检索结果-内蒙古大学图书馆

High-Throughput Independent Component Analysis Processor for Full Duplex Systems

IEEE Journal on Selected Areas in Communications 2023年第9期41卷 2821-2832页

作者： Cheng, Jen-Hao Chang, Tien-Min Shen, Chung-An Fouda, Mohammed E. Eltawil, Ahmed M. National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei10607 Taiwan University of California at Irvine Electrical Engineering and Computer Science Department IrvineCA92697 United States King Abdullah University of Science and Technology Electrical and Computer Engineering Program Thuwal23955 Saudi Arabia

This paper presents the algorithm and very-large-scale integration (VLSI) architecture of a high-throughput and highly efficient independent component analysis (ICA) processor for self-interference cancellation (SIC) in in-band full-duplex (IBFD) systems. This is the first VLSI architecture reported in the literature based on the state-of-the-art entropy bound minimization (EBM) approach. A novel ICA algorithm is presented in this paper with momentum gradient descent optimization. Simulation results show that the number of iterations for the proposed algorithm is significantly reduced compared to the conventional ICA algorithms. Furthermore, a novel early-distribution estimation scheme is proposed in the designed ICA processor to compute multiple distribution functions with low latency and low complexity. The processing flow and the efficiency for the hardware utilization are specifically designed so that the processing speed is maximized with minimum employment of hardware components. The proposed ICA processor is designed and implemented based on the application-specific-integrated circuit (ASIC) flow. The post-layout estimations show that compared with the conventional EBM-based scheme, the proposed design improves the throughput and efficiency by 30x. In addition, compared to prior designs shown in the literature, the proposed ICA processor also demonstrates a significant enhancement in terms of throughput and efficiency. © 1983-2012 IEEE.

关键词： VLSI circuits

来源：评论

学校读者我要写书评

暂无评论

Enhancing waste sorting and recycling efficiency: robust deep learning-based approach for classification and detection

引用

Neural Computing and Applications 2025年第6期37卷 4567-4583页

作者： Sayem, Faizul Rakib Islam, Md. Sakib Bin Naznine, Mansura Nashbat, Mohammad Hasan-Zia, Mazhar Kunju, Ali K Ansaruddin Khandakar, Amith Ashraf, Azad Majid, Molla Ehsanul Kashem, Saad Bin Abul Chowdhury, Muhammad E. H. Department of Electrical and Electronic Engineering University of Dhaka Dhaka Bangladesh Department of Biomedical Engineering Military Institute of Science and Technology Dhaka Bangladesh Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi6204 Bangladesh Chemical Engineering Department University of Doha for Science and Technology Doha Qatar Department of Electrical Engineering Qatar University Doha2713 Qatar Computer Applications Department Academic Bridge Program Qatar Foundation Doha Qatar Department of Computing Science AFG College With the University of Aberdeen Doha Qatar

Given the severity of waste pollution as a major environmental concern, intelligent and sustainable waste management is becoming increasingly crucial in both developed and developing countries. The material composition and volume of urban solid waste are key considerations in processing, managing, and utilizing city waste. Deep learning technologies have emerged as viable solutions to address waste management issues by reducing labor costs and automating complex tasks. However, the limited number of trash image categories and the inadequacy of existing datasets have constrained the proper evaluation of machine learning model performance across a large number of waste classes. In this paper, we present robust waste image classification and object detection studies using deep learning models, utilizing 28 distinct recyclable categories of waste images comprising a total of 10,406 images. For the waste classification task, we proposed a novel dual-stream network that outperformed several state-of-the-art models, achieving an overall classification accuracy of 83.11%. Additionally, we introduced the GELAN-E (generalized efficient layer aggregation network) model for waste object detection tasks, obtaining a mean average precision (mAP50) of 63%, surpassing other state-of-the-art detection models. These advancements demonstrate significant progress in the field of intelligent waste management, paving the way for more efficient and effective solutions. © The Author(s) 2024.

