检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Balloccu, Simone Reiter, Ehud Li, Karen Jia-Hui Sargsyan, Rafael Kumar, Vivek Recupero, Diego Reforgiato Riboni, Daniele Dusek, Ondrej Charles University Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics Prague Czech Republic Department of Computing Science University of Aberdeen United Kingdom FI CODE University of Bundeswehr Munich Germany Department of Mathematics and Computer Science University of Cagliari Italy

ISBN: (纸本)9798891761681

Large Language Models (LLMs) are being employed by end-users for various tasks, including sensitive ones such as health counseling, disregarding potential safety concerns. It is thus necessary to understand how adequately LLMs perform in such domains. We conduct a case study on ChatGPT in nutrition counseling, a popular use-case where the model supports a user with their dietary struggles. We crowdsource real-world diet-related struggles, then work with nutrition experts to generate supportive text using ChatGPT. Finally, experts evaluate the safety and text quality of ChatGPT's output. The result is the HAI-Coaching dataset, containing ∼2.4K crowdsourced dietary struggles and ∼97K corresponding ChatGPT-generated and expert-annotated supportive texts. We analyse ChatGPT's performance, discovering potentially harmful behaviours, especially for sensitive topics like mental health. Finally, we use HAI-Coaching to test open LLMs on various downstream tasks, showing that even the latest models struggle to achieve good performance. HAI-Coaching is available at https://***/uccollab/hai-coaching/. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Towards Differentiating Between Failures and Domain Shifts in Industrial Data Streams

Towards Differentiating Between Failures and Domain Shifts i...

引用

2024 Workshop on Embracing Human-Aware AI in Industry 5.0, HAII5.0 2024

作者： Wojak-Strzelecka, Natalia Bobek, Szymon Nalepa, Grzegorz J. Stefanowski, Jerzy Jagiellonian Human-Centered AI Lab Mark Kac Center for Complex Systems Research Institute of Applied Computer Science Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University ul. prof. Stanislawa Lojasiewicza 11 Krakow30-348 Poland Institute of Computing Science Poznań University of Technology Poznań60-965 Poland

Anomaly and failure detection methods are crucial in identifying deviations from normal system operational conditions, which allows for actions to be taken in advance, usually preventing more serious damages. Long-lasting deviations indicate failures, while sudden, isolated changes in the data indicate anomalies. However, in many practical applications, changes in the data do not always represent abnormal system states. Such changes may be recognized incorrectly as failures, while being a normal evolution of the system, e.g. referring to characteristics of starting the processing of a new product, i.e. realizing a domain shift. Therefore, distinguishing between failures and such"healthy" changes in data distribution is critical to ensure the practical robustness of the system. In this paper, we propose a method that not only detects changes in the data distribution and anomalies but also allows us to distinguish between failures and normal domain shifts inherent to a given process. The proposed method consists of a modified Page-Hinkley changepoint detector for identification of the domain shift and possible failures and supervised domain-adaptation-based algorithms for fast, online anomaly detection. These two are coupled with an explainable artificial intelligence (XAI) component that aims at helping the human operator to finally differentiate between domain shifts and failures. The method is illustrated by an experiment on a data stream from the steel factory. © 2024 Copyright for this paper by its authors.

关键词： Data streams

来源：评论

学校读者我要写书评

暂无评论

Assessing the Chaotic Map Population Initializations for Sine Cosine Algorithm Using the Case Study of Pairwise Test Suite Generation 6th

Assessing the Chaotic Map Population Initializations for Sin...

引用

6th International Conference on Electrical, Control and Computer Engineering, InECCE 2021

作者： Din, Fakhrud Zamli, Kamal Z. Nasser, Abdullah B. Faculty of Computing College of Computing and Applied Sciences Universiti Malaysia Pahang Pahang Pekan26600 Malaysia Department of Computer Science & IT University of Malakand KPK Chakdara Pakistan

ISBN: (纸本)9789811686894

Sine Cosine Algorithm (SCA) is a new population based meta-heuristic algorithm that exploits both the sine and cosine functions for its update operators. The main strength of SCA is its simplicity and straightforward implementation as well as provides no parameter control adjustment. For these reasons, SCA can be adopted in many optimization problems quickly and without much tuning. Despite the aforementioned advantages, SCA convergence can still be problematic depending on the initial starting positions of initial populations. In this work, we propose to assess the effectiveness of pseudo random (i.e., Random) as well as three chaotic map initializations (i.e., sine map, circle map, and logistic map) for SCA using the pairwise test case generation as our case study. The original SCA with random initialization (R_SCA) is outperformed on the adopted experiments by the proposed logistic map SCA (LM_SCA), circle map SCA (CM_SCA) and singer map SCA (SM_SCA). © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

