检索结果-内蒙古大学图书馆

46th ICT and Electronics Convention, MIPRO 2023

作者： Simonoska, Elena Bogatinoska, Dijana Capeska Dimitrievski, Ile Malekian, Reza University of Information Science and Technology 'St. Paul the Apostle' Ohrid Macedonia Malmö University Department of Computer Science and Media Technology Malmö205 06 Sweden University of Pretoria Department of Electrical Electronic and Computer Engineering Pretoria0002 South Africa

ISBN: (纸本)9789532331042

Water pollution is a global issue that has an impact on the entire ecosystems' life cycles. Traditional sampling and laboratory testing techniques are labor-intensive and error-prone, making them ineffective for quickly detecting changes in water quality. This paper presents the development of a low-cost, portable and efficient prototype sensor-based system for monitoring water quality in real-time. The system consists of a microcontroller, temperature, turbidity, pH, and distance sensors, and an application for a visual representation of the data. Extensive testing was carried out to ensure uninterrupted operation. The prototype is a user-friendly sensor system that can be positioned close to the target area in order to assist in preventing environmental and biological harm. This can ensure safe, healthy, and sustainable water supplies for the communities, environment, and the economy. Continuous monitoring of water parameters can also help avoid critical situations. The experimental results demonstrate a successful development of a smart water quality monitoring system with potential applications in various scenarios. © 2023 MIPRO Croatian Society.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

HAROOD: Human Activity Classification and Out-Of-Distribution Detection with Short-Range FMCW Radar

HAROOD: Human Activity Classification and Out-Of-Distributio...

引用

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

作者： Sabri Mustafa Kahya Muhammet Sami Yavuz Eckehard Steinbach Department of Computer Engineering Chair of Media Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich School of Computation Information and Technology Infineon Technologies AG

We propose HAROOD as a short-range FMCW radar-based human activity classifier and out-of-distribution (OOD) detector. It aims to classify human sitting, standing, and walking activities and to detect any other moving or stationary object as OOD. We introduce a two-stage network. The first stage is trained with a novel loss function that includes intermediate reconstruction loss, intermediate contrastive loss, and triplet loss. The second stage uses the first stage’s output as its input and is trained with cross-entropy loss. It creates a simple classifier that performs the activity classification. On our dataset collected by 60 GHz short-range FMCW radar, we achieve an average classification accuracy of 96.51%. Also, we achieve an average AUROC of 95.04% as an OOD detector. Additionally, our extensive evaluations demonstrate the superiority of HAROOD over the state-of-the-art OOD detection methods in terms of standard OOD detection metrics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Food: Facial Authentication And Out-Of-Distribution Detection With Short-Range FMCW Radar

Food: Facial Authentication And Out-Of-Distribution Detectio...

引用

IEEE International Conference on Image Processing

作者： Sabri Mustafa Kahya Boran Hamdi Sivrikaya Muhammet Sami Yavuz Eckehard Steinbach Department of Computer Engineering Chair of Media Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) School of Computation Information and Technology Technical University of Munich Infineon Technologies AG

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

This paper proposes a short-range FMCW radar-based facial authentication and out-of-distribution (OOD) detection framework. Our pipeline jointly estimates the correct classes for the in-distribution (ID) samples and detects the OOD samples to prevent their inaccurate prediction. Our reconstruction-based architecture consists of a main convolutional block with one encoder and multi-decoder configuration, and intermediate linear encoder-decoder parts. Together, these elements form an accurate human face classifier and a robust OOD detector. For our dataset, gathered using a 60 GHz short-range FMCW radar, our network achieves an average classification accuracy of 98.07% in identifying in-distribution human faces. As an OOD detector, it achieves an average Area Under the Receiver Operating Characteristic (AUROC) curve of 98.50% and an average False Positive Rate at 95% True Positive Rate (FPR95) of 6.20%. Also, our extensive experiments show that the proposed approach outperforms previous OOD detectors in terms of common OOD detection metrics.

