MyMedR

Displaying publications 1 - 20 of 907 in total

Abstract:

Sort:

Fulltext Assessing Patient-Perceived Hospital Service Quality and Sentiment in Malaysian Public Hospitals Using Machine Learning and Facebook Reviews

A Rahim AI, Ibrahim MI, Musa KI, Chua SL, Yaacob NM

Int J Environ Res Public Health, 2021 09 21;18(18).
PMID: 34574835 DOI: 10.3390/ijerph18189912

Social media is emerging as a new avenue for hospitals and patients to solicit input on the quality of care. However, social media data is unstructured and enormous in volume. Moreover, no empirical research on the use of social media data and perceived hospital quality of care based on patient online reviews has been performed in Malaysia. The purpose of this study was to investigate the determinants of positive sentiment expressed in hospital Facebook reviews in Malaysia, as well as the association between hospital accreditation and sentiments expressed in Facebook reviews. From 2017 to 2019, we retrieved comments from 48 official public hospitals' Facebook pages. We used machine learning to build a sentiment analyzer and service quality (SERVQUAL) classifier that automatically classifies the sentiment and SERVQUAL dimensions. We utilized logistic regression analysis to determine our goals. We evaluated a total of 1852 reviews and our machine learning sentiment analyzer detected 72.1% of positive reviews and 27.9% of negative reviews. We classified 240 reviews as tangible, 1257 reviews as trustworthy, 125 reviews as responsive, 356 reviews as assurance, and 1174 reviews as empathy using our machine learning SERVQUAL classifier. After adjusting for hospital characteristics, all SERVQUAL dimensions except Tangible were associated with positive sentiment. However, no significant relationship between hospital accreditation and online sentiment was discovered. Facebook reviews powered by machine learning algorithms provide valuable, real-time data that may be missed by traditional hospital quality assessments. Additionally, online patient reviews offer a hitherto untapped indication of quality that may benefit all healthcare stakeholders. Our results confirm prior studies and support the use of Facebook reviews as an adjunct method for assessing the quality of hospital services in Malaysia.

Matched MeSH terms: Machine Learning
Using the ADDIE Model to Develop a Rusnani Concept Mapping Guideline for Nursing Students

Ab Latif R, Mat Nor MZ

Malays J Med Sci, 2020 Dec;27(6):115-127.
PMID: 33447139 DOI: 10.21315/mjms2020.27.6.11

Background: Concept mapping has been established as a learning strategy that encourages critical thinking and creativity among students, leading to the development of a concept mapping guideline designed to guide nurse educators in using this teaching strategy.
Objectives: This paper illustrates the development of a guideline to build a concept mapping based-learning strategy. Called the Rusnani concept mapping (RCM) protocol guideline, it was adapted from the Mohd Afifi learning model (MoAFF) and the analysis, design, development, implementation and evaluation (ADDIE) model, integrated with the Kemp model.
Methods: This model uses the five phases of analysis, design, development, implementation and evaluation. The validity of the guideline was determined by using content and face validity and the Delphi technique. Content validity for this RCM guideline was established using expert review. This formula suggested that if the content validity is greater than 70%, it shows good content validity, and if it is less than 70%, the content validity is low and it is advisable to recheck the content according to the objective of the study.
Results: The reliability of the RCM was 0.816, showing that the RCM guideline has high reliability and validity.
Conclusion: It is practical and acceptable for nurse educators to apply RCM as an effective and innovative teaching method to enhance the academic performance of their nursing students.

Matched MeSH terms: Learning
Fulltext Learning through teaching and sharing in the Jigsaw Classroom

Ab Murat, N.

Ann Dent, 2008;15(2):71-76.
MyJurnal

Teaching is a complex activity which consists not only of giving instructions but also promotion of learning. Different students have different preference for learning styles. Dental educators must therefore attempt to mix and match their methods of teaching to accommodate students with differing learning styles to provide an opportunity to maximize their learning. This paper aims to share the writer's experience and students' perceptions towards a different mode of teaching/learning method. The Jigsaw Classroom method was employed on University of Malaya's third-year dental students during their Water Fluoridation lecture. At the end of the session, students were asked to reflect upon the learning experience and to inscribe their feelings. Initially, students showed their resentment towards the new learning style but their resistance changed once they got into a group and started to learn from each other. In the reflective essay, most students expressed that learning through teaching and discussing as required in the Jigsaw method enhanced their understanding of the topic and they claimed that they were able to retain the information better. In this study, the Jigsaw method proved that learning in the lecture hall can be fun, educational and enriching.

