Pub Date : 2023-09-15DOI: 10.55766/sujst-2023-03-e02351
A. Tiwari, Sanjay K Sharma, V. Kalamkar
This work proposes modeling and optimization of poly-crystalline photovoltaic (PV) modules, validated with experiment, using single diode (SDM) and double diode model(DDM). The PV cell is treated as an equivalent electrical circuit with series and shunt resistance. The weather data like temperature and irradiance are used as input variables. The operating current and maximum power point are obtained using three variables: current, voltage, and power. An experiment was set up in Nagpur city, on the Deccan plateau situated in central India. This place is suited for PV installation due to the high average solar insolation period throughout the year. The outputs of the PV model are optimized using a genetic algorithm (GA) and simulated annealing (SA) algorithm and validated against the experiments with variable load conditions. The metaheuristics optimization techniques worked well for this model and improved the accuracy and precision of the current-voltage (I-V) and power voltage (P-V) curves. The present work compares the errors of the SA and GA algorithms used for extracting the five key points of (I -V) curves using the normalized sum of squared errors (NSSE). The proposed model optimization results are in close agreement with experimental results.
本研究利用单二极管模型（SDM）和双二极管模型（DDM）对多晶硅光伏组件进行建模和优化，并通过实验进行验证。光伏电池被视为具有串联和并联电阻的等效电路。温度和辐照度等天气数据被用作输入变量。通过电流、电压和功率这三个变量可获得工作电流和最大功率点。实验在位于印度中部德干高原的那格浦尔市进行。该地全年平均日照时间长，适合安装光伏设备。使用遗传算法（GA）和模拟退火（SA）算法对光伏模型的输出进行了优化，并根据不同负载条件下的实验进行了验证。元启发式优化技术对该模型效果良好，提高了电流电压（I-V）和功率电压（P-V）曲线的准确性和精确度。本研究使用归一化平方误差之和（NSSE）比较了用于提取（I-V）曲线五个关键点的 SA 算法和 GA 算法的误差。所提出的模型优化结果与实验结果非常吻合。
{"title":"MATHEMATICAL MODELLING AND OPTIMIZATION OF POLY-CRYSTALLINE PHOTOVOLTAIC MODULE","authors":"A. Tiwari, Sanjay K Sharma, V. Kalamkar","doi":"10.55766/sujst-2023-03-e02351","DOIUrl":"https://doi.org/10.55766/sujst-2023-03-e02351","url":null,"abstract":"This work proposes modeling and optimization of poly-crystalline photovoltaic (PV) modules, validated with experiment, using single diode (SDM) and double diode model(DDM). The PV cell is treated as an equivalent electrical circuit with series and shunt resistance. The weather data like temperature and irradiance are used as input variables. The operating current and maximum power point are obtained using three variables: current, voltage, and power. An experiment was set up in Nagpur city, on the Deccan plateau situated in central India. This place is suited for PV installation due to the high average solar insolation period throughout the year. The outputs of the PV model are optimized using a genetic algorithm (GA) and simulated annealing (SA) algorithm and validated against the experiments with variable load conditions. The metaheuristics optimization techniques worked well for this model and improved the accuracy and precision of the current-voltage (I-V) and power voltage (P-V) curves. The present work compares the errors of the SA and GA algorithms used for extracting the five key points of (I -V) curves using the normalized sum of squared errors (NSSE). The proposed model optimization results are in close agreement with experimental results.","PeriodicalId":509211,"journal":{"name":"Suranaree Journal of Science and Technology","volume":"67 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139339764","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}
Pub Date : 2023-09-15DOI: 10.55766/sujst-2023-03-e02349
Mattana Santasnachok, Teeranun Nakyai
The energy crisis and global warming caused by fossil fuel combustion have received increasing attention in recent years. Biomethanol is a clean and environmentally friendly energy produced by reforming biogas-derived syngas. To investigate the most suitable and efficient biomethanol production process, this paper compares the biomethanol production via three different biogas reforming processes, namely steam reforming, autothermal reforming, and tri-reforming using Aspen Plus simulator through safety index, energy and exergetic, and environmental analyses. For the process performance, the tri-reforming process achieved the highest energetic and exergetic efficiencies of 63.17% and 41.24%, respectively, due to producing the highest yield of methanol. In the environmental analysis, the steam reforming of the biogas process showed the lowest CO2 emission intensity of 3.16 ton CO2/ton methanol. The major source of CO2 emission is the combustion of biogas. The Dow Fire and Explosion Index was used for the safety aspect. The biomethanol reactor was discovered to be the most hazardous equipment.
