Rapid progress of industrial development, urbanization and traffic has caused air quality reduction that negatively affects human health and environmental sustainability, especially among developed countries. Numerous studies on the development of air quality forecasting model using machine learning have been conducted to control air pollution. As such, there are significant numbers of reviews on the application of machine learning in air quality forecasting. Shallow architectures of machine learning exhibit several limitations and yield lower forecasting accuracy than deep learning architecture. Deep learning is a new technology in computational intelligence; thus, its application in air quality forecasting is still limited. This study aims to investigate the deep learning applications in time series air quality forecasting. Owing to this, literature search is conducted thoroughly from all scientific databases to avoid unnecessary clutter. This study summarizes and discusses different types of deep learning algorithms applied in air quality forecasting, including the theoretical backgrounds, hyperparameters, applications and limitations. Hybrid deep learning with data decomposition, optimization algorithm and spatiotemporal models are also presented to highlight those techniques' effectiveness in tackling the drawbacks of individual deep learning models. It is clearly stated that hybrid deep learning was able to forecast future air quality with higher accuracy than individual models. At the end of the study, some possible research directions are suggested for future model development. The main objective of this review study is to provide a comprehensive literature summary of deep learning applications in time series air quality forecasting that may benefit interested researchers for subsequent research.
This paper presents an online system for recording attendance based on facial recognition incorporating facial mask detection. The main objective of this project is to develop an effective attendance system based on face recognition and face mask detection, and to provide this service online through a browser interface. This would allow any user to use this system without the need to install special software. They simply need to open the interface of this system in a browser through any terminal. Recording attendance information online allows data to be easily recorded in a centralized online database. Since faces are used as biometric signatures in this project, all users registered in the system will have their profiles loaded with their face-images samples. Initially, before face recognition can be done, the model training phase based on SVM will be carried out, mainly to develop a trained model that can perform face recognition. A set of synthetic data will also be used to train the same model so that it can perform identification for users wearing face masks. The server application is coded in Python and uses the Open-Source Computer Vision (OpenCV) library for image processing. For web interfaces and the database, PHP and MySQL are used. With the integration of Python and PHP scripting programs, the developed system will be able to perform processing on online servers, while being accessible to users through a browser from any terminal. According to the results and analysis, an accuracy of about 81.8% can be achieved based on a pre-trained model for face recognition and 80% for face mask detection.
In recent years, the production of plastic has been estimated to reach 300 million tonnes, and nearly the same amount has been dumped into the waters. This waste material causes long-term damage to the ecosystem, economic sectors, and aquatic environments. Fragmentation of plastics to microplastics has been detected in the world's oceans, which causes a serious global impact. It is found that most of this debris ends up in water environments. Hence, this research aims to review the microbial degradation of microplastic, especially in water bodies and coastal areas. Aerobic bacteria will oxidize and decompose the microplastic from this environment to produce nutrients. Furthermore, plants such as microalgae can employ this nutrient as an energy source, which is the byproduct of microplastic. This paper highlights the reduction of plastics in the environment, typically by ultraviolet reduction, mechanical abrasion processes, and utilization by microorganisms and microalgae. Further discussion on the utilization of microplastics in the current technologies comprised of mechanical, chemical, and biological methods focusing more on the microalgae and microbial pathways via fuel cells has been elaborated. It can be denoted in the fuel cell system, the microalgae are placed in the bio-cathode section, and the anode chamber consists of the colony of microorganisms. Hence, electric current from the fuel cell can be generated to produce clean energy. Thus, the investigation on the emerging technologies via fuel cell systems and the potential use of microplastic pollutants for consumption has been discussed in the paper. The biochemical changes of microplastic and the interaction of microalgae and bacteria towards the degradation pathways of microplastic are also being observed in this review.
