Tujuan Utama: Tujuan dari penelitian ini adalah untuk mengembangkan algoritma deteksi anomali yang lebih efektif dan akurat menggunakan Extended Isolation Forest (EIF) dan mengimplementasikannya ke dalam platform sumber terbuka Machine Learning (ML) H2O-3. Background problem: Algoritma Isolation Forest (IF) asli menghadirkan bentuk deteksi baru, meskipun algoritme mengalami bias yang berasal dari percabangan pohon. Perpanjangan algoritme menghilangkan bias dengan menyesuaikan percabangan, dan algoritme asli hanya menjadi kasus khusus. EIF diimplementasikan ke dalam platform sumber terbuka ML H2O-3. kebaharuan: Kebaruan dari penelitian ini adalah penggunaan algoritma EIF dalam deteksi anomali. Selain itu, penelitian ini juga mengimplementasikan EIF ke dalam platform sumber terbuka ML H2O-3 untuk dijalankan pada sistem komputasi terdistribusi dengan pustaka Map/Reduce. Research Method: Penelitian ini menggunakan metode deteksi anomali dengan fokus pada algoritma EIF. temuan: Hasil pengujian menunjukkan bahwa Extended Isolation Model perlu disesuaikan. Tes kinerja deteksi anomali mengungkapkan sedikit ketidaksempurnaan dalam deteksi struktur data jika dibandingkan dengan satu-satunya implementasi algoritma Python yang tersedia. Hasil ujian untuk tahap evaluasi dinyatakan lulus dan waktu komputasi secara logaritmik lebih kecil dengan jumlah utas. Kesimpulan: pada penelitian selanjutnya, algoritma dapat ditingkatkan lebih lanjut dengan menskalakan anomali deteksi untuk data dimensi tinggi. Ini dapat diimplementasikan dengan menambahkan parameter lain yang memungkinkan metode pemilihan fitur dalam perhitungan..
{"title":"Deteksi Anomali Menggunakan Extended Isolation Forest (Eif)","authors":"None Milka Wijayanti Sunarto, None Dendy Kurniawan, None Edy Siswanto, None Haris Ihsanil Huda","doi":"10.51903/teknik.v1i2.324","DOIUrl":"https://doi.org/10.51903/teknik.v1i2.324","url":null,"abstract":"Tujuan Utama: Tujuan dari penelitian ini adalah untuk mengembangkan algoritma deteksi anomali yang lebih efektif dan akurat menggunakan Extended Isolation Forest (EIF) dan mengimplementasikannya ke dalam platform sumber terbuka Machine Learning (ML) H2O-3. Background problem: Algoritma Isolation Forest (IF) asli menghadirkan bentuk deteksi baru, meskipun algoritme mengalami bias yang berasal dari percabangan pohon. Perpanjangan algoritme menghilangkan bias dengan menyesuaikan percabangan, dan algoritme asli hanya menjadi kasus khusus. EIF diimplementasikan ke dalam platform sumber terbuka ML H2O-3. kebaharuan: Kebaruan dari penelitian ini adalah penggunaan algoritma EIF dalam deteksi anomali. Selain itu, penelitian ini juga mengimplementasikan EIF ke dalam platform sumber terbuka ML H2O-3 untuk dijalankan pada sistem komputasi terdistribusi dengan pustaka Map/Reduce. Research Method: Penelitian ini menggunakan metode deteksi anomali dengan fokus pada algoritma EIF. temuan: Hasil pengujian menunjukkan bahwa Extended Isolation Model perlu disesuaikan. Tes kinerja deteksi anomali mengungkapkan sedikit ketidaksempurnaan dalam deteksi struktur data jika dibandingkan dengan satu-satunya implementasi algoritma Python yang tersedia. Hasil ujian untuk tahap evaluasi dinyatakan lulus dan waktu komputasi secara logaritmik lebih kecil dengan jumlah utas. Kesimpulan: pada penelitian selanjutnya, algoritma dapat ditingkatkan lebih lanjut dengan menskalakan anomali deteksi untuk data dimensi tinggi. Ini dapat diimplementasikan dengan menambahkan parameter lain yang memungkinkan metode pemilihan fitur dalam perhitungan..","PeriodicalId":30795,"journal":{"name":"Teknik","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135806465","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 : 2023-05-06DOI: 10.14710/teknik.v44i1.49522
Iwan ' Kurniawan, Albert Eddy Husin