近年来，化石燃料燃烧引发的能源危机和全球变暖问题日益受到关注。生物甲醇是一种通过重整沼气衍生合成气生产的清洁环保能源。为了研究最合适、最高效的生物甲醇生产工艺，本文使用 Aspen Plus 模拟器，通过安全指数、能效、效价比和环境分析，比较了通过三种不同的沼气重整工艺（即蒸汽重整、自热重整和三重重整）生产生物甲醇的情况。在工艺性能方面，三重转化工艺的能效和效费比最高，分别为 63.17% 和 41.24%，因为甲醇产量最高。在环境分析方面，沼气蒸汽转化工艺的二氧化碳排放强度最低，为 3.16 吨二氧化碳/吨甲醇。二氧化碳排放的主要来源是沼气的燃烧。在安全方面采用了陶氏火灾和爆炸指数。发现生物甲醇反应器是最危险的设备。
{"title":"A COMPARATIVE STUDY ON SAFETY, EXERGETIC, AND ENVIRONMENTAL ANALYSIS FOR BIOMETHANOL VIA BIOGAS REFORMING","authors":"Mattana Santasnachok, Teeranun Nakyai","doi":"10.55766/sujst-2023-03-e02349","DOIUrl":"https://doi.org/10.55766/sujst-2023-03-e02349","url":null,"abstract":"The energy crisis and global warming caused by fossil fuel combustion have received increasing attention in recent years. Biomethanol is a clean and environmentally friendly energy produced by reforming biogas-derived syngas. To investigate the most suitable and efficient biomethanol production process, this paper compares the biomethanol production via three different biogas reforming processes, namely steam reforming, autothermal reforming, and tri-reforming using Aspen Plus simulator through safety index, energy and exergetic, and environmental analyses. For the process performance, the tri-reforming process achieved the highest energetic and exergetic efficiencies of 63.17% and 41.24%, respectively, due to producing the highest yield of methanol. In the environmental analysis, the steam reforming of the biogas process showed the lowest CO2 emission intensity of 3.16 ton CO2/ton methanol. The major source of CO2 emission is the combustion of biogas. The Dow Fire and Explosion Index was used for the safety aspect. The biomethanol reactor was discovered to be the most hazardous equipment.","PeriodicalId":509211,"journal":{"name":"Suranaree Journal of Science and Technology","volume":"87 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139339767","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}
Pub Date : 2023-09-15DOI: 10.55766/sujst-2023-03-e0175
Riky Tri Yunardi, Qurrotul A’yun
Preventing the transmission of the COVID-19 in public places involves the use of disinfection tunnels that sterilize the outer body and clothing. However, most disinfection tunnels use conventional systems operated manually with nozzles constantly spraying disinfectant solution. Automation can be used to control the operation, minimizing not only wasteful disinfectant consumption but also physical contact. This paper proposes a control system design for an automatic body disinfection tunnel with a temperature scanner and UV-C radiation. This study uses an ESP8266 microcontroller and several sensors. The disinfectant solution sprayer is equipped with a 2–3 micron nozzle spray and a UV-C lamp of 30 watts integrated with the control unit. The control system is incorporated into a portable and modular arc-roofed disinfection tunnel. The system has been tested and performed with electrical measurements. The results show that the automatic system works and can be implemented as a disinfection tunnel in public areas to optimize transmission prevention.
