MyMedR

Displaying all 8 publications

Abstract:

Sort:

Fulltext The Deep Learning Solutions on Lossless Compression Methods for Alleviating Data Load on IoT Nodes in Smart Cities

Nasif A, Othman ZA, Sani NS

Sensors (Basel), 2021 Jun 20;21(12).
PMID: 34203024 DOI: 10.3390/s21124223

Networking is crucial for smart city projects nowadays, as it offers an environment where people and things are connected. This paper presents a chronology of factors on the development of smart cities, including IoT technologies as network infrastructure. Increasing IoT nodes leads to increasing data flow, which is a potential source of failure for IoT networks. The biggest challenge of IoT networks is that the IoT may have insufficient memory to handle all transaction data within the IoT network. We aim in this paper to propose a potential compression method for reducing IoT network data traffic. Therefore, we investigate various lossless compression algorithms, such as entropy or dictionary-based algorithms, and general compression methods to determine which algorithm or method adheres to the IoT specifications. Furthermore, this study conducts compression experiments using entropy (Huffman, Adaptive Huffman) and Dictionary (LZ77, LZ78) as well as five different types of datasets of the IoT data traffic. Though the above algorithms can alleviate the IoT data traffic, adaptive Huffman gave the best compression algorithm. Therefore, in this paper, we aim to propose a conceptual compression method for IoT data traffic by improving an adaptive Huffman based on deep learning concepts using weights, pruning, and pooling in the neural network. The proposed algorithm is believed to obtain a better compression ratio. Additionally, in this paper, we also discuss the challenges of applying the proposed algorithm to IoT data compression due to the limitations of IoT memory and IoT processor, which later it can be implemented in IoT networks.
A multi-view representation technique based on principal component analysis for enhanced short text clustering

Ahmed MH, Tiun S, Omar N, Sani NS

PLoS One, 2024;19(8):e0309206.
PMID: 39178180 DOI: 10.1371/journal.pone.0309206

Clustering texts together is an essential task in data mining and information retrieval, whose aim is to group unlabeled texts into meaningful clusters that facilitate extracting and understanding useful information from large volumes of textual data. However, clustering short texts (STC) is complex because they typically contain sparse, ambiguous, noisy, and lacking information. One of the challenges for STC is finding a proper representation for short text documents to generate cohesive clusters. However, typically, STC considers only a single-view representation to do clustering. The single-view representation is inefficient for representing text due to its inability to represent different aspects of the target text. In this paper, we propose the most suitable multi-view representation (MVR) (by finding the best combination of different single-view representations) to enhance STC. Our work will explore different types of MVR based on different sets of single-view representation combinations. The combination of the single-view representations is done by a fixed length concatenation via Principal Component analysis (PCA) technique. Three standard datasets (Twitter, Google News, and StackOverflow) are used to evaluate the performances of various sets of MVRs on STC. Based on experimental results, the best combination of single-view representation as an effective for STC was the 5-views MVR (a combination of BERT, GPT, TF-IDF, FastText, and GloVe). Based on that, we can conclude that MVR improves the performance of STC; however, the design for MVR requires selective single-view representations.
Fulltext Malay Version of the mHealth App Usability Questionnaire (M-MAUQ): Translation, Adaptation, and Validation Study

Mustafa N, Safii NS, Jaffar A, Sani NS, Mohamad MI, Abd Rahman AH, et al.

JMIR Mhealth Uhealth, 2021 02 04;9(2):e24457.
PMID: 33538704 DOI: 10.2196/24457

BACKGROUND: Mobile health (mHealth) apps play an important role in delivering education, providing advice on treatment, and monitoring patients' health. Good usability of mHealth apps is essential to achieve the objectives of mHealth apps efficiently. To date, there are questionnaires available to assess the general system usability but not explicitly tailored to precisely assess the usability of mHealth apps. Hence, the mHealth App Usability Questionnaire (MAUQ) was developed with 4 versions according to the type of app (interactive or standalone) and according to the target user (patient or provider). Standalone MAUQ for patients comprises 3 subscales, which are ease of use, interface and satisfaction, and usefulness.
OBJECTIVE: This study aimed to translate and validate the English version of MAUQ (standalone for patients) into a Malay version of MAUQ (M-MAUQ) for mHealth app research and usage in future in Malaysia.
METHODS: Forward and backward translation and harmonization of M-MAUQ were conducted by Malay native speakers who also spoke English as their second language. The process began with a forward translation by 2 independent translators followed by harmonization to produce an initial translated version of M-MAUQ. Next, the forward translation was continued by another 2 translators who had never seen the original MAUQ. Lastly, harmonization was conducted among the committee members to resolve any ambiguity and inconsistency in the words and sentences of the items derived with the prefinal adapted questionnaire. Subsequently, content and face validations were performed with 10 experts and 10 target users, respectively. Modified kappa statistic was used to determine the interrater agreement among the raters. The reliability of the M-MAUQ was assessed by 51 healthy young adult mobile phone users. Participants needed to install the MyFitnessPal app and use it for 2 days for familiarization before completing the designated task and answer the M-MAUQ. The MyFitnessPal app was selected because it is one among the most popular installed mHealth apps globally available for iPhone and Android users and represents a standalone mHealth app.
RESULTS: The content validity index for the relevancy and clarity of M-MAUQ were determined to be 0.983 and 0.944, respectively, which indicated good relevancy and clarity. The face validity index for understandability was 0.961, which indicated that users understood the M-MAUQ. The kappa statistic for every item in M-MAUQ indicated excellent agreement between the raters (κ ranging from 0.76 to 1.09). The Cronbach α for 18 items was .946, which also indicated good reliability in assessing the usability of the mHealth app.
CONCLUSIONS: The M-MAUQ fulfilled the validation criteria as it revealed good reliability and validity similar to the original version. M-MAUQ can be used to assess the usability of mHealth apps in Malay in the future.
Fulltext Sustainable synthesis of graphene sand composite from waste cooking oil for dye removal

