Logistic regression Sentiment analysis Accuracy Social networking (online) Media Regulation Web sites Multimedia communication

来源：评论

学校读者我要写书评

暂无评论

QoS Under Attack: A Simulation Study on the Impact of Class Hijacking in Wireless LANs

QoS Under Attack: A Simulation Study on the Impact of Class ...

引用

International Conference on computer Theory and Applications (ICCTA)

作者： Christos K. Christodoulou Anastasios C. Politis Constantinos S. Hilas Dept. of Computer Informatics and Telecommunications Engineering International Hellenic University Serres Greece

ISBN: (数字)9798331529680

ISBN: (纸本)9798331529697

User satisfaction in Wireless Networks (WLANs) heavily rely on the efficient provision of Quality of Service (QoS). Nevertheless, misbehaving acts by malicious users have the potential to disrupt the QoS provisioning and impair its overall efficiency. One such abusive behavior is called Class Hijacking (CH) and has the ability to deteriorate the QoS-levels received by the well-behaving users in the network. CH is a hard to detect, yet easy to perform attack, targeting the QoS mechanism in differentiated services networks such as WLANs. This article attempts to illustrate the negative impact of CH actions on the network performance of an infrstructure-based WLAN where stealing network resources is an attractive choice for nefarious users. This is achieved through extensive simulations using the ns-3 network simulator. Applying a gradual increase in the number of deceitful users, we observe how these attacks noticeably deteriorate network performance.

关键词： Wireless LAN Diffserv networks Computational modeling Wireless networks Quality of service

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：