检索结果-内蒙古大学图书馆

Computing and Information Technology (ICCIT-1441), 2020 International Conference on

作者： Mansour Alsulaiman Mohammed Algabri Hassan Mathkour Mohamed A. Bencherif Ghulam Muhammad Saad Al-Gahtani Mohammed Faisal Mohamed Amine Mekhtiche Taha Alfakih Computer Engineering Department College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia Computer Science and Information Systems Department College of Applied Sciences AlMaarefa University Riyadh Saudi Arabia Computer Science Department College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia Centre of Smart Robotics Research (CS2R) King Saud University Riyadh Saudi Arabia Arabic Language Institute King Saud University Saudi Arabia Center of AI & Robotics Kuwait College of Science and Technology (KCST) Kuwait

computer-Aided Pronunciation Training (CAPT) systems are gaining popularity recently due to the advancements in deep neural networks (DNN) and machine learning and the availability of databases of speech of language learners. Unfortunately, research in Arabic CAPT systems suffer from the lack of CAPT datasets compared to other languages. In this paper, we present the details of and the ideas used in the development of a versatile dataset of speech, real and synthesized, of Arabic Learners. To develop the dataset, we utilized an existing Arabic speech corpus, King Saud University Speech Database (KSU-SD). KSU-SD's main application was a speaker recognition system, but it was designed to be useful in other applications such as CAPT systems. KSU-SD includes a large number of speakers from diverse nationalities (Saudis, Arabs, and Non-Arabs). KSU-SD contains the recording of about 60 non-native speakers from more than 20 nationalities, hence we selected it to build the non-native Arabic-CAPT corpus. The developed corpus consists of transcribed, segmented, and annotated speech, which makes it suitable for building Arabic CAPT systems. In addition to presenting the details of developing the dataset, we also present an analysis of the text and speech errors of the dataset. The dataset was verified by many CAPT systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Instant Clustering Approach for Federated Learning Client Selection

Towards Instant Clustering Approach for Federated Learning C...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Sarhad Arisdakessian Omar Abdel Wahab Azzam Mourad Hadi Otrok Department of Computer and Software Engineering Polytechnique Montréal Montréal Canada Department of Computer Science Lebanese American University Beirut Lebanon Division of Science New York University Abu Dhabi UAE Department of EECS Center of Cyber-Physical Systems (C2PS) Khalifa University Abu Dhabi UAE

In just few years, Federated Learning (FL) started to gain unprecedented attention given its ability to solve some fundamental privacy and communication challenges of traditional machine learning. Client selection is one of the main challenges in FL and is usually done in a random fashion, where the central server arbitrarily selects a certain number of clients to participate in each training round. However, given the heterogeneity of the client devices in terms of data quality and resource availability, randomly selecting clients is likely to result in long local training time and thus delayed global model’s convergence. To address this problem, in this work, we propose a real-time and on-demand client selection mechanism that employs the DBSCAN (Density-Based Spatial clustering of Applications with Noise) clustering technique from machine learning to group the clients into a set of homogeneous clusters based on a set of criteria defined by the FL task owners, such as resource availability, data quality, data size, data freshness and non-IID degree. Based on the requirements of each FL task, the server then intelligently selects the clusters of clients that best match with each task’s requirements, thus improving the performance of the overall federated learning process. Experiments suggest that our solution significantly improves the accuracy of FL compared to the Vanilla FL approach.

关键词： Training Privacy Federated learning Data integrity Clustering algorithms Real-time systems Data models

来源：评论

学校读者我要写书评

暂无评论

Design and Comparison of Ammonia Reactors for Power-to-Ammonia

SSRN

引用

SSRN 2024年

作者： Rosbo, Joachim Weel Jensen, Anker Degn Jørgensen, John Bagterp Huusom, Jakob Kjøbsted Department of Chemical and Biochemical Engineering Technical University of Denmark Kongens Lyngby2800 Denmark Department of Applied Mathematics and Computer Science Technical University of Denmark Kongens Lyngby2800 Denmark 2-control ApS Herning7400 Denmark

