Pub Date : 2022-08-24DOI: 10.24032/ijeacs/0407/001
Haoning Pu, Zhan Wen, Bing Wan
{"title":"Research on Bearing Fault Detection Algorithm Based on Convolution Neural Network and SVM","authors":"Haoning Pu, Zhan Wen, Bing Wan","doi":"10.24032/ijeacs/0407/001","DOIUrl":"https://doi.org/10.24032/ijeacs/0407/001","url":null,"abstract":"","PeriodicalId":423763,"journal":{"name":"International Journal of Engineering and Applied Computer Science","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126187123","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 : 2022-07-31DOI: 10.24032/ijeacs/0406/002
Abubakar Bala, Adeleke Hafiz Adesupo, Ohemu Monday Fredrick, Ibrahim Baba Kyari, Umaru Ibrahim Zubairu, B. Muhammad
{"title":"Parameters Identification of Induction Motor Using Bacterial Foraging Algorithm","authors":"Abubakar Bala, Adeleke Hafiz Adesupo, Ohemu Monday Fredrick, Ibrahim Baba Kyari, Umaru Ibrahim Zubairu, B. Muhammad","doi":"10.24032/ijeacs/0406/002","DOIUrl":"https://doi.org/10.24032/ijeacs/0406/002","url":null,"abstract":"","PeriodicalId":423763,"journal":{"name":"International Journal of Engineering and Applied Computer Science","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130421476","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 : 2022-06-04DOI: 10.24032/ijeacs/0404/011
I. Adeyemo, O. Adegbola, O. W. Adebiyi
This paper presents a study of a single-phase cascaded H-bridge multilevel converter-based Distribution Static Synchronous Compensator (D-STATCOM) with active harmonic filtering capability. For the proper operation of the proposed D-STATCOM, a constant voltage is maintained at its DC bus link using a proportional and integral (PI) controller. Based on instantaneous current errors, gate pulses for controlling duty cycles of the D-STATCOM operation are generated using the hysteresis current control (HCC) technique. The proposed D-STATCOM was modeled and simulated in MATLAB. Simulation results show that the proposed method effectively compensates for reactive power and mitigates current harmonics. The proposed method offers structural simplicity and efficiency without complex calculations.
{"title":"Reactive Power Compensation and Harmonic Mitigation in Single-Phase Distribution System using Multilevel Converter Based D-STATCOM","authors":"I. Adeyemo, O. Adegbola, O. W. Adebiyi","doi":"10.24032/ijeacs/0404/011","DOIUrl":"https://doi.org/10.24032/ijeacs/0404/011","url":null,"abstract":"This paper presents a study of a single-phase cascaded H-bridge multilevel converter-based Distribution Static Synchronous Compensator (D-STATCOM) with active harmonic filtering capability. For the proper operation of the proposed D-STATCOM, a constant voltage is maintained at its DC bus link using a proportional and integral (PI) controller. Based on instantaneous current errors, gate pulses for controlling duty cycles of the D-STATCOM operation are generated using the hysteresis current control (HCC) technique. The proposed D-STATCOM was modeled and simulated in MATLAB. Simulation results show that the proposed method effectively compensates for reactive power and mitigates current harmonics. The proposed method offers structural simplicity and efficiency without complex calculations.","PeriodicalId":423763,"journal":{"name":"International Journal of Engineering and Applied Computer Science","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125276849","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 : 2022-06-03DOI: 10.24032/ijeacs/0404/010
Thobius Joseph, H. Wanga, F. Samson, S. Kituma
The paper provides a prototype for multimedia content delivery with reduced channel code rate from conventional Non-Transmittable Codewords Enhanced Viterbi Algorithm. The code rate reduction was simulated using VB.NET Viterbi simulator available at College of Informatics and Virtual Education-University of Dodoma. The study approximates Uplink and downlink speeds limits of the prototype using High Speed Packet Access Evolved technology by assuming all other parameters remain constant. The uplink and downlink of the prototype is clearly presented. The code rate of 1/3 was obtained by simulating different 8-bits patterns. This code rate of 1/3 enabled reduction of encoder output bits from 48-bits to 24-bits, therefore, few bits would be sent to the network and bandwidth conservation is attained. This makes the prototype to be the good choice for low network bandwidth channel. In addition, the reduced code rate will reduce the expenses of user internet bundles, because number of MBs to be charged will be smaller. This prototype for multimedia delivery over network has three benefits, high data transmission reliability due to adopted NTC Enhanced Viterbi, minimum network bandwidth utilization and satisfied uplink and downlink access speed.