{"title":"AUTOMATIC BODY DISINFECTION TUNNEL OF COVID‑19 VIRUS WITH TEMPERATURE SCANNER AND UV-C RADIATION","authors":"Riky Tri Yunardi, Qurrotul A’yun","doi":"10.55766/sujst-2023-03-e0175","DOIUrl":"https://doi.org/10.55766/sujst-2023-03-e0175","url":null,"abstract":"Preventing the transmission of the COVID-19 in public places involves the use of disinfection tunnels that sterilize the outer body and clothing. However, most disinfection tunnels use conventional systems operated manually with nozzles constantly spraying disinfectant solution. Automation can be used to control the operation, minimizing not only wasteful disinfectant consumption but also physical contact. This paper proposes a control system design for an automatic body disinfection tunnel with a temperature scanner and UV-C radiation. This study uses an ESP8266 microcontroller and several sensors. The disinfectant solution sprayer is equipped with a 2–3 micron nozzle spray and a UV-C lamp of 30 watts integrated with the control unit. The control system is incorporated into a portable and modular arc-roofed disinfection tunnel. The system has been tested and performed with electrical measurements. The results show that the automatic system works and can be implemented as a disinfection tunnel in public areas to optimize transmission prevention.","PeriodicalId":509211,"journal":{"name":"Suranaree Journal of Science and Technology","volume":"41 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139339935","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}
Pub Date : 2023-09-15DOI: 10.55766/sujst-2023-03-e0123
L. Kanagasabai
In this paper Extreme Learning Machine and Chaotic based Sphyraena Chrysotaenia Optimization Algorithms are applied for solving the Real Power loss lessening problem. Key objective of this work are Real power loss decreasing, power divergence restraining, and power constancy amplification. Extreme Learning machine and chaotic are integrated in the algorithm to obtain the better solutions. Candidate solutions in the projected Sphyraena Chrysotaenia optimization are Sphyraena Chrysotaenia and population in the inspection region is quixotically enthused. Spasmodically impressive solutions can be erroneous while restructuring the position of inspection agents and renewed positions may be inadequate one than the previous positions so magnificent selection is engaged. Domination comprises recurrence the self-effacing fitting solution to ensuing generation. In Extreme Learning Machine based Sphyraena Chrysotaenia Optimization Algorithm (ELMSC) initial phases of iteration, the Sphyraena Chrysotaenia Optimization Algorithm contestants are diversified in position and exponential standby generates unrestricted impulsive calculations which endow the rudiments to accommodate the entire revelation area. Compatibly, all over end stage of iterations, fundamentals are enclosed by Sphyraena Chrysotaenia Optimization Algorithm contestants and all an optimal condition with equivalent scheme. Chaotic sequences are combined into the Sphyraena Chrysotaenia Optimization Algorithm (CSCO). This amalgamation will augment the Exploration and Exploitation. Tinkerbell chaotic map fabricating tenets are employed. Proposed ELMSC and CSCO are corroborated in IEEE 30, 57, 118, 300, and 354 bus test systems. True power loss lessening, power divergence curtailing, and power constancy augmentation has been achieved. In future proposed ELMSC and CSCO can be applied to solve the others problems in Electrical engineering and also can be applied to resolve the problems in other engineering domains.
{"title":"EXTREME LEARNING MACHINE AND CHAOTIC BASED SPHYRAENA CHRYSOTAENIA OPTIMIZATION ALGORITHMS FOR LOSS LESSENING AND POWER STABILITY MAGNIFICATION","authors":"L. Kanagasabai","doi":"10.55766/sujst-2023-03-e0123","DOIUrl":"https://doi.org/10.55766/sujst-2023-03-e0123","url":null,"abstract":"In this paper Extreme Learning Machine and Chaotic based Sphyraena Chrysotaenia Optimization Algorithms are applied for solving the Real Power loss lessening problem. Key objective of this work are Real power loss decreasing, power divergence restraining, and power constancy amplification. Extreme Learning machine and chaotic are integrated in the algorithm to obtain the better solutions. Candidate solutions in the projected Sphyraena Chrysotaenia optimization are Sphyraena Chrysotaenia and population in the inspection region is quixotically enthused. Spasmodically impressive solutions can be erroneous while restructuring the position of inspection agents and renewed positions may be inadequate one than the previous positions so magnificent