关键词： Accuracy Pipelines Neural networks Authentication Radar detection Detectors Radar

来源：评论

学校读者我要写书评

暂无评论

Crops Leaf Diseases Recognition:A Framework of Optimum Deep Learning Features

引用

computers, Materials & Continua 2023年第1期74卷 1139-1159页

作者： Shafaq Abbas Muhammad Attique Khan Majed Alhaisoni Usman Tariq Ammar Armghan Fayadh Alenezi Arnab Majumdar Orawit Thinnukool Department of Computer Science HITEC UniversityTaxilaPakistan Computer Sciences Department College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh 11671Saudi Arabia College of Computer Engineering and Science Prince Sattam Bin Abdulaziz UniversityAl-Kharaj11942Saudi Arabia Department of Electrical Engineering College of EngineeringJouf UniversitySakakahSaudi Arabia Faculty of Engineering Imperial College LondonLondonSW72AZUK College of Arts Mediaand TechnologyChiang Mai UniversityChiang Mai50200Thailand

Manual diagnosis of crops diseases is not an easy process;thus,a computerized method is widely *** couple of years,advancements in the domain ofmachine learning,such as deep learning,have shown substantial ***,they still faced some challenges such as similarity in disease symptoms and irrelevant features *** this article,we proposed a new deep learning architecture with optimization algorithm for cucumber and potato leaf diseases *** proposed architecture consists of five *** the first step,data augmentation is performed to increase the numbers of training *** the second step,pre-trained DarkNet19 deep model is opted and fine-tuned that later utilized for the training of fine-tuned model through transfer *** features are extracted from the global pooling layer in the next step that is refined using Improved Cuckoo search *** best selected features are finally classified using machine learning classifiers such as SVM,and named a few more for final classification *** proposed architecture is tested using publicly available datasets–Cucumber National Dataset and Plant *** proposed architecture achieved an accuracy of 100.0%,92.9%,and 99.2%,*** with recent techniques is also performed,revealing that the proposed method achieved improved accuracy while consuming less computational time.

关键词： Crops diseases preprocessing convolutional neural network features optimization machine learning

来源：评论

学校读者我要写书评

暂无评论

Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis

arXiv

引用

arXiv 2025年

作者： Hafez, Ahmad Akhormeh, Alireza Naderi Hegazy, Amr Alanwar, Amr Technical University of Munich TUM School of Computation Information and Technology Department of Computer Engineering Germany German university in Cairo Faculty of Media Engineering and Technology Department of Computer Science and Engineering Egypt

The deployment of Large Language Models (LLMs) in robotic systems presents unique safety challenges, particularly in unpredictable environments. Although LLMs, leveraging zero-shot learning, enhance human-robot interaction and decision-making capabilities, their inherent probabilistic nature and lack of formal guarantees raise significant concerns for safety-critical applications. Traditional model-based verification approaches often rely on precise system models, which are difficult to obtain for real-world robotic systems and may not be fully trusted due to modeling inaccuracies, unmodeled dynamics, or environmental uncertainties. To address these challenges, this paper introduces a safety assurance framework for LLM-controlled robots based on data-driven reachability analysis, a formal verification technique that ensures all possible system trajectories remain within safe operational limits. Our framework specifically investigates the problem of instructing an LLM to navigate the robot to a specified goal and assesses its ability to generate low-level control actions that successfully guide the robot safely toward that goal. By leveraging historical data to construct reachable sets of states for the robot-LLM system, our approach provides rigorous safety guarantees against unsafe behaviors without relying on explicit analytical models. We validate the framework through experimental case studies in autonomous navigation and task planning, demonstrating its effectiveness in mitigating risks associated with LLM-generated commands. This work advances the integration of formal methods into LLM-based robotics, offering a principled and practical approach to ensuring safety in next-generation autonomous systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Chaotic Pigeon Inspired Optimization Technique for Clustered Wireless Sensor Networks

引用

computers, Materials & Continua 2022年第12期73卷 6547-6561页

作者： Anwer Mustafa Hilal Aisha Hassan Abdalla Hashim Sami Dhahbi Dalia H.Elkamchouchi Jaber S.Alzahrani Mrim M.Alnfiai Amira Sayed A.Aziz Abdelwahed Motwakel Department of Electrical and Computer Engineering International Islamic University Malaysia53100Kuala LumpurMalaysia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Industrial Engineering College of Engineering at AlqunfudahUmm Al-Qura UniversitySaudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaifP.O.Box 11099Taif21944Saudi Arabia Department of Digital Media Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11835Egypt

