Touhidul Hasan, Muhammad Aumlanul Abrar, Md Zillur Rahman Saimon, Md. Sayeduzzaman, Md. Siyamul Islam
The Internet of Things is quickly becoming one of the most important developments in this century's automation technology field. The Internet of Things (IoT) establishes a new approach to resolving issues that may arise in the foreseeable future by establishing an interface between the many devices that are now in use and integrating the functionalities of these devices. This study's primary objective is to develop methods that will cleverly simplify living arrangements and increase their convenience. The majority of things are now automated and computerized. This work aims to provide a system for integrating sensors and other data sources for different home automation. A home with intelligence on par with humans is called a smart home. This study proposes an IoT-based smart home automation system that operates in different modules to automate the complete home. If there is a problem, it will immediately identify and attempt to resolve it. In that case, it will send a notification to the homeowner. The suggested prototype included an automated door lock system, an automated gas detection system, and a smart smoke and fire alert system that sends an alert message to the owner and remotely controls the inside fan light. The system will immediately notify the users if a fire is detected in the user's residence. A smartphone application known as the Blynk App controls things remotely. As a result of being transformed into a smart home, it can offer security, energy efficiency, and the capability to control all of the current appliances in the house remotely or from a central place. Due to the exponential growth of technology, day-to-day activities are becoming less complicated, which has contributed to the popularity of home automation systems in recent years.
{"title":"Constructing An Integrated IoT-based Smart Home with An Automated Fire and Smoke Security Alert System","authors":"Touhidul Hasan, Muhammad Aumlanul Abrar, Md Zillur Rahman Saimon, Md. Sayeduzzaman, Md. Siyamul Islam","doi":"10.56532/mjsat.v3i1.125","DOIUrl":"https://doi.org/10.56532/mjsat.v3i1.125","url":null,"abstract":"The Internet of Things is quickly becoming one of the most important developments in this century's automation technology field. The Internet of Things (IoT) establishes a new approach to resolving issues that may arise in the foreseeable future by establishing an interface between the many devices that are now in use and integrating the functionalities of these devices. This study's primary objective is to develop methods that will cleverly simplify living arrangements and increase their convenience. The majority of things are now automated and computerized. This work aims to provide a system for integrating sensors and other data sources for different home automation. A home with intelligence on par with humans is called a smart home. This study proposes an IoT-based smart home automation system that operates in different modules to automate the complete home. If there is a problem, it will immediately identify and attempt to resolve it. In that case, it will send a notification to the homeowner. The suggested prototype included an automated door lock system, an automated gas detection system, and a smart smoke and fire alert system that sends an alert message to the owner and remotely controls the inside fan light. The system will immediately notify the users if a fire is detected in the user's residence. A smartphone application known as the Blynk App controls things remotely. As a result of being transformed into a smart home, it can offer security, energy efficiency, and the capability to control all of the current appliances in the house remotely or from a central place. Due to the exponential growth of technology, day-to-day activities are becoming less complicated, which has contributed to the popularity of home automation systems in recent years.","PeriodicalId":407405,"journal":{"name":"Malaysian Journal of Science and Advanced Technology","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125265960","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}
C. Hardianti, Djong Hon Tjong, Mansyurdin, Syaifullah, Dewi Imelda Roesma
Clarias batrachus is a species of fish that can be found in Sundaland. The separation of Sundaland resulted in the separation of the islands, one of which was the island of Sumatra. The island of Sumatra is divided into west and east sides by the Bukit Barisan mountains. So, it is necessary to study the phylogenetic of C. batrachus. The CO1 gene is one of the mtDNA genes that can be used for phylogenetic studies. This study was conducted to determine the geographical relationship to the phylogenetic relationship of C. batrachus populations in Sumatra and other populations in Southeast Asia using the CO1 gene and the relationship between geographic isolation in the eastern and western watersheds of Sumatra. Based on 504 bp of C. batrachus CO1 gene sequence and 19 comparison sequences, three sub-clusters with two subspecies were formed.