{"title":"Prototype for Multimedia Content Delivery based on Non-Transmittable Codewords Enhanced Viterbi Algorithm","authors":"Thobius Joseph, H. Wanga, F. Samson, S. Kituma","doi":"10.24032/ijeacs/0404/010","DOIUrl":"https://doi.org/10.24032/ijeacs/0404/010","url":null,"abstract":"The paper provides a prototype for multimedia content delivery with reduced channel code rate from conventional Non-Transmittable Codewords Enhanced Viterbi Algorithm. The code rate reduction was simulated using VB.NET Viterbi simulator available at College of Informatics and Virtual Education-University of Dodoma. The study approximates Uplink and downlink speeds limits of the prototype using High Speed Packet Access Evolved technology by assuming all other parameters remain constant. The uplink and downlink of the prototype is clearly presented. The code rate of 1/3 was obtained by simulating different 8-bits patterns. This code rate of 1/3 enabled reduction of encoder output bits from 48-bits to 24-bits, therefore, few bits would be sent to the network and bandwidth conservation is attained. This makes the prototype to be the good choice for low network bandwidth channel. In addition, the reduced code rate will reduce the expenses of user internet bundles, because number of MBs to be charged will be smaller. This prototype for multimedia delivery over network has three benefits, high data transmission reliability due to adopted NTC Enhanced Viterbi, minimum network bandwidth utilization and satisfied uplink and downlink access speed.","PeriodicalId":423763,"journal":{"name":"International Journal of Engineering and Applied Computer Science","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133581528","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}
Results of analysis carried out on data of Covid19, in Tabasco State, are presented, from March 2020 to February 2022. The procedure named 7 day´s moving average was applied to smooth the original graph and, in this way, analyze the data more easily. Fast Fourier transform (FFT) was applied to find the frequency that allows us to detect the period (in weeks) of generation of greater Covid19 infections. FFT allows us to determine that for a period of 14n weeks (n=1,3,5,7) there will be a new outbreak. The analysis of data reveals, during the first wave, the week with the highest number of infections was July 7-12 (2751 cases), that is in week 14 ( n=1). FFT indicates that the second wave of infection would be in week 42 with n=3, the maximum was obtained at week 40 (2122 cases). The next prediction (variant Delta) was for week 70 (n=5), where there would be a high number of cases (thrid wave); real data indicates that it was reached in week 73 (7,023 cases). The four-wave (Omicron) is predicted for week 98, however, it was reached in week 94 (12,834 cases). It should be noted that due to the high transmissibility of Omicron, the number of infection grew fast during January 2022, so in this case, the difference between the prediction and the reality, present a difference of four week, however, for week 94 number of cases remains very high (1265 cases). FFT has turned out to be an adequate tool to make predictions of four waves that have occurred in Tabasco.
