Optimizing Deep Learning for Computer-Aided Diagnosis of Lung Diseases: An Automated Method Combining Evolutionary Algorithm, Transfer Learning, and Model Compression

Recent developments in Computer Vision have presented novel opportunities to tackle complex healthcare issues,particularly in the field of lung disease diagnosis.One promising avenue involves the use of chest X-Rays,which are commonly utilized in radiology.To fully exploit their potential,researchers have suggested utilizing deep learning methods to construct computer-aided diagnostic systems.However,constructing and compressing these systems presents a significant challenge,as it relies heavily on the expertise of data scientists.To tackle this issue,we propose an automated approach that utilizes an evolutionary algorithm(EA)to optimize the design and compression of a convolutional neural network(CNN)for X-Ray image classification.Our approach accurately classifies radiography images and detects potential chest abnormalities and infections,including COVID-19.Furthermore,our approach incorporates transfer learning,where a pre-trainedCNNmodel on a vast dataset of chest X-Ray images is fine-tuned for the specific task of detecting COVID-19.This method can help reduce the amount of labeled data required for the task and enhance the overall performance of the model.We have validated our method via a series of experiments against state-of-the-art architectures.

Lecturers’Efforts in Building Rapport in the English-Medium Instruction(EMI)Context:Focus on the Use of Communication Strategies

Past studies reveal the prevalence of anxiety,coupled with low motivation and disengagement among students in English-medium instruction(EMI)programs.Given the detrimental impact these negative emotions can have on learning outcomes,it is imperative that teachers establish positive emotional rapport with their students.This study explores how experienced and highly rated EMI lecturers at a Chinese university’s overseas campus use communication strategies to build rapport with their students during interactive academic activities.It identifies the strategies used by these lecturers and examines how the strategies facilitate the teaching-learning process.The data,consisting of 10 hours of tutorials and 10 hours of supervisor-student supervision meetings,is analyzed using an adapted Conversation Analysis(CA)approach.The analysis reveals three types of communication strategies(CSs)frequently used by lecturers:back-channeling,codeswitching,and co-creation of messages.By employing these strategies,the lecturers established a strong rapport with the students,which created an encouraging and supportive learning environment.Consequently,this positive atmosphere facilitated students’learning of content knowledge through English.The findings of this study have implications for the training of lecturers who encounter difficulties in establishing rapport with multilingual students in the EMI setting.

An Assessment of English Instruction for Elementary-Level Students in Jeddah Governorate, as Perceived by English Supervisors and Educators

This study investigated the perceptions of English educators and supervisors in Jeddah Governorate regarding the process of teaching English to elementary students.A survey was conducted using a sample size of 94 educators and 10 supervisors.The data indicate that respondents considered English instruction at the elementary level essential for expanding kids’perspectives,improving academic performance,and promoting international involvement.The main advantages cited are the development of English language skills and the promotion of early education.Although not as easily noticeable,the disadvantages include potential negative impacts on an individual’s proficiency in Arabic and their sense of national identification.The highlighted challenges encompass insufficient teacher training,student reluctance towards English,limited resources,and school disparities.The proposed techniques focused on prioritizing English instructors’training,ensuring the use of appropriate content,utilizing technology,and promoting awareness of students and educators.The current research found different obstacles in teaching English at elementary stages.To overcome these obstacles,it will be essential to enhance teacher competencies,develop efficient teaching methods,get the backing of stakeholders,assign adequate resources,and carry out continuous evaluations.Further research can also contribute to a better understanding of how early English learning impacts on Arabic identity and proficiency.

A Survey Study of Kindergarten Teachers’Use of ChatGPT to Support Instructional Design

With the rapid development of information technology,Artificial Intelligence(AI)is gradually applied to a wide range of fields,especially the powerful ability of ChatGPT to bring infinite possibilities for education,but teachers’attitudes toward using it are not yet clear.The study investigates the use of ChatGPT by kindergarten teachers to support instructional design using questionnaires and interviews to explore the attitudes and perceptions of kindergarten teachers toward its use.The results indicate that kindergarten teachers hold positive preferences for technology acceptance,perceived self-efficacy,and learning attitudes toward using ChatGPT for instructional design.Meanwhile,the study argues that more research is needed in the future to focus on how kindergarten teachers can aptly use ChatGPT to improve the quality of instruction in realistic instructionenvironments.

