MyMedR

Displaying publications 41 - 60 of 909 in total

Abstract:

Sort:

Fulltext Excessive smartphone usage among early adolescents: impact on social competence

Syed Ahmad Muhajir Alhaddad Syed E, Nurul Hudani Md N, Agnis S

Jurnal Psikologi Malaysia, 2018;32:1-11.

The benefit mobile technology brings is not limited to learning and entertainment but it also modifies human aspect of social communication. Despite the high number of previous research available concerning smartphones, there is still a gap of research that needs to be addressed such as its effect towards social competence. As the social system becomes complex, communication technology evolves to ensure the social needs are accomplished. For this study, 236 students aged between 13-14 years old were recruited and given a set of questionnaire which comprised Mobile Phone Problem Use Scale, Social Competence Scale for Teenagers and Self Scoring Self-Control Scale. In this study, the researcher attempted to examine the effect of excessive smartphone usage on social competence with self-control as mediator. Regression analysis was used to estimate the effect between the variables. The result indicates that there is negative relationship between excessive smartphone usage and social competence. However, when self-control is tested in the model as a mediator, excessive smartphones usage was not prevalent to predict social competence. This concludes to the apparent role of self-control as a mediator. The implication of study has contributed to the practical importance and methodological aspect of studies involving social competence and self-control.

Matched MeSH terms: 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
Landslide spatial modelling using novel bivariate statistical based Naïve Bayes, RBF Classifier, and RBF Network machine learning algorithms

He Q, Shahabi H, Shirzadi A, Li S, Chen W, Wang N, et al.

Sci Total Environ, 2019 May 01;663:1-15.
PMID: 30708212 DOI: 10.1016/j.scitotenv.2019.01.329

Landslides are major hazards for human activities often causing great damage to human lives and infrastructure. Therefore, the main aim of the present study is to evaluate and compare three machine learning algorithms (MLAs) including Naïve Bayes (NB), radial basis function (RBF) Classifier, and RBF Network for landslide susceptibility mapping (LSM) at Longhai area in China. A total of 14 landslide conditioning factors were obtained from various data sources, then the frequency ratio (FR) and support vector machine (SVM) methods were used for the correlation and selection the most important factors for modelling process, respectively. Subsequently, the resulting three models were validated and compared using some statistical metrics including area under the receiver operating characteristics (AUROC) curve, and Friedman and Wilcoxon signed-rank tests The results indicated that the RBF Classifier model had the highest goodness-of-fit and performance based on the training and validation datasets. The results concluded that the RBF Classifier model outperformed and outclassed (AUROC = 0.881), the NB (AUROC = 0.872) and the RBF Network (AUROC = 0.854) models. The obtained results pointed out that the RBF Classifier model is a promising method for spatial prediction of landslide over the world.

Matched MeSH terms: Machine Learning
Modelling gully-erosion susceptibility in a semi-arid region, Iran: Investigation of applicability of certainty factor and maximum entropy models

Azareh A, Rahmati O, Rafiei-Sardooi E, Sankey JB, Lee S, Shahabi H, et al.

Sci Total Environ, 2019 Mar 10;655:684-696.
PMID: 30476849 DOI: 10.1016/j.scitotenv.2018.11.235

Gully erosion susceptibility mapping is a fundamental tool for land-use planning aimed at mitigating land degradation. However, the capabilities of some state-of-the-art data-mining models for developing accurate maps of gully erosion susceptibility have not yet been fully investigated. This study assessed and compared the performance of two different types of data-mining models for accurately mapping gully erosion susceptibility at a regional scale in Chavar, Ilam, Iran. The two methods evaluated were: Certainty Factor (CF), a bivariate statistical model; and Maximum Entropy (ME), an advanced machine learning model. Several geographic and environmental factors that can contribute to gully erosion were considered as predictor variables of gully erosion susceptibility. Based on an existing differential GPS survey inventory of gully erosion, a total of 63 eroded gullies were spatially randomly split in a 70:30 ratio for use in model calibration and validation, respectively. Accuracy assessments completed with the receiver operating characteristic curve method showed that the ME-based regional gully susceptibility map has an area under the curve (AUC) value of 88.6% whereas the CF-based map has an AUC of 81.8%. According to jackknife tests that were used to investigate the relative importance of predictor variables, aspect, distance to river, lithology and land use are the most influential factors for the spatial distribution of gully erosion susceptibility in this region of Iran. The gully erosion susceptibility maps produced in this study could be useful tools for land managers and engineers tasked with road development, urbanization and other future development.

