MyMedR

Displaying publications 81 - 100 of 428 in total

Abstract:

Sort:

Fulltext Chromatographic fingerprint and Chemometric approach for quality control of Tongkat Ali (Eurycoma Longifolia)

Nor Nasriah Zaini, Mardiana Saaid, Hafizan Juahir, Rozita Osman

Pertanika Journal of Science & Technology, 2017;25(103):345-354.
MyJurnal

Tongkat Ali (Eurycoma longifolia) is one of the most popular tropical herbal plants as it is believed to enhance virility and sexual prowess. This study looked examined chromatographic fingerprint of Tongkat Ali roots and its products generated using online solid phase-extraction liquid chromatography (SPE-LC) combined with chemometric approaches. The aim was to determine its quality. Pressurised liquid extraction (PLE) technique was used prior to online SPE-LC using polystyrene divinyl benzene (PSDVB) and C18 columns. Seventeen Tongkat Ali roots and 10 products (capsules) were analysed. Chromatographic dataset was subjected to chemometric techniques, namely cluster analysis (CA), discriminant analysis (DA) and principal component analysis (PCA) using 37 selected peaks. The samples were grouped into three clusters based on their quality. The PCA resulted in 11 latent factors describing 90.8% of the whole variance. Pattern matching analysis showed no significant difference (p>0.05) between the roots and products within the same CA grouping. The findings showed the combination of chromatographic fingerprint and chemometric techniques provided comprehensive evaluation for efficient quality control of Tongkat Ali formulation.

Matched MeSH terms: Cluster Analysis
Fulltext Automatic Annotation of Unlabeled Data from Smartphone-Based Motion and Location Sensors

Pius Owoh N, Mahinderjit Singh M, Zaaba ZF

Sensors (Basel), 2018 Jul 03;18(7).
PMID: 29970823 DOI: 10.3390/s18072134

Automatic data annotation eliminates most of the challenges we faced due to the manual methods of annotating sensor data. It significantly improves users’ experience during sensing activities since their active involvement in the labeling process is reduced. An unsupervised learning technique such as clustering can be used to automatically annotate sensor data. However, the lingering issue with clustering is the validation of generated clusters. In this paper, we adopted the k-means clustering algorithm for annotating unlabeled sensor data for the purpose of detecting sensitive location information of mobile crowd sensing users. Furthermore, we proposed a cluster validation index for the k-means algorithm, which is based on Multiple Pair-Frequency. Thereafter, we trained three classifiers (Support Vector Machine, K-Nearest Neighbor, and Naïve Bayes) using cluster labels generated from the k-means clustering algorithm. The accuracy, precision, and recall of these classifiers were evaluated during the classification of “non-sensitive” and “sensitive” data from motion and location sensors. Very high accuracy scores were recorded from Support Vector Machine and K-Nearest Neighbor classifiers while a fairly high accuracy score was recorded from the Naïve Bayes classifier. With the hybridized machine learning (unsupervised and supervised) technique presented in this paper, unlabeled sensor data was automatically annotated and then classified.

Matched MeSH terms: Cluster Analysis
Fulltext A predictive method for hepatitis disease diagnosis using ensembles of neuro-fuzzy technique

Nilashi M, Ahmadi H, Shahmoradi L, Ibrahim O, Akbari E

J Infect Public Health, 2018 10 04;12(1):13-20.
PMID: 30293875 DOI: 10.1016/j.jiph.2018.09.009

BACKGROUND: Hepatitis is an inflammation of the liver, most commonly caused by a viral infection. Supervised data mining techniques have been successful in hepatitis disease diagnosis through a set of datasets. Many methods have been developed by the aids of data mining techniques for hepatitis disease diagnosis. The majority of these methods are developed by single learning techniques. In addition, these methods do not support the ensemble learning of the data. Combining the outputs of several predictors can result in improved accuracy in classification problems. This study aims to propose an accurate method for the hepatitis disease diagnosis by taking the advantages of ensemble learning.
METHODS: We use Non-linear Iterative Partial Least Squares to perform the data dimensionality reduction, Self-Organizing Map technique for clustering task and ensembles of Neuro-Fuzzy Inference System for predicting the hepatitis disease. We also use decision trees for the selection of most important features in the experimental dataset. We test our method on a real-world dataset and present our results in comparison with the latest results of previous studies.
RESULTS: The results of our analyses on the dataset demonstrated that our method performance is superior to the Neural Network, ANFIS, K-Nearest Neighbors and Support Vector Machine.
CONCLUSIONS: The method has potential to be used as an intelligent learning system for hepatitis disease diagnosis in the healthcare.

