检索结果-内蒙古大学图书馆

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Nedaa Almansour Dheeb Albashish Shahnorbanun Sahran Azizi Abdullah Mohammad Faidzul Nasruddin Xu Xinlan Center for Artificial Intelligence Technology (CAIT) Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Malaysia Computer Science Department Prince Abdullah Bin Ghazi Faculty of Information and Communication Technology Al-Balqa Applied University Salt Jordan

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

computer-aided automated diagnosis is necessary due to the multifaceted nature of skin problems, the scarcity and uneven distribution of qualified dermatologists, and the requirements for timely and accurate diagnosis. Numerous pretrained deep learning models have been introduced to deal with such tasks, but most of them are suffering from hyperparameter tuning. This study aims to utilize metaheuristic algorithms (i.e., Genetic Algorithm (GA) and Bees Algorithm) to adjust the hyperparameters of the pretrained (i.e., MobileNetV2) deep learning model to solve the identification task in skin medical images. The proposed models have been evaluated on the publicly available Kaggle dataset for eight skin diseases. The proposed MobileNetV2+Bees algorithm achieved around 92% accuracy, while the MobileNetV2+GA algorithm achieved 93% accuracy. The obtained results outperformed most of the recent studies on the same dataset. The obtained MobileNetV2+GA model reveals the efficiency of identification and discrimination between eight different classes of skin cancer, which aids pathologists in accurately diagnosing skin diseases.

关键词： Deep learning Bees algorithm Accuracy Computational modeling Metaheuristics Skin Tuning Diseases Skin cancer Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Transcription for Thai Traditional Medicine Texts with Wav2Vec2

Transcription for Thai Traditional Medicine Texts with Wav2V...

引用

International Electrical Engineering Congress (iEECON)

作者： Jettasic Popun Wilaiporn Lee Akara Prayote Kanabadee Srisomboon Luepol Pipanmekaporn Department of Computer and Information Science Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

Recently, Automatic Speech Recognition (ASR) technology is widely used for communication convenience in converting speech to text. Initial surveys reveal that existing studies on ASR, both in Thai and foreign languages, focus on contemporary language communication, lacking support for specialized vocabulary. Thai Traditional Medicine (TTM) contain ancient medical terminology recorded in various media such as palm leaves, parchment, notebooks, and inscriptions. Centuries of textual preservation have led to text degradation. Given the suitability of ASR study to accommodate medical terminology and ancient languages, it is proposed to apply it to convert original Thai Traditional Medicine texts into contemporary language, aiding experts in reading and interpreting them. ASR involves converting speech signals into text. In this paper, we propose an end-to-end speech recognition approach for Thai Traditional Medical texts leveraging self-supervised learning (SSL) to overcome the limitations of limited labeled data. We utilize a transformer-based model pre-trained (XLSR-Wav2Vec) on unlabeled TTM texts speech data using SSL techniques and fine-tune it with a small dataset of labeled TTM texts audio-text pairs. Due to the absence of a Thai Traditional Medicine vocabulary repository, a dataset comprising text and speech is developed, consisting of 1,800 training sentences and 200 test sentences randomly selected from recordings of 10 Thai Traditional Medicine experts. Offline evaluation methods are employed, resulting in improved accuracy rates. Future efforts will focus on expanding the speech dataset to enhance recognition accuracy further. This study lays the groundwork for efficiently extracting knowledge from Thai Traditional Medicine prescriptions, ensuring the preservation of this valuable heritage for future generations.

关键词： Training Surveys Vocabulary Accuracy Terminology Self-supervised learning Speech enhancement Transformers Automatic speech recognition Speech to text

来源：评论

学校读者我要写书评

暂无评论

A Comparison and Evaluation of Named Entity Recognition Methods in Thai Traditional Medicine Texts

A Comparison and Evaluation of Named Entity Recognition Meth...

引用

International Electrical Engineering Congress (iEECON)

作者： Warodom Phungjununt Wilaiporn Lee Akara Prayote Luepol Pipanmekaporn Kanabadee Srisomboon Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut's University of Technology North Bangkok Bangkok Thailand Department of Computer and Information Science Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

The knowledge extraction and transliteration processes for the Thai traditional medicine documents requires experts to extract information from the textbook and spend a plenty of time. To reduce the complexity of these processes, the named entity recognition (NER) from the machine learning principle is applied to extract the key information from the document. In this work, three NER models including, CRFSuite, Bi-LSTM-CRF, and pre-trained model (WangchanBERTa) are considered the accuracy of each model of NER for the Thai traditional documents. After the testing process, the experimental results show that CRFSuite model is the most computationally efficient model and deliver high precision and recall. Moreover, CRFSuite model has the highest scores of each entity. While the accuracy of the WangchanBERTa model is the highest and faster convergence in the training process. Although the results from the Bi-LSTM-CRF model provide moderate accuracy, the Bi-LSTM-CRF can detect the common entities higher than other models.