Matched MeSH terms: Machine Learning
Fulltext Does Short-Term Dietary Omega-3 Fatty Acid Supplementation Influence Brain Hippocampus Gene Expression of Zinc Transporter-3?

Sopian NF, Ajat M, Shafie NI, Noor MH, Ebrahimi M, Rajion MA, et al.

Int J Mol Sci, 2015;16(7):15800-10.
PMID: 26184176 DOI: 10.3390/ijms160715800

Dietary omega-3 fatty acids have been recognized to improve brain cognitive function. Deficiency leads to dysfunctional zinc metabolism associated with learning and memory impairment. The objective of this study is to explore the effect of short-term dietary omega-3 fatty acids on hippocampus gene expression at the molecular level in relation to spatial recognition memory in mice. A total of 24 male BALB/c mice were randomly divided into four groups and fed a standard pellet as a control group (CTL, n = 6), standard pellet added with 10% (w/w) fish oil (FO, n = 6), 10% (w/w) soybean oil (SO, n = 6) and 10% (w/w) butter (BT, n = 6). After 3 weeks on the treatment diets, spatial-recognition memory was tested on a Y-maze. The hippocampus gene expression was determined using a real-time PCR. The results showed that 3 weeks of dietary omega-3 fatty acid supplementation improved cognitive performance along with the up-regulation of α-synuclein, calmodulin and transthyretin genes expression. In addition, dietary omega-3 fatty acid deficiency increased the level of ZnT3 gene and subsequently reduced cognitive performance in mice. These results indicate that the increased the ZnT3 levels caused by the deficiency of omega-3 fatty acids produced an abnormal zinc metabolism that in turn impaired the brain cognitive performance in mice.

Matched MeSH terms: Maze Learning/drug effects
Fulltext The effects of dietary edible bird nest supplementation on learning and memory functions of multigenerational mice

Mahaq O, P Rameli MA, Jaoi Edward M, Mohd Hanafi N, Abdul Aziz S, Abu Hassim H, et al.

Brain Behav, 2020 11;10(11):e01817.
PMID: 32886435 DOI: 10.1002/brb3.1817

INTRODUCTION: Edible bird nest (EBN) is a natural food product produced from edible nest swiftlet's saliva which consists of glycoproteins as one of its main components; these glycoproteins contain an abundant of sialic acid. The dietary EBN supplementation has been reported to enhance brain functions in mammals and that the bioactivities and nutritional value of EBN are important during periods of rapid brain growth particularly for preterm infant. However, the effects of EBN in maternal on multigeneration learning and memory function still remain unclear. Thus, the present study aimed to determine the effects of maternal EBN supplementation on learning and memory function of their first (F1)- and second (F2)-generation mice.
METHODS: CJ57BL/6 breeder F0 mice were fed with EBN (10 mg/kg) from different sources. After 6 weeks of diet supplementations, the F0 animals were bred to produce F1 and F2 animals. At 6 weeks of age, the F1 and F2 animals were tested for spatial recognition memory using a Y-maze test. The sialic acid content from EBN and brain gene expression were analyzed using HPLC and PCR, respectively.
RESULTS: All EBN samples contained glycoprotein with high level of sialic acid. Dietary EBN supplementation also showed an upregulation of GNE, ST8SiaIV, SLC17A5, and BDNF mRNA associated with an improvement in Y-maze cognitive performance in both generations of animal. Qualitatively, the densities of synaptic vesicles in the presynaptic terminal were higher in the F1 and F2 animals which might derive from maternal EBN supplementation.
CONCLUSION: This study provided a solid foundation toward the growing research on nutritional intervention from dietary EBN supplementation on cognitive and neurological development in the generation of mammals.

