检索结果-内蒙古大学图书馆

5th International Conference on High Performance Big data and Intelligent Systems, HDIS 2023

作者： Wang, Yajing Luo, Zongwei Hong Kong Baptist University BNU-HKBU United International College Faculty of science and technology Department of computer science Hongkong Zhuhai China BNU-UIC Institute of AI and Future Networks Artificial Intelligence and Data Science Research Hub Beijing Normal University BNU-HKBU United International College Zhuhai China

ISBN: (纸本)9798350394160

Large Language Models (LLMs) have made significant strides in both scientific research and practical applications. Existing studies have demonstrated the state-of- the-art (SOTA) performance of LLMs in various natural language processing tasks. However, the question of how to further enhance LLMs' performance in specific task using prompting strategies remains a pivotal concern. This paper explores the enhancement of LLMs' performance in sentiment analysis through the application of prompting strategies. We formulate the process of prompting for sentiment analysis tasks and introduce two novel strategies tailored for sentiment analysis: RolePlaying (RP) prompting and Chain-of-thought (CoT) prompting. Specifically, we also propose the RP-CoT prompting strategy which is a combination of RP prompting and CoT prompting. We conduct comparative experiments on three distinct domain datasets to evaluate the effectiveness of the proposed sentiment analysis strategies. The results demonstrate that the adoption of the proposed prompting strategies leads to a increasing enhancement in sentiment analysis accuracy. Further, the CoT prompting strategy exhibits a notable impact on implicit sentiment analysis, with the RP-CoT prompting strategy delivering the most superior performance among all strategies. ©2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Non-convergence of Adam and other adaptive stochastic gradient descent optimization methods for non-vanishing learning rates

arXiv

引用

arXiv 2024年

作者： Dereich, Steffen Graeber, Robin Jentzen, Arnulf Institute for Mathematical Stochastics Faculty of Mathematics and Computer Science University of Münster Germany School of Data Science The Chinese University of Hong Kong CUHK-Shenzhen Shenzhen China School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong CUHK-Shenzhen Shenzhen China Institute for Analysis and Numerics Faculty of Mathematics and Computer Science University of Münster Germany

MSC Codes 60J22 (Primary), 65K10, 60J20, 65C40 (Secondary)Deep learning (DL) approximation algorithms – typically consisting of a class of deep artificial neural networks (DNNs) trained by a stochastic gradient descent (SGD) optimization method – are nowadays the key ingredients in many artificial intelligence (AI) systems and have revolutionized our ways of working and living in modern societies. For example, SGD methods are used to train powerful large language models (LLMs) such as versions of ChatGPT and Gemini, SGD methods are employed to create successful generative AI based text-to-image creation models such as Midjourney, DALL-E, and Stable Diffusion, but SGD methods are also used to train DNNs to approximately solve scientific models such as partial differential equation (PDE) models from physics and biology and optimal control and stopping problems from engineering. It is known that the plain vanilla standard SGD method fails to converge even in the situation of several convex optimization problems if the learning rates are bounded away from zero. However, in many practical relevant training scenarios, often not the plain vanilla standard SGD method but instead adaptive SGD methods such as the RMSprop and the Adam optimizers, in which the learning rates are modified adaptively during the training process, are employed. This naturally rises the question whether such adaptive optimizers, in which the learning rates are modified adaptively during the training process, do converge in the situation of non-vanishing learning rates. In this work we answer this question negatively by proving that adaptive SGD methods such as the popular Adam optimizer fail to converge to any possible random limit point if the learning rates are asymptotically bounded away from zero. In our proof of this non-convergence result we establish suitable pathwise a priori bounds for a class of accelerated and adaptive SGD methods, which are also of independent interest. Copyright © 2024,

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Cultivation: Transforming Agriculture for a Smart and Sustainable Future

Artificial Intelligence Cultivation: Transforming Agricultur...