{"title":"Phylogenetic of Sumatran Clarias batrachus based COI Gene","authors":"C. Hardianti, Djong Hon Tjong, Mansyurdin, Syaifullah, Dewi Imelda Roesma","doi":"10.56532/mjsat.v2i4.123","DOIUrl":"https://doi.org/10.56532/mjsat.v2i4.123","url":null,"abstract":"Clarias batrachus is a species of fish that can be found in Sundaland. The separation of Sundaland resulted in the separation of the islands, one of which was the island of Sumatra. The island of Sumatra is divided into west and east sides by the Bukit Barisan mountains. So, it is necessary to study the phylogenetic of C. batrachus. The CO1 gene is one of the mtDNA genes that can be used for phylogenetic studies. This study was conducted to determine the geographical relationship to the phylogenetic relationship of C. batrachus populations in Sumatra and other populations in Southeast Asia using the CO1 gene and the relationship between geographic isolation in the eastern and western watersheds of Sumatra. Based on 504 bp of C. batrachus CO1 gene sequence and 19 comparison sequences, three sub-clusters with two subspecies were formed.","PeriodicalId":407405,"journal":{"name":"Malaysian Journal of Science and Advanced Technology","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132293397","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}
Mahfujur Rahman, Madina Hasan, Md Masum Billah, Rukaiya Jahan Sajuti
In the neoteric century, education holds the key to bringing tremendous upgradation to the world. In most Asian countries, it is very challenging to apply education data mining techniques due to the variety of institutional data categories. In this research, an efficient data collection technique has been designed to gather institutional data, analyse and pre-process the data and apply specific data mining methods to estimate students’ progress. A real-time dataset has been designed from student transcript data, which helps to analyse the prediction of student quality. In our research, six traditional classification algorithms and a deep neural network (DNN) model is applied to perform prediction efficiency. Different classification models perform an accuracy of 90% ~ 94%. Our research predicts student education efficiency, analyses student patterns and introduces a generalized framework for an advanced level of study.
{"title":"Grading System Prediction of Educational Performance Analysis Using Data Mining Approach","authors":"Mahfujur Rahman, Madina Hasan, Md Masum Billah, Rukaiya Jahan Sajuti","doi":"10.56532/mjsat.v2i4.96","DOIUrl":"https://doi.org/10.56532/mjsat.v2i4.96","url":null,"abstract":"In the neoteric century, education holds the key to bringing tremendous upgradation to the world. In most Asian countries, it is very challenging to apply education data mining techniques due to the variety of institutional data categories. In this research, an efficient data collection technique has been designed to gather institutional data, analyse and pre-process the data and apply specific data mining methods to estimate students’ progress. A real-time dataset has been designed from student transcript data, which helps to analyse the prediction of student quality. In our research, six traditional classification algorithms and a deep neural network (DNN) model is applied to perform prediction efficiency. Different classification models perform an accuracy of 90% ~ 94%. Our research predicts student education efficiency, analyses student patterns and introduces a generalized framework for an advanced level of study.","PeriodicalId":407405,"journal":{"name":"Malaysian Journal of Science and Advanced Technology","volume":"256 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116374477","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}
Glyphosate is a very effective pesticide; hence it has been excessively used in agricultural activities. This led to glyphosate residue accumulation in the soil and resulted in various adverse effects on humans and the ecosystem. This necessitates the need to reduce glyphosate accumulation in the soil and microbial bioremediation can be the solution. Thus, this study aimed to isolate and characterize glyphosate degrading bacteria from agricultural soils exposed to glyphosate weed control method. Bacterial organisms were isolated from glyphosate polluted agricultural soil and were characterized using routine microbiological biochemical methods. The isolates were screened for glyphosate utilization using a mineral salt medium containing glyphosate as a carbon source. Confirmed glyphosate degraders were identified using 16s rDNA sequencing. These isolates were assessed for their ability to degrade 106.16 µg/ml glyphosate in varied volumes (1 ml, 1.5 ml and 2 ml), singly and in consortium. Glyphosate degraders were identified as Exiguobacterium alkaliphiluim, Alcaligenes faecalis, Sinorhizobuim fredii and Acinetobacter nosocomialis. These organisms significantly (p<0.05) degraded different glyphosate volumes as a consortium more than as individual organisms. This study has been able to show the different glyphosate degraders present in some glyphosate-polluted agricultural soils in Awka, Anambra State, Nigeria.