This work investigates the design and performance of three general types of ammonia reactors for Power-to-Ammonia (P2A). Specifically, the reactors are an adiabatic quench cooled reactor (AQCR), adiabatic indirect cooled reactor (AICR) and internal direct cooled reactor (IDCR).We present rigorous steady-state and dynamic models for the three reactor types. Steady-state optimisation at nominal load shows that the AICR and IDCR yield the highest reactant conversion at 30.0 \% and 29.4\% respectively, while the reactant conversion in the AQCR is significantly lower at 26.1 \%. We perform open-loop simulations around the optimal operating point. This illustrates the unstable oscillatory dynamics of the AQCR, while the AICR and IDCR show stable and fast decaying oscillations. However, a stability analysis revealed that the optimal operating points are situated on the verge of reactor extinction for all the reactors. Thus, even minor disturbances pose a risk of extinguishing the reactors when optimally *** optimise the reactors over an operating window from 30\% to 130\% of nominal load relevant for P2A operations. The AICR and IDCR exhibit similar reactant conversions over this operational range and showcase adaptability to varying loads as significantly higher conversions are achieved at lower loads. In contrast, the AQCR exhibits a less pronounced increase in reactant conversion at low *** the location of the optimal operating points close to reactor extinction, we suggest operating the reactors at a 15 K higher feed temperature than optimal (safety margin). We show that a 15 K safety margin only decreases ammonia conversion slightly over the operating window and ensures stable operation even for a 10\% decrease in reaction rate. © 2024, The Authors. All rights reserved.

关键词： Ammonia

来源：评论

学校读者我要写书评

暂无评论

Generalized Hydrodynamics: A Perspective

引用

Physical Review X 2025年第1期15卷 010501-010501页

作者： Benjamin Doyon Sarang Gopalakrishnan Frederik Møller Jörg Schmiedmayer Romain Vasseur Department of Mathematics King’s College London Strand London WC2R 2LS United Kingdom Department of Electrical and Computer Engineering Princeton University Princeton New Jersey 08544 USA Vienna Center for Quantum Science and Technology Atominstitut TU Wien Stadionallee 2 A-1020 Vienna Austria Department of Theoretical Physics University of Geneva 24 quai Ernest-Ansermet 1211 Genève Switzerland Department of Physics University of Massachusetts Amherst Massachusetts 01003 USA

Conventional hydrodynamics describes systems with few long-lived excitations. In one dimension, however, many experimentally relevant systems feature a large number of long-lived excitations and conserved quantities even at high temperature, because they are proximate to integrable limits. Such models cannot be treated using conventional hydrodynamics. The framework of generalized hydrodynamics (GHD) was recently developed to treat the dynamics of one-dimensional models: It combines ideas from integrability, hydrodynamics, and kinetic theory to come up with a quantitative theory of transport. GHD has successfully settled several long-standing questions about one-dimensional transport; it has also been leveraged to study dynamical questions beyond the transport of conserved quantities and to systems that are not integrable. In this article, we introduce the main ideas and predictions of GHD, survey some of the most recent theoretical extensions and experimental tests of the GHD framework, and discuss some open questions in transport that the GHD perspective might elucidate.

关键词： Transport properties

来源：评论

学校读者我要写书评

暂无评论

Optimizing Electricity Theft Detection using Neural Turing Machines and Machine Learning

Optimizing Electricity Theft Detection using Neural Turing M...

引用

Software, Systems and Information Technology (SSITCON), International Conference on

作者： Erdal Büyükbiçakci Selcuk Bulat C Senthilkumar A Rajesh Malatthi Sivasundaram Rama Raju Svsv Palla Department of Computer Technologies University of Applied Sciences Information Technologies Vocational Highschool Sakarya Turkey Department of Nanoscience and Nanoengineering Institute of Natural Sciences Sakarya University Turkey 2 Turkish Standards Institution Istanbul Turkey Department of Artificial Intelligence and Data Science Erode Sengunthar Engineering College Erode India Department of CSE Erode Sengunthar Engineering College Erode India Department of Computer Science and Design KSR College of Engineering Tiruchengode India Department of CSE Vignan’s Institute of Information Technology Duvvada India

ISBN: (数字)9798350352931

ISBN: (纸本)9798350352948

Electricity theft detection (ETD) is crucial for smart grids to maintain their cost-effectiveness. Current approaches for identifying theft struggle with large datasets of electricity use owing to problems with missing values, data variance, and nonlinear patterns in the data; furthermore, an integrated infrastructure to coordinate the study of electricity load data is not currently in *** suggested method trains models after feature extraction and stage preprocessing. Data normalization, missing value imputation, and data cleansing are all components of data preprocessing. Utility data sets often suffer from inconsistent and missing data as a result of manual and unsynchronized meter reading and registering processes; however, this can be mitigated through the feature extraction process. All the way through training, the proposed approach stuck with the NTM paradigm. The average accuracy of this state-of-the-art approach is $\mathbf{94.22\%}$, which is higher than RNN and ELM.