Exploring Pedagogical Ideologies and Strategies for College English Writing Instruction from a Generative Artificial Intelligence Perspective

This study,drawing on the commonalities between generative artificial intelligence and foreign language writing instruction,outlines the core ideology of digital humanities-based college English writing instruction,including auxiliary use of generative artificial intelligence tools,primary focus on humanistic education,and the re-production of knowledge,aiming to foster students’critical thinking,collaborative skills,and creativity.Building on this foundation,the study delves into generative artificial intelligence tools applicable to different stages of process-genre writing and their strategic applications.The use of generative artificial intelligence tools is beneficial for students to present,discuss,and share writing content,encouraging them to enhance their writing,collaboration,critical thinking,and creative abilities through deep interaction with model essays and creative discourses.

“Instruction-Category” Approach of Test Suite Construction for Oven Embedded System

Being different from testing for popular GUI software, the “instruction-category” approach is proposed for testing embedded system. This approach is constructed by three steps including refining items, drawing instruction-brief and instruction-category, and constructing test suite. Consequently, this approach is adopted to test oven embedded system, and detail process is deeply discussed. As a result, the factual result indicates that the “instruction-category” approach can be effectively applied in embedded system testing as a black-box method for conformity testing.

Computer-Aided Diagnosis Model Using Machine Learning for Brain Tumor Detection and Classification

The Brain Tumor(BT)is created by an uncontrollable rise of anomalous cells in brain tissue,and it consists of 2 types of cancers they are malignant and benign tumors.The benevolent BT does not affect the neighbouring healthy and normal tissue;however,the malignant could affect the adjacent brain tissues,which results in death.Initial recognition of BT is highly significant to protecting the patient’s life.Generally,the BT can be identified through the magnetic resonance imaging(MRI)scanning technique.But the radiotherapists are not offering effective tumor segmentation in MRI images because of the position and unequal shape of the tumor in the brain.Recently,ML has prevailed against standard image processing techniques.Several studies denote the superiority of machine learning(ML)techniques over standard techniques.Therefore,this study develops novel brain tumor detection and classification model using met heuristic optimization with machine learning(BTDC-MOML)model.To accomplish the detection of brain tumor effectively,a Computer-Aided Design(CAD)model using Machine Learning(ML)technique is proposed in this research manuscript.Initially,the input image pre-processing is performed using Gaborfiltering(GF)based noise removal,contrast enhancement,and skull stripping.Next,mayfly optimization with the Kapur’s thresholding based segmentation process takes place.For feature extraction proposes,local diagonal extreme patterns(LDEP)are exploited.At last,the Extreme Gradient Boosting(XGBoost)model can be used for the BT classification process.The accuracy analysis is performed in terms of Learning accuracy,and the validation accuracy is performed to determine the efficiency of the proposed research work.The experimental validation of the proposed model demonstrates its promising performance over other existing methods.

Computer-Aided Diagnosis for Tuberculosis Classification with Water Strider Optimization Algorithm

Computer-aided diagnosis(CAD)models exploit artificial intelligence(AI)for chest X-ray(CXR)examination to identify the presence of tuberculosis(TB)and can improve the feasibility and performance of CXR for TB screening and triage.At the same time,CXR interpretation is a time-consuming and subjective process.Furthermore,high resemblance among the radiological patterns of TB and other lung diseases can result in misdiagnosis.Therefore,computer-aided diagnosis(CAD)models using machine learning(ML)and deep learning(DL)can be designed for screening TB accurately.With this motivation,this article develops a Water Strider Optimization with Deep Transfer Learning Enabled Tuberculosis Classification(WSODTL-TBC)model on Chest X-rays(CXR).The presented WSODTL-TBC model aims to detect and classify TB on CXR images.Primarily,the WSODTL-TBC model undergoes image filtering techniques to discard the noise content and U-Net-based image segmentation.Besides,a pre-trained residual network with a two-dimensional convolutional neural network(2D-CNN)model is applied to extract feature vectors.In addition,the WSO algorithm with long short-term memory(LSTM)model was employed for identifying and classifying TB,where the WSO algorithm is applied as a hyperparameter optimizer of the LSTM methodology,showing the novelty of the work.The performance validation of the presented WSODTL-TBC model is carried out on the benchmark dataset,and the outcomes were investigated in many aspects.The experimental development pointed out the betterment of the WSODTL-TBC model over existing algorithms.