selection is engaged. Domination comprises recurrence the self-effacing fitting solution to ensuing generation. In Extreme Learning Machine based Sphyraena Chrysotaenia Optimization Algorithm (ELMSC) initial phases of iteration, the Sphyraena Chrysotaenia Optimization Algorithm contestants are diversified in position and exponential standby generates unrestricted impulsive calculations which endow the rudiments to accommodate the entire revelation area. Compatibly, all over end stage of iterations, fundamentals are enclosed by Sphyraena Chrysotaenia Optimization Algorithm contestants and all an optimal condition with equivalent scheme. Chaotic sequences are combined into the Sphyraena Chrysotaenia Optimization Algorithm (CSCO). This amalgamation will augment the Exploration and Exploitation. Tinkerbell chaotic map fabricating tenets are employed. Proposed ELMSC and CSCO are corroborated in IEEE 30, 57, 118, 300, and 354 bus test systems. True power loss lessening, power divergence curtailing, and power constancy augmentation has been achieved. In future proposed ELMSC and CSCO can be applied to solve the others problems in Electrical engineering and also can be applied to resolve the problems in other engineering domains.","PeriodicalId":509211,"journal":{"name":"Suranaree Journal of Science and Technology","volume":"59 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139339540","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}
Pub Date : 2023-08-07DOI: 10.55766/sujst-2023-03-e02049
Saranchai Sinlapasorn, Benjawan Rodjanadid, J. Tanthanuch, Bura Sindhupakorn, Arjuna Chaiyasena
This research studies factors and creates a model to predict the patients’ postoperative WOMAC score after total knee replacement. First, the influencing factors were found by feature engineering, using several techniques such as Generalized Linear Models, Support Vector Machines, Deep Learning, and Gradient Boost Trees. Afterwards, the model was created by the Gradient Boost Tree technique which groups different attributes from feature engineering. Models were compared to find the model with the best predictability. RapidMiner Studio software version 9.9 was used in this work. The results demonstrate that the model created by the Gradient Boost Tree technique with attributes originating from feature engineering on the Gradient Boost Tree performs most efficiently with root mean square error (RMSE), mean absolute deviation (MAD) and square error (SE) of mathbf{5}.mathbf{311}pmmathbf{0}.mathbf{538}, mathbf{3}.mathbf{550}pmmathbf{0}.mathbf{376}, and mathbf{28}.mathbf{472}pmmathbf{5}.mathbf{811} respectively.
本研究对影响因素进行了研究，并建立了一个模型来预测全膝关节置换术后患者的术后 WOMAC 评分。首先，通过特征工程找到影响因素，使用了多种技术，如广义线性模型、支持向量机、深度学习和梯度提升树。然后，利用梯度提升树技术创建模型，将特征工程中的不同属性进行分组。对模型进行比较，以找出预测性最好的模型。这项工作使用了 RapidMiner Studio 软件 9.9 版本。结果表明，梯度提升树技术创建的模型最有效，该模型的均方根误差（RMSE）、平均绝对偏差（MAD）和平方误差（SE）均为 mathbf{5}。mathbf{311}pmmathbf{0}.mathbf{538}, mathbf{3}.mathbf{550}pmmathbf{0}.mathbf{376}, and mathbf{28}.mathbf{472}pmmathbf{5}.mathbf{811} respectively.
{"title":"MODELING TO PREDICT THE PATIENTS’ POSTOPERATIVE WOMAC SCORE BY FEATURES ENGINEERING AND GRADIENT BOOST TREE","authors":"Saranchai Sinlapasorn, Benjawan Rodjanadid, J. Tanthanuch, Bura Sindhupakorn, Arjuna Chaiyasena","doi":"10.55766/sujst-2023-03-e02049","DOIUrl":"https://doi.org/10.55766/sujst-2023-03-e02049","url":null,"abstract":"This research studies factors and creates a model to predict the patients’ postoperative WOMAC score after total knee replacement. First, the influencing factors were found by feature engineering, using several techniques such as Generalized Linear Models, Support Vector Machines, Deep Learning, and Gradient Boost Trees. Afterwards, the model was created by the Gradient Boost Tree technique which groups different attributes from feature engineering. Models were compared to find the model with the best predictability. RapidMiner Studio software version 9.9 was used in this work. The results demonstrate that the model created by the Gradient Boost Tree technique with attributes originating from feature engineering on the Gradient Boost Tree performs most efficiently with root mean square error (RMSE), mean absolute deviation (MAD) and square error (SE) of mathbf{5}.mathbf{311}pmmathbf{0}.mathbf{538}, mathbf{3}.mathbf{550}pmmathbf{0}.mathbf{376}, and mathbf{28}.mathbf{472}pmmathbf{5}.mathbf{811} respectively.","PeriodicalId":509211,"journal":{"name":"Suranaree Journal of Science and Technology","volume":"323 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139351437","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}
Pub Date : 2023-08-07DOI: 10.55766/sujst-2023-03-e02053