Matched MeSH terms: Cluster Analysis
Impact of DNA extraction methods on the observed microbial communities from the intestinal flora of the penaeid shrimp Litopenaeus vannamei

Jiang B, Sun J, Lv A, Hu X, Shi H, Sung Y, et al.

FEMS Microbiol Lett, 2019 05 01;366(9).
PMID: 31074797 DOI: 10.1093/femsle/fnz099

Two DNA extraction methods, the Zirmil-beating cell disruption method (ZBC) and the QIAamp fast DNA stool mini kit (QIA), were used to extract DNA from the intestinal flora of the penaeid shrimp Litopenaeus vannamei, and their microbial communities were analyzed using 16S rDNA high-throughput sequencing. Results were obtained in terms of the number of reads, alpha diversity indexes, beta diversity indexes and taxonomic composition. The alpha diversity indexes of the community, according to the ZBC method, were higher than those according to the QIA method. Furthermore, results from the three samples using the ZBC method were less consistent than those where the QIA method was used. Further, using the latter method led to substantive clustering. It is suggested that the QIA method is more stable and repeatable than the ZBC method. Although the two extraction methods shared the major abundant microflora based on 16S rDNA high-throughput sequencing, bias associated with diversity analysis indexes and certain species was observed.

Matched MeSH terms: Cluster Analysis
Novel, energy efficient and green cloud point extraction: technology and applications in food processing

Arya SS, Kaimal AM, Chib M, Sonawane SK, Show PL

J Food Sci Technol, 2019 Feb;56(2):524-534.
PMID: 30906010 DOI: 10.1007/s13197-018-3546-7

Recently, a novel technique for extraction of functional thermally sensitive bioactive components from food has been developed due to its green efficacy (no toxic chemicals) and cost effectiveness. Cloud point extraction (CPE) is one of the such best alternative techniques that can be used for extraction of wide range of organic and inorganic components using green surfactants. It is a simple, rapid and inexpensive extraction technique which involves clustering of non-ionic surfactant monomers to form a hydrophobic core (micelle), which then entraps the hydrophobic bioactive compounds within it. CPE can be applied for extraction of bioactives from food processing waste as well as separation and purification of proteins. Besides that, research has received special attention on sample preparation for analysis of food constituents in the last decade. The scope of CPE is very vast in these sectors because of the advantages of CPE over other methods. This review deals with significance of CPE method and their potential green applications in food processing.

Matched MeSH terms: Cluster Analysis
Fulltext Genetic assessment of the internal transcribed spacer region (ITS1.2) in Mangifera indica L. landraces

Fazeli-Nasab B, Sayyed RZ, Farsi M, Ansari S, El-Enshasy HA

Physiol Mol Biol Plants, 2020 Jan;26(1):107-117.
PMID: 32158124 DOI: 10.1007/s12298-019-00732-x

Mango (Mangifera indica) is one of the most important tropical fruits in the world. Twenty-two genotypes of native mangoes from different regions of southern Iran (Hormozgan and Kerman) were collected and analyzed for the ribosomal genes. GC content was found to be 55.5%. Fu and Li's D* test statistic (0.437), Fu and Li's F* test statistic (0.500) and Tajima's D (1.801) were positive and nonsignificant. A total of 769 positions were identified (319 with insertion or deletion including 250 polymorphic and 69 monomorphic loci; 450 loci without any insertion or deletion including 35 Singletons and 22 haplotypes). Nucleotide diversity of 0.309 and a high genetic differentiation including Chi square of 79.8; P value of 0.3605 and df value of 76 was observed among mango genotypes studied. The numerical value of the ratio dN/dS (0.45) indicated a pure selection in the examined gene and the absence of any key changes. Cluster analysis differentiated the mango used in this research (M. indica L.) into two genotypes but could not differentiate their geographical locations. The results of this study indicated that a high genetic distance exists between HajiGholam (Manojan) and Arbabi (Rodan) genotypes and showed higher genetic diversity in mango of Rodan region. Results of present study suggested that for successful breeding, the genotypes of Rodan region mango especially Arbabi mango can be used as a gene donor and ITS can be a suitable tool for genetic evaluations of inter and intra species.