Effect of a low-cost instruction card for automated external defibrillator operation in lay rescuers: a randomized simulation study

BACKGROUND:To evaluate whether a simplified self-instruction card can help potential rescue providers use automated external defibrillators(AEDs)more accurately and quickly.METHODS:From June 1,2018,to November 30,2019,a prospective longitudinal randomized controlled simulation study was conducted among 165 laypeople(18–65 years old)without prior AED training.A self-instruction card was designed to illuminate key AED operation procedures.Subjects were randomly divided into the card(n=83)and control(n=82)groups with age stratification.They were then individually evaluated in the same simulated scenario to use AED with(card group)or without the self-instruction card(control group)at baseline,posttraining,and at the 3-month follow-up.RESULTS:At baseline,the card group reached a significantly higher proportion of successful defibrillation(31.1%vs.15.9%,P=0.03),fully baring the chest(88.9%vs.63.4%,P<0.001),correct electrode placement(32.5%vs.17.1%,P=0.03),and resuming cardiopulmonary resuscitation(CPR)(72.3%vs.9.8%,P<0.001).At post-training and follow-up,there were no significant differences in key behaviors,except for resuming CPR.Time to shock and time to resume CPR were shorter in the card group,while time to power-on AED was not different in each phase of tests.In the 55–65 years group,the card group achieved more skill improvements over the control group compared to the other age groups.CONCLUSION:The self-instruction card could serve as a direction for first-time AED users and as a reminder for trained subjects.This could be a practical,cost-effective way to improve the AED skills of potential rescue providers among different age groups,including seniors.

Novel Computer-Aided Diagnosis System for the Early Detection of Alzheimer’s Disease

Aging is a natural process that leads to debility,disease,and dependency.Alzheimer’s disease(AD)causes degeneration of the brain cells leading to cognitive decline and memory loss,as well as dependence on others to fulfill basic daily needs.AD is the major cause of dementia.Computer-aided diagnosis(CADx)tools aid medical practitioners in accurately identifying diseases such as AD in patients.This study aimed to develop a CADx tool for the early detection of AD using the Intelligent Water Drop(IWD)algorithm and the Random Forest(RF)classifier.The IWD algorithm an efficient feature selection method,was used to identify the most deterministic features of AD in the dataset.RF is an ensemble method that leverages multiple weak learners to classify a patient’s disease as either demented(DN)or cognitively normal(CN).The proposed tool also classifies patients as mild cognitive impairment(MCI)or CN.The dataset on which the performance of the proposed CADx was evaluated was sourced from the Alzheimer’s Disease Neuroimaging Initiative(ADNI).The RF ensemble method achieves 100%accuracy in identifying DN patients from CN patients.The classification accuracy for classifying patients as MCI or CN is 92%.This study emphasizes the significance of pre-processing prior to classification to improve the classification results of the proposed CADx tool.

Pre-Trained Deep Neural Network-Based Computer-Aided Breast Tumor Diagnosis Using ROI Structures

Deep neural network(DNN)based computer-aided breast tumor diagnosis(CABTD)method plays a vital role in the early detection and diagnosis of breast tumors.However,a Brightness mode(B-mode)ultrasound image derives training feature samples that make closer isolation toward the infection part.Hence,it is expensive due to a metaheuristic search of features occupying the global region of interest(ROI)structures of input images.Thus,it may lead to the high computational complexity of the pre-trained DNN-based CABTD method.This paper proposes a novel ensemble pretrained DNN-based CABTD method using global-and local-ROI-structures of B-mode ultrasound images.It conveys the additional consideration of a local-ROI-structures for further enhan-cing the pretrained DNN-based CABTD method’s breast tumor diagnostic performance without degrading its visual quality.The features are extracted at various depths(18,50,and 101)from the global and local ROI structures and feed to support vector machine for better classification.From the experimental results,it has been observed that the combined local and global ROI structure of small depth residual network ResNet18(0.8 in%)has produced significant improve-ment in pixel ratio as compared to ResNet50(0.5 in%)and ResNet101(0.3 in%),respectively.Subsequently,the pretrained DNN-based CABTD methods have been tested by influencing local and global ROI structures to diagnose two specific breast tumors(Benign and Malignant)and improve the diagnostic accuracy(86%)compared to Dense Net,Alex Net,VGG Net,and Google Net.Moreover,it reduces the computational complexity due to the small depth residual network ResNet18,respectively.