Matched MeSH terms: Learning; Problem-Based Learning
Implementation of data intelligence models coupled with ensemble machine learning for prediction of water quality index

Abba SI, Pham QB, Saini G, Linh NTT, Ahmed AN, Mohajane M, et al.

Environ Sci Pollut Res Int, 2020 Nov;27(33):41524-41539.
PMID: 32686045 DOI: 10.1007/s11356-020-09689-x

In recent decades, various conventional techniques have been formulated around the world to evaluate the overall water quality (WQ) at particular locations. In the present study, back propagation neural network (BPNN) and adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR), and one multilinear regression (MLR) are considered for the prediction of water quality index (WQI) at three stations, namely Nizamuddin, Palla, and Udi (Chambal), across the Yamuna River, India. The nonlinear ensemble technique was proposed using the neural network ensemble (NNE) approach to improve the performance accuracy of the single models. The observed WQ parameters were provided by the Central Pollution Control Board (CPCB) including dissolved oxygen (DO), pH, biological oxygen demand (BOD), ammonia (NH3), temperature (T), and WQI. The performance of the models was evaluated by various statistical indices. The obtained results indicated the feasibility of the developed data intelligence models for predicting the WQI at the three stations with the superior modelling results of the NNE. The results also showed that the minimum values for root mean square (RMS) varied between 0.1213 and 0.4107, 0.003 and 0.0367, and 0.002 and 0.0272 for Nizamuddin, Palla, and Udi (Chambal), respectively. ANFIS-M3, BPNN-M4, and BPNN-M3 improved the performance with regard to an absolute error by 41%, 4%, and 3%, over other models for Nizamuddin, Palla, and Udi (Chambal) stations, respectively. The predictive comparison demonstrated that NNE proved to be effective and can therefore serve as a reliable prediction approach. The inferences of this paper would be of interest to policymakers in terms of WQ for establishing sustainable management strategies of water resources.

Matched MeSH terms: Machine Learning
Fulltext Nicotine-prevented learning and memory impairment in REM sleep-deprived rat is modulated by DREAM protein in the hippocampus

Abd Rashid N, Hapidin H, Abdullah H, Ismail Z, Long I

Brain Behav, 2017 06;7(6):e00704.
PMID: 28638710 DOI: 10.1002/brb3.704

INTRODUCTION: REM sleep deprivation is associated with impairment in learning and memory, and nicotine treatment has been shown to attenuate this effect. Recent studies have demonstrated the importance of DREAM protein in learning and memory processes. This study investigates the association of DREAM protein in REM sleep-deprived rats hippocampus upon nicotine treatment.
METHODS: Male Sprague Dawley rats were subjected to normal condition, REM sleep deprivation and control wide platform condition for 72 hr. During this procedure, saline or nicotine (1 mg/kg) was given subcutaneously twice a day. Then, Morris water maze (MWM) test was used to assess learning and memory performance of the rats. The rats were sacrificed and the brain was harvested for immunohistochemistry and Western blot analysis.
RESULTS: MWM test found that REM sleep deprivation significantly impaired learning and memory performance without defect in locomotor function associated with a significant increase in hippocampus DREAM protein expression in CA1, CA2, CA3, and DG regions and the mean relative level of DREAM protein compared to other experimental groups. Treatment with acute nicotine significantly prevented these effects and decreased expression of DREAM protein in all the hippocampus regions but only slightly reduce the mean relative level of DREAM protein.
CONCLUSION: This study suggests that changes in DREAM protein expression in CA1, CA2, CA3, and DG regions of rat's hippocampus and mean relative level of DREAM protein may involve in the mechanism of nicotine treatment-prevented REM sleep deprivation-induced learning and memory impairment in rats.

