MyMedR

Displaying publications 181 - 200 of 987 in total

Abstract:

Sort:

Encouraging learning how to fish: an uphill but worthwhile battle

Azila NM, Sim SM, Atiya AS

Ann Acad Med Singap, 2001 Jul;30(4):375-8.
PMID: 11503543

INTRODUCTION: Encouraging teaching practices such as problem-based learning (PBL) amongst undergraduate students within a lecture-based, system-based integrated curriculum is a challenge. Students are apprehensive about developing an organised framework for acquiring knowledge while lecturers are required to reframe their views on the educational process and their role as educators.
MATERIALS AND METHODS: Lecturers and students in the Phase (Year) II programme were asked to fill questionnaires following the second and fourth PBL cases. The two sets of survey responses were compared to see whether the students' and teachers' perceptions had changed over the 5-month period.
RESULTS: Students' responses from both surveys (1 and 2) were similar in that a majority agreed that the PBL tutorials had encouraged the seeking of information (66% and 67%, respectively), had improved understanding (57% and 56%), integration (65% and 70%) and application (50% and 64%) of knowledge. However, the views given in the form of written comments, following their positive responses, were somewhat contradictory. A large number of students (38% and 40%) faced difficulties in getting involved in discussions during the PBL tutorial and a majority (73% and 82%) preferred the normal subject-based tutorials. The reasons given by approximately 20% of the students were that the subject-based tutorials were more efficient for obtaining information and/or that the information had been pre-selected by the lecturers. More than 80% of the lecturers (in both surveys) perceived that the students had identified the appropriate learning objectives and covered the subject matter. The percentage of lecturers who agreed that PBL tutorials encouraged rapport and teamwork amongst students had increased in the second survey, from 70% to 92% and 55% to 83% respectively.
CONCLUSION: Implementing PBL is not simply a matter of developing new teaching materials and new effective ways of presenting them. It requires a paradigm shift, a change in the roles of students and teachers, and time.

Matched MeSH terms: Problem-Based Learning*
Fulltext Automated mold defects classification in paintings: A comparison of machine learning and rule-based techniques

Nordin H, Abdul Razak B, Mokhtar N, Jamaludin MF, Mehmood A

PLoS One, 2025;20(1):e0316996.
PMID: 39854603 DOI: 10.1371/journal.pone.0316996

Mold defects pose a significant risk to the preservation of valuable fine art paintings, typically arising from fungal growth in humid environments. This paper presents a novel approach for detecting and categorizing mold defects in fine art paintings. The technique leverages a feature extraction method called Derivative Level Thresholding to pinpoint suspicious regions within an image. Subsequently, these regions are classified as mold defects using either morphological filtering or machine learning models such as Classification and Regression Trees (CART) and Linear Discriminant Analysis (LDA). The efficacy of these methods was evaluated using the Mold Features Dataset (MFD) and a separate set of test images. Results indicate that both methods improve the accuracy and precision of mold defect detection compared to no classifier. However, the CART algorithm exhibits superior performance, increasing precision by 32% to 53% while maintaining high accuracy (96%) even with an imbalanced dataset. This innovative method has the potential to transform the approach to managing mold defects in fine art paintings by offering a more precise and efficient means of identification. By enabling early detection of mold defects, this method can play a crucial role in safeguarding these invaluable artworks for future generations.

Matched MeSH terms: Machine Learning*
Fulltext Incoming Work-In-Progress Prediction in Semiconductor Fabrication Foundry Using Long Short-Term Memory

Tin TC, Chiew KL, Phang SC, Sze SN, Tan PS

Comput Intell Neurosci, 2019;2019:8729367.
PMID: 30719036 DOI: 10.1155/2019/8729367

Preventive maintenance activities require a tool to be offline for long hour in order to perform the prescribed maintenance activities. Although preventive maintenance is crucial to ensure operational reliability and efficiency of the tool, long hour of preventive maintenance activities increases the cycle time of the semiconductor fabrication foundry (Fab). Therefore, this activity is usually performed when the incoming Work-in-Progress to the equipment is forecasted to be low. The current statistical forecasting approach has low accuracy because it lacks the ability to capture the time-dependent behavior of the Work-in-Progress. In this paper, we present a forecasting model that utilizes machine learning method to forecast the incoming Work-In-Progress. Specifically, our proposed model uses LSTM to forecast multistep ahead incoming Work-in-Progress prediction to an equipment group. The proposed model's prediction results were compared with the results of the current statistical forecasting method of the Fab. The experimental results demonstrated that the proposed model performed better than the statistical forecasting method in both hit rate and Pearson's correlation coefficient, r.