Wireless Sensor Networks(WSN)interlink numerous Sensor Nodes(SN)to support Internet of Things(loT)*** the data gathered from SNs can be divulged,tempered,and *** WSN data processes manage the data in a centralized format at terminal *** devices are prone to attacks and the security of systems can get *** is a distributed and decentralized technique that has the ability to handle security issues in *** security issues include transactions that may be copied and spread across numerous nodes in a peer-peer network *** breaches the mutual trust and allows data immutability which in turn permits the network to go *** some instances,few nodes die or get compromised due to heavy power *** current article develops an Energy Aware Chaotic Pigeon Inspired Optimization based Clustering scheme for Blockchain assisted WSN technique abbreviated as EACPIO-CB *** primary objective of the proposed EACPIO-CB model is to proficiently group the sensor nodes into clusters and exploit Blockchain(BC)for inter-cluster communication in the *** select ClusterHeads(CHs)and organize the clusters,the presented EACPIO-CB model designs a fitness function that involves distinct input ***,BC technology enables the communication between one CH and the other and with the Base Station(BS)in the *** authors conducted comprehensive set of simulations and the outcomes were investigated under different *** simulation results confirmed the better performance of EACPIO-CB method over recent methodologies.

关键词： Blockchain wireless sensor networks clustering energy efficiency security data transmission

来源：评论

学校读者我要写书评

暂无评论

Two-Stream Deep Learning Architecture-Based Human Action Recognition

引用

computers, Materials & Continua 2023年第3期74卷 5931-5949页

作者： Faheem Shehzad Muhammad Attique Khan Muhammad Asfand E.Yar Muhammad Sharif Majed Alhaisoni Usman Tariq Arnab Majumdar Orawit Thinnukool Department of Computer Science COMSATS University IslamabadWah CampusPakistan Department of Computer Science HITEC UniversityTaxilaPakistan Department of Computer Science Bahria UniversityIslamabadPakistan Computer Sciences Department College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia College of Computer Engineering and Science Prince Sattam Bin Abdulaziz UniversityAl-Kharaj11942Saudi Arabia Faculty of Engineering Imperial College LondonLondonSW72AZUK College of Arts Mediaand TechnologyChiang Mai UniversityChiang Mai50200Thailand

Human action recognition(HAR)based on Artificial intelligence reasoning is the most important research area in computer *** breakthroughs in this field have been observed in the last few years;additionally,the interest in research in this field is evolving,such as understanding of actions and scenes,studying human joints,and human posture *** HAR techniques are introduced in the ***,the challenge of redundant and irrelevant features reduces recognition *** also faced a few other challenges,such as differing perspectives,environmental conditions,and temporal variations,among *** this work,a deep learning and improved whale optimization algorithm based framework is proposed for *** proposed framework consists of a few core stages i.e.,frames initial preprocessing,fine-tuned pre-trained deep learning models through transfer learning(TL),features fusion using modified serial based approach,and improved whale optimization based best features selection for final *** pre-trained deep learning models such as InceptionV3 and Resnet101 are fine-tuned and TL is employed to train on action recognition *** fusion process increases the length of feature vectors;therefore,improved whale optimization algorithm is proposed and selects the best *** best selected features are finally classified usingmachine learning(ML)*** publicly accessible datasets such as Ut-interaction,Hollywood,Free Viewpoint Action Recognition usingMotion History Volumes(IXMAS),and centre of computer vision(UCF)Sports,are employed and achieved the testing accuracy of 100%,99.9%,99.1%,and 100%*** with state of the art techniques(SOTA),the proposed method showed the improved accuracy.

关键词： Human action recognition deep learning transfer learning fusion of multiple features features optimization

来源：评论

学校读者我要写书评

暂无评论

Text Analysis Based on Natural Language Processing (NLP) 2

Text Analysis Based on Natural Language Processing (NLP)

引用

2nd International Conference on Advances in engineering Science and technology, AEST 2022

作者： Flayeh, Azhar Kassem Hamodi, Yaser Issam Zaki, Nashwan Dheyaa Ministry of Higher Education & Scientific Research Department of Computer Engineering & Information Technology Baghdad Iraq Ministry of Higher Education & Scientific Research Computer Engineering College of Electrical and Electronic Techniques Baghdad Iraq University of Information Technology and Communications College of Engineering Media Technology Engineering Baghdad Iraq