引用

Intelligent data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Bhushan Fulkar Samir Mendhe Pawan Patil Department of Artificial Intelligence and Data science Faculty of Engineering and Technology DMIHER(DU) Wardha Maharashtra India Computer Science and Design Faculty of Engineering and Technology DMIHER(DU) Wardha Maharashtra India Artificial Intelligence and Data science Faculty of Engineering and Technology DMIHER(DU) Wardha Maharashtra India

The growing global population is posing unprecedented challenges for the agriculture industry, requiring it to produce more food while also addressing resource constraints and environmental concerns. Artificial intelligence (AI) has changed the game in agriculture by offering creative solutions to increase productivity, optimize resource use, and promote sustainability. Artificial intelligence (AI) has been used in the agriculture sector more and more recently. A few of the problems the industry faces in attempting to maximize its produce are improper soil treatment, disease and pest infestation, the use of driverless tractors, big data requirements, and the knowledge gap between farmers and technology. This work provides an overview of the applications of artificial intelligence in crop, weed, and disease management. The proposed work aims to review various AI techniques, including artificial neural networks (ANN) and fuzzy logic (FL).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloud-Enhanced Machine Learning Models for Predictive Maintenance in Industrial IoT 2

Cloud-Enhanced Machine Learning Models for Predictive Mainte...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Usharani, R. Sivagami, V.M. Saravanan, K. Pushparani, S. Rekha, K. Sashi Department of Computational Intelligence School of Computing Faculty of Engineering and Technology Srm Institute of Science and Technology Tamil Nadu Kattankulathur India Department of Information Technology Sri Venkateswara College of Engineering Sriperumbudur Tamil Nadu Chennai India Department of Artificial Intelligence and Data Science Care College of Engineering Tamil Nadu Trichy India Department of Computer Science and Engineering Meenakshi College of Engineering Tamil Nadu Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India

ISBN: (纸本)9798350384277

This study examines the implementation and impact of Cloud-Enhanced Machine Learning Models in the realm of Predictive Maintenance within Industrial Internet of Things (IIoT) settings. Emphasizing the integration of cloud computing with machine learning, the research focuses on how this synergy improves the accuracy and efficiency of maintenance predictions in industrial environments. Key metrics evaluated include prediction accuracy, operational efficiency, cost savings, and reduction in equipment downtime. The study demonstrates a significant increase in prediction accuracy, from 65% to 88%, attributed to the advanced data processing and analytical capabilities of cloud-enhanced machine learning. Operational efficiency saw marked improvements, with a 50% reduction in response times and a 25% increase in maintenance scheduling efficiency, leading to a 20% rise in asset utilization rates. Financially, the implementation led to a 37% reduction in annual maintenance costs and a 40% decrease in both the cost per downtime incident and long-term repair expenses. Most notably, the study recorded a 62.5% reduction in both the duration and frequency of downtime incidents. These results highlight the transformative potential of integrating cloud computing and machine learning in IIoT for predictive maintenance, showcasing significant advancements in predictive accuracy, operational efficiency, cost-effectiveness, and overall reduction in downtime. The study underscores the critical role of technological innovation in advancing industrial maintenance strategies, leading to more proactive, efficient, and economically viable operations. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Implementing Multi-factor Authentication in Cloud Services for Enhanced Security

Implementing Multi-factor Authentication in Cloud Services f...

引用

2024 IEEE International Conference on Recent Advances in science and Engineering Technology, ICRASET 2024

作者： Rekha, K. Sashi Sivagami, V.M. Usharani, R. Amutha, T. Pushparani, S. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Sri Venkateswara College of Engineering Department of Information Technology Tamil Nadu Chennai India Srm Institute of Science and Technology School of Computing Faculty of Engineering and Technology Department of Computational Intelligence Kattankulathur Chennai India Care College of Engineering Department of Artificial Intelligence & Data Science Tamil Nadu Trichy India Meenakshi College of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350388602

The cloud services which are now the most common data transmission and endanger organizations' confidential information, it's more and more visible that security of any data should be a main priority for companies. MFA, which consists of adopting multi factor approach to authentication and thereby provides multiple types of verification thus ensures effective security, is leveraged to ensure resource access. This paper proposes a full-fledged way of implementing MFA for cloud services in order to strengthen the security given and manage the constatoing risks. The proposed methodology consists of main stages like requirements determining, technology reviewing, risks assessment, technology design, integration with cloud services, users training, pilot deployment and testing, implementation and configuration, monitoring and maintenance as well as constant improvement. Through a systemic approach, the organizations can be equipped with the capability to personalize the MFA solutions according to their security goals, to bring the cloud environments on board, as well as to ensure that the organizations comply with the security standards as set by various governing bodies. This research adds a grain of salt to the development of cloud security good practices through offering a disciplined approach to MFA implementation, which allows partners to harden their cloud assets and protect against growing cyber threats. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Arabic Text Detection From Natural Images Using Transformers