[Title: Influential Factors in the Implementation of the Green Concept in the Main Building of the Flour Mill Plant using Structural Equation Modeling-Partial Least Square (SEM-PLS)] The construction of factory buildings that apply the Green concept is urgently needed; this is following the mission of the Sustainable Development Goals 2030, which by 2030 new buildings have a green concept of 100% and existing buildings of 60%. This study aims to analyze the influential factors in applying the Green Concept to Value Engineering-Based Cost Performance and Life Cycle Cost Analysis by taking objects in the Main Building of the Flour Mill Plant using the Structural Equation Modelling – Part Least Square (SEM-PLS) method. From this research, there are ten factors, namely, Project manager performance with an influence level of 88.4%, Energy efficiency calculation with an influence level of 88.1%, Technical specifications with an influence level of 86.8%, Provision of Parking Areas with an influence level of 84.6%, Supporting regulations with influence level of 82, 8%, Water sources with an influence level of 82.2%, Function analysis with an influence level of 80.6%, Application of waste handling systems with an influence level of 75.9%, Selection of alternative materials 73.1% and Energy costs with an influence level of 72, 4%.
{"title":"Analisis Faktor – Faktor yang Berpengaruh dalam Implementasi Konsep Green Untuk Peningkatan Kinerja Biaya menggunakan Structural Equation Modelling-Partial Least Square (SEM-PLS)","authors":"Iwan ' Kurniawan, Albert Eddy Husin","doi":"10.14710/teknik.v44i1.49522","DOIUrl":"https://doi.org/10.14710/teknik.v44i1.49522","url":null,"abstract":"[Title: Influential Factors in the Implementation of the Green Concept in the Main Building of the Flour Mill Plant using Structural Equation Modeling-Partial Least Square (SEM-PLS)] The construction of factory buildings that apply the Green concept is urgently needed; this is following the mission of the Sustainable Development Goals 2030, which by 2030 new buildings have a green concept of 100% and existing buildings of 60%. This study aims to analyze the influential factors in applying the Green Concept to Value Engineering-Based Cost Performance and Life Cycle Cost Analysis by taking objects in the Main Building of the Flour Mill Plant using the Structural Equation Modelling – Part Least Square (SEM-PLS) method. From this research, there are ten factors, namely, Project manager performance with an influence level of 88.4%, Energy efficiency calculation with an influence level of 88.1%, Technical specifications with an influence level of 86.8%, Provision of Parking Areas with an influence level of 84.6%, Supporting regulations with influence level of 82, 8%, Water sources with an influence level of 82.2%, Function analysis with an influence level of 80.6%, Application of waste handling systems with an influence level of 75.9%, Selection of alternative materials 73.1% and Energy costs with an influence level of 72, 4%.","PeriodicalId":30795,"journal":{"name":"Teknik","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47251043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
[Title: Assessment of Risk Perception on Occupational Safety in Construction Project using Adapted Municipal Public Health Rotterdam-Rijnmond] The causes of work accidents in construction work are still dominated by a lack of information understanding, low levels of knowledge, and low perceptions of workers regarding occupational health and safety. This study aims to assess workers' occupational safety risk perceptions in construction projects. This research was carried out in the Sutt tower and the Jakarta-Bandung High-Speed Railway construction project. The variables of this study were divided into feeling safe/unsafe in carrying out work processes, workers' seriousness of accidents that might occur, workers' anxiety about experiencing accidents and technological failures, and workers' beliefs about effectively taking precautions. The data collection method uses observation, interview, and risk perception questionnaire based on adapted-Municipal Public Health techniques. The study results show that the work process is difficult with a high risk of danger. Workers still struggle to understand the work area, work processes, and safety standards even though Toolbox meetings have been held. Other factors that affect the perception of risk are environmental factors, social factors or encouragement, and work appreciation support which workers need. Adequate knowledge received will make workers more alert, understand the work process being carried out and increase workers' perceptions of risk.
