Ari Kurniawan Saputra, E. Erlangga, Tia Tanjung, F. Ariani, Y. Aprilinda, R. Y. Endra
Machine Learning can be used to process a lot of data and learn patterns from that data to predict the future. One of the most widely used parts of machine learning is Deep Learning. The Deep Learning method that currently provides the most significant results in image recognition is Convolutional Neural Network (CNN). Convolutional Neural Network (CNN) is one of the deep learning algorithms used for computer vision use cases such as image or video classification and detecting objects within images or even image areas. Some research related to the CNN model states that this model has a very good accuracy of 92% but with a fairly small amount of data and the use of epochs, namely 100, resulting in a higher validation error value than the error value in the training process, so that over fitting will occur. Based on several problems in the related research literature, this article aims to identify the weaknesses and shortcomings of Deep Learning algorithms using CNN models that refer to the state of the art, so that they can be used as a reference for further research. The state of the art related to research in the last five years, the Deep Learning algorithm using the CNN model found that (1) The number of epochs can affect the accuracy of the CNN model, (2) 2. The application of architecture can affect the accuracy of the CNN model, (3) the application of the type of layer can affect the accuracy of the CNN model. Based on several problems in the research literature related to the identification of weaknesses and shortcomings of Deep Learning using the CNN model which refers to Table 1. State of the Art summary of literature review research for the last five years, it can be concluded that to increase the accuracy of the CNN model, it is necessary to increase the number of epochs, apply the right architecture according to the problems in the research conducted, and use the type of layer. The hypothesis of this article can be used as a reference for further research related to Deep Learning using the CNN model.
{"title":"Review of Deep Learning Using Convolutional Neural Network Model","authors":"Ari Kurniawan Saputra, E. Erlangga, Tia Tanjung, F. Ariani, Y. Aprilinda, R. Y. Endra","doi":"10.4028/p-kzq3xe","DOIUrl":"https://doi.org/10.4028/p-kzq3xe","url":null,"abstract":"Machine Learning can be used to process a lot of data and learn patterns from that data to predict the future. One of the most widely used parts of machine learning is Deep Learning. The Deep Learning method that currently provides the most significant results in image recognition is Convolutional Neural Network (CNN). Convolutional Neural Network (CNN) is one of the deep learning algorithms used for computer vision use cases such as image or video classification and detecting objects within images or even image areas. Some research related to the CNN model states that this model has a very good accuracy of 92% but with a fairly small amount of data and the use of epochs, namely 100, resulting in a higher validation error value than the error value in the training process, so that over fitting will occur. Based on several problems in the related research literature, this article aims to identify the weaknesses and shortcomings of Deep Learning algorithms using CNN models that refer to the state of the art, so that they can be used as a reference for further research. The state of the art related to research in the last five years, the Deep Learning algorithm using the CNN model found that (1) The number of epochs can affect the accuracy of the CNN model, (2) 2. The application of architecture can affect the accuracy of the CNN model, (3) the application of the type of layer can affect the accuracy of the CNN model. Based on several problems in the research literature related to the identification of weaknesses and shortcomings of Deep Learning using the CNN model which refers to Table 1. State of the Art summary of literature review research for the last five years, it can be concluded that to increase the accuracy of the CNN model, it is necessary to increase the number of epochs, apply the right architecture according to the problems in the research conducted, and use the type of layer. The hypothesis of this article can be used as a reference for further research related to Deep Learning using the CNN model.","PeriodicalId":512976,"journal":{"name":"Engineering Headway","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140264968","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}
Tia Tanjung, R. Muhida, Muhammad Riza, Ari Kurniawan Saputra, E. Erlangga, Nofian Pratama, F. Ariani, Taqwan Thamrin, R. Y. Endra, A. K. Puspa, W. Susanty, A. Cucus
The application of artificial intelligence (AI) in the manufacturing and service industries has witnessed rapid advancements in recent years. One prominent aspect is the utilization of Natural Language Processing (NLP) to facilitate human-machine interactions and enhance efficiency and user experience. This journal explores the implementation of NLP in the context of the manufacturing and service industry, focusing on the skateboard monitoring device. We demonstrate how NLP can improve analysis, prediction, and personalization in skateboard production, providing users with a more interactive and informative experience.