Framework for a Computer-Aided Treatment Prediction (CATP) System for Breast Cancer

This study offers a framework for a breast cancer computer-aided treat-ment prediction(CATP)system.The rising death rate among women due to breast cancer is a worldwide health concern that can only be addressed by early diagno-sis and frequent screening.Mammography has been the most utilized breast ima-ging technique to date.Radiologists have begun to use computer-aided detection and diagnosis(CAD)systems to improve the accuracy of breast cancer diagnosis by minimizing human errors.Despite the progress of artificial intelligence(AI)in the medical field,this study indicates that systems that can anticipate a treatment plan once a patient has been diagnosed with cancer are few and not widely used.Having such a system will assist clinicians in determining the optimal treatment plan and avoid exposing a patient to unnecessary hazardous treatment that wastes a significant amount of money.To develop the prediction model,data from 336,525 patients from the SEER dataset were split into training(80%),and testing(20%)sets.Decision Trees,Random Forest,XGBoost,and CatBoost are utilized with feature importance to build the treatment prediction model.The best overall Area Under the Curve(AUC)achieved was 0.91 using Random Forest on the SEER dataset.

Effect of Specific Verbal Instructions on the Identification of Pain Location during a Passive Straight Leg Raise Test

Musculoskeletal pain is common. Because pain is subjective, objectively describing it is crucial. However, pain assessment may cause distress in patients;therefore, physical therapists (PTs) should conduct these tests quickly and accurately. Simple and clear instructions are recommended for pain assessment. However, few studies have provided evidence to support this hypothesis. Correspondingly, this study aimed to confirm the effectiveness of specific verbal instructions for pain location during five consecutive Passive Straight Leg Raise (PSLR) tests. The 28 asymptomatic participants (age 27.4 ± 9.6 years) who provided informed consent received five consecutive PSLR tests: three without and two with specific verbal instructions to ascertain pain intensity, quality, and location. The participants drew pain locations on a body chart and described the pain intensity and quality after each test. All participants were interviewed regarding the differences they noted in the presence and absence of specific verbal instructions. Each pain location was classified into one of ten areas for statistical analysis. The proportion of participants who changed the pain location was compared between the tests using McNemar’s test, and the kappa coefficient was confirmed for consistency of pain location. There was a significant difference in the proportion of participants who changed their pain location between the second and third tests and from the third to the fourth test (McNemar’s test: p = 0.003). Kappa coefficients had low consistency (κ = 0.28) just after receiving the specific verbal instructions in the fourth test compared to the third test. Consistency improved in the fifth test (κ = 0.57);93% of the participants answered that the pain location had become clearer. This study revealed the effects of specific verbal instructions in identifying pain locations. This detailed information may help PTs provide appropriate treatment and contribute to reducing pain in clinical settings.

An Integrated Image Task Planning in Satellite Networks:From Instruction Release and Observation Perspective

The unreasonable observation arrangements in the satellite operation control center(SOCC)may result in the observation data cannot be downloaded as scheduled.Meanwhile,if the operation instructions released by the satellite telemetry tracking center(STTC)for the on-board payloads are not injected on the specific satellites in time,the corresponding satellites cannot perform the observation operations as planned.Therefore,there is an urgent need to design an integrated instruction release,and observation task planning(I-IRO-TP)scheme by efficiently collaborating the SOCC and STTC.Motivated by this fact,we design an interaction mechanism between the SOCC and the STTC,where we first formulate the I-IRO-TP problem as a constraint satisfaction problem aiming at maximizing the number of completed tasks.Furthermore,we propose an interactive imaging task planning algorithm based on the analysis of resource distribution in the STTC during the previous planning periods to preferentially select the observation arcs that not only satisfy the requirements in the observation resource allocation phase but also facilitate the arrangement of measurement and control instruction release.We conduct extensive simulations to demonstrate the effectiveness of the proposed algorithm in terms of the number of completed tasks.