Abdullah Sani NS, Ang WL, Mohammad AW, Nouri A, Mahmoudi E

Sci Rep, 2023 Feb 02;13(1):1931.
PMID: 36732605 DOI: 10.1038/s41598-023-27477-8

Waste cooking oil (WCO) appears to be a potential carbonaceous source for synthesizing graphene sand composite (GSC) adsorbent in removing pollutants. This study presents a green synthesis method of GSC using WCO as a sustainable carbon source for the synthesis of GSC through the thermal graphitization method. Characterization analysis conducted on GSCWCO verified the successful coating of WCO onto the sand surface and conversion to graphene, which possessed distinct functional groups and features of graphene materials. GSCWCO adsorbent effectiveness in removing Congo Red dye through batch adsorption was studied under the influence of different initial concentrations (20 to 100 mg/L), and the optimum pH (pH 2 to 10), contact time (5 to 240 min), and temperature (25 to 45 °C) were investigated. The GSCWCO showed removal rates of 91.5% achieved at an initial dye concentration of 20 mg L-1, 1.0 g of adsorbent dosage, a temperature of 25 °C, and 150 min of contact time. The GSCWCO exhibited a maximum capacity of 5.52 mg g-1, was well-fitted to the Freundlich isotherm model with an R2 value of 0.989 and had an adsorption mechanism that followed the pseudo-second-order kinetic model. Negative values of enthalpy (ΔH) and Gibbs free energy (ΔG) revealed that CR adsorption onto GSCWCO was a spontaneous and exothermic process. The presence of functional groups on the surface of GSCWCO with such interactions (π-π attractive forces, hydrophobic forces, and hydrogen bonding) was responsible for the anionic dye removal. Regeneration of GSCWCO adsorbent declined after four cycles, possibly due to the chemisorption of dyes with GSC that resulted in inefficient adsorption. Being a waste-to-wealth product, GSCWCO possessed great potential to be used for water treatment and simultaneously benefited the environment through the effort to reduce the excessive discharge of WCO.
Fulltext Addressing Internet of Things security by enhanced sine cosine metaheuristics tuned hybrid machine learning model and results interpretation based on SHAP approach

Dobrojevic M, Zivkovic M, Chhabra A, Sani NS, Bacanin N, Mohd Amin M

PeerJ Comput Sci, 2023;9:e1405.
PMID: 37409075 DOI: 10.7717/peerj-cs.1405

An ever increasing number of electronic devices integrated into the Internet of Things (IoT) generates vast amounts of data, which gets transported via network and stored for further analysis. However, besides the undisputed advantages of this technology, it also brings risks of unauthorized access and data compromise, situations where machine learning (ML) and artificial intelligence (AI) can help with detection of potential threats, intrusions and automation of the diagnostic process. The effectiveness of the applied algorithms largely depends on the previously performed optimization, i.e., predetermined values of hyperparameters and training conducted to achieve the desired result. Therefore, to address very important issue of IoT security, this article proposes an AI framework based on the simple convolutional neural network (CNN) and extreme machine learning machine (ELM) tuned by modified sine cosine algorithm (SCA). Not withstanding that many methods for addressing security issues have been developed, there is always a possibility for further improvements and proposed research tried to fill in this gap. The introduced framework was evaluated on two ToN IoT intrusion detection datasets, that consist of the network traffic data generated in Windows 7 and Windows 10 environments. The analysis of the results suggests that the proposed model achieved superior level of classification performance for the observed datasets. Additionally, besides conducting rigid statistical tests, best derived model is interpreted by SHapley Additive exPlanations (SHAP) analysis and results findings can be used by security experts to further enhance security of IoT systems.
Fulltext An efficient algorithm for energy harvesting in IIoT based on machine learning and swarm intelligence

Xing P, Zhang H, Derbali M, Sefat SM, Alharbi AH, Khafaga DS, et al.

