Jay Nelson Corbita, L. Pabilona, Eliseo Villanueva
{"title":"Energy Audit on Two 22-TPH Coal-fired Boilers of a Pineapple Processing Plant","authors":"Jay Nelson Corbita, L. Pabilona, Eliseo Villanueva","doi":"10.47836/pjst.32.4.25","DOIUrl":"https://doi.org/10.47836/pjst.32.4.25","url":null,"abstract":"The price of coal used by a pineapple processing plant has increased from 3.90 Php/kg in 2018 to 8.60 Php/kg in 2022, thus increasing steam generation costs. This study conducted an energy audit on the two 22-TPH coal-fired boilers of the pineapple processing plant to determine boiler efficiency, quantify sources of heat loss, identify energy conservation measures, and calculate energy and coal savings. The coal-fired boilers investigated were fluidized bed combustion boilers with a reverse osmosis feedwater system. The boiler efficiency was calculated using an indirect method, considering energy losses from sensible heat in refuse and blowdown water. Of the three performance tests conducted, the average boiler efficiency is at 80.655%. The top five sources of heat loss were dry flue gas, hydrogen in coal, moisture in coal, surface radiation and convection, and boiler blowdown. These sources account for 18.322% of the energy input. The identified energy conservation measures include the installation of an automatic oxygen trim control, the installation of an economizer, the installation of a caustic injection system, and the insulation of uninsulated surfaces. These measures have a total potential energy savings of 52,494,974 MJ/yr and coal savings of 2,594,579 kg/yr. While a caustic injection system is not yet installed, setting blowdown TDS to 2,090 ppm can reduce energy consumption by 1,656,496 MJ/yr and coal consumption by 81,873 kg/yr. Using coal with lower hydrogen and moisture content can also reduce energy loss by 6,096,810 MJ/yr per 0.5% reduction in hydrogen content and 6,816,813 MJ/yr per 5% reduction in moisture content.","PeriodicalId":46234,"journal":{"name":"Pertanika Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141815044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Noor Azrieda Abd. Rashid, Hashim W Samsi, Nur Hanina Izzati Khairol Mokhtar, Yanti Abdul Kadir, Khairul Masseat, Siti Zaliha Ali, Muhammad Taufiq Tajuddin
{"title":"Deflection Performance of Particleboards and Their Potential as Built-in Materials","authors":"Noor Azrieda Abd. Rashid, Hashim W Samsi, Nur Hanina Izzati Khairol Mokhtar, Yanti Abdul Kadir, Khairul Masseat, Siti Zaliha Ali, Muhammad Taufiq Tajuddin","doi":"10.47836/pjst.32.4.24","DOIUrl":"https://doi.org/10.47836/pjst.32.4.24","url":null,"abstract":"Particleboard is a commonly used material in the construction of furniture. It is an engineered wood product made from wood particles, such as wood chips, sawmill shavings, or sawdust, combined with a resin binder and compressed into sheets. The advantages of using this material are its uniformity, stability, and affordable price. Some performance must be tested to ensure its quality and strength properties so that it can be used as a built-in material. This study evaluated deflection performance based on the different thicknesses and sizes. The objective of this study was to determine the deflection properties over time. The deflective capabilities of particleboard with 16, 18 and 25 mm thicknesses and sizes of 400 × 384, 560 × 350, 760 × 330, 800 × 380 and 910 × 390 mm were investigated in three weeks. Remarkably, the particleboard with a 25 mm thickness exhibited markedly diminished deflection two to three times lower than that of 18 mm and 16 mm thickness, thereby showcasing its superior strength when subjected to various loads. Conversely, utilizing longer spans resulted in noteworthy deflection increments, implying that extended spans tend to manifest increased deflection as time progresses. These observations indicate that a thicker and shorter particleboard is well-suited for use as a building material, given its lower deflection over time. In conclusion, this study elucidates the intricate relationship between particleboard characteristics and deflection behavior, providing valuable guidance for selecting suitable particleboards based on load requirements and structural considerations.","PeriodicalId":46234,"journal":{"name":"Pertanika Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141817644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Borderline-DEMNET: A Workflow for Detecting Alzheimer’s and Dementia Stage by Solving Class Imbalance Problem","authors":"Neetha Papanna Umalakshmi, Simran Sathyanarayana, Pushpa Chicktotlikere Nagappa, Thriveni Javarappa, Venugopal Kuppanna Rajuk","doi":"10.47836//pjst.32.4.10","DOIUrl":"https://doi.org/10.47836//pjst.32.4.10","url":null,"abstract":"Alzheimer’s