检索结果-内蒙古大学图书馆

Automatic Detection of Outliers in Multi-Channel EMG Signals Using MFCC and SVM

Intelligent Automation & Soft Computing 2023年第4期36卷 169-181页

作者： Muhammad Irfan Khalil Ullah Fazal Muhammad Salman Khan Faisal Althobiani Muhammad Usman Mohammed Alshareef Shadi Alghaffari Saifur Rahman Electrical Engineering Department College of EngineeringNajran University Saudi ArabiaNajran61441Saudi Arabia Department of Software Engineering University of MalakandDir LowerPakistan Department of Electrical Engineering University of Engineering and TechnologyMardan23200Pakistan Faculty of Maritime Studies King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science University of Engineering and TechnologyMardan23200Pakistan

The automatic detection of noisy channels in surface Electromyogram(sEMG)signals,at the time of recording,is very critical in making a noise-free EMG *** an EMG signal contaminated by high-level noise is recorded,then it will be useless and can’t be used for any healthcare *** this research work,a new machine learning-based paradigm is proposed to automate the detection of low-level and high-level noises occurring in different channels of high density and multi-channel sEMG signals.A modiﬁed version of mel fre-quency cepstral coefﬁcients(mMFCC)is proposed for the extraction of features from sEMG channels along with other statistical parameters i-e complexity coef-ﬁcient,hurst exponent,and root mean *** state-of-the-art classiﬁers such as Support Vector Machine(SVM),Ensemble Bagged Trees,Ensemble Sub-space Discriminant,and Logistic Regression are used to automatically identify an EMG channel either bad or good based on these extracted ***-based analyses of these classiﬁers have also been considered based on total classi-ﬁcation accuracy,prediction speed(observations/sec),and processing *** proposed method is tested on 320 simulated EMG channels as well as 640 experi-mental EMG *** is used as our main classiﬁer for the detection of noisy channels which gives a total classiﬁcation accuracy of 99.4%for simulated EMG channels whereas accuracy of 98.9%is achieved for experimental EMG channels.

关键词： Machine learning surface electromyography support vector machine classiﬁcation features

来源：评论

学校读者我要写书评

暂无评论

Handwritten Prescription Recognition Using VGG Based Architecture with Bi-LSTM

Handwritten Prescription Recognition Using VGG Based Archite...

引用

2024 International Research Conference on Smart Computing and Systems engineering, SCSE 2024

作者： Kavinda, Isuru Fernando, Harinda Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer System Engineering Malabe Sri Lanka

ISBN: (纸本)9798350375688

Illegible handwriting on medical prescriptions poses a significant challenge, often leading to the misinterpretation of drug names and dosages. This issue primarily stems from doctors' use of Latin abbreviations, driven by time constraints during patient consultations. The resultant discrepancies in prescription interpretation can potentially expose patients to incorrect medications and dosages, leading to adverse effects. In response to this concern, this study proposes a novel system integrating Convolution Neural Network (CNN) and Recurrent Neural Network (RNN) models. Promising findings are reported in this study, achieving a loss of 0.4874 and an accuracy of 0.83 in the latest trial. The final model offers a potential solution to the persistent problem of illegible prescriptions, enhancing patient safety in the healthcare domain. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Use of Large Language Models for Medical Synthetic Data Generation in Mental Illness 7

Use of Large Language Models for Medical Synthetic Data Gene...

引用

7th IET Smart Cities Symposium, SCS 2023

作者： Aygün, İrfan Kaya, Mehmet Department of Software Engineering Celal Bayar University Manisa Turkey Department of Computer Engineering Fırat University Elazığ Turkey

ISBN: (纸本)9781839539831

Data quantity and quality are very important for the development of medical artificial intelligence research. Nowadays, thanks to easier access to data, studies in this field produce very successful results. However, many factors such as protection of patient rights in medical data and confidentiality of personal data prevent researchers from directly accessing the data. For this reason, synthetic data creation studies are often needed both to expand the training and test sets and to create sample cases to be used in the relevant field. In this study, various synthetic patient data are created to be presented to a language model that enables the detection of psychological disorders through patient text. Synthetic data sets were produced with 200 artificial patient data created with popular LLM examples ChatGPT and Google Bard. The quality of synthetic data was measured with the help of a pre-trained BERT model using these datasets. In the experiments, it was observed that chatbots that generate instant data, such as ChatGPT and Google Bard, produced successful results at rates of 89% and 86% with the language representation model. With the experimental results, it appears that LLM studies can provide more successful results than advanced language models in various medical text production tasks. © The Institution of engineering & Technology 2023.