Matched MeSH terms: Machine Learning*
Fulltext A novel machine learning model for perimeter intrusion detection using intrusion image dataset

Pitafi S, Anwar T, Widia IDM, Sharif Z, Yimwadsana B

PLoS One, 2024;19(12):e0313890.
PMID: 39700114 DOI: 10.1371/journal.pone.0313890

Perimeter Intrusion Detection Systems (PIDS) are crucial for protecting any physical locations by detecting and responding to intrusions around its perimeter. Despite the availability of several PIDS, challenges remain in detection accuracy and precise activity classification. To address these challenges, a new machine learning model is developed. This model utilizes the pre-trained InceptionV3 for feature extraction on PID intrusion image dataset, followed by t-SNE for dimensionality reduction and subsequent clustering. When handling high-dimensional data, the existing Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm faces efficiency issues due to its complexity and varying densities. To overcome these limitations, this research enhances the traditional DBSCAN algorithm. In the enhanced DBSCAN, distances between minimal points are determined using an estimation for the epsilon values with the Manhattan distance formula. The effectiveness of the proposed model is evaluated by comparing it to state-of-the-art techniques found in the literature. The analysis reveals that the proposed model achieved a silhouette score of 0.86, while comparative techniques failed to produce similar results. This research contributes to societal security by improving location perimeter protection, and future researchers can utilize the developed model for human activity recognition from image datasets.

Matched MeSH terms: Machine Learning*
A novel classical machine learning framework for early sepsis prediction using electronic health record data from ICU patients

Prithula J, Islam KR, Kumar J, Tan TL, Reaz MBI, Rahman T, et al.

Comput Biol Med, 2025 Jan;184:109284.
PMID: 39579661 DOI: 10.1016/j.compbiomed.2024.109284

Sepsis, a life-threatening condition triggered by the body's response to infection, remains a significant global health challenge, annually affecting millions in the United States alone with substantial mortality and healthcare costs. Early prediction of sepsis is critical for timely intervention and improved patient outcomes. This study introduces an innovative predictive model leveraging machine learning techniques and a specific data-splitting approach on highly imbalanced electronic health records (EHRs). Using PhysioNet/CinC Challenge 2019 data from 40,336 patients, including vital signs, lab values, and demographics. Preliminary assessments using classical and stacked ML models with Synthetic Minority Oversampling Technique (SMOTE) augmentation were conducted, showing improved performance. It is found that stacking ML models enhances overall accuracy but faces limitations in precision, recall, and F1 score for positive class prediction. A novel data-splitting approach with 5-fold cross-validation and SMOTE and COPULA augmentation techniques demonstrated promise, with F1 scores ranging from 93 % to 94 % using the COPULA technique. COPULA excelled at predictions for different hours' onsets compared to the SMOTE technique. The proposed model outperformed existing studies, suggesting clinical viability for early sepsis prediction.

Matched MeSH terms: Machine Learning*
Fulltext Problem-based learning as perceived by dental students in universiti sains malaysia