ISBN: (纸本)9798350334906

In the modern era of information explosion, where there is enormous information including thousands and millions of texts loaded on the Internet of over 1.2 million terabytes, there are no accurate statistics on the size of texts within this huge amount of data. Given the multiplicity of websites on the Internet and the spread of social networking services like Twitter, for example, it is stated that about 6000 tweets are posted per second in the year 2019. This work aims to analyze these texts through resorting to artificial intelligence to help solve this problem. In this article, a review is presented on the latest concepts in the field of word processing, information extraction, and implementing an interface for text analysis using the C++ programming language and Visual Studio 2015 edition. A comparison is made between two articles in terms of the number of verbs, prepositions, article strength, number of letters, with the possibility of sorting the text into verbs, nouns, object, and adjectives, as will be displayed in the program interface. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Optimal Deep Hybrid Boltzmann Machine Based Arabic Corpus Classification Model

引用

computer Systems Science & engineering 2023年第9期46卷 2755-2772页

作者： Mesfer Al Duhayyim Badriyya B.Al-onazi Mohamed K.Nour Ayman Yafoz Amal S.Mehanna Ishfaq Yaseen Amgad Atta Abdelmageed Gouse Pasha Mohammed Department of Computer Science College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj16273Saudi Arabia Department of Language Preparation Arabic Language Teaching InstitutePrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversityMakkah 24211Saudi Arabia Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Digital Media Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Natural Language Processing(NLP)for the Arabic language has gained much significance in recent *** most commonly-utilized NLP task is the‘Text Classification’*** main intention is to apply the Machine Learning(ML)approaches for automatically classifying the textual files into one or more pre-defined *** ML approaches,the first and foremost crucial step is identifying an appropriate large dataset to test and train the *** of the trending ML techniques,i.e.,Deep Learning(DL)technique needs huge volumes of different types of datasets for training to yield the best *** current study designs a new Dice Optimization with a Deep Hybrid Boltzmann Machinebased Arabic Corpus Classification(DODHBM-ACC)model in this *** presented DODHBM-ACC model primarily relies upon different stages of pre-processing and the word2vec word embedding *** Arabic text classification,the DHBM technique is *** technique is a hybrid version of the Deep Boltzmann Machine(DBM)and Deep Belief Network(DBN).It has the advantage of learning the decisive intention of the classification *** adjust the hyperparameters of the DHBM technique,the Dice Optimization Algorithm(DOA)is exploited in this *** experimental analysis was conducted to establish the superior performance of the proposed DODHBM-ACC *** outcomes inferred the better performance of the proposed DODHBM-ACC model over other recent approaches.

关键词： Arabic corpus text classification machine learning deep learning dice optimization

来源：评论

学校读者我要写书评

暂无评论

Optimal Quad Channel Long Short-Term Memory Based Fake News Classification on English Corpus

引用

computer Systems Science & engineering 2023年第9期46卷 3303-3319页

作者： Manar Ahmed Hamza Hala J.Alshahrani Khaled Tarmissi Ayman Yafoz Amal S.Mehanna Ishfaq Yaseen Amgad Atta Abdelmageed Mohamed I.Eldesouki Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Applied Linguistics College of LanguagesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Digital Media Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11845Egypt Department of Information System College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

The term‘corpus’refers to a huge volume of structured datasets containing machine-readable *** texts are generated in a natural communicative *** explosion of social media permitted individuals to spread data with minimal examination and filters *** to this,the old problem of fake news has *** has become an important concern due to its negative impact on the *** manage the spread of fake news,automatic recognition approaches have been investigated earlier using Artificial Intelligence(AI)and Machine Learning(ML)*** perform the medicinal text classification tasks,the ML approaches were applied,and they performed quite ***,a huge effort is required from the human side to generate the labelled training *** recent progress of the Deep Learning(DL)methods seems to be a promising solution to tackle difficult types of Natural Language Processing(NLP)tasks,especially fake news *** unlock social media data,an automatic text classifier is highly helpful in the domain of *** current research article focuses on the design of the Optimal Quad ChannelHybrid Long Short-Term Memory-based Fake News Classification(QCLSTM-FNC)*** presented QCLSTM-FNC approach aims to identify and differentiate fake news from actual *** attain this,the proposed QCLSTM-FNC approach follows two methods such as the pre-processing data method and the Glovebased word embedding ***,the QCLSTM model is utilized for *** boost the classification results of the QCLSTM model,a Quasi-Oppositional Sandpiper Optimization(QOSPO)algorithm is utilized to fine-tune the *** proposed QCLSTM-FNC approach was experimentally validated against a benchmark *** QCLSTMFNC approach successfully outperformed all other existing DL models under different measures.

关键词： English corpus fake news detection social media natural language processing artificial intelligence deep learning

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：