Arabic Text Detection From Natural Images Using Transformers

引用

International Symposium on Signal, Image, Video and Communications (ISIVC)

作者： Ayad Abdessamad Ayad Habib Adib Abdellah Team Data Science & Artificial Intelligence Mathematics Computer Science & Applications Laboratory Faculty of Sciences and Technologies Mohammedia Hassan II University of Casablanca Morocco

ISBN: (数字)9798350385267

ISBN: (纸本)9798350385274

Text detection in the wild is an important stage for recognizing and interpreting text present in images or videos captured in uncontrolled environments in the wild. It helps in various applications such as scene understanding, robot navigation, augmented reality, and automatic captioning. However, it remains a difficult task, due to the vast differences in lighting, backgrounds, textures, and fonts. The research, in this topic, has predominantly concentrated on languages utilizing Latin characters, neglecting other languages with distinct features, such as the Arabic language. This work specifically addresses the topic of Arabic scene text detection. We propose a model for Arabic text detection from natural images based on transformers. We experiment two variations of this model: the first focuses on Arabic text, whereas the second is bilingual and handles both Latin and Arabic languages. We evaluate the performance of both models on existing datasets namely, the Everyday Arabic-English Scene Text dataset EvarEst [1] and the Arabic-Latin Scene Text Localization in Highway Traffic Panels dataset ASAYAR [2].

关键词： Road transportation Location awareness Deformable models Text recognition Navigation Text detection Transformers

来源：评论

学校读者我要写书评

暂无评论

From ASR to TTS: Enhancing Synthesis with Cleaned ASR data

From ASR to TTS: Enhancing Synthesis with Cleaned ASR Data

引用

International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)

作者： Atsadawut Surinrangsee Ausdang Thangthai Data Science Research Center Faculty of Science Chiang Mai University Chiang Mai Thailand National Electronics and Computer Technology Center(NECTEC) Thailand

ISBN: (数字)9798331509910

ISBN: (纸本)9798331509927

This paper investigates a novel method for handling with the scarcity of appropriate speech corpora for Text-to-Speech (TTS) systems in the Thai language by repurposing Automatic Speech Recognition (ASR) corpus. In this paper, we focus on whether noisy ASR by exploiting the Miipher speech restoration model approach and examine its suitability for TTS corpus *** study compares single-speaker and multi-speaker Tacotron2 models trained on both original and Miipher-processed datasets. Through a series of experiments including A/B preference tests and Mean Opinion Score (MOS) evaluations, we demonstrate the efficacy of our approach. Results show a clear preference for Miipher-processed data over original noisy data, with 67.65% of participants favoring the processed audio. As expected, given the limited amount of data per speaker in the multi-speaker dataset, the single-speaker TTS model outperformed the multi-speaker model in preference tests, with 63.55% of participants preferring the single-speaker system. MOS evaluations revealed that Miipher-processed data achieved the highest score of 3.69 ± 0.15, followed by the original noisy data at 3.56 ± 0.17, while both TTS systems showed lower scores. These findings indicate that repurposing ASR data with appropriate processing can effectively improve speech quality, but translating this improvement to TTS systems requires further investigation. Our results suggest that the quantity of per-speaker data may be more crucial than speaker diversity for TTS development using processed ASR data. We have made demo audio samples available at "From ASR to TTS: Enhancing Synthesis with Cleaned ASR data (***)".

关键词： Translation data integrity Speech enhancement Market research data models Natural language processing Cleaning Text to speech Noise measurement Automatic speech recognition

来源：评论

学校读者我要写书评

暂无评论

Detection and Discrimination of Arabic Phonemes Using Long Short-Term Memory (LSTM) Model

Detection and Discrimination of Arabic Phonemes Using Long S...