关键词： Hospital data processing

来源：评论

学校读者我要写书评

暂无评论

Self-Adaptive Genetic Algorithm For Permutation Flow Shop Scheduling Problems 10

Self-Adaptive Genetic Algorithm For Permutation Flow Shop Sc...

引用

10th International Conference on Electrical and Electronics engineering, ICEEE 2023

作者： Çaliskan, Cihanser Erdogdu, Kazim Graduate School Yasar University Department of Computer Engineering Izmir Turkey Yasar University Department of Software Engineering Izmir Turkey

ISBN: (纸本)9798350304299

The permutation flow shop scheduling problem (PFSSP) is a well-known, extensively researched, and heavily applied non-polynomial (NP)-Hard combinatorial optimization problem. It is encountered in various real-life manufacturing problems such as automotive manufacturing, integrated circuit fabrication, and agricultural food industries. It continues to gain popularity in operational research areas as new manufacturing areas are developed. Therefore, finding a solution to these NP-Hard problems attract the attention of scientists. In this paper, we studied a PFSSP and proposed a new heuristic for its solution: The Self-Adaptive Genetic Algorithm (GA). This proposed algorithm uses a conventional GA with cycle crossover and random swap mutation. Its novelty, on the other hand, lies in incorporating an adaptive mechanism in the GA. The proposed algorithm uses three different local searches (i.e. 2-Opt, Greedy Insert, and Greedy Swap local searches) based on their successes. In other words, the proposed algorithm evaluates the performance of each local search at each generational iteration and makes a decision on which one to use based on their previous performances. The more successful local searches increase their probability of selection and vice versa. This way, Self-Adaptive GA, hence the name, adapts and directs its exploitation by the information it obtains in its previous generations. The proposed algorithm was applied to a subset of well-known Taillard problem instances. The experimental studies show its successful performance. Self-Adaptive GA obtained the optimum results for 7 out of 18 benchmark instances. In the rest of the 11 instances, the differences between the results of the proposed method and the optimum values are less than 2%. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Determining the Critical Factors of Antenatal Care Follow-Up Using Two-Phase Machine Learning 27

Determining the Critical Factors of Antenatal Care Follow-Up...

引用

27th International Conference on Soft Computing and Measurements, SCM 2024

作者： Bessmertny, Igor A. Enkomaryam, Bidru C. Mamuye, Adane L. Itmo University Faculty of Software Engineering and Computer Systems Saint Petersburg Russia University of Gondar Department of Computer Science Gondar Ethiopia

ISBN: (纸本)9798350363708

Determining the critical factors affecting antenatal visits will greatly contribute to reducing maternal and infant mortality. This study, thus attempted to construct a cluster-based predictive model to determine the critical factors of antenatal care follow-up among women in Ethiopia using two-step machine learning techniques. The 5,990 preprocessed obstetric dataset with 13 selected attributes were used that was collected from the Dabat Research Center at the University of Gondar, Ethiopia. To solve the study problem, six cluster models were developed using K-means, Expectation Maximization and Make Density clustering algorithms, which are well-suited for analyzing health datasets, providing scalability, flexibility, robustness to noise, and the ability to handle uneven cluster sizes. K-means out-formers Density based and Expectation Maximization clustering algorithms with minimum number of sum of square errors (17094) and number of iteration (3). Then, output of the K-means cluster model was used as input to segment the dataset and build a total of 21 predictive models using the tree-based J48 classifier, PART and JRip rule generators while adjusting their parameters. The model for predicting antenatal care follow-up is constructed by induction of the truncated PART rule (accuracy of 99.93%) and extracts attributes of interest such as antenatal care attendance, antenatal care location, antenatal care frequency, current vaccination, woman's age, and HIV testing to predict antenatal care follow-up in the study area. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating machine learning and statistical learning techniques for cancer classification and diagnosis

