39506 research outputs found
Sort by
Navigating the microarray landscape: a comprehensive review of feature selection techniques and their applications
No full textThis review systematically summarizes recent advances in microarray feature selection techniques and their applications in biomedical research. It addresses
the challenges posed by the high dimensionality and noise of microarray data, aiming to integrate the strengths and limitations of various methods while exploring their applicability across different scenarios. By identifying
gaps in current research, highlighting underexplored areas, and proposing clear directions for future studies, this review seeks to inspire academics to develop novel techniques and applications. Furthermore, it provides a
comprehensive evaluation of feature selection methods, offering both a theoretical foundation and practical guidance to help researchers select the
most suitable approaches for their specific research questions. Emphasizing the importance of interdisciplinary collaboration, the study underscores the potential
of feature selection in transformative applications such as personalized medicine, cancer diagnosis, and drug discovery. Through this review, not only does it provide in-depth theoretical support for the academic community, but also
practical guidance for the practical field, which significantly contributes to the overall improvement of microarray data analysis technology
Ensemble Filter Based Feature Selection Technique for Classification of Human Activity Recognition
No full textThrough the advancement of wearable sensors, wireless communication, and machine learning techniques,
Assistive Technologies (AT) which endorse autonomous, active, and healthy lifestyles are emerging in recent years. Among these advances, Human Activity Recognition (HAR) is one of the most innovative means to support or monitor human
activities. However, misclassifications such as intra-class variation and inter-class overlap in similar activities degrade classification accuracy in HAR. To improve the recognition of daily human activities, handcrafted features of time-domain and frequency-domain are combined. However, several extracted features may not be significant in describing the activities. Therefore, this research aims to propose a feature selection technique for optimal human activities recognition. The methodology proposed for this research is the Ensemble Filter (Relief-F and mRMR) to select the most relevant and less redundant features. Although a filter feature ranking approach is commonly used in related studies, most works fail to consider the threshold limit to exclude unnecessary and redundant features. An ensemble Random Forest (RF) was used as
the base classifier to evaluate the performance of the hybrid algorithm. The results demonstrate that the proposed ensemble filter selection was beneficial in reducing the total number of features while improving overall classification accuracy
Conveyance Properties of Subsurface Stormwater Module
No full textSubsurface stormwater module is one of the components of a sustainable drainage system as recommended by Urban Stormwater Management Manual for Malaysia. Existing subsurface stormwater module in the literature are either suited for storage (higher roughness) or to convey flow (lower roughness). The current study was conducted to evaluate the conveyance properties for a new stormwater module design that is suited for both storage or conveyance purposes. The experiment was set up in the laboratory using a rectangular flume to determine the conveyance capability in terms of the flow retardation and roughness coefficient Manning’s n value. Results from the experiment have shown that installation of the new stormwater module design can cause reduction in the mean discharge between 2.50% to 9.09%. The Manning’s n values were found to range between 0.027 and 0.064 which falls within the mid-range value of existing literature. This implies the suitability of the new stormwater module design for both detention and subsurface conveyance purposes
POTENTIAL SKIN CANCER CHEMOPREVENTIVE EFFECTS OF TERPENOID-RICH CANARIUM ODONTOPHYLLUM (TRCO) LEAF EXTRACT IN UVB-IRRADIATED HUMAN KERATINOCYTES (HaCaT)
No full textSkin cancer is a prevalent form of cancer, primarily driven by the harmful effects of ultraviolet-B (UVB) rays from the sun. Cancer chemoprevention seeks to prevent cancer development in the ongoing battle against the disease. Canarium odontophyllum Miq., recognised as “dabai” is a native plant found in Sarawak, Malaysia. Our study investigated the chemopreventive activity of the terpenoid-rich extract of C. odontophyllum Miq. leaves (TRCO) in skin cancer model in vitro. The terpenoid profiling was done using gas chromatography-mass spectrometry (GC-MS). A skin cancer model using human keratinocytes (HaCaT) was used (induced with 30 mJ/cm2 UVB for 6 passages and pretreated with 500 and 1000 μg/mL TRCO). Results demonstrated that the extract was rich in terpenoids, particularly phytol and spathulenol. Pre-treatment with TRCO significantly increased (p < 0.05) the level of tumour protein p53 (TP53), reduced proliferative protein KI-67 (KI67) and vascular endothelial growth factor (VEGF) compared to the UVB-only group. The abundance of terpenoids in TRCO functioned as potent exogenous antioxidants, countering free radicals, reducing inflammation and minimising cell and tissue damage. TRCO exhibited promising chemopreventive activity and held great potential as a chemopreventive agent against UVB-induced skin cancer by promoting cell repair and suppressing proliferation and angiogenesis levels. In conclusion, the findings may facilitate the exploitation of the endemic C. odontophyllum Miq. of Sarawak as a possible cancer chemoprevention agent
A Cost-Effective and Efficient DC Converter Driver Circuit for Photovoltaic Applications using Timer 555 Control Circuit