N. Uchegbu, Eric Okoli, Laura Okpala
In an attempt to maximize the antioxidant potentials of pigeon peas, the effect of steeping and germination times on the antioxidant content and radical scavenging activities of pigeon pea was investigated using response surface methodology. Using the central composite rotatable design (CCRD), pigeon pea seeds were soaked in water (2-28 h) and germinated (9-111 h). Thirteen samples were generated and analyzed for phenols, flavonoids, reducing power, 1, 1, Diphenyl-2-picrylhydrazyl (DPPH) free radical scavenging activity and ferric reducing antioxidant power (FRAP). Results revealed that the quadratic effects of both steeping and fermentation times were significant for predicting the phenols, flavonoids, reducing power, and FRAP while only the steeping time had a significant quadratic effect on DPPH. Significant correlation coefficients (r) were found to exist between the antioxidants and most of the antioxidant activities. The optimum steeping and germination times obtained were 15 and 96 hours respectively; predicted values for phenols, flavonoids, reducing power, and FRAP were 50.09 mg/100g, 26.56mg/100 g, 0.75 µg/ml, and 69.30 µmol/g respectively.
{"title":"OPTIMISATION OF STEEPING AND GERMINATION TIMES ON THE ANTIOXIDANT POTENTIALS OF PIGEON PEA (CAJANUS CAJAN)","authors":"N. Uchegbu, Eric Okoli, Laura Okpala","doi":"10.55766/sujst-2023-03-e02053","DOIUrl":"https://doi.org/10.55766/sujst-2023-03-e02053","url":null,"abstract":"In an attempt to maximize the antioxidant potentials of pigeon peas, the effect of steeping and germination times on the antioxidant content and radical scavenging activities of pigeon pea was investigated using response surface methodology. Using the central composite rotatable design (CCRD), pigeon pea seeds were soaked in water (2-28 h) and germinated (9-111 h). Thirteen samples were generated and analyzed for phenols, flavonoids, reducing power, 1, 1, Diphenyl-2-picrylhydrazyl (DPPH) free radical scavenging activity and ferric reducing antioxidant power (FRAP). Results revealed that the quadratic effects of both steeping and fermentation times were significant for predicting the phenols, flavonoids, reducing power, and FRAP while only the steeping time had a significant quadratic effect on DPPH. Significant correlation coefficients (r) were found to exist between the antioxidants and most of the antioxidant activities. The optimum steeping and germination times obtained were 15 and 96 hours respectively; predicted values for phenols, flavonoids, reducing power, and FRAP were 50.09 mg/100g, 26.56mg/100 g, 0.75 µg/ml, and 69.30 µmol/g respectively.","PeriodicalId":509211,"journal":{"name":"Suranaree Journal of Science and Technology","volume":"75 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139351438","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}
Pub Date : 2023-08-07DOI: 10.55766/sujst-2023-03-e02055
Muhammad Yaseen, Muhammad Hamza Khan, Dương Văn Hào, Muhammad Naveed Anjum, Muhammad Jalal, Aqib Javid, Muhmmad Bilal Mehmood
This study is conducted to evaluate aggregate characteristics and potential of carbonates rocks of the Kashala Formation, Babuzai area Khyber Pakhtunkhwa Pakistan. Physical and chemical tests were performed to assess aggregate suitability. Laboratory tests reveal Los Angeles Abrasion values of 17%, Flakiness and Elongation Index of 13% and 19.7% respectively, and Clay lumps and friable value of 0.12%. Stripping and Coating value greater than 95%, Specific gravity value (2.7-2.9). The aggregate soundness value was logged at 1.28. These parameter values were evaluated through the ASTM (American Society for Testing and Materials) and BS (British Standards) which specify that the Kashala Formation (KF) of the Alpurai group can be the potential source for dimension stone i.e., natural rock material in form of blocks or slabs quarried for commercial purposes, road, and concrete aggregates. The petrographic studies of the selected samples have majorly 70 to 75% of Calcite with an insignificant amount of 20 to 25% dolomite, 5 to 8% quartz along with ores of 1 to 2%. The small number of quartz grains and ore minerals indicate that sample formation is composed of dolomitic marble having a limited amount of deleterious content such as quartz, dolomite, and clays, which suggests that the carbonates have an insignificant threat of ACR (Alkali carbonate reaction) and ASR (Alkali silica reaction). The study indicates that the carbonates of the Babuzai area fall within the standard specification limits and can be used as a source for the indigenous construction industry.