Matched MeSH terms: Learning
Special care dentistry education during the COVID-19 pandemic: The impact of online peer-assisted learning

Mohd Suria TYI, Omar AF, Wan Mokhtar I, Rahman ANAA, Kamaruddin AA, Ahmad MS

Spec Care Dentist, 2023;43(6):848-855.
PMID: 37013967 DOI: 10.1111/scd.12857

OBJECTIVES: This study aims to analyze the impact and students' perceptions of online peer-assisted learning (OPL), developed as an alternative and innovative approach to Special Care Dentistry (SCD) training during the COVID-19 pandemic. Online peer-assisted learning (OPL) is an alternative pedagogical approach that combines online education and peer-assisted teaching.
METHODS: The OPL session was conducted by two postgraduate students in SCD (as teachers), to final year undergraduate dental students (as learners) (n = 90), supervised by two specialists in SCD-related areas (as supervisors). Vetted online pre- and post-intervention quizzes were conducted before and after the session, respectively, followed by an online validated feedback survey of the students' learning experiences. Meanwhile, a reflective session was conducted between the postgraduate students and supervisors to explore their perceptions of OPL. Quantitative data was analyzed via paired t-test (significance level, P

Matched MeSH terms: Learning
Visual Hybrid Development Learning System (VHDLS) framework for children with autism

Banire B, Jomhari N, Ahmad R

J Autism Dev Disord, 2015 Oct;45(10):3069-84.
PMID: 25997598 DOI: 10.1007/s10803-015-2469-7

The effect of education on children with autism serves as a relative cure for their deficits. As a result of this, they require special techniques to gain their attention and interest in learning as compared to typical children. Several studies have shown that these children are visual learners. In this study, we proposed a Visual Hybrid Development Learning System (VHDLS) framework that is based on an instructional design model, multimedia cognitive learning theory, and learning style in order to guide software developers in developing learning systems for children with autism. The results from this study showed that the attention of children with autism increased more with the proposed VHDLS framework.

Matched MeSH terms: Learning
Fulltext Parkinson's Disease Diagnosis and Severity Assessment Using Ground Reaction Forces and Neural Networks

Veeraragavan S, Gopalai AA, Gouwanda D, Ahmad SA

Front Physiol, 2020;11:587057.
PMID: 33240106 DOI: 10.3389/fphys.2020.587057

Gait analysis plays a key role in the diagnosis of Parkinson's Disease (PD), as patients generally exhibit abnormal gait patterns compared to healthy controls. Current diagnosis and severity assessment procedures entail manual visual examinations of motor tasks, speech, and handwriting, among numerous other tests, which can vary between clinicians based on their expertise and visual observation of gait tasks. Automating gait differentiation procedure can serve as a useful tool in early diagnosis and severity assessment of PD and limits the data collection to solely walking gait. In this research, a holistic, non-intrusive method is proposed to diagnose and assess PD severity in its early and moderate stages by using only Vertical Ground Reaction Force (VGRF). From the VGRF data, gait features are extracted and selected to use as training features for the Artificial Neural Network (ANN) model to diagnose PD using cross validation. If the diagnosis is positive, another ANN model will predict their Hoehn and Yahr (H&Y) score to assess their PD severity using the same VGRF data. PD Diagnosis is achieved with a high accuracy of 97.4% using simple network architecture. Additionally, the results indicate a better performance compared to other complex machine learning models that have been researched previously. Severity Assessment is also performed on the H&Y scale with 87.1% accuracy. The results of this study show that it is plausible to use only VGRF data in diagnosing and assessing early stage Parkinson's Disease, helping patients manage the symptoms earlier and giving them a better quality of life.

Matched MeSH terms: Machine Learning
Neurorestorative effect of FTY720 in a rat model of Alzheimer's disease: comparison with memantine

Hemmati F, Dargahi L, Nasoohi S, Omidbakhsh R, Mohamed Z, Chik Z, et al.