关键词： Training Accuracy Computational modeling Named entity recognition Machine learning Real-time systems Computational efficiency Data mining Testing Convergence

来源：评论

学校读者我要写书评

暂无评论

Prediction of sentiment polarity in restaurant reviews using an ordinal regression approach based on evolutionary XGBoost

引用

PeerJ computer science 2025年 11卷 e2370-e2370页

作者： Al-Qudah, Dana A. Al-Zoubi, Ala M. Cristea, Alexandra I. Merelo-Guervós, Juan J. Castillo, Pedro A. Faris, Hossam King Abdullah II School for Information Technology The University of Jordan Amman Jordan Faculty of Information Technology Applied Science Private University Amman Jordan Department of Computer Science Durham University Durham United Kingdom Department of Computer Architecture and Technology Universidad de Granada Granada Spain Granada Spain

As the business world shifts to the web and tremendous amounts of data become available on multilingual mobile applications, new business and research challenges and opportunities have been explored. This research aims to intensify the usage of data analytics, machine learning, and sentiment analysis of textual data to classify customers’ reviews, feedback, and ratings of businesses in Jordan’s food and restaurant industry. The main methods used in this research were sentiment polarity (to address the challenges posed by businesses to automatically apply text analysis) and bio-metric techniques (to systematically identify users’ emotional states, so reviews can be thoroughly understood). The research was extended to deal with reviews in Arabic, dialectic Arabic, and English, with the main focus on the Arabic language, as the application examined (Talabat) is based in Jordan. Arabic and English reviews were collected from the application, and a new model was proposed to sentimentally analyze reviews. The proposed model has four main stages: data collection, data preparation, model building, and model evaluation. The main purpose of this research is to study the problem expressed above using a model of ordinal regression to overcome issues related to misclassification. Additionally, an automatic multi-language prediction approach for online restaurant reviews was proposed by combining the eXtreme gradient boosting (XGBoost) and particle swarm optimization (PSO) techniques for the ordinal regression of these reviews. The proposed PSO-XGB algorithm showed superior results when compared to support vector machine (SVM) and other optimization methods in terms of root mean square error (RMSE) for the English and Arabic datasets. Specifically, for the Arabic dataset, PSO-XGB achieved an RMSE value of 0.7722, whereas PSO-SVM achieved an RSME value of 0.9988. Copyright 2025 Al-Qudah et al.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Exploring structural, optical, and magnetic analysis of dilute Co incorporated CdS thick films for spintronics

引用

Current applied Physics 2025年 75卷 40-49页

作者： Alasmari, Aeshah Alshehri, Salma Almalki, Abdulaziz Algarni, Fahad Gomaa, Hosam M. Aldosari, F.M. Ismail, Atef Department of Physics College of Science University of Bisha P.O. Box 551 Bisha61922 Saudi Arabia Department of Physics Faculty of Science Taibah University Yanbu46423 Saudi Arabia College of Computing and Information Technology University of Bisha Saudi Arabia Pharaohs Higher Institute for Computer Information Systems and Management Giza Egypt Department of Physics College of Science and Humanities Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia Physics Department Al-Azhar University Asyut71452 Egypt

This study involves the preparation using a solid-state reaction method of six thin films of Cd1-xCoxS by varying the concentrations of cobalt and cadmium, where x = 0.0, 0.02, 0.04, 0.06, 0.08, and 0.1 At. %. The process included mixing Co2S3 and CdS powders in stoichiometric ratios, followed by mechanical ball milling, compacting into discs, and analyzing the films' properties. X-ray diffraction (XRD) confirmed the films' crystalline structure and energy-dispersive X-ray spectroscopy (EDX) verified the elemental composition, indicating the successful incorporation of Co into the CdS matrix. X-ray photoelectron spectroscopy (XPS) further detailed the chemical states within the films, showing that Co substitution influenced optical properties. The films' optical transmittance decreased with higher Co content, while reflectance and absorption increased, attributed to Co's impact on the electronic structure. The study also demonstrated a decrease in crystallite size and an increase in lattice strain with rising Co concentration, suggesting a reduction in crystallinity. Optical analyses revealed a decrease in the energy band gap and an increase in refractive index as Co content increased. The refractive index was modeled using the Cauchy equation, and the study noted a corresponding rise in static refractive index and dielectric constant, implying enhanced electromagnetic energy storage capability. Additionally, the magnetic properties showed room-temperature ferromagnetism (RT-FM) across all films, with significant values for saturation magnetization, coercivity, and retentivity. © 2025 Korean Physical Society

关键词： Saturation magnetization

来源：评论

学校读者我要写书评

暂无评论

Design of a Dust Cleaning Prototype for Photovoltaic Generators 4th

Design of a Dust Cleaning Prototype for Photovoltaic Generat...