{"title":"PETROGRAPHY AND AGGREGATE ANALYSIS OF THE CARBONATES FROM THE BABUZAI AREA, PAKISTAN","authors":"Muhammad Yaseen, Muhammad Hamza Khan, Dương Văn Hào, Muhammad Naveed Anjum, Muhammad Jalal, Aqib Javid, Muhmmad Bilal Mehmood","doi":"10.55766/sujst-2023-03-e02055","DOIUrl":"https://doi.org/10.55766/sujst-2023-03-e02055","url":null,"abstract":"This study is conducted to evaluate aggregate characteristics and potential of carbonates rocks of the Kashala Formation, Babuzai area Khyber Pakhtunkhwa Pakistan. Physical and chemical tests were performed to assess aggregate suitability. Laboratory tests reveal Los Angeles Abrasion values of 17%, Flakiness and Elongation Index of 13% and 19.7% respectively, and Clay lumps and friable value of 0.12%. Stripping and Coating value greater than 95%, Specific gravity value (2.7-2.9). The aggregate soundness value was logged at 1.28. These parameter values were evaluated through the ASTM (American Society for Testing and Materials) and BS (British Standards) which specify that the Kashala Formation (KF) of the Alpurai group can be the potential source for dimension stone i.e., natural rock material in form of blocks or slabs quarried for commercial purposes, road, and concrete aggregates. The petrographic studies of the selected samples have majorly 70 to 75% of Calcite with an insignificant amount of 20 to 25% dolomite, 5 to 8% quartz along with ores of 1 to 2%. The small number of quartz grains and ore minerals indicate that sample formation is composed of dolomitic marble having a limited amount of deleterious content such as quartz, dolomite, and clays, which suggests that the carbonates have an insignificant threat of ACR (Alkali carbonate reaction) and ASR (Alkali silica reaction). The study indicates that the carbonates of the Babuzai area fall within the standard specification limits and can be used as a source for the indigenous construction industry.","PeriodicalId":509211,"journal":{"name":"Suranaree Journal of Science and Technology","volume":"42 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139351487","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}
Pub Date : 2023-08-07DOI: 10.55766/sujst-2023-03-e02057
Taffazul H. Choudhury, Bismita Choudhury
Acute lymphoblastic leukemia (ALL) is the most common variant of paediatric cancer that creates numerous immature white blood cells affecting the bone marrow. Manual diagnosis of leukemia from microscopic evaluation of stained sample slides is an exhausting process, which is less accurate and susceptible to human errors. Additionally, identifying the leukemic blast cells under the microscope is complicated due to morphological similarity with the normal cell images. In this paper, we proposed an automated method to analyse the blood smear images using Local Binary Pattern (LBP) and classify the leukemic blast cells and normal cells. We have analysed the performance of machine learning and deep learning models such as Support Vector Machine (SVM), k-Nearest Neighbor algorithm (kNN), Artificial Neural Network (ANN), and Convolutional Neural Network (CNN). For classifying ALL and normal cell images, kNN achieved an accuracy of 94.4%, SVM, and ANN achieved an accuracy of 98.6%, and CNN achieved an accuracy of 99.6%. SVM achieved the highest sensitivity of 100%.