关键词： Training Accuracy Turing machines Electricity Biological system modeling Feature extraction Imputation Smart grids Meter reading Synchronization

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review of Machine Learning in Sports Betting: Techniques, Challenges, and Future Directions

arXiv

引用

arXiv 2024年

作者： Galekwa, René Manassé Tshimula, Jean Marie Tajeuna, Etienne Gael Kyandoghere, Kyamakya Institute of Smart Systems Technologies University of Klagenfurt Klagenfurt am Wörthersee9020 Austria Mathematics Statistics and Computer Science Department University of Kinshasa Kinshasa Democratic Republic Congo Department of Computer Science Université de Sherbrooke QCJ1K 2R1 Canada Department of Computer Science and Engineering Université du Québec en Outaouais QCJ8X 3X7 Canada Polytechnic Faculty University of Kinshasa Kinshasa Democratic Republic Congo

The sports betting industry has experienced rapid growth, driven largely by technological advancements and the proliferation of online platforms. Machine learning (ML) has played a pivotal role in the transformation of this sector by enabling more accurate predictions, dynamic odds-setting, and enhanced risk management for both bookmakers and bettors. This systematic review explores various ML techniques, including support vector machines, random forests, and neural networks, as applied in different sports such as soccer, basketball, tennis, and cricket. These models utilize historical data, in-game statistics, and real-time information to optimize betting strategies and identify value bets, ultimately improving profitability. For bookmakers, ML facilitates dynamic odds adjustment and effective risk management, while bettors leverage data-driven insights to exploit market inefficiencies. This review also underscores the role of ML in fraud detection, where anomaly detection models are used to identify suspicious betting patterns. Despite these advancements, challenges such as data quality, real-time decision-making, and the inherent unpredictability of sports outcomes remain. Ethical concerns related to transparency and fairness are also of significant importance. Future research should focus on developing adaptive models that integrate multimodal data and manage risk in a manner akin to financial portfolios. This review provides a comprehensive examination of the current applications of ML in sports betting, and highlights both the potential and the limitations of these technologies. © 2024, CC BY.

关键词： Cricket (Sports)

来源：评论

学校读者我要写书评

暂无评论

Developing Safe and Responsible Large Language Model: Can We Balance Bias Reduction and Language Understanding

arXiv

引用

arXiv 2024年

作者： Raza, Shaina Bamgbose, Oluwanifemi Ghuge, Shardul Tavakoli, Fatemeh Reji, Deepak John Bashir, Syed Raza AI Engineering Vector Institute for Artificial Intelligence TorontoONM5G 1M1 Canada Computer Science Department University of Limerick Castletroy Limerick V94 T9PX Ireland Computer Science Department Sheridan College Trafalgar Rd ONL6H 2L1 Canada

Large Language Models (LLMs) have advanced various Natural Language Processing (NLP) tasks, such as text generation and translation, among others. However, these models often generate texts that can perpetuate biases. Existing approaches to mitigate these biases usually compromise knowledge retention. This study explores whether LLMs can produce safe, unbiased outputs without sacrificing knowledge or comprehension. We introduce the Safe and Responsible Large Language Model (SRLLM), which has been instruction fine-tuned atop of a safe fine-tuned auto-regressive decoder-only LLM to reduce biases in generated texts. We developed a specialized dataset with examples of unsafe and corresponding safe variations to train SRLLM to identify and correct biased text. Experiments on our specialized dataset and out-of-distribution test sets reveal that SRLLM effectively reduces biases while preserving knowledge integrity. This performance surpasses that of traditional fine-tuning of smaller language models and base LLMs that merely reply on prompting techniques. Our findings demonstrate that instruction fine-tuning on custom datasets tailored for tasks such as debiasing is a highly effective strategy for minimizing bias in LLM while preserving their inherent knowledge and capabilities. The code and dataset are accessible at SR-LLM. © 2024, CC BY-NC-SA.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Optimizing AI for Mobile Malware Detection by Self-Built-Dataset GAN Oversampling and LGBM

Optimizing AI for Mobile Malware Detection by Self-Built-Dat...

引用

Cyber Security and Resilience (CSR), IEEE International Conference on

作者： Ortal Dayan Lior Wolf Fang Wang Yaniv Harel School of Computer Science Tel-Aviv University Tel-Aviv Israel Department of Electrical Engineering and Computer Science C2PS Khalifa University Abu Dhabi United Arab Emirates Blavatnik Interdisciplinary Research Center Tel-Aviv University Tel-Aviv Israel

The cyber detection industry focuses on analyzing the behavior of threats in order to develop IOCs and triggers. This process makes the detection always behind the attackers, as there is an analysis time between the attack tool launch and the detection ability. To address the challenges, a dedicated Sandbox environment was built, and thousands of mobile devices' samples were tested, resulted in creation of an up-to-date training dataset that is not based on the attacks analysis. With this dataset, the research focus was directed towards optimizing the AI methodology to achieve the best detection rates for a compromised mobile device. A CupolaGAN was implemented to oversample dataset and to compare results obtained from training LGBM models on both original imbalanced dataset and oversampled dataset. Classification scores on the oversampled data increase by maximum of 0.47+/-0.37%. The performance of the fine-tuned model using Optuna on the balanced data reaches 99.36+/-0.19% accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CMA of Non-uniform Metasurface Circularly-Polarized Slotted-Patch Antenna with L-Shaped Feed Structure

CMA of Non-uniform Metasurface Circularly-Polarized Slotted-...