{"title":"Penilaian Persepsi Risiko Keselamatan Kerja pada Proyek Konstruksi menggunakan Adaptasi Kuesioner Municipal Public Health Rotterdam-Rijnmond","authors":"Novie Susanto, Septina Graselia Lumbantobing, Heru Prastawa","doi":"10.14710/teknik.v44i1.50304","DOIUrl":"https://doi.org/10.14710/teknik.v44i1.50304","url":null,"abstract":"[Title: Assessment of Risk Perception on Occupational Safety in Construction Project using Adapted Municipal Public Health Rotterdam-Rijnmond] The causes of work accidents in construction work are still dominated by a lack of information understanding, low levels of knowledge, and low perceptions of workers regarding occupational health and safety. This study aims to assess workers' occupational safety risk perceptions in construction projects. This research was carried out in the Sutt tower and the Jakarta-Bandung High-Speed Railway construction project. The variables of this study were divided into feeling safe/unsafe in carrying out work processes, workers' seriousness of accidents that might occur, workers' anxiety about experiencing accidents and technological failures, and workers' beliefs about effectively taking precautions. The data collection method uses observation, interview, and risk perception questionnaire based on adapted-Municipal Public Health techniques. The study results show that the work process is difficult with a high risk of danger. Workers still struggle to understand the work area, work processes, and safety standards even though Toolbox meetings have been held. Other factors that affect the perception of risk are environmental factors, social factors or encouragement, and work appreciation support which workers need. Adequate knowledge received will make workers more alert, understand the work process being carried out and increase workers' perceptions of risk.","PeriodicalId":30795,"journal":{"name":"Teknik","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45742114","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 : 2022-08-30DOI: 10.14710/teknik.v43i2.45612
A. Santosa, Reimigius Baskatara Bungkang, Ocid Mursid
Baja AISI 1020 dalam industri perkapalan banyak digunakan sebagai pipa air air laut kapal. Dilihat dari kegunaannya baja jenis ini akan mudah terkorosi jika mengaliri air laut tanpa perlindungan apapun, hal tersebut disebabkan karena air laut merupakan salah satu media korosif bagi baja. Tujuan dilaksanakannya penelitian ini untuk mengetahui pengaruh penggunaan metode pelapisan Hot Dip Galvanizing dengan variasi temperatur dan lama waktu pencelupan terhadap laju korosi pipa kapal baja AISI 1020. Temperatur yang digunakan pada proses galvanis adalah 440 ºC, 455 ºC, dan 480 ºC dengan variable waktu pencelupan 2 menit, 4 menit, dan 6 menit. Efek korosi dipantau selama 192 jam dengan media air laut Pantai Cipta Kota Semarang. Dari hasil pengukuran weight loss didapatkan hasil bahwa laju korosi baja non galvanis sebesar 1,81462 mmpy, Sedangkan laju korosi teroptimal dari masing-masing variasi temperatur dengan penggunaan metode Hot Dip Galvanizing pada 440ºC waktu pencelupan 6 menit sebesar 0,01796 mmpy, pada 455 ºC waktu pencelupan 6 menit sebesar 0,01289 mmpy, dan pada 480ºC waktu pencelupan 4 menit sebesar 0,0074 mmpy. Berdasarkan data tersebut penggunaan metode pelapisan Hot Dip Galvanizing mampu mengurangi laju korosi yang terjadi pada baja AISI 1020.