关键词： Deep learning for waste management Intelligent waste management Object detection in waste management Sustainable waste processing Urban solid waste Waste image classification

来源：评论

学校读者我要写书评

暂无评论

The Effectiveness of CNN-Based Models in Macroscopic Motion Direction Detection 6

The Effectiveness of CNN-Based Models in Macroscopic Motion ...

引用

6th International Conference on Robotics and computer Vision, ICRCV 2024

作者： Qiu, Zhiyu Chen, Tianqi Hua, Yuxiao Todo, Yuki Graduate School of Natural Science & Technology Kanazawa University Division of Electrical Engineering and Computer Science Kanazawa Japan Kanazawa University Faculty of Electrical Information and Communication Engineering Kanazawa Japan

ISBN: (纸本)9798331527426

Convolutional Neural Networks (CNNs) have revolutionized the field of computer vision, offering significant advancements in image and video recognition, classification, and segmentation tasks. Leveraging hierarchical pattern recognition capabilities, CNNs have demonstrated superior performance over traditional machine learning methods. One particularly critical application of CNNs is in motion direction detection, which is essential for enhancing security in surveillance systems, ensuring safe navigation in autonomous vehicles, and providing valuable insights in sports analytics. In this study, our primary goal was to investigate how different types of input data impact the accuracy of motion direction detection. We applied five distinct preprocessing methods to test the effect of input data on accuracy. Furthermore, we conducted experiments in various object and background scenarios to evaluate adaptability of simple 4-layer CNN, EfficientNetBO and ResNet50 in detecting motion direction. Finally, we tested the noise resistance of these three models. The results indicate that CNNs are capable of extracting the macroscopic motion direction of objects in images. Our study highlights the potential of CNN-based models for efficient and effective motion direction detection. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Investigation of Colors Categorized into Color Names on a Liquid Crystal Display to Enhance CAPTCHAs

引用

International Journal of the Society of Material engineering for Resources 2022年第2期25卷 212-217页

作者： Ishizawa, Chikako Kobayashi, Nozomu Kageyama, Yoichi Department of Mathematical Science and Electrical-Electronic-Computer Engineering Graduate School of Engineering Science Akita University Akita010-8502 Japan

This study focuses on the human ability to tolerate subtle diff erences in color and categorize similar colors into a single mass to enhance completely automated public turing test to tell computers and humans apart (CAPTCHA). First, an experiment was conducted to check whether the color selection condition could control the color categorization results. Consequently, it was clarifi ed that when the selection condition was added, the color to be categorized changed, implying the possibility of controlling the categorized result. Subsequently, an investigation was conducted to clarify the range of liquid crystal display colors categorized as major color names. As a result, it was clarified that the hue angle size of the colors categorized by more than half of the participants was sometimes greater than the hue angle size between the primary and complementary colors. It was also clarifi ed that among the categorized colors, there were categorized colors in the two color names. Finally, results from the fi rst and second experiments were collated. It was confi rmed that by using the categorized color range and selection conditions, it is possible to obtain an answer with a color name that is diff erent from the original color name. These results suggest that the ability of humans to categorize similar colors into a single mass enhances CAPTCHA. © 2022 Society of Materials engineering for Resources of Japan. All rights reserved.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Hotel Information System Management Audit Using COBIT 2019 - APO12 2

Hotel Information System Management Audit Using COBIT 2019 -...