Barman A, Jaafar R, Ismail NM

Malays J Med Sci, 2006 Jan;13(1):63-7.
PMID: 22589593

The implementation of problem-based learning started in 1969 and has spread since then throughout different parts of the world with variations in its implementation. In spite of its growth and advantages, there is continuing debate about its effectiveness over the conventional teaching learning methods. In the School of Dental Sciences (SDS), Universiti Sains Malaysia (USM), the Doctor of Dental Sciences (DDS) program follows a 5-year integrated curriculum. Basically the curriculum is problem-based and community oriented. This study was to explore the perception of DDS students about PBL sessions. This questionnaires-based cross sectional descriptive study were carried out on all the 110 students of the SDS who completed their second year of the course and participated in PBL sessions. Ninety five (86%) students responded to the questionnaires. Dental students found PBL session interesting and wanted to maintain PBL from the beginning of year 2 up to the end of year 3. Most students reported their participation in discussion during PBL sessions but the level of participation varied. Some of them worked hard to prepare themselves for discussion while others were relatively passive. PBL helped them with in-depth understanding of certain topics and link their basic science knowledge to clinical classes. They felt that guidance from subject specialists and well-prepared facilitators of the sessions were beneficial. The students believed that repetition of triggers from year to year discouraged their active search for learning issues. Majority of the students were undecided or disagreed about the availability of adequate learning resources Most of the students were undecided or disagreed about the availability of adequate learning resources for their self-study. Reviewing and renewing the PBL triggers, providing guidelines for searching for resource materials and briefing the students and facilitators about the philosophy and principles of PBL may make the PBL sessions more beneficial.

Matched MeSH terms: Learning; Problem-Based Learning
Fulltext Effectiveness of Team-Based Learning in teaching Medical Genetics to Medical Undergraduates

Ismail NA

Malays J Med Sci, 2016 Mar;23(2):73-7.
PMID: 27547118 MyJurnal

This study explores the experience of both learners and a teacher during a team-based learning (TBL) session. TBL involves active learning that allows medical students to utilise their visual, auditory, writing and kinetic learning styles in order to strengthen their knowledge and retain it for longer, which is important with regard to applying basic sciences in clinical settings. This pilot study explored the effectiveness of TBL in learning medical genetics, and its potential to replace conventional lectures. First-year medical students (n = 194) studying at Universiti Kebangsaan, Malaysia, during 2014/2015 were selected to participate in this study. The topic of 'Mutation and Mutation Analysis' was selected, and the principles of TBL were adhered to during the study. It was found that the students' performance in a group readiness test was better than in individual readiness tests. The effectiveness of TBL was further shown in the examination, during which the marks obtained were tremendously improved. Collective commentaries from both the learners and the teacher recommended TBL as another useful tool in learning medical genetics. Implementation strategies should be advanced for the benefit of future learners and teachers.

Matched MeSH terms: Learning; Problem-Based Learning
Environmental enrichment improves cognitive function, learning, memory and anxiety-related behaviours in rodent models of dementia: Implications for future study

Mohd Sahini SN, Mohd Nor Hazalin NA, Srikumar BN, Jayasingh Chellammal HS, Surindar Singh GK

Neurobiol Learn Mem, 2024 Feb;208:107880.
PMID: 38103676 DOI: 10.1016/j.nlm.2023.107880

Environmental enrichment (EE) is a process of brain stimulation by modifying the surroundings, for example, by changing the sensory, social, or physical conditions. Rodents have been used in such experimental strategies through exposure to diverse physical, social, and exploration conditions. The present study conducted an extensive analysis of the existing literature surrounding the impact of EE on dementia rodent models. The review emphasised the two principal aspects that are very closely related to dementia: cognitive function (learning and memory) as well as psychological factors (anxiety-related behaviours such as phobias and unrealistic worries). Also highlighted were the mechanisms involved in the rodent models of dementia showing EE effects. Two search engines, PubMed and Science Direct, were used for data collection using the following keywords: environmental enrichment, dementia, rodent model, cognitive performance, and anxiety-related behaviour. Fifty-five articles were chosen depending on the criteria for inclusion and exclusion. The rodent models with dementia demonstrated improved learning and memory in the form of hampered inflammatory responses, enhanced neuronal plasticity, and sustained neuronal activity. EE housing also prevented memory impairment through the prevention of amyloid beta (Aβ) seeding formation, an early stage of Aβ plaque formation. The rodents subjected to EE were observed to present increased exploratory activity and exert less anxiety-related behaviour, compared to those in standard housing. However, some studies have proposed that EE intervention through exercise would be too mild to counteract the anxiety-related behaviour and risk assessment behaviour deficits in the Alzheimer's disease rodent model. Future studies should be conducted on old-aged rodents and the duration of EE exposure that would elicit the greatest benefits since the existing studies have been conducted on a range of ages and EE durations. In summary, EE had a considerable effect on dementia rodent models, with the most evident being improved cognitive function.