Matched MeSH terms: Learning/drug effects; Learning/physiology; Learning Disorders/metabolism; Learning Disorders/prevention & control; Maze Learning/drug effects
Effectiveness of enhanced video-based learning on removable partial denture module

Abd-Shukor SN, Yahaya N, Tamil AM, Botelho MG, Ho TK

Eur J Dent Educ, 2021 Nov;25(4):744-752.
PMID: 33368978 DOI: 10.1111/eje.12653

INTRODUCTION: The application of video-based learning in dentistry has been widely investigated; however, the nature of on-screen video enhancements of the video has been minimally explored in the literature. This study investigated the effectiveness of an in-class and on-demand enhanced video to support learning on removable partial dentures in terms of knowledge acquisition, perception and clinical skill performance.
METHODS: Fifty-four dental students enrolled in 2018 were recruited as participants and assigned to two groups. Both groups were given the same lecture and asked to watch the same video in either the enhanced or non-enhanced version. The enhanced video was modified with the contemporaneous subtitle of the presenters' dialogue, text bullet points and summary text pages. The knowledge acquisition from the two types of video was subjected to pre- and post-tests one month after the students watched the video. A questionnaire was used to evaluate the students' perceptions of the learning experience and a performance test on practical skills was performed after six weeks. All the students responded to the test (100%).
RESULTS: The enhanced video demonstration improved the students' short-term knowledge acquisition after they watched the video, with an average score of 1.59 points higher in the enhanced group than in the non-enhanced group (p

Matched MeSH terms: Learning
Fulltext Attitude towards problem-based learning and its relationship with locus of control and academic self-concept among medical students

Abdalla MMI, Abdelal MS, Soon SC

Korean J Med Educ, 2019 Mar;31(1):11-18.
PMID: 30852857 DOI: 10.3946/kjme.2019.114

PURPOSE: This study aimed to assess the degree of acceptance of problem-based learning (PBL) among phase one medical students and its association with academic self-concept (ASC) and internal locus of control (ILOC).
METHODS: A 5-point Likert scale valid and reliable questionnaire assessing the attitude towards PBL, ASC, and ILOC was given to phase one medical students at MAHSA University. Data were analysed using IBM SPSS ver. 22.0 (IBM Corp., Armonk, USA).
RESULTS: Out of 255 participants, there were 84 males and 171 females, 175 Malaysians and 80 non-Malaysians. The results showed an overall acceptance of PBL with a mean of 3.7±0.07, ASC of 3.5±0.05 and ILOC of 2.9±0.05. Females showed a higher significant acceptance of PBL, ASC, and ILOC as compared with males. There was no difference between Malaysians and non-Malaysians in any of the variables measured. Simple regression analysis revealed a significant predictive effect of acceptance of PBL on ASC and ILOC (r=0.44 and r=0.88, respectively).
CONCLUSION: The higher the acceptance of PBL among students, the higher is the ASC and ILOC. This reflects the importance of PBL as a teaching method as well as the importance of increasing the level of appreciation of PBL amongst students.

Matched MeSH terms: Problem-Based Learning*
IAPSO-AIRS: A novel improved machine learning-based system for wart disease treatment

Abdar M, Wijayaningrum VN, Hussain S, Alizadehsani R, Plawiak P, Acharya UR, et al.

J Med Syst, 2019 Jun 07;43(7):220.
PMID: 31175462 DOI: 10.1007/s10916-019-1343-0

Wart disease (WD) is a skin illness on the human body which is caused by the human papillomavirus (HPV). This study mainly concentrates on common and plantar warts. There are various treatment methods for this disease, including the popular immunotherapy and cryotherapy methods. Manual evaluation of the WD treatment response is challenging. Furthermore, traditional machine learning methods are not robust enough in WD classification as they cannot deal effectively with small number of attributes. This study proposes a new evolutionary-based computer-aided diagnosis (CAD) system using machine learning to classify the WD treatment response. The main architecture of our CAD system is based on the combination of improved adaptive particle swarm optimization (IAPSO) algorithm and artificial immune recognition system (AIRS). The cross-validation protocol was applied to test our machine learning-based classification system, including five different partition protocols (K2, K3, K4, K5 and K10). Our database consisted of 180 records taken from immunotherapy and cryotherapy databases. The best results were obtained using the K10 protocol that provided the precision, recall, F-measure and accuracy values of 0.8908, 0.8943, 0.8916 and 90%, respectively. Our IAPSO system showed the reliability of 98.68%. It was implemented in Java, while integrated development environment (IDE) was implemented using NetBeans. Our encouraging results suggest that the proposed IAPSO-AIRS system can be employed for the WD management in clinical environment.