Matched MeSH terms: Cluster Analysis
Fulltext birgHPC: creating instant computing clusters for bioinformatics and molecular dynamics

Chew TH, Joyce-Tan KH, Akma F, Shamsir MS

Bioinformatics, 2011 May 1;27(9):1320-1.
PMID: 21398666 DOI: 10.1093/bioinformatics/btr109

birgHPC, a bootable Linux Live CD has been developed to create high-performance clusters for bioinformatics and molecular dynamics studies using any Local Area Network (LAN)-networked computers. birgHPC features automated hardware and slots detection as well as provides a simple job submission interface. The latest versions of GROMACS, NAMD, mpiBLAST and ClustalW-MPI can be run in parallel by simply booting the birgHPC CD or flash drive from the head node, which immediately positions the rest of the PCs on the network as computing nodes. Thus, a temporary, affordable, scalable and high-performance computing environment can be built by non-computing-based researchers using low-cost commodity hardware.

Matched MeSH terms: Cluster Analysis
Effect of Milling Time on the Microstructure, Physical and Mechanical Properties of Al-Al₂O₃ Nanocomposite Synthesized by Ball Milling and Powder Metallurgy

Toozandehjani M, Matori KA, Ostovan F, Abdul Aziz S, Mamat MS

Materials (Basel), 2017 Oct 26;10(11).
PMID: 29072632 DOI: 10.3390/ma10111232

The effect of milling time on the morphology, microstructure, physical and mechanical properties of pure Al-5 wt % Al₂O₃ (Al-5Al₂O₃) has been investigated. Al-5Al₂O₃ nanocomposites were fabricated using ball milling in a powder metallurgy route. The increase in the milling time resulted in the homogenous dispersion of 5 wt % Al₂O₃ nanoparticles, the reduction of particle clustering, and the reduction of distances between the composite particles. The significant grain refining during milling was revealed which showed as a reduction of particle size resulting from longer milling time. X-Ray diffraction (XRD) analysis of the nanocomposite powders also showed that designated ball milling contributes to the crystalline refining and accumulation of internal stress due to induced severe plastic deformation of the particles. It can be argued that these morphological and microstructural variations of nanocomposite powders induced by designated ball milling time was found to contribute to an improvement in the density, densification, micro-hardness (HV), nano-hardness (HN), and Young's modulus (E) of Al-5Al₂O₃ nanocomposites. HV, HN, and E values of nanocomposites were increased by ~48%, 46%, and 40%, after 12 h of milling, respectively.

Matched MeSH terms: Cluster Analysis
Fulltext Genotyping of Salmonella strains isolated from ducks, their rearing and processing environments in Penang, Malaysia, using RAPD

Adzitey F, Ali GR, Huda N, Ahmad R

3 Biotech, 2013 Dec;3(6):521-527.
PMID: 28324423 DOI: 10.1007/s13205-013-0115-7

Salmonella species are important foodborne pathogens that can cause illness and death in humans. The objective of this study was to determine the genetic relatedness of 115 Salmonella strains isolated from ducks and their environment using random amplified polymorphic deoxyribonucleic acid (RAPD). The analysis of Salmonella strains by RAPD produced DNA fingerprints of different sizes for differentiation purposes, and cluster analysis at a coefficient of 0.85 grouped the Salmonella strains into various clusters and singletons. S. Typhimurium were grouped into nine clusters and ten singletons, S. Hadar were grouped into seven clusters and nine singletons, S. Enteritidis were grouped into four clusters and five singletons, S. Braenderup were grouped into five clusters and four singletons, S. Albany were grouped into two clusters and seven singletons, and S. Derby were grouped into two clusters and four singletons at a coefficient of 0.85 with discriminatory index (D) ranging from 0.879 to 0.957. With the exception of S. Typhimurium strains which were grouped into three major groups (genotypes) by RAPD analysis, the rest were grouped into two major genotypes. RAPD was a useful genotyping tool for determining the genetic relatedness of the duck Salmonella strains. Comparison of the genetic relatedness among foodborne pathogens and their sources of isolation are important to trace their source and possibly the source of human infection.