Disease (AD) is the leading cause of dementia, a broad term encompassing memory loss and other cognitive impairments. Although there is no known cure for dementia, managing specific symptoms associated with it can be effective. Mild dementia stages, including AD, can be treated, and computer-based techniques have been developed to aid in early diagnosis. This paper presents a new workflow called Borderline-DEMNET, designed to classify various stages of Alzheimer’s/dementia with more than three classes. Borderline-SMOTE is employed to address the issue of imbalanced datasets. A comparison is made between the proposed Borderline-DEMNET workflow and the existing DEMNET model, which focuses on classifying different dementia and AD stages. The evaluation metrics specified in the paper are used to assess the results. The framework is trained, tested, and validated using the Kaggle dataset, while the robustness of the work is checked using the ADNI dataset. The proposed workflow achieves an accuracy of 99.17% for the Kaggle dataset and 99.14% for the ADNI dataset. In conclusion, the proposed workflow outperforms previously identified models, particularly in terms of accuracy. It also proves that selecting a proper class balancing technique will increase accuracy.","PeriodicalId":46234,"journal":{"name":"Pertanika Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141641059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sarini Ahmad Wakid, Nor Azwady Abd Aziz, Zazali Alias, Muskhazli Mustafa, Wan Mohd Syazwan, Syaizwan Zahmir Zulkifli
{"title":"Evaluation of Glutathione S-transferases Expression as Biomarkers by Heavy Metals in Geloina expansa from Sepang Besar River, Selangor, Malaysia","authors":"Sarini Ahmad Wakid, Nor Azwady Abd Aziz, Zazali Alias, Muskhazli Mustafa, Wan Mohd Syazwan, Syaizwan Zahmir Zulkifli","doi":"10.47836/pjst.32.4.01","DOIUrl":"https://doi.org/10.47836/pjst.32.4.01","url":null,"abstract":"Glutathione S-transferases (GSTs) are enzymes involved in phase II of detoxification metabolism and could be used as biomarkers for water pollution. This study aims to determine heavy metal concentrations in the soft tissue of the mangrove clam Geloina expansa, as well as the expression of GSTs in the species. The acid digestion method was used to digest the samples, followed by a standard USEPA 6010B procedure using inductively coupled plasma optical emission spectrometry (ICP-OES) to measure the heavy metal contents in the samples. GST enzyme activity was measured using 1-chloro-2, 4-dinitrobenzene (CDNB) as substrate. One-way ANOVA was performed to compare the mean values of heavy metal concentration, protein concentration, enzyme activity, and specific activity. There was a significant difference (p<0.05) for Zn, total protein, and specific activity in G. expansa, but no significant difference in Pb, Cu and enzyme activity. GST enzyme activities were estimated at 0.16 ± 0.01 µmol/min, with a protein content of 1.24 ± 0.04 mg. The specific activity for GST was 0.13 ± 0.01 µmol/min/mg, calculated as the ratio of enzyme activity to the total protein. GST-specific activity positively correlates with Pb concentration in the soft tissue of G. expansa. Detailed studies on the effects of pollution on the expression of GST need to be further investigated for the future use of this species as an efficient biomarker model.","PeriodicalId":46234,"journal":{"name":"Pertanika Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141642539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vinicius Andrade de Barros, Carlos Pedro Boechat Soares, Gilson Fernandes Da Silva, Gianmarco Goycochea Casas, Helio Garcia Leite
{"title":"Conversion Factor Estimation of Stacked Eucalypt Timber Using Supervised Image Classification with Artificial Neural Networks","authors":"Vinicius Andrade de Barros, Carlos Pedro Boechat Soares, Gilson Fernandes Da Silva, Gianmarco Goycochea Casas, Helio Garcia Leite","doi":"10.47836/pjst.32.4.05","DOIUrl":"https://doi.org/10.47836/pjst.32.4.05","url":null,"abstract":"Stacked timber is quantified in-store units and then adjusted with a conversion factor for volume estimation in cubic meters, which is important for the wood trade in South America. However, measuring large quantities accurately can be challenging. Digital image processing and artificial intelligence advancements offer promising solutions, making research in this area increasingly attractive. This study aims to estimate conversion factors of stacked Eucalyptus grandis timber using supervised image classification with Artificial Neuronal Network (ANN). Measured data and photographs from an experiment involving thirty stacks of timber were used to achieve this. The conversion factor was determined using photographic methods that involved the applications of equidistant points and ANN and subsequently validated with values observed through the manual method. The ANN method produced more accurate conversion factor estimates than the equidistant points method. Approximately 97% of the ANN estimates were within the ±1% error class, even when using low-resolution digital photographs.","PeriodicalId":46234,"journal":{"name":"Pertanika Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141640588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mohamad Firzan Ahmad Harazi, A. Hairuddin, A. As’arry, S. Masuri