Matched MeSH terms: Machine Learning*
Fulltext A Hybridised Intelligent Technique for the diagnosis of medical diseases

Abdu Masanawa Sagir, Saratha Sathasivam

Pertanika Journal of Science & Technology, 2017;25(2):425-440.
MyJurnal

Medical diagnosis is the process of determining which disease or medical condition explains a person’s determinable signs and symptoms. Diagnosis of most diseases is very expensive as many tests are required for predictions. This paper aims to introduce an improved hybrid approach for training the adaptive network based fuzzy inference system (ANFIS). It incorporates hybrid learning algorithms least square estimates with Levenberg-Marquardt algorithm using analytic derivation for computation of Jacobian matrix, as well as code optimisation technique, which indexes membership functions. The goal is to investigate how certain diseases are affected by patient’s characteristics and measurement such as abnormalities or a decision about the presence or absence of a disease. In order to achieve an accurate diagnosis at this complex stage of symptom analysis, the physician may need efficient diagnosis system to classify and predict patient condition by using an adaptive neuro fuzzy inference system (ANFIS) pre-processed by grid partitioning. The proposed hybridised intelligent technique was tested with Statlog heart disease and Hepatitis disease datasets obtained from the University of California at Irvine’s (UCI) machine learning repository. The robustness of the performance measuring total accuracy, sensitivity and specificity was examined. In comparison, the proposed method was found to achieve superior
performance when compared to some other related existing methods.

Matched MeSH terms: Machine Learning
Fulltext Verbal memory test performance in patients with bipolar I disorder attending a psychiatric clinic of a university hospital in Kuala Lumpur, Malaysia.

Abdul Hamid Abdul Rahman, Shamsul Azhar Shah, Normala Ibrahim

ASEAN Journal of Psychiatry, 2009;10(2):157-168.
MyJurnal

Objective: The study aims to determine pattern of verbal memory and learning impairment and its associated factors among patients with bipolar I disorder in a psychiatric clinic of a university hospital. Methods: A case control study comparing verbal memory test
performance in 40 patients with bipolar I disorder to that of 40 healthy normal subjects using Rey Auditory Verbal Learning Test (RAVLT). The association between demographic, clinical
characteristics and poor verbal memory performance were examined. Results: Up to 92% of patients with bipolar I disorder have impaired short term working memory in this hospital-based study. They also recalled fewer words in all the RAVLT trials and had difficulties
learning the word list in comparison to that of normal healthy individuals. Verbal memory and learning impairment are observed in bipolar illness in the absence of active mood symptoms while duration and severity of illness are not found to have any effect on verbal memory and learning. Conclusion: There is consistent verbal memory and learning problems in individuals with bipolar I disorder and their presence in the absence of mania, depression and mixed symptoms during the course of the illness suggests a trait related deficit.

Study site: Psychiatric Clinic, Pusat Perubatan Universiti Kebangsaan Malaysia (PPUKM)

Matched MeSH terms: Verbal Learning
Fulltext Obsessive-Compulsive Disorder in Schizophrenia: Clinical and Neurocognitive Correlates

Abdul Hamid, A.R., Abdul Razak, O.