The Effectiveness of Explicit Vocabulary Instruction on Productive Vocabulary Learning in Writing Among Intermediate School Learners in Saudi Arabia

This study aimed to identify the effectiveness of explicit vocabulary instruction on productive vocabulary learning in writing among intermediate school learners in Saudi Arabia,verify the existence of any statistically significant differences at the significance level of 0.01 between the mean scores of the post-test of the control group and the experimental group in the vocabulary test,and verify the existence of any statistically significant differences at the significance level of 0.01 between the mean scores of the pre-and post-test of the experimental group in the vocabulary test in favor of the post-test.The study community consisted of all intermediate school students in the Kingdom of Saudi Arabia,while the study sample included 30 students.The experimental method was adopted to identify the effectiveness of explicit vocabulary instruction on productive vocabulary learning in writing and the achievement test was used as the study tool.The study reached many results including there were no statistically significant differences at the significance level of 0.01 between the mean scores of the post-test of the control group and the experimental group in the vocabulary test and there were no statistically significant differences at the significance level of 0.01 between the mean scores of the pre-and post-test of the experimental group in the vocabulary test in favor of the post-test.According to these results,some recommendations and proposals were made including training English teachers at the intermediate school level in the Kingdom of Saudi Arabia,on explicit vocabulary instruction and conducting future researches on the trends of English teachers at the intermediate school level,in the Kingdom of Saudi Arabia,regarding the adoption of explicit vocabulary instruction while teaching the English language.

The Reform Process of English Medium Instruction in Korean Higher Education

In the context of the internationalization of higher education,many non-English speaking countries,from Europe to Asia,are promoting English as a medium of instruction(EMI).The EMI in South Korea started earlier and developed rapidly under the promotion.From the initial“Study Abroad in Korea Plan”to the World Class University(WCU)and Brain Korea 21st century(BK21)PLUS programs,with the support and guidance of the government,South Korea’s higher education has made significant progress,with the global top 100 universities in QS increasing from 1 to 6 in South Korea.

A Study on the Instructional Design of Interdisciplinary Thematic Learning in Middle School Physical Education Based on the CASES-T Model

With the deepening of educational reform,interdisciplinary thematic learning,as an emerging educational model,has become a focus of attention in the field of educational research.Based on the STEM(science,technology,engineering,and mathematics)education concept and CASES-T(Content,Activity,Situation,Evaluation,Strategy-Target)model,this study provides a theoretical basis for the teaching design and implementation of interdisciplinary thematic learning in middle school physical education.Through the analysis of specific interdisciplinary thematic learning cases,it aims to provide theoretical support and practical guidance for the reform of middle school physical education through the CASES-T model-based interdisciplinary thematic teaching design research in middle school physical education,in order to enhance students’learning effects,cultivate core literacy in physical education,and promote students’all-round development.

Peer-Instruction—哈佛大学物理课程教学新方法

Peer—Instruction教学方法是哈佛大学著名教授Eric Mazur创立，使用专门设计的用于揭示学生错误概念和引导学生深入探究的概念测试题（Concep Tests），借助计算机投票系统（Computerized Voting System），组织大班课堂教学，变传统单一的讲授为基于问题的自主学习和协作探究，有效地改变了传统课堂教学手段、教学模式。在大班课堂教学中实现学生自主学习、合作学习、师生互动、生生互动。本文旨在介绍这种教学方法，阐明其教育意义和促进学生学习方面的作用，综述了PI教学方法的广泛应用和相关研究结果。

基于Peer Instruction教学方法研究大学生物理错误概念——以动生电动势为例

我们使用同伴教学法(Peer Instruction)讲授大学物理课程,分析学生在讨论概念测试题的过程中出现的各种错误表述,研究学生在动生电动势概念方面存在的错误概念.再基于研究得到的学生的错误概念开发多项选择题,对130名学习大学物理课程的学生进行测试,定量研究这些错误概念在他们中存在的普遍程度.研究表明:在动生电动势概念方面,大学生普遍存在一些错误概念.

The Effects of Schema Instruction on Reading Comprehension of English Argumentation

Based on the perspective of the schema theory and modern education technology,In this paper,the method of ran dom experimnet is used to measure how two types of schema instruction‘video clip’and‘multimedia courseware’influence Chinese college students’reading comprehension of English argumentation.The results illustrate the schema instruction can not only develop the students’sensibility of English argumentation structure,but also activate the schema in students’memory.Mul timedia courseware instruction is superior to video clip instruction.The paper proposes its viewpoints concerned.