{"title":"Outbreaks Predictions of Covid19 in Tabasco, Mexico, using Fast Fourier Transform","authors":"Manuel Sandoval Martínez, Janette Moreno Sandoval, Claudia Morales Barrón, Luz Elba Castillo Izquierdo","doi":"10.24032/ijeacs/0404/012","DOIUrl":"https://doi.org/10.24032/ijeacs/0404/012","url":null,"abstract":"Results of analysis carried out on data of Covid19, in Tabasco State, are presented, from March 2020 to February 2022. The procedure named 7 day´s moving average was applied to smooth the original graph and, in this way, analyze the data more easily. Fast Fourier transform (FFT) was applied to find the frequency that allows us to detect the period (in weeks) of generation of greater Covid19 infections. FFT allows us to determine that for a period of 14n weeks (n=1,3,5,7) there will be a new outbreak. The analysis of data reveals, during the first wave, the week with the highest number of infections was July 7-12 (2751 cases), that is in week 14 ( n=1). FFT indicates that the second wave of infection would be in week 42 with n=3, the maximum was obtained at week 40 (2122 cases). The next prediction (variant Delta) was for week 70 (n=5), where there would be a high number of cases (thrid wave); real data indicates that it was reached in week 73 (7,023 cases). The four-wave (Omicron) is predicted for week 98, however, it was reached in week 94 (12,834 cases). It should be noted that due to the high transmissibility of Omicron, the number of infection grew fast during January 2022, so in this case, the difference between the prediction and the reality, present a difference of four week, however, for week 94 number of cases remains very high (1265 cases). FFT has turned out to be an adequate tool to make predictions of four waves that have occurred in Tabasco.","PeriodicalId":423763,"journal":{"name":"International Journal of Engineering and Applied Computer Science","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116914169","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 : 2022-05-23DOI: 10.24032/ijeacs/0404/004
Yogendra Kumar Sharma, Imran Khan
VLSI technology development nowadays is mostly focused on the downsizing of semiconductor devices, which is significantly reliant on advancements in complementary metal-oxide-semiconductor technology. Due to capacitance, shorter channel length, body biassing, faster-switching transistor, limited variability, and faster running transistor, Silicon-on-Insulator technology has seen a lot of changes. In comparison to traditional bulk technology, Silicon on Insulator offers intriguing new possibilities. The recent stalling of advancement in CMOS technology has been noticed. A fully depleted silicon on the insulator provides additional performance. Power usage and communication speed are two areas where performance can be improved. Silicon on insulator technology has the potential to reduce power consumption by nearly half while increasing speed by about 40%. Using the Atlas module of the SILVACO software, the research presents a comprehensive analysis of silicon on insulator-based nano metal oxide semiconductor field-effect transistors. Atlas is used to virtually construct a 20 nm silicon on insulator MOSFET. The gate metals employed are Aluminum, N. poly, W (Tungsten), and WSi2 (Tungsten Silicide), and their respective characteristics are obtained and compared. Finally, WSi2 was chosen as the final gate metal because it has the desired band offset, resulting in a positive threshold voltage without the need for any further implants in the channel region. Other metrics are collected, such as the variation of ID vs. VGS features at various values. There is also a fluctuation in drain current as a function of drain to source voltage.
{"title":"Performance Evaluation of Fully Depleted Silicon on Insulator MOSFET","authors":"Yogendra Kumar Sharma, Imran Khan","doi":"10.24032/ijeacs/0404/004","DOIUrl":"https://doi.org/10.24032/ijeacs/0404/004","url":null,"abstract":"VLSI technology development nowadays is mostly focused on the downsizing of semiconductor devices, which is significantly reliant on advancements in complementary metal-oxide-semiconductor technology. Due to capacitance, shorter channel length, body biassing, faster-switching transistor, limited variability, and faster running transistor, Silicon-on-Insulator technology has seen a lot of changes. In comparison to traditional bulk technology, Silicon on Insulator offers intriguing new possibilities. The recent stalling of advancement in CMOS technology has been noticed. A fully depleted silicon on the insulator provides additional performance. Power usage and communication speed are two areas where performance can be improved. Silicon on insulator technology has the potential to reduce power consumption by nearly half while increasing speed by about 40%. Using the Atlas module of the SILVACO software, the research presents a comprehensive analysis of silicon on insulator-based nano metal oxide semiconductor field-effect transistors. Atlas is used to virtually construct a 20 nm silicon on insulator MOSFET. The gate metals employed are Aluminum, N. poly, W (Tungsten), and WSi2 (Tungsten Silicide), and their respective characteristics are obtained and compared. Finally, WSi2 was chosen as the final gate metal because it has the desired band offset, resulting in a positive threshold voltage without the need for any further implants in the channel region. Other metrics are collected, such as the variation of ID vs. VGS features at various values. There is also a fluctuation in drain current as a function of drain to source voltage.","PeriodicalId":423763,"journal":{"name":"International Journal of Engineering and Applied Computer Science","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134476885","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 : 2022-05-22DOI: 10.24032/ijeacs/0404/009
Olatunji Timothy Ogbeye, Felix Ola Aranuwa, O. Oriola, Alaba Olu Akingbesote, Ayokunle Olalekan Ige
The tourism information system in Nigeria is not novel. What is novel is the need to develop reliable real-time recommender systems that can adequately aid tourists in their decisions. Several researchers have proposed various models. However, there are still issues about the applicability, effectiveness, efficiency, and reliability of the existing recommenders in the Nigerian tourism sector. This work is aimed at developing an improved model for real-time tourism recommender in Nigeria based on a data mining model. The objectives include the development of a data mining model for real-time reliable user-centric tourism recommendation and evaluation of the recommender system. To achieve these, a supervised machine learning-based classifier is modelled. The classifier system is evaluated using four thousand (4,000) datasets acquired from online and physical Nigerian tourism sources. Nine machine learning algorithms are compared during the testing process based on accuracy and other standard performance metrics. Experimental results show that the PART algorithm outperforms all other algorithms with an accuracy of 91.65%, F-Measure of 0.917, true positive rate of 0.913, the false-positive rate of 0.029, and the precision of 0.917, and recall of 0.917. In terms of efficiency, it also records the least time-to-model of 0.02 seconds. The rules generated from this algorithm are incorporated into the design of a prototype to test the recommender. The usefulness and efficiency scores based on test cases involving 20 participants prove that the recommender system would be a veritable tool for tourism in Nigeria.