Malaysian Journal of Psychiatry, 2010;19(2):1-9.
MyJurnal

This study aims to determine the prevalence of obsessive compulsive disorder (OCD) among schizophrenic patients and the association of this condition with clinical and selected neurocognitive factors. This is a cross sectional study on one hundred schizophrenic patients who attended psychiatric clinic in National University Hospital and Kuala Lumpur Hospital over a four-months period. All patients diagnosed as schizophrenia according to DSM 1V were assessed using Mini International Neuropsychiatric Interview (MINI) Version 5 for the presence of Obsessive Compulsive Disorder, Brief Psychiatric rating Scale (BPRS) for severity of psychosis and Yale Brown Obsessive Compulsive Scale (YBOCS) for severity of obsessive compulsive (OC) symptoms. Socio-demographic data were obtained by direct interview. The neurocognitive assessment were done using Mini Mental State Examination , Rey Auditory Verbal Learning Test (RAVLT) and Digit Span. Fifteen percent of schizophrenic patients (15%) in this sample were found to have a diagnosis of Obsessive compulsive Disorder (OCD). The OCD and non-OCD schizophrenic patients did not differ significantly in term of age ,gender, race and family history of mental illness. However they differ significantly on employment, type of treatment medication and the presence or severity of current psychosis. Schizophrenic patients with OCD also showed no significant different in selected neurocognitive functions.

Matched MeSH terms: Verbal Learning
Fulltext The usage of computers and internet web 2.0 in generation Y among university students (Penggunaan komputer dan internet Web 2.0 dalam kalangan generasi Y pelajar universiti)

Abdul Manaf, S.Z., Din, R., Hamdan, A., Mat Salleh, N.S., Kamsin, I.F., Abdul Aziz, J.

Journal of Advanced Research Design, 2015;7(1):10-18.
MyJurnal

At present, the learning activities carried out is in line with the rapid growth of development of technology and lifestyle. ICT literacy is categorised as those who can operate a computer and Internet. This study is conducted to determine the level of computer and Internet literacy in generation Y. A total of ten respondents among university students were interviewed. The level of the skill is measured in terms of the use of information processing systems and the Internet. The new knowledge addresses the themes in information communication technology literacy namely; defining, accessing, assessing, managing, integrating, creating and passing data. As such, the model of computer technology in education can also be produced. A more robust method of learning can be heightened by seeing the level of skills possessed by university students. The findings of this study is expected to determine the level of competence of the students and university can provide the necessary equipment to ensure effective teaching and learning.

Matched MeSH terms: Problem-Based Learning
Fulltext A comparative analysis of reflection in a primary care outpatient setting in two learning environments

Abdul Rahman NF, Albualy R

Education in Medicine Journal, 2018;10(2):41-47.
MyJurnal

Situated learning characterises the learning that takes place in the clinical environment. Learning in the workplace is characterised by transferring classroom knowledge into performing tasks and this may take various forms. In the medical education field, the cognitive apprenticeship instructional model developed by Collins (2016) supported this learning in the workplace setting due to its common characteristics of apprenticeship. This paper analysed two concrete learning situations in a Malaysian undergraduate and an Omani postgraduate learning environment. Both learning situations occurred in the primary healthcare outpatient setting. The cognitive apprenticeship model was used to identify characteristics of the individual learning environments and discusses factors that stimulate learning. Attention was paid to the role of reflection in stimulating learning in the described settings. The paper provided the context in both institutes, described the learning situation and provided an analysis based on the theoretical framework. Based on the analysis of the situations, solutions to problems in the two settings were suggested.

Matched MeSH terms: Learning; Problem-Based Learning
Transformative learning in clinical reasoning: a meta-synthesis in undergraduate primary care medical education

Abdul Rahman NF, Davies N, Suhaimi J, Idris F, Syed Mohamad SN, Park S

Educ Prim Care, 2023 Jul;34(4):211-219.
PMID: 37742228 DOI: 10.1080/14739879.2023.2248070

Clinical reasoning is a vital medical education skill, yet its nuances in undergraduate primary care settings remain debated. This systematic review explores clinical reasoning teaching and learning intricacies within primary care. We redefine clinical reasoning as dynamically assimilating and prioritising synthesised patient, significant other, or healthcare professional information for diagnoses or non-diagnoses. This focused meta-synthesis applies transformative learning theory to primary care clinical reasoning education. A comprehensive analysis of 29 selected studies encompassing various designs made insights into clinical reasoning learning dimensions visible. Primary care placements in varying duration and settings foster diverse instructional methods like bedside teaching, clinical consultations, simulated clinics, virtual case libraries, and more. This review highlights the interplay between disease-oriented and patient-centred orientations in clinical reasoning learning. Transformative learning theory provides an innovative lens, revealing stages of initiation, persistence, time and space, and competence and confidence in students' clinical reasoning evolution. Clinical teachers guide this transformation, adopting roles as fortifiers, connoisseurs, mediators, and monitors. Patient engagement spans passive to active involvement, co-constructing clinical reasoning. The review underscores theoretical underpinnings' significance in shaping clinical reasoning pedagogy, advocating broader diversity. Intentional student guidance amid primary care complexities is vital. Utilising transformative learning, interventions bridging cognitive boundaries enhance meaningful clinical reasoning learning experiences. This study contributes insights for refining pedagogy, encouraging diverse research, and fostering holistic clinical reasoning development.