Matched MeSH terms: Cluster Analysis
Fulltext Genetic Diversity and Clustering of the Rhoptry Associated Protein-1 of Plasmodium knowlesi from Peninsular Malaysia and Malaysian Borneo

Azlan UW, Lau YL, Fong MY

Korean J Parasitol, 2022 Dec;60(6):393-400.
PMID: 36588415 DOI: 10.3347/kjp.2022.60.6.393

Human infection with simian malaria Plasmodium knowlesi is a cause for concern in Southeast Asian countries, especially in Malaysia. A previous study on Peninsular Malaysia P. knowlesi rhoptry associated protein-1 (PkRAP1) gene has discovered the existence of dimorphism. In this study, genetic analysis of PkRAP1 in a larger number of P. knowlesi samples from Malaysian Borneo was conducted. The PkRAP1 of these P. knowlesi isolates was PCR-amplified and sequenced. The newly obtained PkRAP1 gene sequences (n = 34) were combined with those from the previous study (n = 26) and analysed for polymorphism and natural selection. Sequence analysis revealed a higher genetic diversity of PkRAP1 compared to the previous study. Exon II of the gene had higher diversity (π = 0.0172) than exon I (π = 0.0128). The diversity of the total coding region (π = 0.0167) was much higher than those of RAP1 orthologues such as PfRAP-1 (π = 0.0041) and PvRAP1 (π = 0.00088). Z-test results indicated that the gene was under purifying selection. Phylogenetic tree and haplotype network showed distinct clustering of Peninsular Malaysia and Malaysian Borneo PkRAP1 haplotypes. This geographical-based clustering of PkRAP1 haplotypes provides further evidence of the dimorphism of the gene and possible existence of 2 distinct P. knowlesi lineages in Malaysia.

Matched MeSH terms: Cluster Analysis
Fulltext Machine Learning-Based Ensemble Classifiers for Anomaly Handling in Smart Home Energy Consumption Data

Kasaraneni PP, Venkata Pavan Kumar Y, Moganti GLK, Kannan R

Sensors (Basel), 2022 Nov 30;22(23).
PMID: 36502025 DOI: 10.3390/s22239323

Addressing data anomalies (e.g., garbage data, outliers, redundant data, and missing data) plays a vital role in performing accurate analytics (billing, forecasting, load profiling, etc.) on smart homes' energy consumption data. From the literature, it has been identified that the data imputation with machine learning (ML)-based single-classifier approaches are used to address data quality issues. However, these approaches are not effective to address the hidden issues of smart home energy consumption data due to the presence of a variety of anomalies. Hence, this paper proposes ML-based ensemble classifiers using random forest (RF), support vector machine (SVM), decision tree (DT), naive Bayes, K-nearest neighbor, and neural networks to handle all the possible anomalies in smart home energy consumption data. The proposed approach initially identifies all anomalies and removes them, and then imputes this removed/missing information. The entire implementation consists of four parts. Part 1 presents anomaly detection and removal, part 2 presents data imputation, part 3 presents single-classifier approaches, and part 4 presents ensemble classifiers approaches. To assess the classifiers' performance, various metrics, namely, accuracy, precision, recall/sensitivity, specificity, and F1 score are computed. From these metrics, it is identified that the ensemble classifier "RF+SVM+DT" has shown superior performance over the conventional single classifiers as well the other ensemble classifiers for anomaly handling.

Matched MeSH terms: Cluster Analysis
Fulltext Development of an effective clustering algorithm for older fallers