{"title":"Isolation and Characterization of Glyphosate–Degrading Bacteria from Agricultural Soil in Awka, Anambra State, Nigeria","authors":"Obianuju Helen Obiefuna, S. Onuorah","doi":"10.56532/mjsat.v2i4.81","DOIUrl":"https://doi.org/10.56532/mjsat.v2i4.81","url":null,"abstract":"Glyphosate is a very effective pesticide; hence it has been excessively used in agricultural activities. This led to glyphosate residue accumulation in the soil and resulted in various adverse effects on humans and the ecosystem. This necessitates the need to reduce glyphosate accumulation in the soil and microbial bioremediation can be the solution. Thus, this study aimed to isolate and characterize glyphosate degrading bacteria from agricultural soils exposed to glyphosate weed control method. Bacterial organisms were isolated from glyphosate polluted agricultural soil and were characterized using routine microbiological biochemical methods. The isolates were screened for glyphosate utilization using a mineral salt medium containing glyphosate as a carbon source. Confirmed glyphosate degraders were identified using 16s rDNA sequencing. These isolates were assessed for their ability to degrade 106.16 µg/ml glyphosate in varied volumes (1 ml, 1.5 ml and 2 ml), singly and in consortium. Glyphosate degraders were identified as Exiguobacterium alkaliphiluim, Alcaligenes faecalis, Sinorhizobuim fredii and Acinetobacter nosocomialis. These organisms significantly (p<0.05) degraded different glyphosate volumes as a consortium more than as individual organisms. This study has been able to show the different glyphosate degraders present in some glyphosate-polluted agricultural soils in Awka, Anambra State, Nigeria.","PeriodicalId":407405,"journal":{"name":"Malaysian Journal of Science and Advanced Technology","volume":"106 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131054556","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}
Over the years, development in control industry has brought a conventional controller, Proportional-Integral-Derivative (PID) controller as Brushless DC (BLDC) motor speed regulator. The PID controller suffers from lengthy design time due to the large number of rules and parameter tuning. Thus, this paper proposes a newly developed Sliding Mode Controller (SMC) to be used as the BLDC motor speed controller. SMC is a modern speed controller which is also a non-linear speed controller where it can show high performance controlling non-linear plant like BLDC motor. SMC gives a speed performance comparable to the PID but with much robust speed performance in terms of small overshoot and short settling time. The motor performance with SMC is evaluated through simulation and experimental approach in terms of speed response under several test conditions. The performance is then compared with the motor performance with PID speed controller. Overall, SMC is outperformed PID controller in terms of speed performance with no overshoot and less settling time.