Matched MeSH terms: Learning
Fulltext Evaluating teachers' pedagogical content knowledge in implementing classroom-based assessment: A case study among esl secondary school teachers in Selangor, Malaysia

Abdul Razak R, Mat Yusoff S, Hai Leng C, Mohamadd Marzaini AF

PLoS One, 2023;18(12):e0293325.
PMID: 38157377 DOI: 10.1371/journal.pone.0293325

The Malaysian Education Blueprint (PPPM) 2013-2025 has spurred significant reforms in the Primary School Standard Curriculum (KSSR) and Secondary School Standard Curriculum (KSSM), particularly concerning classroom-based assessment (CBA). CBA evaluates students' understanding and progress, informs instruction, and enhances the learning outcomes. Teachers with robust pedagogical content knowledge (PCK) are better equipped to design and implement effective CBA strategies that accurately assess students' comprehension and growth, provide personalised feedback, and guide instruction. This study aims to investigate the relationship between PCK and CBA among English as a Second Language (ESL) secondary school teachers in Selangor, Malaysia. A 5-point Likert-scale questionnaire was administered to 338 teachers across 27 regional secondary schools in Selangor. The Covariance-based structural equation modelling (SEM) was used to analyse the data. The findings revealed that the secondary school teachers demonstrated a high level of PCK, with content knowledge (CK) obtaining the highest mean, followed by pedagogical knowledge (PK) and pedagogical content knowledge (PCK). The CBA practices among these teachers were also found to be high. SEM analysis showed a positive association between PK and CBA practices and between PCK and CBA. However, no positive association was observed between CK and CBA practices. In order to enhance teachers' PCK and ensure the effective implementation of CBA, which is crucial for student learning outcomes in Malaysian ESL secondary schools, it is recommended that continuous professional development opportunities be provided, specifically focusing on PCK and CBA.

Matched MeSH terms: Learning*
Fulltext Weak and strong ties and its connection to experts' problem-solving styles in scaffolding students' PBL activities on social media

Abdullah AH, Neo TK, Low JH

F1000Res, 2021;10:1076.
PMID: 35035894 DOI: 10.12688/f1000research.73210.2

Background: Studies have acknowledged that social media enables students to connect with and learn from experts from different ties available in the students' personal learning environment (PLE). Incorporating experts into formal learning activities such as scaffolding problem-solving tasks through social media, allows students to understand how experts solve real-world problems. However, studies that evaluate experts' problem-solving styles on social media in relation to the tie strength of the experts with the students are scarce in the extant literature. This study aimed to explore the problem-solving styles that the experts portrayed based on their ties with the students in problem-based learning (PBL) on Facebook. Methods: This study employed a simultaneous within-subject experimental design which was conducted in three closed Facebook groups with 12 final year management students, six business experts, and one instructor as the participants. The experts were invited by the students from the weak and strong ties in their PLE. Hinging on the Strength of Weak Ties Theory (Granovetter, 1973) and problem-solving styles (Selby et al., 2004), this study employed thematic analysis using the ATLAS.ti qualitative data analysis software to map the experts' comments on Facebook. Results: The experts from strong and weak ties who had a prior relationship with the students showed people preference style by being more sensitive to the students' learning needs and demonstrating firmer scaffolding compared to the weak ties' experts who had no prior relationship with the students. Regardless of the types of ties, all experts applied all manner of processing information and orientation to change but the degree of its applications are correlated with the working experience of the experts. Conclusion: The use of weak or strong ties benefited the students as it expedited their problem-solving tasks since the experts have unique expertise to offer depending on the problem-solving styles that they exhibited.