The Sustainable Energy Development Authority of Malaysia (SEDA) regularly receives complaints about damaged components and distribution boards of PV systems due to lightning strikes. Permanent and momentary interruptions of distribution circuits may also occur from the disturbance. In this paper, a solar PV Rooftop system (3.91 kWp) provided by SEDA was modelled in the PSCAD/EMTDC. The Heidler function was used as a lightning current waveform model to analyse the transient current and voltage at two different points susceptible to the influence of lightning events such as different lightning current wave shape, standard lightning current and non-standard lightning current. This study examines the effect on the system components when lightning directly strikes at two different points of the installation. The two points lie between the inverter and the solar PV array and between inverter and grid. Exceptionally high current and voltage due to the direct lightning strike on a certain point of a PV Rooftop system was also studied. The result of this case study is observed with and without the inclusion of surge protective devices (SPDs). The parameters used were 31 kA of peak current, 10 metres cable length and lightning impulse current wave shape of 8/20μs. The high current and voltage at P1 striking point were 31 kA and 2397 kV, respectively. As for the AC part, the current and voltage values were found to be 5.97 kA and 5392 kV, respectively.Therefore, SPDs with suitable rating provided by SEDA were deployed. Results showed that high transient current voltage is expected to clamp sharply at the values of 1.915 kV and 0 A at the P1 striking point. As for the AC part, the current and voltage values were found to be 0 kA and 0.751 V, respectively. Varying lightning impulse current wave shapes at striking point P2 showed that the highest voltage was obtained at waveshape 10/350 μs at 11277 kV followed by wave shapes of 2/70 μs, 8/20 μs and 0.7/6 μs. The high value of transient voltage was clamped at a lower level of 2.029 kV. Different lightning amplitudes were also applied, ranging from 2-200 kA selected based on the CIGRE distribution. It showed that the current and voltage at P1 and P2 were directly proportional. Therefore, the SPD will be designed at an acceptable rating and proper position of SPD installation at solar PV Rooftop will be proposed. The results obtained in this study can then be utilised to appropriately assign a SPD to protect the PV systems that are connected to the grid. Installing SPDs without considering the needs of lightning protection zones would expose the expensive equipment to potential damage even though the proper energy coordination of SPDs is in place. As such, the simulation results provide a basis for controlling the impacts of direct lightning strikes on electrical equipment and power grids and thus justify SPD coordination to ensure the reliability of the system.
Accurately predicting meteorological parameters such as air temperature and humidity plays a crucial role in air quality management. This study proposes different machine learning algorithms: Gradient Boosting Tree (G.B.T.), Random forest (R.F.), Linear regression (LR) and different artificial neural network (ANN) architectures (multi-layered perceptron, radial basis function) for prediction of such as air temperature (T) and relative humidity (Rh). Daily data over 24 years for Kula Terengganu station were obtained from the Malaysia Meteorological Department. Results showed that MLP-NN performs well among the others in predicting daily T and Rh with R of 0.7132 and 0.633, respectively. However, in monthly prediction T also MLP-NN model provided closer standards deviation to actual value and can be used to predict monthly T with R 0.8462. Whereas in prediction monthly Rh, the RBF-NN model's efficiency was higher than other models with R of 0.7113. To validate the performance of the trained both artificial neural network (ANN) architectures MLP-NN and RBF-NN, both were applied to an unseen data set from observation data in the region. The results indicated that on either architecture of ANN, there is good potential to predict daily and monthly T and Rh values with an acceptable range of accuracy.
Kenaf (Hibiscus cannabinus L.) seed is a non-conventional edible oilseed that can be valorized into various food products. There is a recent discovery of kenaf seed beverage (KSB) potential as a novel plant-based beverage. KSB had less crude protein than soybean (SB)but more carbohydrate, magnesium, and phosphorus contents.Levels of crude fat, phytates, oxalates, total saponins, and lipid peroxidability in KSB were lower than SB. Sugar content between KSB and SB were comparable, while antioxidant properties of KSB were superior. Ultra-high performance liquid chromatography-mass spectrometry (UHPLC-MS) analysis detected gluconic acid, citric acid, palmitic acid, oleic acid, and 13-hydroxyoctadecadienoic acid in both KSB and SB. Considering its novelty, acute and subacute oral toxicity assessments in male Sprague Dawley rats were conducted. The acute toxicity assessment was performed at a single dose of 9.2 ml/kg body weight of KSB. In the following subacute toxicity assessment, different groups of rats consumed different doses of KSB (3.1, 6.1, and 9.2 ml/kg body weight) daily for 28 days. Rats presented normal behavioral and physiological states in both toxicity studies. Growth, food and water intakes, organ weight, and hematological parameters were unaffected. No mortality was reported. Several alterations in serum biochemical parameters were within the normal range, and unassociated with histopathological changes. The oral lethal dose (LD50) and the no-observed-adverse-effect-level (NOAEL) of KSB in rats was greater than 9.2 ml/kg (=1533 mg/kg) body weight. Interestingly, KSB exhibited comparable effects with soybean beverage (SB) on high-density lipoprotein cholesterol and triglycerides which worth further research Follow-up toxicity assessments in animals and human trials are also recommended to ascertain its long term safety.
Rapid growth in industrialization and urbanization have resulted in high concentration of air pollutants in the environment and thus causing severe air pollution. Excessive emission of particulate matter to ambient air has negatively impacted the health and well-being of human society. Therefore, accurate forecasting of air pollutant concentration is crucial to mitigate the associated health risk. This study aims to predict the hourly PM2.5 concentration for an urban area in Malaysia using a hybrid deep learning model. Ensemble empirical mode decomposition (EEMD) was employed to decompose the original sequence data of particulate matter into several subseries. Long short-term memory (LSTM) was used to individually forecast the decomposed subseries considering the influence of air pollutant parameters for 1-h ahead forecasting. Then, the outputs of each forecast were aggregated to obtain the final forecasting of PM2.5 concentration. This study utilized two air quality datasets from two monitoring stations to validate the performance of proposed hybrid EEMD-LSTM model based on various data distributions. The spatial and temporal correlation for the proposed dataset were analysed to determine the significant input parameters for the forecasting model. The LSTM architecture consists of two LSTM layers and the data decomposition method is added in the data pre-processing stage to improve the forecasting accuracy. Finally, a comparison analysis was conducted to compare the performance of the proposed model with other deep learning models. The results illustrated that EEMD-LSTM yielded the highest accuracy results among other deep learning models, and the hybrid forecasting model was proved to have superior performance as compared to individual models.