Matched MeSH terms: Maze Learning/physiology
Fulltext Knowledge building and vocabulary growth: Assessing the impact of seamless Chinese vocabulary learning for international students

Zhou X, Goh YS

PLoS One, 2025;20(2):e0319285.
PMID: 39992994 DOI: 10.1371/journal.pone.0319285

This study investigates the effectiveness of Seamless Chinese Vocabulary Learning (SCVL) among international students learning Chinese as a Foreign Language (CFL) to foster vocabulary knowledge building. A new theoretical framework of SCVL was introduced and validated to guide this exploration. The research involved 32 international students enrolled in a Chinese university. Data collection included Chinese Lexical Frequency Profile (LFP) were at HSK Level 4, a SCVL questionnaire, and semi-structured interviews. The findings indicate that SCVL significantly enhances students' HSK Level 4 vocabulary learning and retention across diverse performance groups over time, while also providing a positive and engaging learning experience. SCVL creates an authentic and repetition-enabled learning context, fostering higher levels of interaction and multi-modal, immediate, and learner-friendly scaffolding. Moreover, the study reveals that SCVL motivates students to actively participate in vocabulary acquisition, despite facing certain challenges. By incorporating the SCVL framework, language instructors can enhance their pedagogical practices and promote sustainable language learning outcomes. Future research is recommended to include a broader range of learners with diverse backgrounds and language proficiency levels, as well as to compare seamless learning with traditional learning approaches. Additionally, exploring CFL teachers' perceptions of SCVL would be valuable to further understand its impact on language instruction.

Matched MeSH terms: Learning*
Fulltext Latest clinical frontiers related to autism diagnostic strategies

Cortese S, Bellato A, Gabellone A, Marzulli L, Matera E, Parlatini V, et al.

Cell Rep Med, 2025 Feb 18;6(2):101916.
PMID: 39879991 DOI: 10.1016/j.xcrm.2024.101916

The diagnosis of autism is currently based on the developmental history, direct observation of behavior, and reported symptoms, supplemented by rating scales/interviews/structured observational evaluations-which is influenced by the clinician's knowledge and experience-with no established diagnostic biomarkers. A growing body of research has been conducted over the past decades to improve diagnostic accuracy. Here, we provide an overview of the current diagnostic assessment process as well as of recent and ongoing developments to support diagnosis in terms of genetic evaluation, telemedicine, digital technologies, use of machine learning/artificial intelligence, and research on candidate diagnostic biomarkers. Genetic testing can meaningfully contribute to the assessment process, but caution is required when interpreting negative results, and more work is needed to strengthen the transferability of genetic information into clinical practice. Digital diagnostic and machine-learning-based analyses are emerging as promising approaches, but larger and more robust studies are needed. To date, there are no available diagnostic biomarkers. Moving forward, international collaborations may help develop multimodal datasets to identify biomarkers, ensure reproducibility, and support clinical translation.

Matched MeSH terms: Machine Learning*
Fulltext Need analysis on developing Students' higher order thinking skills one-to-one Western classical instrumental music lessons in higher education

Pu J, Safian ARB, Nasrifan MNB, Saidon ZLB

Acta Psychol (Amst), 2025 Apr;254:104759.
PMID: 39933442 DOI: 10.1016/j.actpsy.2025.104759