引用

4th International Conference on Electronic Engineering and Renewable Energy systems, ICEERE 2024

作者： Latreche, M. Medjahed, B. Mellit, A. Rabhi, H. Hajji, B. Faculty of Science and Technology University of Jijel Algiers Algeria Laboratory of Modelization Information and Systems University of Picardie Jules Verne 3 Rue Saint Leu Amiens Cedex 180039 France Embedded System and Data Processing Laboratory Renewable Energy National School of Applied Sciences Mohamed First University Oujda Morocco

ISBN: (纸本)9789819799749

Solar panels are vulnerable to accumulated dust and sand, especially in desert regions, which significantly decreases their efficiency. Therefore, the necessity of developing modern cleaning systems is a crucial task. Various types of cleaning systems have been proposed in the literature, such as electrostatic, ultrasonic, and robotic systems. However, the best methods are the ones guarantee as much efficiency as possible at the lowest cost. In this work, we propose a simple automatic system based on a rotating brush. The system is composed of two parts linked together by Bluetooth modules. The first one is a dust sensor, its main task is to send a signal to the second part, which is the cleaner, in case of detecting dirt or sand. The feasibility of the proposed prototype has been experimentally demonstrated. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cleaner production

来源：评论

学校读者我要写书评

暂无评论

Toward AI-Driven Cough Sound Analysis for Respiratory Disease Diagnosis

引用

IEEE Access 2025年 13卷 92554-92568页

作者： Houda Benaliouche Houda Hafi Hakim Bendjenna Zeyad Alshaikh Faculty of New Information and Communication Technologies Abdelhamid Mehri Constantine 2 University Constantine Algeria Laboratory of Mathematics Informatics and Systems (LAMIS) Tebessa Algeria Department of Computer Science College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh Saudi Arabia

Respiratory diseases represent a significant health concern that attracts scientists and health professionals due to their impact on public health. Various techniques are used to identify respiratory conditions, from diagnosis to therapy, such as computer Tomography (CT) scans and Chest X-ray (CXR) images. However, these methods require expert radiologists for manual examination, posing time challenges. This is especially critical during a pandemic, where swift detection and early treatment are paramount. In this regard, an AI-based diagnostic system for automatic identification would play a major role, particularly regarding the analysis of patient cough patterns. Coughs, as a diagnostic cue, provide distinctive information about glottis behavior related to different respiratory pathological cases. This work proposes a comparative investigation of respiratory disease detection techniques using cough sounds, with COVID-19 as a case study. Our study involves the application of three distinct models: a Convolutional Neural Network (CNN) model, a CNN-Support Vector Machine (CNN-SVM) hybrid model, and a transfer learning-based model. We methodically evaluate different model architectures, ranging from custom-built networks to pre-trained deep models, applying spectrogram or Mel-Frequency Cepstral Coefficients (MFCC) in transfer learning-based feature extraction, to determine which is the best approach in terms of accuracy, precision, recall, F1-score, and loss. The experimental findings highlight the superior performance of transfer learning and MFCC feature extraction upon deep learning results using CNN and CNN-SVM with best validation accuracies ranging from 99.55% to 100%. This significant advantage is attributed 1) the capacity of transfer learning to utilize prior knowledge from related domains, even in data-scarce target tasks, and 2) the proficiency of MFCC in capturing and representing the rich and essential information embedded within cough sounds. Furthermore

关键词： Pulmonary diseases COVID-19 Accuracy Feature extraction Transfer learning Support vector machines Mel frequency cepstral coefficient Convolutional neural networks Pandemics Spectrogram

来源：评论

学校读者我要写书评

暂无评论

Leveraging Generalizability of Image-to-Image Translation for Enhanced Adversarial Defense

arXiv

引用

arXiv 2025年

作者： Zhang, Haibo Yao, Zhihua Sakurai, Kouichi Saitoh, Takeshi Department of Artificial Intelligence Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Japan Faculty of Economics and Business Administration The University of Kitakyushu Japan Department of Informatics Faculty of Information Science and Electrical Engineering Kyushu University Japan