急性淋巴细胞白血病（ALL）是儿科癌症中最常见的变种，会在骨髓中产生大量不成熟的白细胞。通过对染色样本切片进行显微镜评估来人工诊断白血病是一个耗时耗力的过程，准确性较低且容易出现人为错误。此外，由于白血病爆破细胞与正常细胞图像形态相似，因此在显微镜下识别白血病爆破细胞非常复杂。在本文中，我们提出了一种自动方法，利用局部二元模式（LBP）分析血液涂片图像，并对白血病突变细胞和正常细胞进行分类。我们分析了支持向量机（SVM）、k-近邻算法（kNN）、人工神经网络（ANN）和卷积神经网络（CNN）等机器学习和深度学习模型的性能。在对 ALL 和正常细胞图像进行分类时，kNN 的准确率为 94.4%，SVM 和 ANN 的准确率为 98.6%，CNN 的准确率为 99.6%。SVM 的灵敏度最高，达到 100%。
{"title":"AUTOMATED ACUTE LYMPHOBLASTIC LEUKEMIA CELL CLASSIFICATION USING OPTIMIZED CONVOLUTIONAL NEURAL NETWORK","authors":"Taffazul H. Choudhury, Bismita Choudhury","doi":"10.55766/sujst-2023-03-e02057","DOIUrl":"https://doi.org/10.55766/sujst-2023-03-e02057","url":null,"abstract":"Acute lymphoblastic leukemia (ALL) is the most common variant of paediatric cancer that creates numerous immature white blood cells affecting the bone marrow. Manual diagnosis of leukemia from microscopic evaluation of stained sample slides is an exhausting process, which is less accurate and susceptible to human errors. Additionally, identifying the leukemic blast cells under the microscope is complicated due to morphological similarity with the normal cell images. In this paper, we proposed an automated method to analyse the blood smear images using Local Binary Pattern (LBP) and classify the leukemic blast cells and normal cells. We have analysed the performance of machine learning and deep learning models such as Support Vector Machine (SVM), k-Nearest Neighbor algorithm (kNN), Artificial Neural Network (ANN), and Convolutional Neural Network (CNN). For classifying ALL and normal cell images, kNN achieved an accuracy of 94.4%, SVM, and ANN achieved an accuracy of 98.6%, and CNN achieved an accuracy of 99.6%. SVM achieved the highest sensitivity of 100%.","PeriodicalId":509211,"journal":{"name":"Suranaree Journal of Science and Technology","volume":"67 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139351528","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}
Pub Date : 2023-08-07DOI: 10.55766/sujst-2023-03-e02051
Jigme Namgyal, Eckart Schulz
This work applies five variants of the support vector machine to the classification of the various stages of nonproliferative diabetic retinopathy. Four hundred eye fundus images from the Messidor repository are preprocessed and thirteen features extracted. The features best suited as inputs for support vector machine classification are identified. Initially, binary classification of severe nonproliferative diabetic retinopathy alone versus a normal eye is performed, achieving an accuracy of 97.44% using the standard support vector machine with Gaussian kernel and when optimized for accuracy. When optimized for sensitivity, the twin bounded support vector machine achieves the highest sensitivity of 99.06%. Then multiclass grading into all four stages of nonproliferative diabetic retinopathy is performed. Best performance with regards to four performance metrics, namely accuracy, sensitivity, specificity, and precision is achieved with the twin bounded support vector machine variant, when one-versus-one decision configuration is used in combination with a novel decision strategy that includes accumulated distances from the decision hyperplanes in the decision algorithm. The results compare favorably with data published in the literature.