One-to-one teaching remains significant in music teaching, however, this approach to Western Classical Instrumental Music (WCIM) teaching in higher education institutes prioritizes the technical aspect of music and tends to ignore its interpretive aspects and music institutions are often called to justify the need for such an expensive and resource-intensive approach to music education. The mastery of musical instruments requires a sensibility towards the music as well as a competency to interpret music, and manipulate the instruments. Therefore, there is a significant need to investigate the need for developing students' higher order thinking skills (HOTS) within this context. The present study adopts an exploratory sequential mixed approach to collect data by interviewing 15 teachers and surveying 538 students for Need Analysis in higher education. The findings revealed that teachers and students in one-to-one WCIM instruction have a strong Target Need for developing HOTS in Higher Education. Meanwhile, more practice on HOTS for students within the classroom is vital Route for Learning Needs, however, there is a challenge in stimulating different levels of students' motivation to explore independently. Furthermore, given the current obstacles faced by teachers, the present study implies the need for broader HOTS studies on WCIM teaching and learning, which will bring benefit to both students' lifelong learning and healthy development of WCIM education discipline. In addition, the study recommends the designing and developing of a more feasible framework for teachers as an urgent further study to improve the HOTS implementation.

Matched MeSH terms: Learning/physiology
Fulltext An efficient detection of Sinkhole attacks using machine learning: Impact on energy and security

Hasan MZ, Hanapi ZM, Zukarnain ZA, Huyop FH, Abdullah MDH

PLoS One, 2025;20(3):e0309532.
PMID: 40096085 DOI: 10.1371/journal.pone.0309532

In the realm of Wireless Sensor Networks (WSNs), the detection and mitigation of sinkhole attacks remain pivotal for ensuring network integrity and efficiency. This paper introduces SFlexCrypt, an innovative approach tailored to address these security challenges while optimizing energy consumption in WSNs. SFlexCrypt stands out by seamlessly integrating advanced machine learning algorithms to achieve high-precision detection and effective mitigation of sinkhole attacks. Employing a dataset from Contiki-Cooja, SFlexCrypt has been rigorously tested, demonstrating a detection accuracy of 100% and a mitigation rate of 97.31%. This remarkable performance not only bolsters network security but also significantly extends network longevity and reduces energy expenditure, crucial factors in the sustainability of WSNs. The study contributes substantially to the field of IoT security, offering a comprehensive and efficient framework for implementing Internet-based security strategies. The results affirm that SFlexCrypt is a robust solution, capable of enhancing the resilience of WSNs against sinkhole attacks while maintaining optimal energy efficiency.

Matched MeSH terms: Machine Learning*
Fulltext Equivalence and practice effect of alternate forms for Malay version of Auditory Verbal Learning Test (MAVLT)

Munjir N, Othman Z, Zakaria R, Shafin N, Hussain NA, Desa AM, et al.

EXCLI J, 2015;14:801-8.
PMID: 26600750 DOI: 10.17179/excli2015-280

This study aims to develop two alternate forms for Malay version of Auditory Verbal Learning Test (MAVLT) and to determine their equivalency and practice effect. Ninety healthy volunteers were subjected to the following neuropsychological tests at baseline, and at one month interval according to their assigned group; group 1 (MAVLT - MAVLT), group 2 (MAVLT - Alternate Form 1 - Alternate Form 1), and group 3 (MAVLT - Alternate Form 2 - Alternate Form 2). There were no significant difference in the mean score of all the trials at baseline among the three groups, and most of the mean score of trials between MAVLT and Alternate Form 1, and between MAVLT and Alternate Form 2. There was significant improvement in the mean score of each trial when the same form was used repeatedly at the interval of one month. However, there was no significant improvement in the mean score of each trial when the Alternate Form 2 was used during repeated neuropsychological testing. The MAVLT is a reliable instrument for repeated neuropsychological testing as long as alternate forms are used. The Alternate Form 2 showed better equivalency to MAVLT and less practice effects.

Matched MeSH terms: Verbal Learning
Fulltext Embedding a learning management system into an undergraduate medical informatics course in Saudi Arabia: lessons learned

Zakaria N, Jamal A, Bisht S, Koppel C

Med 2 0, 2013 Nov 27;2(2):e13.
PMID: 25075236 DOI: 10.2196/med20.2735

Public universities in Saudi Arabia today are making substantial investments in e-learning as part of their educational system, especially in the implementation of learning management systems (LMS). To our knowledge, this is the first study conducted in Saudi Arabia exploring medical students' experience with an LMS, particularly as part of a medical informatics course.