Goh CH, Wong KK, Tan MP, Ng SC, Chuah YD, Kwan BH

PLoS One, 2022;17(11):e0277966.
PMID: 36441703 DOI: 10.1371/journal.pone.0277966

Falls are common and often lead to serious physical and psychological consequences for older persons. The occurrence of falls are usually attributed to the interaction between multiple risk factors. The clinical evaluation of falls risks is time-consuming as a result, hence limiting its availability. The purpose of this study was, therefore, to develop a clustering-based algorithm to determine falls risk. Data from the Malaysian Elders Longitudinal Research (MELoR), comprising 1411 subjects aged ≥55 years, were utilized. The proposed algorithm was developed through the stages of: data pre-processing, feature identification and extraction with either t-Distributed Stochastic Neighbour Embedding (t-SNE) or principal component analysis (PCA)), clustering (K-means clustering, Hierarchical clustering, and Fuzzy C-means clustering) and characteristics interpretation with statistical analysis. A total of 1279 subjects and 9 variables were selected for clustering after the data pre-possessing stage. Using feature extraction with the t-SNE and the K-means clustering algorithm, subjects were clustered into low, intermediate A, intermediate B and high fall risk groups which corresponded with fall occurrence of 13%, 19%, 21% and 31% respectively. Slower gait, poorer balance, weaker muscle strength, presence of cardiovascular disorder, poorer cognitive performance, and advancing age were the key variables identified. The proposed fall risk clustering algorithm grouped the subjects according to features. Such a tool could serve as a case identification or clinical decision support tool for clinical practice to enhance access to falls prevention efforts.

Matched MeSH terms: Cluster Analysis
Short-term residual characteristics of ambient-cured green geopolymer mortar exposed to elevated temperatures

Zakka WP, Lim NHAS, Khun MC, Samadi M, Aluko O, Odubela C

Environ Sci Pollut Res Int, 2024 Apr;31(17):25129-25146.
PMID: 38468004 DOI: 10.1007/s11356-024-32786-0

Every structure might be exposed to fire at some point in its lifecycle. The ability of geopolymer composites to withstand the effects of fire damage early before it is put out is of great importance. This study examined the effects of fire on geopolymer composite samples made with high-calcium fly ash and alkaline solution synthesised from waste banana peduncle and silica fume. A ratio of 0.30, 0.35, and 0.4 was used in the study for the alkaline solution to fly ash. Also used were ratios of 0.5, 0.75, and 1 for silica oxide (silica fume) to potassium hydroxide ratio. The strength loss, residual compressive strength, percentage strength loss, relative residual compressive strength, ultrasonic pulse velocity, and microstructural properties of the thirteen mortar mixes were measured after exposure to temperatures of 200, 400, 600, and 800 °C for 1 h, respectively. The results reveal that geopolymer samples exposed to elevated temperatures showed great dimensional stability with no visible surface cracks. There was a colour transition from dark grey to whitish brown for the green geopolymer mortar and brown to whitish brown for the control sample. As the temperature rose, weight loss became more pronounced, with 800 °C producing the most significant weight reduction. The optimum mixes had a residual compressive strength of 25.02 MPa after being exposed to 200 °C, 18.72 MPa after being exposed to 400 °C, 14.04 MPa after being exposed to 600 °C, and 7.41 MPa after being exposed to 800 °C. The control had a residual compressive strength of 8.45 MPa after being exposed to 200 °C, 6.67 MPa after being exposed to 400 °C, 3.16 MPa after being exposed to 600 °C, and 2.23 MPa after being exposed to 800 °C. The relative residual compressive strength decreases for green geopolymer mortar are most significant at 600 and 800 °C, with an average decrease of 0.47 and 0.30, respectively. The microstructure of the samples revealed various phase changes and new product formations as the temperature increased.

Matched MeSH terms: Cluster Analysis
Fulltext Spatial clustering of colorectal cancer in Malaysia

Syed Soffian SS, Mohammed Nawi A, Hod R, Abdul Maulud KN, Mohd Azmi AT, Hasim Hashim MH, et al.

Geospat Health, 2023 May 25;18(1).
PMID: 37246545 DOI: 10.4081/gh.2023.1158

INTRODUCTION: The rise in colorectal cancer (CRC) incidence becomes a global concern. As geographical variations in the CRC incidence suggests the role of area-level determinants, the current study was designed to identify the spatial distribution pattern of CRC at the neighbourhood level in Malaysia.
METHOD: Newly diagnosed CRC cases between 2010 and 2016 in Malaysia were identified from the National Cancer Registry. Residential addresses were geocoded. Clustering analysis was subsequently performed to examine the spatial dependence between CRC cases. Differences in socio-demographic characteristics of individuals between the clusters were also compared. Identified clusters were categorized into urban and semi-rural areas based on the population background.
RESULT: Most of the 18 405 individuals included in the study were male (56%), aged between 60 and 69 years (30.3%) and only presented for care at stages 3 or 4 of the disease (71.3%). The states shown to have CRC clusters were Kedah, Penang, Perak, Selangor, Kuala Lumpur, Melaka, Johor, Kelantan, and Sarawak. The spatial autocorrelation detected a significant clustering pattern (Moran's Index 0.244, p< 0.01, Z score >2.58). CRC clusters in Penang, Selangor, Kuala Lumpur, Melaka, Johor, and Sarawak were in urbanized areas, while those in Kedah, Perak and Kelantan were in semi-rural areas.
CONCLUSION: The presence of several clusters in urbanized and semi-rural areas implied the role of ecological determinants at the neighbourhood level in Malaysia. Such findings could be used to guide the policymakers in resource allocation and cancer control.