Behav Brain Res, 2013 Sep 1;252:415-21.
PMID: 23777795 DOI: 10.1016/j.bbr.2013.06.016

Alzheimer's disease (AD) as a neurodegenerative brain disorder is the most common cause of dementia. To date, there is no causative treatment for AD and there are few preventive treatments either. The sphingosine-1-phosphate receptor modulator FTY720 (fingolimod) prevents lymphocytes from contributing to an autoimmune reaction and has been approved for multiple sclerosis treatment. In concert with other studies showing the anti-inflammatory and protective effect of FTY720 in some neurodegenerative disorders like ischemia, we have recently shown that FTY720 chronic administration prevents from impairment of spatial learning and memory in AD rats. Here FTY720 was examined on AD rats in comparison to the only clinically approved NMDA receptor antagonist, Memantine. Passive avoidance task showed significant memory restoration in AD animals received FTY720 comparable to Memantine. Upon gene profiling by QuantiGene Plex, this behavioral outcomes was concurrent with considerable alterations in some genes transcripts like that of mitogen activated protein kinases (MAPKs) and some inflammatory markers that may particularly account for the detected decline in hippocampal neural damage or memory impairment associated with AD. From a therapeutic standpoint, our findings conclude that FTY720 may suggest new opportunities for AD management probably based on several modulatory effects on genes involved in cell death or survival.

Matched MeSH terms: Avoidance Learning/drug effects
Non-polyphenolic compounds of a specific kind of dried grape (Maviz) inhibit memory impairments induced by beta-amyloid peptide

Bakhtiyari E, Ahmadian-Attari MM, Salehi P, Khallaghi B, Dargahi L, Mohamed Z, et al.

Nutr Neurosci, 2017 Oct;20(8):469-477.
PMID: 27219682 DOI: 10.1080/1028415X.2016.1183986

OBJECTIVES: Although grape has been recently the topic of many investigations, Maviz (a kind of dried one) has remained neglected. The aim of this study was to assess anti-Alzheimer activity of Maviz.
METHODS: To reach this goal, total phenolic content (TPC) of ethanolic (Eth) and aqueous (Aq) extracts were determined and radical scavenging activity was assayed by 2,2-diphenyl-1-picrylhydrazyl. Chemical compositions of each extract were also determined via GC-Mass. Behavioral changes were studied via passive avoidance and Morris water maze in Aβ-induced model of Alzheimer's disease. Catalase (CAT) and superoxide dismutase (SOD) determination were also done on rats' hippocampus.
RESULTS: The results showed that seed Eth extract has a high level of TPC and radical scavenging activity. However, this extract had surprisingly no effect on memory and CAT and SOD activities. In contrast, fruit Aq and Eth extracts (containing furfurals as major compounds) inhibited memory impairment (P

Matched MeSH terms: Avoidance Learning; Maze Learning/drug effects
Groundwater level forecasting with machine learning models: A review

Boo KBW, El-Shafie A, Othman F, Khan MMH, Birima AH, Ahmed AN

Water Res, 2024 Mar 15;252:121249.
PMID: 38330715 DOI: 10.1016/j.watres.2024.121249

Groundwater, the world's most abundant source of freshwater, is rapidly depleting in many regions due to a variety of factors. Accurate forecasting of groundwater level (GWL) is essential for effective management of this vital resource, but it remains a complex and challenging task. In recent years, there has been a notable increase in the use of machine learning (ML) techniques to model GWL, with many studies reporting exceptional results. In this paper, we present a comprehensive review of 142 relevant articles indexed by the Web of Science from 2017 to 2023, focusing on key ML models, including artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), support vector regression (SVR), evolutionary computing (EC), deep learning (DL), ensemble learning (EN), and hybrid-modeling (HM). We also discussed key modeling concepts such as dataset size, data splitting, input variable selection, forecasting time-step, performance metrics (PM), study zones, and aquifers, highlighting best practices for optimal GWL forecasting with ML. This review provides valuable insights and recommendations for researchers and water management agencies working in the field of groundwater management and hydrology.

Matched MeSH terms: Machine Learning
Pharmacological Effects of Turmeric on Learning, Memory and Expression of Muscarinic Receptor Genes (M1, M3 and M5) in Stress-induced Mouse Model

Khalid A, Shakeel R, Justin S, Iqbal G, Shah SAA, Zahid S, et al.