引用

IEEE International Conference on Intelligent Computing and Information Systems (ICICIS)

作者： Rahma M. Tolba Zaki T. Fayed Hamzah A. Alsayadi NourEldin O. Saad Taha Elarif Computer Science Department Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Computer Science Department Faculty of Sciences Ibb University Yemen Data Science Department School of Computer Science Canadian International Collage New Cairo Egypt

Phonetics is a crucial branch of linguistics that studies human speech sounds and is essential for language learning, speech therapy, and speech technology development. However, current Arabic speech systems cannot instantly analyze and detect mispronunciation of Arabic phonemes, only offering a recording feature for self-evaluation. So, this paper presents a state-of-the-art approach using a Long Short-Term Memory (LSTM) model for detecting and discriminating between Arabic phonemes. The model was tested on a collected dataset for the Arabic phonemes /s/ 'sīn' and /sˤ/ 'ṣād and demonstrated excellent performance in discriminating between them despite their close articulation. The model achieved an accuracy of 97.33% and outperformed other techniques proposed for small datasets. The model can be utilized either independently or integrated into a computer-assisted language learning (CALL) system. Furthermore, our findings suggest that there is significant room for improvement in this area, particularly in collecting large audio datasets for all the Arabic phonemes, refining the algorithms, and optimizing the data processing pipeline.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection of Toxic Content on Social Networking Platforms Using Fine Tuned ULMFiT Model

引用

Intelligent Automation & Soft Computing 2023年第1期35卷 15-30页

作者： Hafsa Naveed Abid Sohail Jasni Mohamad Zain Noman Saleem Rao Faizan Ali Shahid Anwar Department of Software Engineering Faculty of ScienceUniversity of LahorePakistan Department of Computer Science COMSATS University IslamabadLahore CampusPakistan Institute for Big Data Analyics and Artifcial Intelligence(IBDAAI) Kompleks Al-KhawarizmiUniversii Tekoogi MARA40450Shah AlamSelangorMalaysia TechnoGenics SMC PVT LTD LahorePakistan Department of Computer and Infomation Science Universiti Teknologi PETRONASBandar Ser IskandarTronohPerakMalaysia Depatment of Information Engineering Technology National Skils University IslamabadSector H-8/1Faiz AhmedFaiz RoadIslamabadPakistan

Question and answer websites such as Quora,Stack Overflow,Yahoo Answers and Answer Bag are used by *** users post questions on these websites to get the answers from domain specific *** websites are multilingual meaning they are available in many different *** problem for these types of websites is to handle meaningless and irrelevant *** this paper we have worked on the Quora insincere questions(questions which are based on false assumptions or questions which are trying to make a statement rather than seeking for helpful answers)dataset in order to identify user insincere questions,so that Quora can eliminate those questions from their platform and ultimately improve the communication among users over the ***,a research was carried out with recurrent neural network and pretrained glove word embeddings,that achieved the F1 score of *** proposed study has used a pre-trained ULMFiT *** model has outperformed the previous model with an F1 score of 0.91,which is much higher than the previous studies.

关键词： Machine learning text mining quora mining artificial intelligence natural language processing

来源：评论

学校读者我要写书评

暂无评论

Speech as a Window to the Brain: Innovative Techniques in Early Alzheimer’s Disease Detection

Speech as a Window to the Brain: Innovative Techniques in Ea...

引用

International Symposium on Signal, Image, Video and Communications (ISIVC)

作者： Anass El Hallani Adil Chakhtouna Abdellah Adib Team Data Science and Artificial Intelligence Laboratory of Mathematics Computer Science and Applications (LMCSA) Faculty of Sciences and Technologies Hassan II University Mohammedia Morocco

ISBN: (数字)9798350385267

ISBN: (纸本)9798350385274

As dementia cases are projected to reach 150 million by 2050, with Alzheimer’s disease (AD) accounting for $60-70 \%$ of instances, early detection becomes crucial. AD and other dementias currently rank as the seventh leading cause of death globally. Our study addresses this by employing speech analysis for AD detection, offering a non-invasive and cost-effective diagnostic tool. Utilizing the ADReSS dataset, we integrated advanced Deep Learning techniques, including YAMNet and VGGish, with Mel Frequency Cepstral Coefficients (MFCCs) for feature extraction. An autoencoder was employed for dimensionality reduction to isolate key speech features. We applied Random Forest (RF), Artificial Neural Networks (ANN), and Support Vector Machines (SVM) for classification. The ANN model outperformed others, achieving an impressive $89.3 \%$ accuracy, surpassing current methodologies. This research highlights the efficacy of using speech analysis and ML, DL for early AD detection. Our approach, accessible and precise, promises advancements in early diagnosis and care for AD. Future work will aim to enhance model applicability to various stages of AD and related disorders.

关键词： Support vector machines Radio frequency Dimensionality reduction Speech analysis Accuracy Artificial neural networks Feature extraction

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：