On a Survival Gradient Boosting, Neural Network and Cox PH Based Approach to Predicting Dementia Diagnosis Risk on ADNI

On a Survival Gradient Boosting, Neural Network and Cox PH B...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Musto, Henry Stamate, Daniel Logofatu, Doina Ouarbya, Lahcen Goldsmiths College University of London Department of Computing United Kingdom Goldsmiths College University of London School of Health Sciences The University of Manchester Department of Computing United Kingdom Frankfurt University of Applied Sciences Faculty of Computer Science and Engineering Germany

ISBN: (纸本)9798350337488

In recent years, attention within the clinical prediction community has turned to the use of survival machine learning as a tool for predicting the risk of developing a disease as a function of time. The current work seeks to contribute to existing literature which demonstrates the utility of these methods when applied to a dementia prediction context. We use the Alzheimer's Disease Neuroimaging Initiative ADNI dataset and model deterioration within two distinct groups, those deemed cognitively normal and those with a formal diagnosis of Mild Cognitive Impairment. In agreement with existing literature we find that survival machine learning outperforms standard survival analysis methods such as Cox PH model, and has very good predictive ability. We propose an innovative approach to predicting dementia diagnosis risk on ADNI, which explores the use of survival neural network and survival extreme gradient boosting techniques that have hitherto seldom been applied to this context. The stability of our models was investigated within a Monte Carlo simulation framework. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

An Efficient Technique to Prevent Data Misuse with Matrix Cipher Encryption Algorithms

引用

Computers, Materials & Continua 2023年第2期74卷 4059-4079页

作者： Muhammad Nadeem Ali Arshad Saman Riaz Syeda Wajiha Zahra Ashit Kumar Dutta Moteeb Al Moteri Sultan Almotairi Department of Computing Abasyn UniversityIslamabadPakistan Department of Computer Science National University of TechnologyIslamabadPakistan Department of Computer Science and Information Systems College of Applied SciencesAlMaarefa UniversityRiyadh13713Kingdom of Saudi Arabia Department of Management Information Systems Business Administration CollegeKing Saud UniversityRiyadh11451Saudi Arabia Department of Natural and Applied Sciences Faculty of Community CollegeMajmaah UniversityMajmaah11952Saudi Arabia

Many symmetric and asymmetric encryption algorithms have been developed in cloud computing to transmit data in a secure *** cryptography is a data encryption mechanism that consists of different steps and prevents the attacker from misusing the *** paper has developed an efficient algorithm to protect the data from invaders and secure the data from *** this algorithm is applied to the cloud network,the attacker will not be able to access the *** encrypt the data,the values of the bytes have been obtained by converting the plain text to ASCII.A key has been generated using the Non-Deterministic Bit Generator(NRBG)mechanism,and the key is XNORed with plain text bits,and then Bit toggling has been *** that,an efficient matrix cipher encryption algorithm has been developed,and this algorithm has been applied to this *** capability of this algorithm is that with its help,a key has been obtained from the plain text,and only by using this key can the data be decrypted in the first steps.A plain text key will never be used for another plain *** data has been secured by implementing different mechanisms in both stages,and after that,a ciphertext has been *** the end of the article,the latest technique will be compared with different *** will be a discussion on how the present technique is better than all the other techniques;then,the conclusion will be drawn based on comparative analysis.

关键词： Symmetric cryptography ciphertext encryption decryption cloud security matrix cipher

来源：评论

学校读者我要写书评

暂无评论

Blockchain and IIoT Enabled Solution for Social Distancing and Isolation Management to Prevent Pandemics

引用

Computers, Materials & Continua 2023年第7期76卷 687-709页

作者： Muhammad Saad Maaz Bin Ahmad Muhammad Asif Muhammad Khalid Khan Toqeer Mahmood Elsayed Tag Eldin Hala Abdel Hameed College of Computing and Information Sciences Karachi Institute of Economics&TechnologyKarachiPakistan Department of Computer Science Lahore Garrison UniversityLahorePakistan Department of Computer Science National Textile UniversityFaisalabad37610Pakistan Faculty of Engineering and Technology Future University in Egypt New Cairo11835Egypt Faculty of Computer and Information Systems Fayoum UniversityFaiyumEgypt Khaybar Applied College Taibah UniversityMedinaSaudi Arabia