{"title":"Data Mining-based Real-Time User-centric Recommender System for Nigerian Tourism Industry","authors":"Olatunji Timothy Ogbeye, Felix Ola Aranuwa, O. Oriola, Alaba Olu Akingbesote, Ayokunle Olalekan Ige","doi":"10.24032/ijeacs/0404/009","DOIUrl":"https://doi.org/10.24032/ijeacs/0404/009","url":null,"abstract":"The tourism information system in Nigeria is not novel. What is novel is the need to develop reliable real-time recommender systems that can adequately aid tourists in their decisions. Several researchers have proposed various models. However, there are still issues about the applicability, effectiveness, efficiency, and reliability of the existing recommenders in the Nigerian tourism sector. This work is aimed at developing an improved model for real-time tourism recommender in Nigeria based on a data mining model. The objectives include the development of a data mining model for real-time reliable user-centric tourism recommendation and evaluation of the recommender system. To achieve these, a supervised machine learning-based classifier is modelled. The classifier system is evaluated using four thousand (4,000) datasets acquired from online and physical Nigerian tourism sources. Nine machine learning algorithms are compared during the testing process based on accuracy and other standard performance metrics. Experimental results show that the PART algorithm outperforms all other algorithms with an accuracy of 91.65%, F-Measure of 0.917, true positive rate of 0.913, the false-positive rate of 0.029, and the precision of 0.917, and recall of 0.917. In terms of efficiency, it also records the least time-to-model of 0.02 seconds. The rules generated from this algorithm are incorporated into the design of a prototype to test the recommender. The usefulness and efficiency scores based on test cases involving 20 participants prove that the recommender system would be a veritable tool for tourism in Nigeria.","PeriodicalId":423763,"journal":{"name":"International Journal of Engineering and Applied Computer Science","volume":"55 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115979018","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 : 2022-05-22DOI: 10.24032/ijeacs/0404/007
Abdool Qaiyum Mohabuth, Ibrahim Haashim Gunnoo
Landscape architecture is a comparatively new concept and is gaining prominence in town and country planning exercises. People marveled at the design of new towns when the infrastructure looks nice and well placed. However, when the planning exercise is not done properly this results in the implementation of poor infrastructure with narrow roads, lack of green spaces, no parking spots, congested streets and so. Architects are still using traditional hand drawing for their designs and sketches which have several limitations. Developing a landscape architecture planning system with appropriate tools will facilitate architects’ tasks and others to have an appropriate to ensure proper landscape planning without unnecessarily wasting time manually. This paper aims to present a desktop application with features for generating appropriate cartography which allows users to place appropriate objects representing real-world urban structures and buildings. The Waterfall methodology was used to build and implement the proposed system. The latter is expected to help in the reduction of parking problems and increase the number of green areas in towns. The application proposed includes appropriate validation techniques to allow users to plan a site and made sure that the standards set for parking spaces and green areas are being respected.