{"title":"Analisa Pengaruh Metode Hot Dip Galvanizing Dengan Variasi Temperatur dan Waktu Pencelupan Terhadap Laju Korosi Pipa Air Laut Kapal Material Baja AISI 1020","authors":"A. Santosa, Reimigius Baskatara Bungkang, Ocid Mursid","doi":"10.14710/teknik.v43i2.45612","DOIUrl":"https://doi.org/10.14710/teknik.v43i2.45612","url":null,"abstract":"Baja AISI 1020 dalam industri perkapalan banyak digunakan sebagai pipa air air laut kapal. Dilihat dari kegunaannya baja jenis ini akan mudah terkorosi jika mengaliri air laut tanpa perlindungan apapun, hal tersebut disebabkan karena air laut merupakan salah satu media korosif bagi baja. Tujuan dilaksanakannya penelitian ini untuk mengetahui pengaruh penggunaan metode pelapisan Hot Dip Galvanizing dengan variasi temperatur dan lama waktu pencelupan terhadap laju korosi pipa kapal baja AISI 1020. Temperatur yang digunakan pada proses galvanis adalah 440 ºC, 455 ºC, dan 480 ºC dengan variable waktu pencelupan 2 menit, 4 menit, dan 6 menit. Efek korosi dipantau selama 192 jam dengan media air laut Pantai Cipta Kota Semarang. Dari hasil pengukuran weight loss didapatkan hasil bahwa laju korosi baja non galvanis sebesar 1,81462 mmpy, Sedangkan laju korosi teroptimal dari masing-masing variasi temperatur dengan penggunaan metode Hot Dip Galvanizing pada 440ºC waktu pencelupan 6 menit sebesar 0,01796 mmpy, pada 455 ºC waktu pencelupan 6 menit sebesar 0,01289 mmpy, dan pada 480ºC waktu pencelupan 4 menit sebesar 0,0074 mmpy. Berdasarkan data tersebut penggunaan metode pelapisan Hot Dip Galvanizing mampu mengurangi laju korosi yang terjadi pada baja AISI 1020.","PeriodicalId":30795,"journal":{"name":"Teknik","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47806299","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 : 2022-08-29DOI: 10.14710/teknik.v43i2.45876
J. U. D. Hatmoko, Arif Hidayat, M. Zachari, Satria Sentik Herman Merukh
[Title: Investigating The Impact of Construction Project Delay Payment from The Owner to The Contractor] Existing literature shows that project delays are still a common problem in many countries. Generally, factors causing project delays are mostly attributed to the contractor's responsibility. Meanwhile, it is still rare to find research that examines the causal factors of project delays from the owner's side. This study intends to investigate the effect of late payments from the owner to the contractor in construction projects. The preliminary study was conducted through an interview, followed by data collection through questionnaires distributed to 80 contractors as the respondents, using a mixed method of qualitative and quantitative analysis techniques. The results show that the three biggest impacts are late payments by contractors to subcontractors and suppliers, disruption of contractor cashflows, and difficulty in obtaining materials. The main causes of delays in owner payments include complex bureaucracy in submitting payments, incomplete document requirements, and poor quality of work. The solutions taken by the contractor include, among others, billing the owner continuously, demanding the owner to pay the interest due to late payments, and delaying payment obligations to suppliers and subcontractors. The results of this study indicate that late payment from the owner is still a serious problem in the construction industry in Indonesia. The findings of this study serve as inputs for stakeholders in the construction industry to understand the problems of late owner payment and their impact on the project, as well as to formulate appropriate preventive strategies.