Background: The ability to adapt to the psychosocial disruptions associated with the refugee experience may influence the course of complicated grief reactions. Objective: We examine these relationships amongst Myanmar refugees relocated to Malaysia who participated in a six-week course of Integrative Adapt Therapy (IAT). Method: Participants (n = 170) included Rohingya, Chin, and Kachin refugees relocated to Malaysia. At baseline and six-week post-treatment, we applied culturally adapted measures to assess symptoms of Prolonged Complex Bereavement Disorder (PCBD) and adaptive capacity to psychosocial disruptions, based on the Adaptive Stress Index (ASI). The ASI comprises five sub-scales of safety/security (ASI-1); bonds and networks (ASI-2); injustice (ASI-3); roles and identity (ASI-4); and existential meaning (ASI-5). Results: Multilevel linear models indicated that the relationship between baseline and posttreatment PCBD symptoms was mediated by the ASI scale scores. Further, ASI scale scores assessed posttreatment mediated the relationship between baseline and posttreatment PCBD symptoms. Mediation of PCBD change was greatest for the ASI II scale representing disrupted bonds and networks. Conclusion: Our findings are consistent with the informing model of IAT in demonstrating that changes in adaptive capacity, and especially in dealing with disrupted bonds and networks, may mediate the process of symptom improvement over the course of therapy.
It is well known in the field of materials science that a substance's longevity is significantly influenced by its environment. Everything begins with the initial contact on a material's surface. This influence will then deteriorate and have an extended negative impact on the strength of the material. In this study, the effect of natural weathering in tropical climates on magnetorheological elastomer (MRE) was investigated through microstructural evaluation to understand the aging behavior of the environmentally exposed MRE. To understand and elucidate the process, MREs made of silicone rubber and 70 wt% micron-sized carbonyl iron particles were prepared and exposed to the natural weathering of a tropical climate for 90 days. The MRE samples were then mechanically tensile tested, which revealed that Young's modulus increased, while elongation at break decreased. Surface degradation due to weathering was suspected to be the primary cause of this condition. Using scanning electron microscopy (SEM), the degradation of MRE was investigated as a function of morphological evidence. Upon examination through SEM, it was noted that the weathering effects on the morphology of the exposed samples showed distinct characteristics on the degraded surfaces of the MRE, including numerous microvoids, cavities, and microcracks. While these features were not prominent for the MRE itself, they bear resemblance to the effects observed in similar materials like rubber and elastomer. An atomic force microscope (AFM) is used to investigate the surface topography and local degradation conditions. This observation revealed a distinctive degradation characteristic of the MRE in connection to natural weathering in tropical climates. The surface damage of the MRE samples became severe and inhomogeneous during the environmental aging process, and degradation began from the exposed MRE surface, causing the mechanical characteristics of the MRE to significantly change.
Common sensors in many applications are in the form of rigid devices that can react according to external stimuli. However, a magnetorheological plastomer (MRP) can offer a new type of sensing capability, as it is flexible in shape, soft, and responsive to an external magnetic field. In this study, graphite (Gr) particles are introduced into an MRP as an additive, to investigate the advantages of its electrical properties in MRPs, such as conductivity, which is absolutely required in a potential sensor. As a first step to achieve this, MRP samples containing carbonyl iron particles (CIPs) and various amounts of of Gr, from 0 to 10 wt.%, are prepared, and their magnetic-field-dependent electrical properties are experimentally evaluated. After the morphological aspect of Gr-MRP is characterized using environmental scanning electron microscopy (ESEM), the magnetic properties of MRP and Gr-MRP are evaluated via a vibrating sample magnetometer (VSM). The resistivities of the Gr-MRP samples are then tested under various applied magnetic flux densities, showing that the resistivity of Gr-MRP decreases with increasing of Gr content up to 10 wt.%. In addition, the electrical conductivity is tested using a test rig, showing that the conductivity increases as the amount of Gr additive increases, up to 10 wt.%. The conductivity of 10 wt.% Gr-MRP is found to be highest, at 178.06% higher than the Gr-MRP with 6 wt.%, for a magnetic flux density of 400 mT. It is observed that with the addition of Gr, the conductivity properties are improved with increases in the magnetic flux density, which could contribute to the potential usefulness of these materials as sensing detection devices.