In the rapidly evolving field of artificial intelligence, machine learning emerges as a key technology characterized by its vast potential and inherent risks. The stability and reliability of these models are important, as they are frequent targets of security threats. Adversarial attacks, first rigorously defined by Ian Goodfellow et al. in 2013, highlight a critical vulnerability: they can trick machine learning models into making incorrect predictions by applying nearly invisible perturbations to images. Although many studies have focused on constructing sophisticated defensive mechanisms to mitigate such attacks, they often overlook the substantial time and computational costs of training and maintaining these models. Ideally, a defense method should be able to generalize across various, even unseen, adversarial attacks with minimal overhead. Building on our previous work on image-to-image translation-based defenses, this study introduces an improved model that incorporates residual blocks to enhance generalizability. The proposed method requires training only a single model, effectively defends against diverse attack types, and is well-transferable between different target models. Experiments show that our model can restore the classification accuracy from near zero to an average of 72% while maintaining competitive performance compared to state-of-the-art methods. Significantly, our model operates more efficiently, reducing the time needed to process individual images and speeding up the training process to achieve faster convergence. Robustness tests further confirm stable performance under varying attack strengths, demonstrating the model’s practical value in real-world adversarial settings. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Deep gradient reinforcement learning for music improvisation in cloud computing framework

引用

PeerJ computer science 2025年 11卷 e2265-e2265页

作者： Alrowais, Fadwa Arasi, Munya A. Alotaibi, Saud S. Alonazi, Mohammed Marzouk, Radwa Salama, Ahmed S. Department of Computer Sciences College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh Saudi Arabia Department of Computer Science Applied College King Khalid University RijalAlmaa Saudi Arabia Department of Computer Science and Artificial Intelligence College of Computing Umm Al-Qura University Mecca Saudi Arabia Department of Information Systems College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh Saudi Arabia Department of Electrical Engineering Faculty of Engineering & Technology Future University in Egypt New Cairo New Cairo Egypt

Artificial intelligence (AI) in music improvisation offers promising new avenues for developing human creativity. The difficulty of writing dynamic, flexible musical compositions in real time is discussed in this article. We explore using reinforcement learning (RL) techniques to create more interactive and responsive music creation systems. Here, the musical structures train an RL agent to navigate the complex space of musical possibilities to provide improvisations. The melodic framework in the input musical data is initially identified using bi-directional gated recurrent units. The lyrical concepts such as notes, chords, and rhythms from the recognised framework are transformed into a format suitable for RL input. The deep gradient-based reinforcement learning technique used in this research formulates a reward system that directs the agent to compose aesthetically intriguing and harmonically cohesive musical improvisations. The improvised music is further rendered in the MIDI format. The Bach Chorales dataset with six different attributes relevant to musical compositions is employed in implementing the present research. The model was set up in a containerised cloud environment and controlled for smooth load distribution. Five different parameters, such as pitch frequency (PF), standard pitch delay (SPD), average distance between peaks (ADP), note duration gradient (NDG) and pitch class gradient (PCG), are leveraged to assess the quality of the improvised music. The proposed model obtains +0.15 of PF, -0.43 of SPD, -0.07 of ADP and 0.0041 NDG, which is a better value than other improvisation methods. © 2025 Alrowais et al.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Attackers Can Do Better: Over- and Understated Factors of Model Stealing Attacks

arXiv

引用

arXiv 2025年

作者： Oliynyk, Daryna Mayer, Rudolf Rauber, Andreas CDL AsTra Faculty of Computer Science University of Vienna Vienna Austria SBA Research Vienna Austria Institute of Information Systems Engineering Faculty of Informatics TU Wien Vienna Austria

Machine learning (ML) models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other attack methods, substitute model training is an all-encompassing attack applicable to any machine learning model whose behaviour can be approximated from input-output queries. Whereas previous works mainly focused on improving the performance of substitute models by, e.g. developing a new substitute training method, there have been only limited ablation studies that try to understand the impact the strength of an attacker has on the substitute model’s performance. As a result, different authors came to diverse, sometimes contradicting, conclusions. In this work, we exhaustively examine the ambivalent influence of different factors resulting from varying the attacker’s capabilities and knowledge on a substitute training attack. Our findings suggest that some of the factors that have been considered important in the past are, in fact, not that influential;instead, we discover new correlations between attack conditions and success rate. In particular, we demonstrate that better-performing target models enable higher-fidelity attacks and explain the intuition behind this phenomenon. Further, we propose to shift the focus from the complexity of target models toward the complexity of their learning tasks. Therefore, for the substitute model, rather than aiming for a higher architecture complexity, we suggest focusing on getting data of higher complexity and an appropriate architecture. Finally, we demonstrate that even in the most limited data-free scenario, there is no need to overcompensate weak knowledge with unrealistic capabilities in the form of millions of queries. Our results often exceed or match the performance of previous attacks that assume a stronger attacker, suggesting that these stronger attacks are likely endangering a model owner’s intellectual property to a significantly higher degree than shown until now. Cop

关键词： Adversarial machine 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：