{"title":"Investigasi Pengaruh Keterlambatan Pembayaran Proyek Konstruksi dari Owner kepada Kontraktor","authors":"J. U. D. Hatmoko, Arif Hidayat, M. Zachari, Satria Sentik Herman Merukh","doi":"10.14710/teknik.v43i2.45876","DOIUrl":"https://doi.org/10.14710/teknik.v43i2.45876","url":null,"abstract":"[Title: Investigating The Impact of Construction Project Delay Payment from The Owner to The Contractor] Existing literature shows that project delays are still a common problem in many countries. Generally, factors causing project delays are mostly attributed to the contractor's responsibility. Meanwhile, it is still rare to find research that examines the causal factors of project delays from the owner's side. This study intends to investigate the effect of late payments from the owner to the contractor in construction projects. The preliminary study was conducted through an interview, followed by data collection through questionnaires distributed to 80 contractors as the respondents, using a mixed method of qualitative and quantitative analysis techniques. The results show that the three biggest impacts are late payments by contractors to subcontractors and suppliers, disruption of contractor cashflows, and difficulty in obtaining materials. The main causes of delays in owner payments include complex bureaucracy in submitting payments, incomplete document requirements, and poor quality of work. The solutions taken by the contractor include, among others, billing the owner continuously, demanding the owner to pay the interest due to late payments, and delaying payment obligations to suppliers and subcontractors. The results of this study indicate that late payment from the owner is still a serious problem in the construction industry in Indonesia. The findings of this study serve as inputs for stakeholders in the construction industry to understand the problems of late owner payment and their impact on the project, as well as to formulate appropriate preventive strategies.","PeriodicalId":30795,"journal":{"name":"Teknik","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42430449","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 : 2022-08-28DOI: 10.14710/teknik.v43i2.45642
H. Afrisal, Ghanis Kauchya Nugraha, Aan Aria Nanda, A. Setiyadi, O. Toirov, R. Ismail, W. Syafei, M. Riyadi, I. Setiawan
This research aims to develop a low-cost mobile robotic arm for an indoor delivery system. Current pandemic and possible future threat of communicable disease become challenging scenarios in developing an unmanned logistic delivery system with a minimum human involvement, especially for inter-room items delivery inside a highly regulated building such as in hospital, clinic, pharmaceutical, foods and beverages industries. In this paper, a prototype of mobile robotic arm is designed to achieve an autonomous level of navigation utilizing a 2D LIDAR with a guided remote monitoring and control of object selections for loading/unloading process. The mobile robotic arm is an integrated robotics system of mobile robot with an attached robotic arm in its body. The base of the mobile robotic arm utilizes a differential-drive wheels configuration equipped with wheels odometry system. The robotic arm is configured of a 4-DoF SCARA-like structure. The 2-dimensional environment map is generated using LIDAR sensor utilizing Hector SLAM method prior to navigation. The autonomous navigation is performed using a 2D LIDAR-based technique by employing an A* algorithm for path planning and tracking mechanism. Experimental works were conducted in a small building environment consisting of some rooms and narrow corridors. The result of experiments show that the prototype of mobile robotic arm can safely and effectively navigate through the testing environment, subsequently to load and unload objects from one room to another room without colliding to objects and obstacles.
{"title":"Mobile Robotic-Arm Development for A Small-Scale Inter-Room Logistic Delivery using 2D LIDAR-guided Navigation","authors":"H. Afrisal, Ghanis Kauchya Nugraha, Aan Aria Nanda, A. Setiyadi, O. Toirov, R. Ismail, W. Syafei, M. Riyadi, I. Setiawan","doi":"10.14710/teknik.v43i2.45642","DOIUrl":"https://doi.org/10.14710/teknik.v43i2.45642","url":null,"abstract":"This research aims to develop a low-cost mobile robotic arm for an indoor delivery system. Current pandemic and possible future threat of communicable disease become challenging scenarios in developing an unmanned logistic delivery system with a minimum human involvement, especially for inter-room items delivery inside a highly regulated building such as in hospital, clinic, pharmaceutical, foods and beverages industries. In this paper, a prototype of mobile robotic arm is designed to achieve an autonomous level of navigation utilizing a 2D LIDAR with a guided remote monitoring and control of object selections for loading/unloading process. The mobile robotic arm is an integrated robotics system of mobile robot with an attached robotic arm in its body. The base of the mobile robotic arm utilizes a differential-drive wheels configuration equipped with wheels odometry system. The robotic arm is configured of a 4-DoF SCARA-like structure. The 2-dimensional environment map is generated using LIDAR sensor utilizing Hector SLAM method prior to navigation. The autonomous navigation is performed using a 2D LIDAR-based technique by employing an A* algorithm for path planning and tracking mechanism. Experimental works were conducted in a small building environment consisting of some rooms and narrow corridors. The result of experiments show that the prototype of mobile robotic arm can safely and effectively navigate through the testing environment, subsequently to load and unload objects from one room to another room without colliding to objects and obstacles.","PeriodicalId":30795,"journal":{"name":"Teknik","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45084554","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 : 2022-08-26DOI: 10.14710/teknik.v43i2.46439
Ichsan Arsyi Putra, O. Nurhayati, D. Eridani
Human Action Recognition is an important research topic in Machine Learning and Computer Vision domains. One of the proposed methods is a combination of MediaPipe library and Long Short-Term Memory concerning the testing accuracy and training duration as indicators to evaluate the model performance. This research tried to adapt proposed LSTM models to implement HAR with image features extracted by MediaPipe library. There would be a comparison between LSTM models based on their testing accuracy and training duration. This research was conducted under OSEMN methods (Obtain, Scrub, Explore, Model, and iNterpret). The dataset was preprocessed Weizmann dataset with data preprocessing and data augmentation implementations. Video features extracted by MediaPipe: Pose was used in training and validation processes on neural network models focusing on Long Short-Term Memory layers. The processes were finished by model performance evaluation based on confusion matrices interpretation and calculations of accuracy, error rate, precision, recall, and F1score. This research yielded seven LSTM model variants with the highest testing accuracy at 82% taking 10 minutes and 50 seconds of training duration.