{"title":"Sliding Mode Control of Brushless DC Motor Speed Control","authors":"Jun Wei Chan","doi":"10.56532/mjsat.v2i4.57","DOIUrl":"https://doi.org/10.56532/mjsat.v2i4.57","url":null,"abstract":"Over the years, development in control industry has brought a conventional controller, Proportional-Integral-Derivative (PID) controller as Brushless DC (BLDC) motor speed regulator. The PID controller suffers from lengthy design time due to the large number of rules and parameter tuning. Thus, this paper proposes a newly developed Sliding Mode Controller (SMC) to be used as the BLDC motor speed controller. SMC is a modern speed controller which is also a non-linear speed controller where it can show high performance controlling non-linear plant like BLDC motor. SMC gives a speed performance comparable to the PID but with much robust speed performance in terms of small overshoot and short settling time. The motor performance with SMC is evaluated through simulation and experimental approach in terms of speed response under several test conditions. The performance is then compared with the motor performance with PID speed controller. Overall, SMC is outperformed PID controller in terms of speed performance with no overshoot and less settling time.","PeriodicalId":407405,"journal":{"name":"Malaysian Journal of Science and Advanced Technology","volume":"606 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132347944","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}
Tanvir Ahmed, Rashidul Hasan Nabil, MD. Siyamul Islam
If rice infections spread, the agricultural industry as well as the people who eat rice as their primary food grain suffer greatly from production and financial losses as well as food shortages. One of the deadliest diseases that can affect paddy plants at any stage of development and hinder the growth of rice plants is paddy leaf blast. Because the brown spot and the leaf blast have the same appearance but distinct shapes, it is quite difficult to distinguish between them. In this case, paddy leaf blast is detected using computer vision methods. But because of their resemblance to other spots and poor color channel selection, previous procedures are difficult, time-consuming, and poorly able to detect blasts. In this article, an effective and automated image analysis method has been proposed to identify paddy leaf blasts that can identify leaf blasts by utilizing various shapes. Additionally, the process minimized pointless data exploration and provided superior accuracy of 95.34 percent.
{"title":"Detection of Paddy Blast: An Image Processing Approach with Threshold based OTSU","authors":"Tanvir Ahmed, Rashidul Hasan Nabil, MD. Siyamul Islam","doi":"10.56532/mjsat.v2i4.77","DOIUrl":"https://doi.org/10.56532/mjsat.v2i4.77","url":null,"abstract":"If rice infections spread, the agricultural industry as well as the people who eat rice as their primary food grain suffer greatly from production and financial losses as well as food shortages. One of the deadliest diseases that can affect paddy plants at any stage of development and hinder the growth of rice plants is paddy leaf blast. Because the brown spot and the leaf blast have the same appearance but distinct shapes, it is quite difficult to distinguish between them. In this case, paddy leaf blast is detected using computer vision methods. But because of their resemblance to other spots and poor color channel selection, previous procedures are difficult, time-consuming, and poorly able to detect blasts. In this article, an effective and automated image analysis method has been proposed to identify paddy leaf blasts that can identify leaf blasts by utilizing various shapes. Additionally, the process minimized pointless data exploration and provided superior accuracy of 95.34 percent.","PeriodicalId":407405,"journal":{"name":"Malaysian Journal of Science and Advanced Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122845327","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}
Sehan Amandu Gamage, Krishnan Subramaniam, A. Zainuddin
The decrease of surface area is a critical concern for any type of digital circuit. For example, the VLSI approach is used to lower the chip's size, which increases both the device's density and its performance. When it comes to digital circuits, a full adder circuit is a crucial part of any arithmetic processor. A computer, or any other type of computer, will have this component. Most arithmetic operations performed as of now are 64 bits. As a result, we need a sizable amount of room to complete this procedure. We can also take use of these advantages even if we increase the number of bits that need to be processed in parallel. This research attempts to demonstrate how a 4-bit CMOS-based full adder circuit is designed and simulated using Microwind and DSCH at various technology levels. It is then compared to determine if the transistor size may help achieve those benefits. Afterwards. A four-bit binary addition is the goal of the circuit that was built. A 4-bit full adder may be built using a totally automated CMOS design process. The concept and layout of a 4-bit full adder are developed in the initial CMOS design. With nodes of 90, 65 and 45 nm, the designs are produced and modelled utilizing technology. Digital integrated circuits with smaller nodes perform better when compared to those with larger ones, according to simulation findings and distinct outputs.