Get PDFThis paper presents a cost-effective and efficient DC converter driver circuit designed for photovoltaic (PV) applications. The circuit utilizes the Timer 555 as the control circuit for regulating the input voltage of the DC-DC boost converter. Simulation results obtained using Multisim software demonstrate the feasibility and effectiveness of the proposed circuit. The simulation results reveal that the circuit successfully increases voltages and decreases currents as load resistance rises, while significantly reducing load power with higher load resistance. Furthermore, the simulated boost converter achieves a higher output voltage and demonstrates an efficiency range of 91.42% to 92.54%, indicating its ability to efficiently convert input power into desired output power. These findings highlight the promising performance of the designed circuit for PV applications, offering effective power conversion and acceptable load current
Performance analysis on fingerprint identification by deep learning approach
Get PDFAchieving high accuracy in fingerprint identification remains challenging, despite various approaches that have been introduced over the years, including deep learning-based methods. These approaches can be
computationally complex and may require a vast amount of training data. This
study aims to evaluate the performance of deep learning-based approaches for
fingerprint identification using two pretrained deep network models, i.e.,
GoogLeNet and ResNet18. The images in the datasets are first registered and
cropped before being trained and validated. The validation rates demonstrated
that the preprocessed images produced higher average validation rates
compared to the original images. These images are then applied during the testing phase, resulting in nearly perfect identification rates for both models. In
comparison, with only 20% of the training dataset, GoogLeNet and ResNet18
achieved 93.00% and 97.00% for the FingerDOS database, respectively. Both
models obtained an 88.75% identification rate on the FVC2002 DB1A
database, outperforming other methods
Modeling and Simulation of Integrated Solar PV/Battery/Hydrogen Hybrid System for Enhanced System
No full textThis paper describes an ongoing engineering project and outlines the modeling and simulation of a Hybrid Energy Storage System (HESS) of an electric vehicle using fuel
cells and batteries with the aid of MATLAB/Simulink. The key purpose of this research is to develop and demonstrate the hybridization compatibility between both devices
to ensure overall system stability and minimize transient effects. At present, researchers have proposed several types of nonhybrid Energy Storage System (ESS) which mostly involves batteries, also referred to as Battery Energy Storage System (BESS). The problem with this conventional system is that the system itself is jeopardizing and not efficient enough to lower the rate of transient, resulting in a longer response time. On that account, the hybridization between two types of sources, which in this case is the fuel cell and battery, is required along with the presence of a network controller. The network controller proposed for the HESS is Artificial Neural Network (ANN) as it is suitable for capturing complex and nonlinear
relationships data. In general, this research aims to increase the stability and reliability of the entire system performance
Empowering Youth through Play : Promoting Awareness of Sexual Grooming among Schoolchildren through Game-based Learning
Get PDFSexual grooming is engaging with a child to build a relationship with intentions of sexual exploitation. In some cases, it precedes child sexual abuse. The need for child sex education can be further illustrated by the severity of the trauma that results from the abuse. Hence, it is ideal to recognise the signs of grooming to reduce the risk of child sexual grooming. This project aims to develop an age-appropriate game to assess game-based learning to educate children on preventing sexual grooming. The methodology implemented in this project is the outcome-based methodology. First, a survey was distributed to guide the design of the game and to identify the relevant learning outcomes relating to sex education the respondents wish their children to learn. Based on the results, there are four learning outcomes to be achieved. Second, the genre of the game was determined to be a visual novel. Third, the premise of the game was written. Fourth, assets to enhance the playing experience were either created or sourced online. Fifth, the game mechanics were developed using Godot Engine. Sixth, the game mechanics were play tested iteratively, before and after integration with one another. Seventh, all the mechanics and non-mechanic elements were integrated to complete development. Eighth, the game was play tested online. Pre- and post-test results from the playtest were recorded and evaluated. Using paired samples t-test with a 95% confidence interval, the calculated t-value 12.011 was more significant than the critical t-value of 2.042, and the p-value 0.00001 was lesser than the significance level of 0.05. The result suggests that using the game to create awareness of physical and online grooming towards children was effective
BOX-PCR and ERIC-PCR evaluation for genotyping Shiga toxin-producing Escherichia coli and Salmonella enterica serovar Typhimurium in raw milk
Get PDFOver the past decade, the occurrence of milk-borne infections caused by Shiga toxin-producing Escherichia coli (STEC) and Salmonella enterica serovar Typhimurium (S. Typhimurium) has adversely affected consumer health and the milk industry.
We aimed to detect and genotype the strains of E. coli and S. Typhimurium isolated from cow and goat milks using two genotyping tools, BOX-PCR and ERIC-PCR. A total of 200 cow and goat milk samples were collected from the dairy farms in Southern Sarawak, Malaysia.
First, E. coli and Salmonella spp. detected in the samples were characterized using PCRs to identify pathogenic strains, STEC and S. Typhimurium. Next, the bacterial strains were genotyped using ERIC-PCR and BOX-PCR to determine their genetic relatedness. Out of 200 raw milk samples, 46.5% tested positive for non-STEC, 39.5% showed the presence of S. Typhimurium, and 11% were positive for STEC. The two genotyping tools showed different discrimination indexes, with BOX-PCR exhibiting a higher index mean (0.991) compared to ERIC-PCR (0.937). This suggested that BOX-PCR had better discriminatory power for genotyping the bacteria.
Our study provides information on the safety of milk sourced from dairy farms, underscoring the importance of regular inspections and surveillance at the farm level to minimize the risk of E. coli and Salmonella outbreaks from milk consumption