引用

Iran Journal of computer Science 2025年第2期8卷 471-490页

作者： Alwazy, Asmaa Salim Hussaien Buyrukoğlu, Gonca Buyrukoğlu, Selim Baker, Mohammed Rashad Department of Electronics and Computer Engineering Çankırı Karatekin University Çankırı 18100 Türkiye Department of Statistics Çankırı Karatekin University Çankırı 18100 Türkiye Department of Computer Engineering Çankırı Karatekin University Çankırı 18100 Türkiye Department of Software Engineering University of Kirkuk Kirkuk Iraq

Accurate cancer diagnosis is critical for effective treatment and positive patient outcomes. This study investigates the robustness of machine learning (ML) and statistical learning (SL) algorithms in classifying and diagnosing lung, prostate, breast, and heart disease. We evaluated and compared the performance of several algorithms, including support vector classifier (SVC), random forest (RF), XGBoost, decision tree (DT), elastic net, Lasso, and ridge, using four medical data sets. Multiple metrics, such as accuracy, precision, recall, F1-score, and area under the curve (AUC), are used to assess the performance. Hyperparameter tuning is conducted using GridSearchCV. The results demonstrated that RF and SVC achieved near-perfect accuracy (up to 98%) and AUC scores (1.00) in distinguishing between benign and malignant lung and breast cancer samples. SL algorithms exhibited robust and consistent performance for prostate cancer, achieving accuracy, precision, recall, and F1-scores of approximately 90%, making them suitable for data sets with smaller sample sizes. However, SVC-based ML algorithms outperformed SL methods in overall accuracy for prostate cancer, although SL methods provided a stable baseline. For heart disease, SVC achieved the highest accuracy (82%), while regularized SL models such as Elastic Net and Lasso performed similarly, with an accuracy of 80%. This study highlights the importance of selecting algorithms tailored to the data set’s characteristics and the specific diagnostic requirements. It also underscores the complementary strengths of ML and SL approaches, suggesting that an integrated strategy may offer the most effective solution. The findings contribute to the growing evidence supporting integrating computational methods into clinical practice to enhance diagnostic accuracy and improve patient care. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Cancer classification Data mining Diagnosis Machine learning algorithms Statistical learning algorithms

来源：评论

学校读者我要写书评

暂无评论

ViT Enhanced Privacy-Preserving Secure Medical Data Sharing and Classification 22

ViT Enhanced Privacy-Preserving Secure Medical Data Sharing ...

引用

22nd IEEE Consumer Communications and Networking Conference, CCNC 2025

作者： Amin, Al Hasan, Kamrul Ullah, Sharif Hossain, M. Shamim College of Engineering Tennessee State University Department of Electrical & Computer Engineering TN United States College of Science and Engineering University of Central Arkansas Department of Computer Science & Engineering ConwayAR United States College of Computer and Information Sciences King Saud University Department of Software Engineering Riyadh Saudi Arabia

ISBN: (纸本)9798331508050

Privacy-preserving and secure data sharing are critical for medical image analysis while maintaining accuracy and minimizing computational overhead are also crucial. Applying existing deep neural networks (DNNs) to encrypted medical data is not always easy and often compromises performance and security. To address these limitations, this research introduces a secure framework consisting of a learnable encryption method based on block-pixel operation to encrypt the data and subsequently integrate it with the Vision Transformer (ViT). The proposed framework ensures data privacy and security by creating unique scrambling patterns per key, providing robust performance against leading bit attacks and minimum difference attacks. © 2025 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Injections Attacks Efficient and Secure Techniques Based on Bidirectional Long Short Time Memory Model

引用

computers, Materials & Continua 2023年第9期76卷 3605-3622页

作者： Abdulgbar A.R.Farea Gehad Abdullah Amran Ebraheem Farea Amerah Alabrah Ahmed A.Abdulraheem Muhammad Mursil Mohammed A.A.Al-qaness School of Big Data&Software Engineering Chongqing UniversityChongqing401331China Department of Management Science Engineering Dalian University of TechnologyDalian116024China Software College Northeastern UniversityShenyang110169China Department of Information Systems College of Computer and Information ScienceKing Saud UniversityRiyadh11543Saudi Arabia Department of Management Science and Engineering South China University of TechnologyGuangzhou510641China Department of Computer Engineering and Mathematics University of Rovira i VirgiliTarragonaSpain College of Physics and Electronic Information Engineering Zhejiang Normal UniversityJinhua321004China