{"title":"Comparative Analysis of CMOS based Full Adders by Simulation in DSCH and Microwind","authors":"Sehan Amandu Gamage, Krishnan Subramaniam, A. Zainuddin","doi":"10.56532/mjsat.v2i4.63","DOIUrl":"https://doi.org/10.56532/mjsat.v2i4.63","url":null,"abstract":"The decrease of surface area is a critical concern for any type of digital circuit. For example, the VLSI approach is used to lower the chip's size, which increases both the device's density and its performance. When it comes to digital circuits, a full adder circuit is a crucial part of any arithmetic processor. A computer, or any other type of computer, will have this component. Most arithmetic operations performed as of now are 64 bits. As a result, we need a sizable amount of room to complete this procedure. We can also take use of these advantages even if we increase the number of bits that need to be processed in parallel. This research attempts to demonstrate how a 4-bit CMOS-based full adder circuit is designed and simulated using Microwind and DSCH at various technology levels. It is then compared to determine if the transistor size may help achieve those benefits. Afterwards. A four-bit binary addition is the goal of the circuit that was built. A 4-bit full adder may be built using a totally automated CMOS design process. The concept and layout of a 4-bit full adder are developed in the initial CMOS design. With nodes of 90, 65 and 45 nm, the designs are produced and modelled utilizing technology. Digital integrated circuits with smaller nodes perform better when compared to those with larger ones, according to simulation findings and distinct outputs.","PeriodicalId":407405,"journal":{"name":"Malaysian Journal of Science and Advanced Technology","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134222955","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}
Md. Nabobi Hasan, Mufrad Mustavi, Md. Abu Jubaer, Md. Tanvir Shahriar, Tanvir Ahmed
In this review paper, previous and current works for plant leaf disease detection have been studied. The traditional manual visual quality inspection cannot be defined systematically as this method is unpredictable and inconsistent. Moreover, it involves a remarkable amount of expertise in the field of plant disease diagnostics (phytopathology) in addition to the disproportionate processing times. Hence, image processing has been applied for the recognition of plant diseases. This paper has been divided into three main parts. In the first part, a comprehensive review based on algorithms is provided were the major algorithms and works conducted using image processing and artificial intelligence algorithms have been compared. The second part discusses the frameworks and compared the previous works. Then, a comprehensive discussion based on the accuracy of the results was provided. Based on the review conducted, a detailed explanation of the illnesses detection and classification performance is provided. Finally, the findings and challenges in plant leaf detection using image processing are summarized and discussed.
{"title":"Plant Leaf Disease Detection Using Image Processing: A Comprehensive Review","authors":"Md. Nabobi Hasan, Mufrad Mustavi, Md. Abu Jubaer, Md. Tanvir Shahriar, Tanvir Ahmed","doi":"10.56532/mjsat.v2i4.80","DOIUrl":"https://doi.org/10.56532/mjsat.v2i4.80","url":null,"abstract":"In this review paper, previous and current works for plant leaf disease detection have been studied. The traditional manual visual quality inspection cannot be defined systematically as this method is unpredictable and inconsistent. Moreover, it involves a remarkable amount of expertise in the field of plant disease diagnostics (phytopathology) in addition to the disproportionate processing times. Hence, image processing has been applied for the recognition of plant diseases. This paper has been divided into three main parts. In the first part, a comprehensive review based on algorithms is provided were the major algorithms and works conducted using image processing and artificial intelligence algorithms have been compared. The second part discusses the frameworks and compared the previous works. Then, a comprehensive discussion based on the accuracy of the results was provided. Based on the review conducted, a detailed explanation of the illnesses detection and classification performance is provided. Finally, the findings and challenges in plant leaf detection using image processing are summarized and discussed.","PeriodicalId":407405,"journal":{"name":"Malaysian Journal of Science and Advanced Technology","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133512873","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}
D. Bouchiha, Abdelghani Bouziane, Noureddine Doumi
The ultimate aim of Machine Learning (ML) is to make machine acts like a human. In particular, ML algorithms are widely used to classify texts. Text classification is the process of classifying texts into a predefined set of categories based on the texts’ content. It contributes to improving information retrieval on the Web. In this paper, we focus on the "Arabic" text classification since there is a large community in the world that uses this language. The Arabic text classification process consists of three main steps: preprocessing, feature extraction and ML algorithm. This paper presents a comparative empirical study to see which combination (feature extraction - ML algorithm) acts well when dealing with Arabic documents. So, we implemented one hundred sixty classifiers by combining 5 feature extraction techniques and 32 machine learning algorithms. Then, we made these classifiers open access for the benefit of the AI and NLP communities. Experiments were carried out using a huge open dataset. The comparison study reveals that TFIDF-Perceptron is the best performing combination of a classifier.