{"title":"The Implementation of Natural Language Processing in Manufacturing and Service Industry through Skateboard Monitoring Device","authors":"Tia Tanjung, R. Muhida, Muhammad Riza, Ari Kurniawan Saputra, E. Erlangga, Nofian Pratama, F. Ariani, Taqwan Thamrin, R. Y. Endra, A. K. Puspa, W. Susanty, A. Cucus","doi":"10.4028/p-piuwy7","DOIUrl":"https://doi.org/10.4028/p-piuwy7","url":null,"abstract":"The application of artificial intelligence (AI) in the manufacturing and service industries has witnessed rapid advancements in recent years. One prominent aspect is the utilization of Natural Language Processing (NLP) to facilitate human-machine interactions and enhance efficiency and user experience. This journal explores the implementation of NLP in the context of the manufacturing and service industry, focusing on the skateboard monitoring device. We demonstrate how NLP can improve analysis, prediction, and personalization in skateboard production, providing users with a more interactive and informative experience.","PeriodicalId":512976,"journal":{"name":"Engineering Headway","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140078606","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}
Gusti Ayu Widayanti, H. Widjajanti, S. Salni, A. Sutjipto
Endophytic fungi are microbes that live in plant tissues and can synthesize the same active biochemical compounds as their hosts. This study aims to determine the type of endophytic fungi of Jeruju leaves (Acanthus ilicifolius) isolate DJS1. This research was conducted in January 2020 and is a type of descriptive qualitative research. The subjects in this study were one type of endophytic fungi isolate that has the potential as an antibacterial. Identification of endophytic fungi of Jeruju leaves (Acanthus ilicifolius) isolated DJS1 which have antibacterial potential by observing macroscopic and microscopic morphological phenotypic characters. Macroscopic observations described the form of colony structure, aerial hyphae forms, and radial lines that appeared on the fungal isolates. Microscopic observations were made to observe the shape of the hyphae and the shape of the conidia. While molecular observations were carried out by amplifying DNA using ITS primers.
内生真菌是生活在植物组织中的微生物，能合成与其宿主相同的活性生化化合物。本研究旨在确定Jeruju叶（Acanthus ilicifolius）分离物DJS1的内生真菌类型。本研究于 2020 年 1 月进行，属于描述性定性研究。研究对象是一种具有抗菌潜力的内生真菌分离物。通过观察宏观和微观形态表型特征，鉴定分离出的具有抗菌潜力的Jeruju叶（Acanthus ilicifolius）内生真菌DJS1。宏观观察描述了真菌分离物上出现的菌落结构形式、气生菌丝形式和放射线。显微镜观察是为了观察菌丝的形状和分生孢子的形状。分子观察是通过使用 ITS 引物扩增 DNA 进行的。
{"title":"Identification of Endophytic Fungi on the Leaves of Jeruju (Acanthus ilicifolius) which are Potential as Antibacteria","authors":"Gusti Ayu Widayanti, H. Widjajanti, S. Salni, A. Sutjipto","doi":"10.4028/p-lzq74e","DOIUrl":"https://doi.org/10.4028/p-lzq74e","url":null,"abstract":"Endophytic fungi are microbes that live in plant tissues and can synthesize the same active biochemical compounds as their hosts. This study aims to determine the type of endophytic fungi of Jeruju leaves (Acanthus ilicifolius) isolate DJS1. This research was conducted in January 2020 and is a type of descriptive qualitative research. The subjects in this study were one type of endophytic fungi isolate that has the potential as an antibacterial. Identification of endophytic fungi of Jeruju leaves (Acanthus ilicifolius) isolated DJS1 which have antibacterial potential by observing macroscopic and microscopic morphological phenotypic characters. Macroscopic observations described the form of colony structure, aerial hyphae forms, and radial lines that appeared on the fungal isolates. Microscopic observations were made to observe the shape of the hyphae and the shape of the conidia. While molecular observations were carried out by amplifying DNA using ITS primers.","PeriodicalId":512976,"journal":{"name":"Engineering Headway","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140079428","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}
R. Muhida, Muhammad Riza, Bambang Pratowo, Zein Muhamad, A. Cucus, Taqwan Thamrin, A. Sutjipto, R. Muhida, Ari Legowo, Mochamad Safari, Handri Santoso
The extraordinary swimming capacity of fish in nature makes them unique among Allah's creations. It is extremely difficult for a robotic system to achieve fish-like swimming behaviors, especially in terms of swimming performance. Many fish use their pectoral fins to provide thrust over a wide speed range and to carry out tricky maneuvers. In this paper, we report a robotic fish that can travel forward and backward using its propulsion system. In this report, the creation of a conceptual design for an interactive fish robot took into account a number of factors, including swimming ability, leakage testing, and motion controller. This needed considerable mechanical design work, and the result is a quick-return mechanism for the fish's body. We made the decision to divide the body into the head, body, and tail. In order to create the propulsion system, we employed five servo motors. Finally, controlling the robot's motion is absolutely essential, especially if there is an obstruction in its path. The servo controller, which is located at the fish's head, serves as the primary controller for all of the motors and sensors.