引用

2nd International Conference for Innovation in Technology, INOCON 2023

作者： Utamajaya, Joy Nashar Supangat, Suhono Harso Gaol, Ford Lumban Ranti, Benny BINUS University BINUS Graduate Program School of Information System Jakarta Indonesia Bandung Institute of Technology School of Electrical Engineering and Informatic Bandung Indonesia Bina Nusantara University Computer Science Department BINUS Graduate Program Computer Science Jakarta Indonesia University of Indonesia Computer Science Department Faculty of Computer Science Depok Indonesia

ISBN: (纸本)9798350320923

In general, public or private organizations or companies have used information-based technology as a support to improve business performance to be more effective and efficient in order to achieve a company's business goals. Given the large contribution of information technology in the application of hotel applications as a supporting information system, it is a vital system that must avoid risks that can hinder and cause harm to the hotel management business processes. Therefore, it is necessary to carry out risk management using the COBIT 5 framework to manage possible risks that may occur based on the APO12 (Manage Risk) domain. From the evaluation results of the data obtained through observation and interviews as well as the calculation of the results of the questionnaire based on 6 APO12 subdomains, the results of the risk management level capability assessment in hotel applications are still at level 3 or have reached the level of established process with the target to be achieved at level 4 resulting in a gap of 1 level. Based on the results obtained, it is necessary to propose recommendations that can be used by hotels in improving the application of information technology risk management so that in the future it can achieve the expected target level so that the APO12 level of capability can increase and become more optimal. © 2023 IEEE.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Density Based Spatial Clustering of Applications with Noise and Sentence Bert Embedding for Indonesian Utterance Clustering

Density Based Spatial Clustering of Applications with Noise ...

引用

2023 International Conference on computer science, Information Technology and engineering, ICCoSITE 2023

作者： Hasani, Muhammad Fikri Heryadi, Yaya Arifin, Yulyani Lukas Suparta, Wayan Bina Nusantara University BINUS Graduate Program Computer Science School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia Jakarta12930 Indonesia Institut Teknologi Nasional Yogyakarta Faculty of Industrial Technology Department of Electrical Engineering Yogyakarta55281 Indonesia

ISBN: (纸本)9798350320954

Task oriented chatbots are a sub-topic related to chatbots, where chatbots will perform certain tasks with specific goals. One part of creating a task-oriented chatbot is doing intent classification. Intent classification is a task of text classification. As in general text classification, the required dataset requires a label to carry out the classification process. To speed up and help the utterance analysis process, there is already a method, namely clustering, and Density-based clustering is a part of clustering that can determine cluster patterns based on arbitrary data, with DBScan as one of its algorithms. This research used 10000 client utterance data of awhatsapp based e-commerce conversation. SentenceBert also used as a state of art sentence embedding. This research yield silhouette score of 0.327 as the best result from eps of 0.1 and MinPts of 95. However, based on the cluster result, sentences labelled as noise can be further clustered. Text Preprocessing, text augmentation and sentence embedding techniques can be explored to increase the cluster performance. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Forecasting Bitcoin Prices Using Deep Learning for Consumer-Centric Industrial Applications

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 1351-1358页

作者： Roy, Pradeep Kumar Kumar, Abhinav Singh, Ashish Sangaiah, Arun Kumar Indian Institute of Information Technology Surat Department of Computer Science and Engineering Surat394190 India Motilal Nehru National Institute of Technology Allahabad Department of Computer Science and Engineering Prayagraj211004 India KIIT Deemed to Be University School of Computer Engineering Bhubaneswar751024 India National Yunlin University of Science and Technology International Graduate Institute of AI Douliou64002 Taiwan Lebanese American University Department of Electrical and Computer Engineering Byblos1102-2801 Lebanon

As cryptocurrencies become more popular as investment vehicles, bitcoin draws interest from businesses, consumers, and computer scientists all across the world. Bitcoin is a computer file stored in digital wallet applications where each transaction is secured using strong cryptographic algorithms. It was challenging to forecast the future price of bitcoin due to its nonlinearity and extreme volatility. Several recent classic parametric models have been found with limited accuracy. To address the limitations and fill the existing research gaps, there is a need for a good prediction model which will provide the desired accuracy in the case of uncertainty and dynamism. This research suggested a deep learning-based framework for predicting and forecasting Bitcoin price. The research will be helpful for worldwide consumers and industries to take their decision on whether to invest or not. The research utilizes Yahoo! finance dataset for the period of 01-03-2016 to 26-02-2021 having 1828 samples. The experimental outcomes of the proposed Long Short-Term Memory (LSTM) model outperformed similar deep learning models by securing minimum loss and confirming that it can be used for future price prediction of the cryptocurrencies, which is helpful for the buyer to take their decision. © 1975-2011 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Objective Sleep Quality Measurement based on Fuzzy Logic and Wearable Device 8

Objective Sleep Quality Measurement based on Fuzzy Logic and...