Curr Drug Targets, 2017;18(13):1545-1557.
PMID: 28302036 DOI: 10.2174/1389450118666170315120627

BACKGROUND: Stress is involved in memory impairment through multiple mechanisms, including activation of hypothalamic-pituitary axis, which in turn activates release of corticosterone in blood. Cholinergic system blockade by the muscarinic antagonist, scopolamine, also impairs memory.
OBJECTIVE: This study aimed to investigate the effect of turmeric (20mg/kg) on learning and memory and cholinergic system in a mouse model of stress along with cholinergic blockade.
METHODS: Restrained stress was induced and cholinergic receptors were blocked using scopolamine in mice. Animals were treated with turmeric (turmeric rhizome powder which was also subjected to NMR analyses) and learning and social behavior was examined. Effect of turmeric on cholinergic muscarinic receptors (mAChR; M1, M3 and M5) gene expression was assessed by RT-PCR in both pre-frontal cortex and hippocampus.
RESULTS: Ar-turmerone, curcuminoids and α-linolenic acid were the lead compounds present in turmeric extract. Increased serum corticosterone levels were observed in stressed mice when compared to the control group, while turmeric treatment significantly reduced serum corticosterone level. Turmeric treatment caused an improved learning and memory in Morris water maze test in stressed animals. Social novelty preference was also restored in turmeric treated animals. Following turmeric treatment, M5 expression was improved in the cortex and M3 expression was improved in the hippocampus of stress + scopolamine + turmeric treated group.
CONCLUSIONS: These findings highlight the therapeutic role of turmeric by increasing the expression of M3, M5 and improving learning and memory. Turmeric can be an effective candidate for the treatment of amnesia caused by the stress.

Matched MeSH terms: Learning/drug effects
Fulltext Medical professionalism videos on YouTube: Content exploration and appraisal of user engagement

Ahmad T, Sattar K, Akram A

Saudi J Biol Sci, 2020 Sep;27(9):2287-2292.
PMID: 32884409 DOI: 10.1016/j.sjbs.2020.06.007

Background: Social media has become the fastest growing platform for sharing and retrieving information and knowledge, and YouTube is one of the most popular and growing sources of health and educational information video-sharing website. But, videos on this open platform are not peer-assessed, therefore, the accessible data should be adequately assessed. Till date, no exploration and analysis for assessing the credibility and usefulness of Medical professionalism videos available on YouTube are conducted.
Objective: To analyze the video sources, contents and quality of YouTube videos about the topic of medical professionalism.
Methods: A systematic search was accomplished on YouTube videos during the period between March 1, 2020 and March 27, 2020. The phrases as significant words used throughout YouTube web search were 'Professionalism in Medical Education', Professionalism in medicine', 'Professionalism of medical students', 'Professionalism in healthcare'. 'Teaching professionalism', 'Attributes of professionalism'. The basic information collected for each video included author's/publisher's name, total number of watchers, likes, dislikes and positive and undesirable remarks. The videos were categorized into educationally useful and useless established on the content, correctness of the knowledge and the advices. Different variables were measured and correlated for the data analysis.YouTube website was searched the using keywords 'Professionalism in Medical Education', Professionalism in medicine', 'Professionalism of medical students', 'Professionalism in healthcare'. 'Teaching professionalism', and 'Attributes of professionalism'.
Results: After 2 rounds of screening by the subject experts and critical analysis of all the 137 YouTube videos, only 41 (29.92%) were identified as pertinent to the subject matter, i.e., educational type. After on expert viewing these 41 videos established upon our pre-set inclusion/exclusion criteria, only 17 (41.46%) videos were found to be academically valuable in nature.
Conclusion: Medical professionalism multimedia videos uploaded by the healthcare specialists or organizations on YouTube provided reliable information for medical students, healthcare workers and other professional. We conclude that YouTube is a leading and free online source of videos meant for students or other healthcare workers yet the viewers need to be aware of the source prior to using it for training learning.