引用

13th International Electrical engineering Congress, iEECON 2025

作者： Musika, Chanwit Konpang, Jessada Thitimahatthanakusol, Phatsakul Supreeyatitikul, Nathapat Rajamangala University of Technology Krungthep Faculty of Science and Technology Department of Computer Science Krungthep 2 Nanglingee Rd. Thungmahamek Sathorn Bangkok10120 Thailand Rajamangala University of Technology Krungthep Faculty of Engineering Department of Electrical and Telecommunication Engineering 2 Nanglingee Rd. Thungmahamek Sathorn Bangkok10120 Thailand Rajamangala University of Technology Isan Faculty of Engineering and Technology Department of Telecommunication Engineering 744 Sura Narai Rd. Nai-muang Muang Ratchasima Thailand

ISBN: (纸本)9798331543952

This research presents a non-uniform metasurface (MTS) scheme circularly-polarized slotted-patch (CPSP) antenna for modern cellular technology. The proposed non-uniform MTS CPSP antenna was combined with non-uniform MTS scheme (upper-layer substrate) and slot-coupled feed (lower-layer substrate). The slot-coupled feed comprised of the L-shaped microstrip-line feed and rhombus-slotted ground plane. The non-uniform MTS scheme was characterized using characteristic mode analysis (CMA). The CP mode at 4.6 GHz (center frequency) was realized by two orthogonal modes (modes 1 and 2). To achieve wide return loss bandwidth (RLBW), the use of the different sizes (two sizes) of square-shaped MTS unit cells was adopted. The simulated RLBW and axial ratio bandwidth (ARBW) results achieved 34.78% (between 4.1 - 5.7 GHz) and 5.65% (between 4.43 - 4.69 GHz). The optimal gain of right-hand circular polarization was 3.56 dBic at 4.35 GHz, rendering this proposed non-uniform MTS CPSP antenna is functional for wireless communications. © 2025 IEEE.

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

Neural network-based small cursor detection for embedded assistive technology

引用

Visual computer 2024年第12期40卷 8425-8439页

作者： Darmawan, Jeremie Theddy Sigalingging, Xanno Kharis Faisal, Muhamad Leu, Jenq-Shiou Ratnasari, Nanda Rizqia Pradana Department of Electronic and Computer Engineering National Taiwan University of Science and Technology No. 43 Section 4 Keelung Rd Da’an District Taipei City106 Taiwan Department of Bioinformatics School of Life Sciences Indonesia International Institute for Life Sciences Jl. Pulomas Barat No.Kav. 88 RT.4/RW.9 Kayu Putih Kec. Pulo GadungSpecial Capital Region of Jakarta East Jakarta13210 Indonesia Department of Biochemistry Yong Loo Lin School of Medicine National University of Singapore C/O MD7 Level 2 8 Medical Drive Singapore117597 Singapore

Assistive technology (AT) is invaluable to people with special educational needs and disabilities, enabling them to interact with computers more efficiently. It is able to improve the interactivity between humans and computers for learning purposes. However, there is a lack of accessibility and interactivity with touchscreen devices and visual content that AT users encounter. These issues are critical in providing much-needed assistance and enhancing the daily lives of disabled individuals. Therefore, we propose an AT framework based on neural networks using embedded systems for improving the accessibility and interactivity of AT users. The proposed framework utilizes the Jetson Nano and is mainly used with a speech-to-intent neural network to process speech and move cursors. When improved with cursor object detection, the framework could obtain the location of the cursors in external displays and move the cursors of other devices. Since cursor datasets are very limited and not many detection models are up for the task, we investigated the use of Slicing Aided Hyper Inference (SAHI) pipeline along with two fine-tuned models, Fully Convoluted One-Stage (FCOS) and Task-aligned One-stage Object Detection (TOOD), to identify the minimum data required for these models to work optimally. With less than 120 annotated images and a data multiplier of 5 and 30, both models were able to achieve ~ 52 and ~ 60mAP, respectively. These results were comparable to performance on other small object detection datasets. In addition, we also present a working proof-of-concept for our proposed embedded assistive technology framework. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Assistive technology

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：