Matched MeSH terms: Cluster Analysis
Fulltext Interactions between all pairs of neighboring trees in 16 forests worldwide reveal details of unique ecological processes in each forest, and provide windows into their evolutionary histories

Wills C, Wang B, Fang S, Wang Y, Jin Y, Lutz J, et al.

PLoS Comput Biol, 2021 Apr;17(4):e1008853.
PMID: 33914731 DOI: 10.1371/journal.pcbi.1008853

When Darwin visited the Galapagos archipelago, he observed that, in spite of the islands' physical similarity, members of species that had dispersed to them recently were beginning to diverge from each other. He postulated that these divergences must have resulted primarily from interactions with sets of other species that had also diverged across these otherwise similar islands. By extrapolation, if Darwin is correct, such complex interactions must be driving species divergences across all ecosystems. However, many current general ecological theories that predict observed distributions of species in ecosystems do not take the details of between-species interactions into account. Here we quantify, in sixteen forest diversity plots (FDPs) worldwide, highly significant negative density-dependent (NDD) components of both conspecific and heterospecific between-tree interactions that affect the trees' distributions, growth, recruitment, and mortality. These interactions decline smoothly in significance with increasing physical distance between trees. They also tend to decline in significance with increasing phylogenetic distance between the trees, but each FDP exhibits its own unique pattern of exceptions to this overall decline. Unique patterns of between-species interactions in ecosystems, of the general type that Darwin postulated, are likely to have contributed to the exceptions. We test the power of our null-model method by using a deliberately modified data set, and show that the method easily identifies the modifications. We examine how some of the exceptions, at the Wind River (USA) FDP, reveal new details of a known allelopathic effect of one of the Wind River gymnosperm species. Finally, we explore how similar analyses can be used to investigate details of many types of interactions in these complex ecosystems, and can provide clues to the evolution of these interactions.

Matched MeSH terms: Cluster Analysis
A hybrid ensemble approach to accelerate the classification accuracy for predicting malnutrition among under-five children in sub-Saharan African countries

Khan MNA, Yunus RM

Nutrition, 2023 Apr;108:111947.
PMID: 36641887 DOI: 10.1016/j.nut.2022.111947

BACKGROUND: The proper intake of nutrients is essential to the growth and maturation of youngsters. In sub-Saharan Africa, 1 in 7 children dies before age 5 y, and more than a third of these deaths are attributed to malnutrition. The main purpose of this study was to develop a majority voting-based hybrid ensemble (MVBHE) learning model to accelerate the prediction accuracy of malnutrition data of under-five children in sub-Saharan Africa.
METHODS: This study used available under-five nutritional secondary data from the Demographic and Health Surveys performed in sub-Saharan African countries. The research used bagging, boosting, and voting algorithms, such as random forest, decision tree, eXtreme Gradient Boosting, and k-nearest neighbors machine learning methods, to generate the MVBHE model.
RESULTS: We evaluated the model performances in contrast to each other using different measures, including accuracy, precision, recall, and the F1 score. The results of the experiment showed that the MVBHE model (96%) was better at predicting malnutrition than the random forest (81%), decision tree (60%), eXtreme Gradient Boosting (79%), and k-nearest neighbors (74%).
CONCLUSIONS: The random forest algorithm demonstrated the highest prediction accuracy (81%) compared with the decision tree, eXtreme Gradient Boosting, and k-nearest neighbors algorithms. The accuracy was then enhanced to 96% using the MVBHE model. The MVBHE model is recommended by the present study as the best way to predict malnutrition in under-five children.