{"title":"Effects of Different Throttle Opening and Air Intake Lengths on the Volumetric Efficiency of SI Engine Using 1D Simulation Method","authors":"Mohamad Firzan Ahmad Harazi, A. Hairuddin, A. As’arry, S. Masuri","doi":"10.47836/pjst.32.4.03","DOIUrl":"https://doi.org/10.47836/pjst.32.4.03","url":null,"abstract":"Engine performance is influenced by volumetric efficiency, an engine’s ability to put air into its cylinders. It is known for its intake length being tuned based on engine speed due to the air pressure wave behavior. However, the airflow into the intake system is controlled by the throttle opening, so there is a need to study the performance effect of intake length that is tuned based on it. Thus, this current study focuses on the impact of different throttle opening and intake lengths in relation to engine speed on the volumetric efficiency of the Proton CamPro 1.6L SI engine. The simulation runs on different ranges of engine speeds from 1000 rpm to 7000 rpm and different intake lengths with different throttle opening angles. The critical finding of this study revealed that tuning intake length based on throttle opening showed an improvement of 1.3% for volumetric efficiency at the low rpm range. It is by tuning the intake length to 400 mm at a throttle opening of 70° for 1000 rpm and 450 mm intake length with a throttle opening of 50° at 2000 rpm. However, it showed that 90° or wide-open throttle provides the best volumetric efficiency for mid and high-range rpm for all intake lengths. The highest efficiency achieved is 101% at 4000 rpm with a 500 mm length intake and wide-open throttle. The findings from this study contribute to a good understanding of engine performance through intake length tuned based on throttle opening.","PeriodicalId":46234,"journal":{"name":"Pertanika Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141644026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Deep Learning-based Classification Model for Arabic News Tweets Using Bidirectional Long Short-Term Memory Networks","authors":"Chin-Teng Lin, Mohammed Thanoon, Sami Karali","doi":"10.47836/pjst.32.4.09","DOIUrl":"https://doi.org/10.47836/pjst.32.4.09","url":null,"abstract":"This research develops a classification model for Arabic news tweets using Bidirectional Long Short-Term Memory networks (BiLSTM). Tweets about Arabic news were gathered between August 2016 and August 2020 and divided into five categories. Custom Python scripts, Twitter API and the GetOldTweets3 Python library were used to collect the data. BiLSTM was used to train and test the model. The results indicated an average accuracy, precision, recall, and f1-score of 0.88, 0.92, 0.88, and 0.89, respectively. The results could have practical implications for Arabic machine learning and NLP tasks in research and practice.","PeriodicalId":46234,"journal":{"name":"Pertanika Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141640290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Anna Sergeyevna Olkova, Evgeniya Vladimirovna Tovstik
{"title":"Computer Vision―The Frontier of Modern Environmental Diagnostics: A Review","authors":"Anna Sergeyevna Olkova, Evgeniya Vladimirovna Tovstik","doi":"10.47836/pjst.32.4.08","DOIUrl":"https://doi.org/10.47836/pjst.32.4.08","url":null,"abstract":"Computer vision (CV), in combination with various sensors and image analysis algorithms, is a frontier direction in diagnosing the state of the environment and its biogenic and abiogenic objects. The work generalizes scientific achievements and identifies scientific and technical problems in this area of research based on the conceptual system of analysis on the time axis: from implemented achievements as part of the past and present to original new solutions—the future. Our work gives an idea of three areas of application of CV in diagnosing the state of the environment: phenotype recognition in digital images, monitoring of living and abiogenic objects, and development of new methods for identifying pollution and its consequences. The advantages of CV, which can be attributed to scientific