Pandemics have always been a nightmare for humanity,especially in developing *** lockdowns are considered one of the effective ways to deal with spreading such ***,developing countries cannot afford such solutions because these may severely damage the country’s ***,this study presents the proactive technological mechanisms for business organizations to run their standard business processes during pandemic-like situations *** novelty of this study is to provide a state-of-the-art solution to prevent pandemics using industrial internet of things(IIoT)and blockchain-enabled *** to existing studies,the immutable and tamper-proof contact tracing and quarantine management solution is *** use of advanced technologies and information security is a critical area for practitioners in the internet of things(IoT)and corresponding ***,this study also emphasizes information security,end-to-end solution,and experimental ***,a wearable wristband is proposed,incorporating 4G-enabled ultra-wideband(UWB)technology for smart contact tracing mechanisms in industries to comply with standard operating procedures outlined by the world health organization(WHO).Secondly,distributed ledger technology(DLT)omits the centralized dependency for transmitting contact tracing ***,a privacy-preserving tracing mechanism is discussed using a public/private key cryptography-based authentication ***,based on geofencing techniques,blockchain-enabled machine-to-machine(M2M)technology is proposed for quarantine *** step-by-step methodology and test results are proposed to ensure contact tracing and quarantine *** existing research studies,the security aspect is also considered in the realm of *** practical implementation of the proposed solution also obtains the *** results indicate the successful implementation of blockchain-enabled contac

关键词： Blockchain contact tracing distributed ledger technology geo-fencing internet of things industrial internet of things isolation management social distancing ultra-wideband

来源：评论

学校读者我要写书评

暂无评论

A Review of Smart Contract Blockchain Based on Multi-Criteria Analysis:Challenges and Motivations

引用

Computers, Materials & Continua 2023年第5期75卷 2833-2858页

作者： Norah M.Alshahrani M.L.Mat Kiah B.B.Zaidan A.H.Alamoodi Abdu Saif Department of Computer System&Technology Faculty of Computer Science&ITUniversity of MalayaLembah Pantai50603Kuala LumpurMalaysia Department of Computer Science Applied CollageKing Khalid UniversityP.O.Box 62569AbhaSaudi Arabia Future Technology Research Center National Yunlin University of Science and Technology123 University RoadSection 3DouliouYunlin64002Taiwan Department of Computing Faculty of ArtsComputing and Creative Industry(FSKIK)Universiti Pendidikan Sultan IdrisTanjung MalimMalaysia Department of Electrical Engineering Faculty of EngineeringUniversity of MalayaKuala Lumpur50603Malaysia

A smart contract is a digital program of transaction protocol(rules of contract)based on the consensus architecture of *** contracts with Blockchain are modern technologies that have gained enormous attention in scientific and practical applications.A smart contract is the central aspect of a blockchain that facilitates blockchain as a platformoutside the cryptocurrency *** development of blockchain technology,with a focus on smart contracts,has advanced significantly in recent ***,research on the smart contract idea has weaknesses in the implementation sectors based on a decentralized network that shares an identical *** paper extensively reviews smart contracts based on multi-criteria analysis,challenges and ***,implementing blockchain in multicriteria research is required to increase the efficiency of interaction between users via supporting information exchange with high *** blockchain in the multi-criteria analysis is necessary to increase the efficiency of interaction between users via supporting information exchange and with high confidence,detecting malfunctioning,helping users with performance issues,reaching a consensus,deploying distributed solutions and allocating plans,tasks and joint *** smart contract with decision-making performance,planning and execution improves the implementation based on efficiency,sustainability and ***,the uncertainty and supply chain performance lead to improved users’confidence in offering new solutions in exchange for problems in smart *** includes code analysis and performance,while development performance can be under development.

关键词： Blockchain smart contract MCDM MADM

来源：评论

学校读者我要写书评

暂无评论

Divide-and-train: A new approach to improve the predictive tasks of bike-sharing systems

引用

Mathematical Biosciences and Engineering 2024年第7期21卷 6471-6492页

作者： Ali, Ahmed Salah, Ahmad Bekhit, Mahmoud Fathalla, Ahmed Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia Higher Future Institute for Specialized Technological Studies Cairo3044 Egypt College of Computing and Information Sciences University of Technology and Applied Sciences Ad-Dhahirah Ibri Oman Zagazig University Department of Computer Science Faculty of Computers and Informatics Sharkeya Zagazig Egypt Sydney Australia Kaplan Business School Sydney Australia Department of Mathematics Faculty of Science Suez Canal University Ismailia Egypt

Bike-sharing systems (BSSs) have become commonplace in most cities worldwide as an important part of many smart cities. These systems generate a continuous amount of large data volumes. The effectiveness of these BSS systems depends on making decisions at the proper time. Thus, there is a vital need to build predictive models on the BSS data for the sake of improving the process of decision-making. The overwhelming majority of BSS users register before utilizing the service. Thus, several BSSs have prior knowledge of the user’s data, such as age, gender, and other relevant details. Several machine learning and deep learning models, for instance, are used to predict urban flows, trip duration, and other factors. The standard practice for these models is to train on the entire dataset to build a predictive model, whereas the biking patterns of various users are intuitively distinct. For instance, the user’s age influences the duration of a trip. This endeavor was motivated by the existence of distinct user patterns. In this work, we proposed divide-and-train, a new method for training predictive models on station-based BSS datasets by dividing the original datasets on the values of a given dataset attribute. Then, the proposed method was validated on different machine learning and deep learning models. All employed models were trained on both the complete and split datasets. The enhancements made to the evaluation metric were then reported. Results demonstrated that the proposed method outperformed the conventional training approach. Specifically, the root mean squared error (RMSE) and mean absolute error (MAE) metrics have shown improvements in both trip duration and distance prediction, with an average accuracy of 85% across the divided sub-datasets for the best performing model, i.e., random forest. © 2024 the Author(s).