{"title":"A Digital Planning Tool for Shaping Up the Landscaping Architecture","authors":"Abdool Qaiyum Mohabuth, Ibrahim Haashim Gunnoo","doi":"10.24032/ijeacs/0404/007","DOIUrl":"https://doi.org/10.24032/ijeacs/0404/007","url":null,"abstract":"Landscape architecture is a comparatively new concept and is gaining prominence in town and country planning exercises. People marveled at the design of new towns when the infrastructure looks nice and well placed. However, when the planning exercise is not done properly this results in the implementation of poor infrastructure with narrow roads, lack of green spaces, no parking spots, congested streets and so. Architects are still using traditional hand drawing for their designs and sketches which have several limitations. Developing a landscape architecture planning system with appropriate tools will facilitate architects’ tasks and others to have an appropriate to ensure proper landscape planning without unnecessarily wasting time manually. This paper aims to present a desktop application with features for generating appropriate cartography which allows users to place appropriate objects representing real-world urban structures and buildings. The Waterfall methodology was used to build and implement the proposed system. The latter is expected to help in the reduction of parking problems and increase the number of green areas in towns. The application proposed includes appropriate validation techniques to allow users to plan a site and made sure that the standards set for parking spaces and green areas are being respected.","PeriodicalId":423763,"journal":{"name":"International Journal of Engineering and Applied Computer Science","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114836161","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 : 2022-05-20DOI: 10.24032/ijeacs/0404/005
Stanley Ziweritin
The huge amount of library data stored in our modern research and statistic centers of organizations is springing up on daily bases. These databases grow exponentially in size with respect to time, it becomes exceptionally difficult to easily understand the behavior and interpret data with the relationships that exist between attributes. This exponential growth of data poses new organizational challenges like the conventional record management system infrastructure could no longer cope to give precise and detailed information about the behavior data over time. There is confusion and novel concern in selecting tools that can support and handle big data visualization that deals with multi-dimension. Viewing all related data at once in a database is a problem that has attracted the interest of data professionals with machine learning skills. This is a lingering issue in the data industry because the existing techniques cannot be used to remove or filter noise from relevant data and pad up missing values in order to get the required information. The aim is to develop a stacked generalization model that combines the functionality of random forest and decision tree to visualization library database visualization. In this paper, the random forest and decision tree techniques were employed to effectively visualize large amounts of school library data. The proposed system was implemented with a few lines of Python code to create visualizations that can help users at a glance understand and interpret the behavior of data and its relationships. The model was trained and tested to learn and extract hidden patterns of data with a cross-validation test. It combined the functionalities of both models to form a stacked generalization model that performed better than the individual techniques. The stacked model produced 95% followed by the RF which produced a 95% accuracy rate and 0.223600 RMSE error value in comparison with the DT which recorded an 80.00% success rate and 0.15990 RMSE value.
{"title":"Stacked Generalization of Random Forest and Decision Tree Techniques for Library Data Visualization","authors":"Stanley Ziweritin","doi":"10.24032/ijeacs/0404/005","DOIUrl":"https://doi.org/10.24032/ijeacs/0404/005","url":null,"abstract":"The huge amount of library data stored in our modern research and statistic centers of organizations is springing up on daily bases. These databases grow exponentially in size with respect to time, it becomes exceptionally difficult to easily understand the behavior and interpret data with the relationships that exist between attributes. This exponential growth of data poses new organizational challenges like the conventional record management system infrastructure could no longer cope to give precise and detailed information about the behavior data over time. There is confusion and novel concern in selecting tools that can support and handle big data visualization that deals with multi-dimension. Viewing all related data at once in a database is a problem that has attracted the interest of data professionals with machine learning skills. This is a lingering issue in the data industry because the existing techniques cannot be used to remove or filter noise from relevant data and pad up missing values in order to get the required information. The aim is to develop a stacked generalization model that combines the functionality of random forest and decision tree to visualization library database visualization. In this paper, the random forest and decision tree techniques were employed to effectively visualize large