E-commerce,online ticketing,online banking,and other web-based applications that handle sensitive data,such as passwords,payment information,and financial information,are widely *** web developers may have varying levels of understanding when it comes to securing an online *** Query language SQL injection and cross-site scripting are the two vulnerabilities defined by the OpenWeb Application Security Project(OWASP)for its 2017 Top Ten List Cross Site Scripting(XSS).An attacker can exploit these two flaws and launch malicious web-based actions as a result of these *** published articles focused on these attacks’binary *** article described a novel deep-learning approach for detecting SQL injection and XSS *** datasets for SQL injection and XSS payloads are combined into a single *** dataset is labeledmanually into three labels,each representing a kind of *** work implements some pre-processing algorithms,including Porter stemming,one-hot encoding,and the word-embedding method to convert a word’s text into a *** model used bidirectional long short-term memory(BiLSTM)to extract features automatically,train,and test the payload *** payloads were classified into three types by BiLSTM:XSS,SQL injection attacks,and *** outcomes demonstrated excellent performance in classifying payloads into XSS attacks,injection attacks,and non-malicious ***’s high performance was demonstrated by its accuracy of 99.26%.

关键词： Web security SQL injection XSS deep learning RNN LSTM BiLSTM

来源：评论

学校读者我要写书评

暂无评论

Internet of Things (IoT): survey of most important security risks 3

Internet of Things (IoT): survey of most important security ...

引用

3rd IEEE International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and computer engineering, MI-STA 2023

作者： Alaskri, Ahmed Salem Ahmed, Nuredin Ali Shaari, Hala Collage of Computer Technology Software Engineering Dep. Tripoli Libya Faculty of Engineering Computer Engineering Department Tripoli Libya Faculty of Information Web Technologies Department Tripoli Libya

ISBN: (纸本)9798350319897

The Internet of things (IoT) is getting more and more intrusive into our lives until the day comes when everything becomes connected to the Internet. Due to the limited resources and heterogeneous Internet of Things (IoT) devices, the traditional means of protection are useless and cannot be used to protect these devices. The most important security risks, their causes and the consequences of their occurrence have been listed, scheduled and categorized. The study concluded that there are real security risks that cannot be ignored, and they need to find innovative solutions to eliminate them or reduce their damage to a minimum. This paper showed the main risks addressed in previews research, and outlined the gaps in this field of technology, also producing a brief summary information about the most important solution to avoid many threats against the IoT field. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Leveraging Transfer Learning for Spatio-Temporal Human Activity Recognition from Video Sequences

引用

computers, Materials & Continua 2023年第3期74卷 5017-5033页

作者： Umair Muneer Butt Hadiqa Aman Ullah Sukumar Letchmunan Iqra Tariq Fadratul Hafinaz Hassan Tieng Wei Koh School of Computer Sciences Universiti Sains MalaysiaPenang1180Malaysia Department of Computer Science The University of ChenabGujrat50700Pakistan Department of Software Engineering and Information System Universiti Putra MalaysiaSelangor43400Malaysia

Human Activity Recognition(HAR)is an active research area due to its applications in pervasive computing,human-computer interaction,artificial intelligence,health care,and social ***,dynamic environments and anthropometric differences between individuals make it harder to recognize *** study focused on human activity in video sequences acquired with an RGB camera because of its vast range of real-world *** uses two-stream ConvNet to extract spatial and temporal information and proposes a fine-tuned deep neural ***,the transfer learning paradigm is adopted to extract varied and fixed frames while reusing object identification *** state-of-the-art pre-trained models are exploited to find the best model for spatial feature *** temporal sequence,this study uses dense optical flow following the two-stream ConvNet and Bidirectional Long Short TermMemory(BiLSTM)to capture *** state-of-the-art datasets,UCF101 and HMDB51,are used for evaluation *** addition,seven state-of-the-art optimizers are used to fine-tune the proposed network ***,this study utilizes an ensemble mechanism to aggregate spatial-temporal features using a four-stream Convolutional Neural Network(CNN),where two streams use RGB *** contrast,the other uses optical flow ***,the proposed ensemble approach using max hard voting outperforms state-ofthe-art methods with 96.30%and 90.07%accuracies on the UCF101 and HMDB51 datasets.

关键词： Human activity recognition deep learning transfer learning neural network ensemble learning spatio-temporal

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：