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Cognitive Load Optimization in Digital (ESL) Learning: A Hybrid BERT and FNN Approach for Adaptive Content Personalization

引用

International Journal of Advanced Computer science and Applications 2025年第4期16卷 564-576页

作者： Ramesh, Komminni Thomas, Christine Ann Osei-Asiamah, Joel Pagidipati, Bhuvaneswari Muniyandy, Elangovan Reddy, B. V. Suresh El-Ebiary, Yousef A. Baker BoS Anurag Engineering College Suryapet District Telangana Kodad India Department of English and Cultural Studies Christ University Bengaluru India Gauteng Province Pretoria South Africa West Godavari Dt Andhra Pradesh Bhimavaram534204 India Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Applied Science Research Center Applied Science Private University Amman Jordan Department of CSE Koneru Lakshmaiah Education Foundation AP Vaddeswaram India Faculty of Informatics and Computing UniSZA University Malaysia

Traditional English as a Secondary Language (ESL) learning platform rely on static content delivery, often failing to adapt to individual learners’ cognitive capacities, leading to inefficient comprehension and increased cognitive load. A novel hybrid Feedforward Neural Network and Bidirectional Encoder Representation Transformer (FNN-BERT) framework stands as our solution because it performs dynamic content personalization through predictions of real-time cognitive load. The proposed approach incorporates Feedforward Neural Networks (FNN) alongside Bidirectional Encoder Representations from Transformers (BERT) to process behavioral analytics for optimized content complexity adjustment and adaptive and scalable learning delivery. Real-time adaptability, scalability and high computational needs of current models reduce their effectiveness in personalized learning environments. Through the application of Test of English for International Communication (TOEIC), International English Language Testing System (IELTS) and Test of English as a Foreign Language (TOEFL) datasets, our methodology uses Feedforward Neural Network (FNN) to forecast cognitive load based on student engagement behaviors and application errors then Bidirectional Encoders Representations from Transformer (BERT) processes content difficulty adjustments automatically. The proposed model delivers a 95.3% accuracy rate, 96.22% precision level, 96.1% recall capability and 97.2% F1-score which surpasses conventional Artificial Intelligence-based English as a Secondary Language (ESL) learning systems. The system makes use of Python for its implementation to improve understanding as well as student focus and mental processing speed. Personalized content presentation methods lead to lower cognitive strain which simultaneously advances student achievement numbers. The research adds value to smart educational frameworks through its introduction of a scalable framework that allows adaptable learning systems for E

关键词： Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction and Classification Stage on Facial Expression: A Review 6

Feature Extraction and Classification Stage on Facial Expres...

引用

6th International Conference on Informatics and Computational sciences, ICICoS 2022

作者： Shidiq, Muchamad Bachram Ernawan, Ferda Khubrani, Mousa Nugroho, Fajar Agung Universitas Nusa Mandiri Faculty of Computer Science Jakarta Indonesia Universiti Malaysia Pahang Faculty of Computing College of Computing & Applied Sciences Pahang Malaysia Jazan University Faculty of Computer Science & Information Technology Jazan Saudi Arabia Diponegoro University Department of Informatics Semarang Indonesia

ISBN: (数字)9781665460996

ISBN: (纸本)9781665460996

Human facial expression becomes an important technology in recent years. As information technology and networks have grown, identification and authentication have become more frequent in people's daily lives, especially using biometric technology. Human facial recognition involves face detection, feature extraction, and classification. A lot of experiments showed that there are various techniques for extracting facial features and classifying facial expressions. This paper reviews and analyze the various optimization techniques on extract feature and classification stage for human facial expression recognition. This review will compare two kinds of extract features methods and one classification method. The first technique of extracting features is the optimization technique using the K-Mean algorithm, which helps to increase recognition accuracy. The second extract feature is an optimization technique using improved Gradient Local Ternary Pattern (GLTP) which is beneficial for computational resources efficiency. Lastly, the optimization technique for image classification using a three-staged Support Vector Machine (SVM) is very helpful for increasing accuracy and eliminating error. The modified GLTP is able to obtain an accuracy of 97%. © 2022 IEEE.

关键词： Classification (of information)

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：