Matched MeSH terms: Cluster Analysis
Segmentation Approach Towards Phase-Contrast Microscopic Images of Activated Sludge to Monitor the Wastewater Treatment

Khan MB, Nisar H, Ng CA, Yeap KH, Lai KC

Microsc Microanal, 2017 12;23(6):1130-1142.
PMID: 29212566 DOI: 10.1017/S1431927617012673

Image processing and analysis is an effective tool for monitoring and fault diagnosis of activated sludge (AS) wastewater treatment plants. The AS image comprise of flocs (microbial aggregates) and filamentous bacteria. In this paper, nine different approaches are proposed for image segmentation of phase-contrast microscopic (PCM) images of AS samples. The proposed strategies are assessed for their effectiveness from the perspective of microscopic artifacts associated with PCM. The first approach uses an algorithm that is based on the idea that different color space representation of images other than red-green-blue may have better contrast. The second uses an edge detection approach. The third strategy, employs a clustering algorithm for the segmentation and the fourth applies local adaptive thresholding. The fifth technique is based on texture-based segmentation and the sixth uses watershed algorithm. The seventh adopts a split-and-merge approach. The eighth employs Kittler's thresholding. Finally, the ninth uses a top-hat and bottom-hat filtering-based technique. The approaches are assessed, and analyzed critically with reference to the artifacts of PCM. Gold approximations of ground truth images are prepared to assess the segmentations. Overall, the edge detection-based approach exhibits the best results in terms of accuracy, and the texture-based algorithm in terms of false negative ratio. The respective scenarios are explained for suitability of edge detection and texture-based algorithms.

Matched MeSH terms: Cluster Analysis
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: Cluster Analysis
Fulltext The impact of preschool children's physical fitness evaluation under self organizing maps neural network

Wang L, Zou W, Wang Y, Koh D, Munsif Bin Wan Pa WA, Gao R

Sci Rep, 2025 Jan 09;15(1):1461.
PMID: 39789314 DOI: 10.1038/s41598-025-85725-5

To improve the scientific accuracy and precision of children's physical fitness evaluations, this study proposes a model that combines self-organizing maps (SOM) neural networks with cluster analysis. Existing evaluation methods often rely on traditional, single statistical analyses, which struggle to handle the complexity of high-dimensional, nonlinear data, resulting in a lack of precision and personalization. This study uses the SOM neural network to reduce the dimensionality of high-dimensional health data. Moreover, it integrates cluster analysis to categorize and analyze key physical fitness attributes, such as strength, flexibility, and endurance. Experimental results show that the proposed optimized model outperforms comparison models such as T-distributed stochastic neighbor embedding, density peak clustering, and deep embedded clustering in terms of performance. The accuracy for the strength dimension reaches 0.934, the F1 score is 0.862, and the area under the curve of receiver operating characteristic is 0.944. The silhouette coefficients for cluster analysis in strength, flexibility, and endurance dimensions are 0.655, 0.559, and 0.601, respectively, demonstrating good intra-class and inter-class distances. The proposed model enhances the comprehensive analysis of children's physical fitness and provides a scientific basis for personalized health interventions, making an important contribution to research in this field.

Matched MeSH terms: Cluster Analysis
Fulltext An Efficient Optimization Method for Solving Unsupervised Data Classification Problems

Shabanzadeh P, Yusof R

Comput Math Methods Med, 2015;2015:802754.
PMID: 26336509 DOI: 10.1155/2015/802754

Unsupervised data classification (or clustering) analysis is one of the most useful tools and a descriptive task in data mining that seeks to classify homogeneous groups of objects based on similarity and is used in many medical disciplines and various applications. In general, there is no single algorithm that is suitable for all types of data, conditions, and applications. Each algorithm has its own advantages, limitations, and deficiencies. Hence, research for novel and effective approaches for unsupervised data classification is still active. In this paper a heuristic algorithm, Biogeography-Based Optimization (BBO) algorithm, was adapted for data clustering problems by modifying the main operators of BBO algorithm, which is inspired from the natural biogeography distribution of different species. Similar to other population-based algorithms, BBO algorithm starts with an initial population of candidate solutions to an optimization problem and an objective function that is calculated for them. To evaluate the performance of the proposed algorithm assessment was carried on six medical and real life datasets and was compared with eight well known and recent unsupervised data classification algorithms. Numerical results demonstrate that the proposed evolutionary optimization algorithm is efficient for unsupervised data classification.

Matched MeSH terms: Cluster Analysis*

Filters

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

External Links