引用

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Wijaya, Jason A. Andersen, Pauw D. Surantha, Nico Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia Department of Electrical Electronic and Communication Engineering Tokyo City University Japan

Sleep is the natural state of relaxation for human being. Sleep quality is an essential yet frequently neglected aspect of sleep in general. Sleep quality is essential because it allows the body to restore itself and prepare for the next day. The standard method for evaluating sleep quality was subjective evaluation. Actigraphy devices, which can measure the sleep cycle, are now widely available. This study developed a method using Fuzzy Logic and an actigraphy device to measure and classify sleep quality. The fuzzy logic method was developed in several stages, which are determining the sleep quality measurement parameters, constructing the fuzzy set for each input variable, and developing the fuzzy rules. To evaluate the proposed fuzzy model, five individuals were invited to participate in the experiment and required to complete the PSQI subjective sleep questionnaire. The evaluation result shows that our proposed Fuzzy model achieves lower error compared to the existing method. © 2023 The Authors. Published by Elsevier B.V.

关键词： actigraphy artificial intelligences fuzzy logic sleep sleep quality

来源：评论

学校读者我要写书评

暂无评论

Jointprop: Joint Semi-supervised Learning for Entity and Relation Extraction with Heterogeneous Graph-based Propagation 61

Jointprop: Joint Semi-supervised Learning for Entity and Rel...

引用

61st Annual Meeting of the Association for Computational Linguistics, ACL 2023

作者： Yandan, Zheng Anran, Hao Tuan, Luu Anh School of Computer Science and Engineering Interdisciplinary Graduate Program-HealthTech Nanyang Technological University Singapore

ISBN: (纸本)9781959429722

Semi-supervised learning has been an important approach to address challenges in extracting entities and relations from limited data. However, current semi-supervised works handle the two tasks (i.e., Named Entity Recognition and Relation Extraction) separately and ignore the cross-correlation of entity and relation instances as well as the existence of similar instances across unlabeled data. To alleviate the issues, we propose Jointprop, a Heterogeneous Graph-based Propagation framework for joint semi-supervised entity and relation extraction, which captures the global structure information between individual tasks and exploits interactions within unlabeled data. Specifically, we construct a unified span-based heterogeneous graph from entity and relation candidates and propagate class labels based on confidence scores. We then employ a propagation learning scheme to leverage the affinities between labelled and unlabeled samples. Experiments on benchmark datasets show that our framework outperforms the state-of-the-art semi-supervised approaches on NER and RE tasks. We show that the joint semi-supervised learning of the two tasks benefits from their codependency and validates the importance of utilizing the shared information between unlabeled data. © 2023 Association for Computational Linguistics.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

TaxDiff: taxonomic-guided diffusion model for protein sequence generation

引用

science China(Information sciences) 2025年第4期68卷 385-386页

作者： Zongying LIN Hao LI Liuzhenghao LV Yu WANG Bin LIN Junwu ZHANG Zijun CHEN Calvin Yu-Chian CHEN Li YUAN Yonghong TIAN School of Electronic and Computer Engineering Peking University AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Peng Cheng Laboratory School of Chemical Biology and Biotechnology Peking University

Protein design aims to generate protein variants with targeted biological functions, which is significant in multiple biological areas, including enzyme reaction catalysis, vaccine design, and fluorescence intensity. Protein design contains two paradigms: sequence generation and structure generation. Recently, EvoDiff [1] proposed a universal designing paradigm, combining structure and sequence generation using the diffusion framework, which improves the protein design efficiency.

关键词：

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：