Matched MeSH terms: Problem-Based Learning
The Eight Stages of Trust and "Amanah" in Medicine and the Dunning-Kruger effect

Abdullah JM

Malays J Med Sci, 2014 Jul;21(4):1-3.
PMID: 25977614

The Dunning-Kruger effect is a cognitive bias in which unskilled people make poor decisions and reach erroneous conclusions, but their incompetence denies them the metacognitive ability to recognise their mistakes. These unskilled people therefore suffer from illusory superiority, rating their ability as above average, much higher than it actually is, while the highly skilled underrate their own abilities, suffering from illusory inferiority.

Matched MeSH terms: Learning
Fulltext Feature Selection for High-Dimensional and Imbalanced Biomedical Data Based on Robust Correlation Based Redundancy and Binary Grasshopper Optimization Algorithm

Abdulrauf Sharifai G, Zainol Z

Genes (Basel), 2020 06 27;11(7).
PMID: 32605144 DOI: 10.3390/genes11070717

The training machine learning algorithm from an imbalanced data set is an inherently challenging task. It becomes more demanding with limited samples but with a massive number of features (high dimensionality). The high dimensional and imbalanced data set has posed severe challenges in many real-world applications, such as biomedical data sets. Numerous researchers investigated either imbalanced class or high dimensional data sets and came up with various methods. Nonetheless, few approaches reported in the literature have addressed the intersection of the high dimensional and imbalanced class problem due to their complicated interactions. Lately, feature selection has become a well-known technique that has been used to overcome this problem by selecting discriminative features that represent minority and majority class. This paper proposes a new method called Robust Correlation Based Redundancy and Binary Grasshopper Optimization Algorithm (rCBR-BGOA); rCBR-BGOA has employed an ensemble of multi-filters coupled with the Correlation-Based Redundancy method to select optimal feature subsets. A binary Grasshopper optimisation algorithm (BGOA) is used to construct the feature selection process as an optimisation problem to select the best (near-optimal) combination of features from the majority and minority class. The obtained results, supported by the proper statistical analysis, indicate that rCBR-BGOA can improve the classification performance for high dimensional and imbalanced datasets in terms of G-mean and the Area Under the Curve (AUC) performance metrics.

Matched MeSH terms: Machine Learning*
Self-directed learning

Abraham RR, Upadhya S, Ramnarayan K

Adv Physiol Educ, 2005 Jun;29(2):135-6.
PMID: 15905163
Matched MeSH terms: Learning*
Fulltext Classification of Suncus murinus species complex (Soricidae: Crocidurinae) in Peninsular Malaysia using image analysis and machine learning approaches

Abu A, Leow LK, Ramli R, Omar H

BMC Bioinformatics, 2016 Dec 22;17(Suppl 19):505.
PMID: 28155645 DOI: 10.1186/s12859-016-1362-5

BACKGROUND: Taxonomists frequently identify specimen from various populations based on the morphological characteristics and molecular data. This study looks into another invasive process in identification of house shrew (Suncus murinus) using image analysis and machine learning approaches. Thus, an automated identification system is developed to assist and simplify this task. In this study, seven descriptors namely area, convex area, major axis length, minor axis length, perimeter, equivalent diameter and extent which are based on the shape are used as features to represent digital image of skull that consists of dorsal, lateral and jaw views for each specimen. An Artificial Neural Network (ANN) is used as classifier to classify the skulls of S. murinus based on region (northern and southern populations of Peninsular Malaysia) and sex (adult male and female). Thus, specimen classification using Training data set and identification using Testing data set were performed through two stages of ANNs.
RESULTS: At present, the classifier used has achieved an accuracy of 100% based on skulls' views. Classification and identification to regions and sexes have also attained 72.5%, 87.5% and 80.0% of accuracy for dorsal, lateral, and jaw views, respectively. This results show that the shape characteristic features used are substantial because they can differentiate the specimens based on regions and sexes up to the accuracy of 80% and above. Finally, an application was developed and can be used for the scientific community.
CONCLUSIONS: This automated system demonstrates the practicability of using computer-assisted systems in providing interesting alternative approach for quick and easy identification of unknown species.

Matched MeSH terms: Machine Learning*

Filters

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

External Links