{"title":"SUPPORT VECTOR MACHINE MODELS FOR DIABETIC RETINOPATHY DIAGNOSIS AND GRADING","authors":"Jigme Namgyal, Eckart Schulz","doi":"10.55766/sujst-2023-03-e02051","DOIUrl":"https://doi.org/10.55766/sujst-2023-03-e02051","url":null,"abstract":"This work applies five variants of the support vector machine to the classification of the various stages of nonproliferative diabetic retinopathy. Four hundred eye fundus images from the Messidor repository are preprocessed and thirteen features extracted. The features best suited as inputs for support vector machine classification are identified. Initially, binary classification of severe nonproliferative diabetic retinopathy alone versus a normal eye is performed, achieving an accuracy of 97.44% using the standard support vector machine with Gaussian kernel and when optimized for accuracy. When optimized for sensitivity, the twin bounded support vector machine achieves the highest sensitivity of 99.06%. Then multiclass grading into all four stages of nonproliferative diabetic retinopathy is performed. Best performance with regards to four performance metrics, namely accuracy, sensitivity, specificity, and precision is achieved with the twin bounded support vector machine variant, when one-versus-one decision configuration is used in combination with a novel decision strategy that includes accumulated distances from the decision hyperplanes in the decision algorithm. The results compare favorably with data published in the literature.","PeriodicalId":509211,"journal":{"name":"Suranaree Journal of Science and Technology","volume":"51 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139351491","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}
Pub Date : 2023-08-04DOI: 10.55766/sujst-2023-03-e0887
Hidayatulah Himawan, Bobby Umroh, Md Nizam Abd Rahman, Mohd Najib Ali Mokhtar, Armansyah Ginting, Irianto Harny, R.L. Muhamud
Alumina, renowned for its outstanding resistance to corrosion and heat, poses a formidable challenge due to its brittle nature when it comes to machining. Nonetheless, laser machining has emerged as a particularly suitable method for working with hard and brittle materials like alumina. While traditional machining techniques can also be effective, they often necessitate prolonged machining durations and significantly high tool wear rates, thereby driving up the overall machining costs. By employing experimentation and optimization techniques, laser machining technologies such as Nd: YAG lasers, fiber lasers, and CO2 lasers have displayed remarkable efficacy in machining alumina. Notably, CO2 lasers offer distinctive advantages owing to their maximum power output of 45 kW and laser wavelength of 10.6 μm, rendering them suitable for macro material cutting applications. This paper aims to consolidate pertinent information on laser machining of alumina into a single document. The primary focus of this paper revolves around key laser machining parameters, including pulse duration, frequency, peak power, laser power, piercing time, gas pressure, and cutting speed, along with their impact on machining quality aspects such as surface irregularity, kerf width, taper angle, and the Heat-Affected Zone (HAZ).
氧化铝因其出色的耐腐蚀性和耐热性而闻名于世，但由于其脆性，在加工时却面临着巨大的挑战。然而，激光加工已成为一种特别适合加工氧化铝等硬脆材料的方法。虽然传统的加工技术也很有效，但往往需要延长加工时间，而且刀具磨损率很高，从而增加了总体加工成本。通过采用实验和优化技术，Nd：YAG 激光器、光纤激光器和 CO2 激光器等激光加工技术在加工氧化铝方面显示出显著的功效。值得注意的是，CO2 激光器的最大输出功率为 45 kW，激光波长为 10.6 μm，因此具有独特的优势，适用于宏观材料切割应用。本文旨在将氧化铝激光加工的相关信息整合成一份文件。本文的主要关注点是激光加工的关键参数，包括脉冲持续时间、频率、峰值功率、激光功率、穿孔时间、气体压力和切割速度，以及它们对加工质量的影响，如表面不平整度、切口宽度、锥角和热影响区（HAZ）。
{"title":"A REVIEW ON LASER MACHINING OF ALUMUNIA CERAMIC","authors":"Hidayatulah Himawan, Bobby Umroh, Md Nizam Abd Rahman, Mohd Najib Ali Mokhtar, Armansyah Ginting, Irianto Harny, R.L. Muhamud","doi":"10.55766/sujst-2023-03-e0887","DOIUrl":"https://doi.org/10.55766/sujst-2023-03-e0887","url":null,"abstract":"Alumina, renowned for its outstanding resistance to corrosion and heat, poses a formidable challenge due to its brittle nature when it comes to machining. Nonetheless, laser machining has emerged as a particularly suitable method for working with hard and brittle materials like alumina. While traditional machining techniques can also be effective, they often necessitate prolonged machining durations and significantly high tool wear rates, thereby driving up the overall machining costs. By employing experimentation and optimization techniques, laser machining technologies such as Nd: YAG lasers, fiber lasers, and CO2 lasers have displayed remarkable efficacy in machining alumina. Notably, CO2 lasers offer distinctive advantages owing to their maximum power output of 45 kW and laser wavelength of 10.6 μm, rendering them suitable for macro material cutting applications. This paper aims to consolidate pertinent information on laser machining of alumina into a single document. The primary focus of this paper revolves around key laser machining parameters, including pulse duration, frequency, peak power, laser power, piercing time, gas pressure, and cutting speed, along with their impact on machining quality aspects such as surface irregularity, kerf width, taper angle, and the Heat-Affected Zone (HAZ).","PeriodicalId":509211,"journal":{"name":"Suranaree Journal of Science and Technology","volume":"127 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139351796","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：