Matched MeSH terms: Learning
Fulltext Malay sentiment analysis based on combined classification approaches and Senti-lexicon algorithm

Al-Saffar A, Awang S, Tao H, Omar N, Al-Saiagh W, Al-Bared M

PLoS One, 2018;13(4):e0194852.
PMID: 29684036 DOI: 10.1371/journal.pone.0194852

Sentiment analysis techniques are increasingly exploited to categorize the opinion text to one or more predefined sentiment classes for the creation and automated maintenance of review-aggregation websites. In this paper, a Malay sentiment analysis classification model is proposed to improve classification performances based on the semantic orientation and machine learning approaches. First, a total of 2,478 Malay sentiment-lexicon phrases and words are assigned with a synonym and stored with the help of more than one Malay native speaker, and the polarity is manually allotted with a score. In addition, the supervised machine learning approaches and lexicon knowledge method are combined for Malay sentiment classification with evaluating thirteen features. Finally, three individual classifiers and a combined classifier are used to evaluate the classification accuracy. In experimental results, a wide-range of comparative experiments is conducted on a Malay Reviews Corpus (MRC), and it demonstrates that the feature extraction improves the performance of Malay sentiment analysis based on the combined classification. However, the results depend on three factors, the features, the number of features and the classification approach.

Matched MeSH terms: Supervised Machine Learning/classification
Fulltext Medical professionalism from a socio-cultural perspective: evaluating medical residents communicative attitudes during the medical encounter in malaysia

Ganasegeran K, Al-Dubai SA

J Postgrad Med, 2014 Jan-Mar;60(1):12-5.
PMID: 24625933 DOI: 10.4103/0022-3859.128799

The practice of medicine requires good communication skills to foster excellent rapport in doctor patient relationship. Reports on communication skills learning attitude among medical professionals are key essentials toward improving patient safety and quality of care.

Matched MeSH terms: Learning
Fulltext Classification of forensic autopsy reports through conceptual graph-based document representation model

Mujtaba G, Shuib L, Raj RG, Rajandram R, Shaikh K, Al-Garadi MA

J Biomed Inform, 2018 06;82:88-105.
PMID: 29738820 DOI: 10.1016/j.jbi.2018.04.013

Text categorization has been used extensively in recent years to classify plain-text clinical reports. This study employs text categorization techniques for the classification of open narrative forensic autopsy reports. One of the key steps in text classification is document representation. In document representation, a clinical report is transformed into a format that is suitable for classification. The traditional document representation technique for text categorization is the bag-of-words (BoW) technique. In this study, the traditional BoW technique is ineffective in classifying forensic autopsy reports because it merely extracts frequent but discriminative features from clinical reports. Moreover, this technique fails to capture word inversion, as well as word-level synonymy and polysemy, when classifying autopsy reports. Hence, the BoW technique suffers from low accuracy and low robustness unless it is improved with contextual and application-specific information. To overcome the aforementioned limitations of the BoW technique, this research aims to develop an effective conceptual graph-based document representation (CGDR) technique to classify 1500 forensic autopsy reports from four (4) manners of death (MoD) and sixteen (16) causes of death (CoD). Term-based and Systematized Nomenclature of Medicine-Clinical Terms (SNOMED CT) based conceptual features were extracted and represented through graphs. These features were then used to train a two-level text classifier. The first level classifier was responsible for predicting MoD. In addition, the second level classifier was responsible for predicting CoD using the proposed conceptual graph-based document representation technique. To demonstrate the significance of the proposed technique, its results were compared with those of six (6) state-of-the-art document representation techniques. Lastly, this study compared the effects of one-level classification and two-level classification on the experimental results. The experimental results indicated that the CGDR technique achieved 12% to 15% improvement in accuracy compared with fully automated document representation baseline techniques. Moreover, two-level classification obtained better results compared with one-level classification. The promising results of the proposed conceptual graph-based document representation technique suggest that pathologists can adopt the proposed system as their basis for second opinion, thereby supporting them in effectively determining CoD.

Matched MeSH terms: Machine Learning
Fulltext Deep-Learning-Based Approach for Iraqi and Malaysian Vehicle License Plate Recognition

Habeeb D, Noman F, Alkahtani AA, Alsariera YA, Alkawsi G, Fazea Y, et al.