{"title":"Machine Learning for Arabic Text Classification: A Comparative Study","authors":"D. Bouchiha, Abdelghani Bouziane, Noureddine Doumi","doi":"10.56532/mjsat.v2i4.83","DOIUrl":"https://doi.org/10.56532/mjsat.v2i4.83","url":null,"abstract":"The ultimate aim of Machine Learning (ML) is to make machine acts like a human. In particular, ML algorithms are widely used to classify texts. Text classification is the process of classifying texts into a predefined set of categories based on the texts’ content. It contributes to improving information retrieval on the Web. In this paper, we focus on the \"Arabic\" text classification since there is a large community in the world that uses this language. The Arabic text classification process consists of three main steps: preprocessing, feature extraction and ML algorithm. This paper presents a comparative empirical study to see which combination (feature extraction - ML algorithm) acts well when dealing with Arabic documents. So, we implemented one hundred sixty classifiers by combining 5 feature extraction techniques and 32 machine learning algorithms. Then, we made these classifiers open access for the benefit of the AI and NLP communities. Experiments were carried out using a huge open dataset. The comparison study reveals that TFIDF-Perceptron is the best performing combination of a classifier.","PeriodicalId":407405,"journal":{"name":"Malaysian Journal of Science and Advanced Technology","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116302548","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}
Md. Abdul Al Mohit, Md. Towhiduzzaman, Mossa. Samima Nasrin, Mst. Rabiba Khatun
This study investigates the impact of climate change on the genesis of storms in the Bay of Bengal. Almost all the countries of the world are facing losses due to the global warming issue and related climate disasters. Bangladesh is one of the most vulnerable countries in South Asia facing damage due to climate change. In this study, the characteristic features of genesis have been analysed using the probability formula in the small latitude area of 2 degrees. To analyse the characteristics of Genesis's behaviour, we reviewed storms that occurred in the 21st century. A reliable probability calibration is derived for every 2 degrees of latitude that explains the changes of genesis due to climate changes. For a clear view of climate change's impact on cyclone genesis, we have regenerated the study domain in a 1 by 1-degree longitude and latitude box. Which represents the clear view of genesis probability. And, it is clearly viewed that the genesis will be shifted from low latitude to high latitude.
{"title":"Investigation of the Effects of Climate Change on Tropical Storms and their Genesis in the Bay of Bengal","authors":"Md. Abdul Al Mohit, Md. Towhiduzzaman, Mossa. Samima Nasrin, Mst. Rabiba Khatun","doi":"10.56532/mjsat.v2i4.78","DOIUrl":"https://doi.org/10.56532/mjsat.v2i4.78","url":null,"abstract":"This study investigates the impact of climate change on the genesis of storms in the Bay of Bengal. Almost all the countries of the world are facing losses due to the global warming issue and related climate disasters. Bangladesh is one of the most vulnerable countries in South Asia facing damage due to climate change. In this study, the characteristic features of genesis have been analysed using the probability formula in the small latitude area of 2 degrees. To analyse the characteristics of Genesis's behaviour, we reviewed storms that occurred in the 21st century. A reliable probability calibration is derived for every 2 degrees of latitude that explains the changes of genesis due to climate changes. For a clear view of climate change's impact on cyclone genesis, we have regenerated the study domain in a 1 by 1-degree longitude and latitude box. Which represents the clear view of genesis probability. And, it is clearly viewed that the genesis will be shifted from low latitude to high latitude.","PeriodicalId":407405,"journal":{"name":"Malaysian Journal of Science and Advanced Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117048705","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：