achievements in this field of research, are shown: an increase in the volume of analyzed samples, simultaneous analysis of several parameters of the object of observation, and leveling of subjective evaluation factors. The main CV problems currently solved are the accuracy of diagnostics and changing quality of the survey, identification of the object of analysis with minimal operator participation, simultaneous monitoring of objects of different quality, and development of software and hardware systems with CV. A promising direction for the future is to combine the capabilities of CV and artificial intelligence. Thus, the review can be useful for specialists in environmental sciences and scientists working in interdisciplinary fields.","PeriodicalId":46234,"journal":{"name":"Pertanika Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141640350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Blood CO Status Classification Using UV-VIS Spectroscopy and PSO-optimized 1D-CNN Model","authors":"A. Huong, Kim Gaik Tay, Kok Beng Gan, X. Ngu","doi":"10.47836/pjst.32.4.02","DOIUrl":"https://doi.org/10.47836/pjst.32.4.02","url":null,"abstract":"Rapid and effective blood carbon monoxide (CO) assessment is of great importance, especially in estimating CO-related morbidity and instituting effective preventive measures. The conventional detection methods using CO breath analysis lack sensitivity, while collecting biological fluid samples for CO level measurement is prone to external contamination and expensive for frequent use. This study proposes a one-dimensional convolutional neural network (1D-CNN) consisting of three stacked biconvolutional layers for binary classification of blood CO status using the diffuse reflectance spectroscopy technique. Iterative particle swarm optimization (PSO) has efficiently found the best network parameters to learn important features from the reflectance spectroscopy data. The findings showed good testing accuracy, specificity, and precision of 92.9%, 90%, and 89.7%, respectively, and a high sensitivity of 96.3% in determining abnormal blood CO among smokers using the proposed CNN network. Comparisons with eight existing machine learning and deep learning models revealed the proposed method’s effectiveness in classifying blood CO status while reducing computing time by 8–13 folds. The findings of this work provide new insights that are valuable for researchers in neural network design automation, healthcare management, and skin-related research, specifically for application in nondestructive evaluation and clinical decision-making.","PeriodicalId":46234,"journal":{"name":"Pertanika Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141640278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tien-Ping Tan, Lei Qin, Sarah Flora Samson Juan, Jasmina Yen Min Khaw
{"title":"Low Resource Malay Dialect Automatic Speech Recognition Modeling Using Transfer Learning from a Standard Malay Model","authors":"Tien-Ping Tan, Lei Qin, Sarah Flora Samson Juan, Jasmina Yen Min Khaw","doi":"10.47836/pjst.32.4.06","DOIUrl":"https://doi.org/10.47836/pjst.32.4.06","url":null,"abstract":"Approaches to automatic speech recognition have transited from Hidden Markov Model (HMM)-based ASR to deep neural networks. The advantages of deep neural network approaches are that they can be developed quickly and perform better given large language resources. Nevertheless, dialect speech recognition is still challenging due to the limited resources. Transfer learning approaches have been proposed to improve speech recognition for low resources. In the first approach, the model is pre-trained on a large and diverse labeled dataset to learn the acoustic and language patterns from the speech signal. Then, the model parameters are updated with a new dataset, and the pre-trained model is fine-tuned on a low-resource language dataset. The fine-tuning process is usually completed by freezing the pre-trained layers and training the remaining layers of the model on the low-resource language corpus. Another approach is to use a pre-trained model to capture the compact and meaningful features as input to the encoder. Pre-training in this approach usually involves using unsupervised learning methods to train models on a corpus of large amounts of unmarked data. It enables the model to learn the general patterns and relationships between the input speech signals. This paper proposes a training recipe using transfer learning and Standard Malay models to improve automatic speech recognition for Kelantan and Sarawak Malay dialects.","PeriodicalId":46234,"journal":{"name":"Pertanika Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141641181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}