Matched MeSH terms: Learning
Learning and memory-enhancing effect of Bacopa monniera in neonatal rats

Vollala VR, Upadhya S, Nayak S

Bratisl Lek Listy, 2011;112(12):663-9.
PMID: 22372329

The aim of this study was to evaluate the learning and memory-enhancing effect of Bacopa monniera in neonatal rats.

Matched MeSH terms: Avoidance Learning/drug effects*; Maze Learning/drug effects*
Effect of ascorbic acid on the monosodium glutamate-induced neurobehavioral changes in periadolescent rats

Narayanan SN, Kumar RS, Paval J, Nayak S

Bratisl Lek Listy, 2010;111(5):247-52.
PMID: 20568412

In the current study we evaluated adverse effects of monosodium glutamate (MSG) on memory formation and its retrieval as well as the role of ascorbic acid (Vitamin-C) in prevention of MSG-induced alteration of neurobehavioral performance in periadolescent rats.

Matched MeSH terms: Avoidance Learning/drug effects; Maze Learning/drug effects
Fulltext Notes for primary care teachers: how do adults learn?

Kwa SK

Malays Fam Physician, 2007;2(1):25-6.
PMID: 25606073
Matched MeSH terms: Learning
Prediction of recombinant protein overexpression in Escherichia coli using a machine learning based model (RPOLP)

Habibi N, Norouzi A, Mohd Hashim SZ, Shamsir MS, Samian R

Comput Biol Med, 2015 Nov 1;66:330-6.
PMID: 26476414 DOI: 10.1016/j.compbiomed.2015.09.015

Recombinant protein overexpression, an important biotechnological process, is ruled by complex biological rules which are mostly unknown, is in need of an intelligent algorithm so as to avoid resource-intensive lab-based trial and error experiments in order to determine the expression level of the recombinant protein. The purpose of this study is to propose a predictive model to estimate the level of recombinant protein overexpression for the first time in the literature using a machine learning approach based on the sequence, expression vector, and expression host. The expression host was confined to Escherichia coli which is the most popular bacterial host to overexpress recombinant proteins. To provide a handle to the problem, the overexpression level was categorized as low, medium and high. A set of features which were likely to affect the overexpression level was generated based on the known facts (e.g. gene length) and knowledge gathered from related literature. Then, a representative sub-set of features generated in the previous objective was determined using feature selection techniques. Finally a predictive model was developed using random forest classifier which was able to adequately classify the multi-class imbalanced small dataset constructed. The result showed that the predictive model provided a promising accuracy of 80% on average, in estimating the overexpression level of a recombinant protein.

Matched MeSH terms: Machine Learning
Fulltext A qualitative study on the effect of gam e board strategy on the stud ent's motivation of learning statistics course

Nurul Aityqah Yaacob, Rosemawati Ali, Foo, Kien Kheng, Nadiah Mohamed, Mardiana Ahmad, Siti Noor Dina Ahmad, et al.

Journal of Academia Universiti Teknologi MARA Negeri Sembilan, 2019;7(101):142-145.
MyJurnal

An interactive teaching tool that utilizes a game board strategy to facilitate the learning of statistics has been developed and employed. This study aims to determine the impact of the board game on the motivation of diploma students towards learning statistics. Data are collected from 7 respondents using a face to face interview. Responses are qualitatively analysed. Results show that respondents are generally positive about the effectiveness of the board game as a teaching tool to enhance le arning and understanding. More importantly, respondents have shown a change in attitude towards statistics and are more motivated to learn statistics under this innovative learning environment. Some suggestions for future research are outlined.

Matched MeSH terms: Learning
Ten maxims for creating a safe learning environment

Prashanti E, Ramnarayan K

Adv Physiol Educ, 2020 Dec 01;44(4):550-553.
PMID: 32880485 DOI: 10.1152/advan.00085.2020

To foster a milieu in which student learning can be optimum, teachers need to be aware of the attributes of a safe learning environment. This is the space created in the students' minds to seamlessly promote learning. The 10 maxims, presented in this paper, are the cornerstones, nay, the capstones, for making this happen.

Matched MeSH terms: Learning

Filters

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links