Comput Intell Neurosci, 2021;2021:3971834.
PMID: 34782832 DOI: 10.1155/2021/3971834

Recognizing vehicle plate numbers is a key step towards implementing the legislation on traffic and reducing the number of daily traffic accidents. Although machine learning has advanced considerably, the recognition of license plates remains an obstacle, particularly in countries whose plate numbers are written in different languages or blended with Latin alphabets. This paper introduces a recognition system for Arabic and Latin alphabet license plates using a deep-learning-based approach in conjugation with data collected from two specific countries: Iraq and Malaysia. The system under study is proposed to detect, segment, and recognize vehicle plate numbers. Moreover, Iraqi and Malaysian plates were used to compare these processes. A total of 404 Iraqi images and 681 Malaysian images were tested and used for the proposed techniques. The evaluation took place under various atmospheric environments, including fog, different contrasts, dirt, different colours, and distortion problems. The proposed approach showed an average recognition rate of 85.56% and 88.86% on Iraqi and Malaysian datasets, respectively. Thus, this evidences that the deep-learning-based method outperforms other state-of-the-art methods as it can successfully detect plate numbers regardless of the deterioration level of image quality.

Matched MeSH terms: Machine Learning
Fulltext An improved wrapper-based feature selection method for machinery fault diagnosis

Hui KH, Ooi CS, Lim MH, Leong MS, Al-Obaidi SM

PLoS One, 2017;12(12):e0189143.
PMID: 29261689 DOI: 10.1371/journal.pone.0189143

A major issue of machinery fault diagnosis using vibration signals is that it is over-reliant on personnel knowledge and experience in interpreting the signal. Thus, machine learning has been adapted for machinery fault diagnosis. The quantity and quality of the input features, however, influence the fault classification performance. Feature selection plays a vital role in selecting the most representative feature subset for the machine learning algorithm. In contrast, the trade-off relationship between capability when selecting the best feature subset and computational effort is inevitable in the wrapper-based feature selection (WFS) method. This paper proposes an improved WFS technique before integration with a support vector machine (SVM) model classifier as a complete fault diagnosis system for a rolling element bearing case study. The bearing vibration dataset made available by the Case Western Reserve University Bearing Data Centre was executed using the proposed WFS and its performance has been analysed and discussed. The results reveal that the proposed WFS secures the best feature subset with a lower computational effort by eliminating the redundancy of re-evaluation. The proposed WFS has therefore been found to be capable and efficient to carry out feature selection tasks.

Matched MeSH terms: Machine Learning
Fulltext A Novel Feature-Engineered-NGBoost Machine-Learning Framework for Fraud Detection in Electric Power Consumption Data

Hussain S, Mustafa MW, Al-Shqeerat KHA, Saeed F, Al-Rimy BAS

Sensors (Basel), 2021 Dec 17;21(24).
PMID: 34960516 DOI: 10.3390/s21248423

This study presents a novel feature-engineered-natural gradient descent ensemble-boosting (NGBoost) machine-learning framework for detecting fraud in power consumption data. The proposed framework was sequentially executed in three stages: data pre-processing, feature engineering, and model evaluation. It utilized the random forest algorithm-based imputation technique initially to impute the missing data entries in the acquired smart meter dataset. In the second phase, the majority weighted minority oversampling technique (MWMOTE) algorithm was used to avoid an unequal distribution of data samples among different classes. The time-series feature-extraction library and whale optimization algorithm were utilized to extract and select the most relevant features from the kWh reading of consumers. Once the most relevant features were acquired, the model training and testing process was initiated by using the NGBoost algorithm to classify the consumers into two distinct categories ("Healthy" and "Theft"). Finally, each input feature's impact (positive or negative) in predicting the target variable was recognized with the tree SHAP additive-explanations algorithm. The proposed framework achieved an accuracy of 93%, recall of 91%, and precision of 95%, which was greater than all the competing models, and thus validated its efficacy and significance in the studied field of research.

Matched MeSH terms: Machine Learning*

Filters

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

External Links