Heliyon, 2023 Jul;9(7):e17622.
PMID: 37424589 DOI: 10.1016/j.heliyon.2023.e17622

The Internet of Things (IoT) is a network of smart gadgets that are connected through the Internet, including computers, cameras, smart sensors, and mobile phones. Recent developments in the industrial IoT (IIoT) have enabled a wide range of applications, from small businesses to smart cities, which have become indispensable to many facets of human existence. In a system with a few devices, the short lifespan of conventional batteries, which raises maintenance costs, necessitates more replacements and has a negative environmental impact, does not present a problem. However, in networks with millions or even billions of devices, it poses a serious problem. The rapid expansion of the IoT paradigm is threatened by these battery restrictions, thus academics and businesses are now interested in prolonging the lifespan of IoT devices while retaining optimal performance. Resource management is an important aspect of IIoT because it's scarce and limited. Therefore, this paper proposed an efficient algorithm based on federated learning. Firstly, the optimization problem is decomposed into various sub-problems. Then, the particle swarm optimization algorithm is deployed to solve the energy budget. Finally, a communication resource is optimized by an iterative matching algorithm. Simulation results show that the proposed algorithm has better performance as compared with existing algorithms.
Fulltext Clustering analysis for classifying fake real estate listings

Mohd Amin M, Sani NS, Nasrudin MF, Abdullah S, Chhabra A, Abd Kadir F

PeerJ Comput Sci, 2024;10:e2019.
PMID: 38983188 DOI: 10.7717/peerj-cs.2019

With the rapid growth of online property rental and sale platforms, the prevalence of fake real estate listings has become a significant concern. These deceptive listings waste time and effort for buyers and sellers and pose potential risks. Therefore, developing effective methods to distinguish genuine from fake listings is crucial. Accurately identifying fake real estate listings is a critical challenge, and clustering analysis can significantly improve this process. While clustering has been widely used to detect fraud in various fields, its application in the real estate domain has been somewhat limited, primarily focused on auctions and property appraisals. This study aims to fill this gap by using clustering to classify properties into fake and genuine listings based on datasets curated by industry experts. This study developed a K-means model to group properties into clusters, clearly distinguishing between fake and genuine listings. To assure the quality of the training data, data pre-processing procedures were performed on the raw dataset. Several techniques were used to determine the optimal value for each parameter of the K-means model. The clusters are determined using the Silhouette coefficient, the Calinski-Harabasz index, and the Davies-Bouldin index. It was found that the value of cluster 2 is the best and the Camberra technique is the best method when compared to overlapping similarity and Jaccard for distance. The clustering results are assessed using two machine learning algorithms: Random Forest and Decision Tree. The observational results have shown that the optimized K-means significantly improves the accuracy of the Random Forest classification model, boosting it by an impressive 96%. Furthermore, this research demonstrates that clustering helps create a balanced dataset containing fake and genuine clusters. This balanced dataset holds promise for future investigations, particularly for deep learning models that require balanced data to perform optimally. This study presents a practical and effective way to identify fake real estate listings by harnessing the power of clustering analysis, ultimately contributing to a more trustworthy and secure real estate market.
Fulltext A clustering approach to identify multidimensional poverty indicators for the bottom 40 percent group

Abdul Rahman M, Sani NS, Hamdan R, Ali Othman Z, Abu Bakar A

PLoS One, 2021;16(8):e0255312.
PMID: 34339480 DOI: 10.1371/journal.pone.0255312

The Multidimensional Poverty Index (MPI) is an income-based poverty index which measures multiple deprivations alongside other relevant factors to determine and classify poverty. The implementation of a reliable MPI is one of the significant efforts by the Malaysian government to improve measures in alleviating poverty, in line with the recent policy for Bottom 40 Percent (B40) group. However, using this measurement, only 0.86% of Malaysians are regarded as multidimensionally poor, and this measurement was claimed to be irrelevant for Malaysia as a country that has rapid economic development. Therefore, this study proposes a B40 clustering-based K-Means with cosine similarity architecture to identify the right indicators and dimensions that will provide data driven MPI measurement. In order to evaluate the approach, this study conducted extensive experiments on the Malaysian Census dataset. A series of data preprocessing steps were implemented, including data integration, attribute generation, data filtering, data cleaning, data transformation and attribute selection. The clustering model produced eight clusters of B40 group. The study included a comprehensive clustering analysis to meaningfully understand each of the clusters. The analysis discovered seven indicators of multidimensional poverty from three dimensions encompassing education, living standard and employment. Out of the seven indicators, this study proposed six indicators to be added to the current MPI to establish a more meaningful scenario of the current poverty trend in Malaysia. The outcomes from this study may help the government in properly identifying the B40 group who suffers from financial burden, which could have been currently misclassified.