amounts of school library data. The proposed system was implemented with a few lines of Python code to create visualizations that can help users at a glance understand and interpret the behavior of data and its relationships. The model was trained and tested to learn and extract hidden patterns of data with a cross-validation test. It combined the functionalities of both models to form a stacked generalization model that performed better than the individual techniques. The stacked model produced 95% followed by the RF which produced a 95% accuracy rate and 0.223600 RMSE error value in comparison with the DT which recorded an 80.00% success rate and 0.15990 RMSE value.","PeriodicalId":423763,"journal":{"name":"International Journal of Engineering and Applied Computer Science","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125658569","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 : 2022-05-20DOI: 10.24032/ijeacs/0404/003
A. F M Nazmus Sadat, N. Zahan, Debobrata Sharma, Khairunnahar Smriti, Fatema Tuz Zohora, Sanjida Halim, Mohammad Ali, Imranul Kabir, Sayeda Khadija Tuj Johora, A. Sultana
Bryophyllum pinnatum is a potential medicinal plant widely used in different tribes in Bangladesh. The leaves of B. pinnatum were used in the present study for the compatibility assessment of a proposed ultrasound-assisted green extraction method with the conventional extraction method. An aqueous Ultrasound-Assisted Extraction (UAE) by using both fresh and dried leaves of B. pinnatum was proposed in the present study and successively compared with the traditional methanolic and aqueous (decoction) extraction method. The promising extraction yield was found through the proposed extraction method which was much better than decoction and almost similar to the methanolic extraction method. Phytochemical contents were also observed similar to the methanolic extract. Both methanolic and UAE extracts obtained from B. pinnatum leaves showed favorable antimicrobial sensitivity against both grams positive (Staphylococcus aureus and Streptococcus pyogenes) and gram-negative (Escherichia coli and Salmonella typhi) bacteria. Extracts obtained from the decoction method showed slightly poor antimicrobial activities. The difference in efficiency and efficacy of aqueous UAE extract obtained from fresh and dried leaves was observed insignificant. This indicates there is no necessity to impart the drying stage before extraction normally practiced in the conventional extraction method. Drying of plant material is a common stage of the conventional extraction cycle which ultimately lengthy the process and impose cost due to energy consumption and labor. Ultrasound-assisted extraction may successfully decrease the overall extraction cycle and ultimately reduce the overall cost of extraction. This method also creates opportunities to replace the water instead of with hazardous organic solvent for phytochemical extraction.
{"title":"Comparative Phytochemical and Antimicrobial Study of Ultrasound-Assisted Aqueous Extract from Fresh Plants of Bryophyllum pinnatum with Conventional Extraction Method","authors":"A. F M Nazmus Sadat, N. Zahan, Debobrata Sharma, Khairunnahar Smriti, Fatema Tuz Zohora, Sanjida Halim, Mohammad Ali, Imranul Kabir, Sayeda Khadija Tuj Johora, A. Sultana","doi":"10.24032/ijeacs/0404/003","DOIUrl":"https://doi.org/10.24032/ijeacs/0404/003","url":null,"abstract":"Bryophyllum pinnatum is a potential medicinal plant widely used in different tribes in Bangladesh. The leaves of B. pinnatum were used in the present study for the compatibility assessment of a proposed ultrasound-assisted green extraction method with the conventional extraction method. An aqueous Ultrasound-Assisted Extraction (UAE) by using both fresh and dried leaves of B. pinnatum was proposed in the present study and successively compared with the traditional methanolic and aqueous (decoction) extraction method. The promising extraction yield was found through the proposed extraction method which was much better than decoction and almost similar to the methanolic extraction method. Phytochemical contents were also observed similar to the methanolic extract. Both methanolic and UAE extracts obtained from B. pinnatum leaves showed favorable antimicrobial sensitivity against both grams positive (Staphylococcus aureus and Streptococcus pyogenes) and gram-negative (Escherichia coli and Salmonella typhi) bacteria. Extracts obtained from the decoction method showed slightly poor antimicrobial activities. The difference in efficiency and efficacy of aqueous UAE extract obtained from fresh and dried leaves was observed insignificant. This indicates there is no necessity to impart the drying stage before extraction normally practiced in the conventional extraction method. Drying of plant material is a common stage of the conventional extraction cycle which ultimately lengthy the process and impose cost due to energy consumption and labor. Ultrasound-assisted extraction may successfully decrease the overall extraction cycle and ultimately reduce the overall cost of extraction. This method also creates opportunities to replace the water instead of with hazardous organic solvent for phytochemical extraction.","PeriodicalId":423763,"journal":{"name":"International Journal of Engineering and Applied Computer Science","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114430625","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：