{"title":"Development of the Obstacle Avoider of Fish Robot","authors":"R. Muhida, Muhammad Riza, Bambang Pratowo, Zein Muhamad, A. Cucus, Taqwan Thamrin, A. Sutjipto, R. Muhida, Ari Legowo, Mochamad Safari, Handri Santoso","doi":"10.4028/p-e5az8j","DOIUrl":"https://doi.org/10.4028/p-e5az8j","url":null,"abstract":"The extraordinary swimming capacity of fish in nature makes them unique among Allah's creations. It is extremely difficult for a robotic system to achieve fish-like swimming behaviors, especially in terms of swimming performance. Many fish use their pectoral fins to provide thrust over a wide speed range and to carry out tricky maneuvers. In this paper, we report a robotic fish that can travel forward and backward using its propulsion system. In this report, the creation of a conceptual design for an interactive fish robot took into account a number of factors, including swimming ability, leakage testing, and motion controller. This needed considerable mechanical design work, and the result is a quick-return mechanism for the fish's body. We made the decision to divide the body into the head, body, and tail. In order to create the propulsion system, we employed five servo motors. Finally, controlling the robot's motion is absolutely essential, especially if there is an obstruction in its path. The servo controller, which is located at the fish's head, serves as the primary controller for all of the motors and sensors.","PeriodicalId":512976,"journal":{"name":"Engineering Headway","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140078964","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}
Ina Aprillia, Muhammad Iqbal, Guntur Pragustiandi, A. Sutjipto, Arum Setiawan, Adhitya Wicaksono, I. Yustian
This study aims to assess the diversity of butterflies (Lepidoptera: Rhopalocera) at the location of the PT Pertamina Geothermal Energy (PGE) Lumut Balai Geothermal powerplant, Muara Enim, South Sumatra. This rapid survey was carried out on 4-15 June 2023, taking place in 7 locations namely Cluster 5, Cluster 6, Cluster 7, Cluster 9, Cluster 10, APL 17 and APL 18. The method used is the direct observation method by walking along a 1000 meter transect line (Yustian et al., 2017) in each type of habitat (secondary forest, mixed shrub secondary forest, coffee plantation , open areas and secondary forests near to rivers/water sources). The results obtained in this rapid survey are that there are 5 butterfly families consisting of Papilionidae, Pieridae, Nymphalidae, Hesperiidae and Lycaenidae with a total of 51 species and 254 individuals. The highest diversity index based on Shannon's diversity index and Margaleff's species richness index is in APL 17 with a secondary forest habitat type near to coffee plantations (H'=3.14, R=7.08) and the lowest is in Cluster 9 (H'=2.11, R=3.23) which is a secondary forest near to a geothermal power plant. Meanwhile, the highest evenness index was found in APL 17 (E=0.97) and the lowest in Cluster 7 (E=0.87) with a riparian habitat type. During the research, protected species were recorded, namely Troidesamphrysus and Troideshelena.
{"title":"Butterflies Diversity in Geothermal Powerplant Areas: Case Studies in Pt. Pertamina Geothermal Energy Lumut Balai, Muara Enim, South Sumatera","authors":"Ina Aprillia, Muhammad Iqbal, Guntur Pragustiandi, A. Sutjipto, Arum Setiawan, Adhitya Wicaksono, I. Yustian","doi":"10.4028/p-6vijh1","DOIUrl":"https://doi.org/10.4028/p-6vijh1","url":null,"abstract":"This study aims to assess the diversity of butterflies (Lepidoptera: Rhopalocera) at the location of the PT Pertamina Geothermal Energy (PGE) Lumut Balai Geothermal powerplant, Muara Enim, South Sumatra. This rapid survey was carried out on 4-15 June 2023, taking place in 7 locations namely Cluster 5, Cluster 6, Cluster 7, Cluster 9, Cluster 10, APL 17 and APL 18. The method used is the direct observation method by walking along a 1000 meter transect line (Yustian et al., 2017) in each type of habitat (secondary forest, mixed shrub secondary forest, coffee plantation , open areas and secondary forests near to rivers/water sources). The results obtained in this rapid survey are that there are 5 butterfly families consisting of Papilionidae, Pieridae, Nymphalidae, Hesperiidae and Lycaenidae with a total of 51 species and 254 individuals. The highest diversity index based on Shannon's diversity index and Margaleff's species richness index is in APL 17 with a secondary forest habitat type near to coffee plantations (H'=3.14, R=7.08) and the lowest is in Cluster 9 (H'=2.11, R=3.23) which is a secondary forest near to a geothermal power plant. Meanwhile, the highest evenness index was found in APL 17 (E=0.97) and the lowest in Cluster 7 (E=0.87) with a riparian habitat type. During the research, protected species were recorded, namely Troidesamphrysus and Troideshelena.","PeriodicalId":512976,"journal":{"name":"Engineering Headway","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140264308","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：