{"title":"Human Action Recognition (HAR) Classification Using MediaPipe and Long Short-Term Memory (LSTM)","authors":"Ichsan Arsyi Putra, O. Nurhayati, D. Eridani","doi":"10.14710/teknik.v43i2.46439","DOIUrl":"https://doi.org/10.14710/teknik.v43i2.46439","url":null,"abstract":"Human Action Recognition is an important research topic in Machine Learning and Computer Vision domains. One of the proposed methods is a combination of MediaPipe library and Long Short-Term Memory concerning the testing accuracy and training duration as indicators to evaluate the model performance. This research tried to adapt proposed LSTM models to implement HAR with image features extracted by MediaPipe library. There would be a comparison between LSTM models based on their testing accuracy and training duration. This research was conducted under OSEMN methods (Obtain, Scrub, Explore, Model, and iNterpret). The dataset was preprocessed Weizmann dataset with data preprocessing and data augmentation implementations. Video features extracted by MediaPipe: Pose was used in training and validation processes on neural network models focusing on Long Short-Term Memory layers. The processes were finished by model performance evaluation based on confusion matrices interpretation and calculations of accuracy, error rate, precision, recall, and F1score. This research yielded seven LSTM model variants with the highest testing accuracy at 82% taking 10 minutes and 50 seconds of training duration.","PeriodicalId":30795,"journal":{"name":"Teknik","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45498197","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 : 2022-08-23DOI: 10.14710/teknik.v43i2.46469
Bandi Sasmito, Nurhadi Bashit, Erliza Rachmadiana
AbstrakDanau Rawa Pening merupakan danau alami yang termasuk danau prioritas utama untuk dilakukan restorasi karena pertumbuhan eceng gondok yang tinggi. Pertumbuhan eceng gondok menyebabkan tertutupnya permukaan air danau dan penumpukan sedimen di dasar perairan. Sedimentasi adalah salah satu faktor penyebab munculnya Total Suspended Solid (TSS) yang menggambarkan kualitas perairan. Pemantauan perubahan kualitas perairan dapat dilakukan dengan melakukan pemetaan menggunakan metode pengindraan jauh. Pada penelitian ini pemetaan TSS dilakukan guna mencari algoritma empiris yang sesuai dengan kondisi Danau Rawa Pening dan menganalisis sebaran konsentrasi TSS melalui algoritma yang didapat. Metode yang digunakan dalam analisis konsentrasi TSS adalah pembangunan model algoritma melalui regresi data reflektan Citra Sentinel 2A tahun 2021 band 1 – 8A yang memiliki kemungkinan tinggi dalam penyerapan dan hamburan balik dari objek air dengan data TSS in situ. Percobaan penerapan regresi dipakai jika nilai ≥ 0,5 yang menunjukkan adanya hubungan keterkaitan yang kuat antara variabel TSS in situ dan nilai reflektans band. Hasil dari penelitian ini berupa 2 model dengan nilai ≥ 0,5 yaitu model persamaan regresi berganda menggunakan ratio band , nilai sebesar 0,620 dan persamaan regresinya . Sebaran konsentrasi TSS di Danau Rawa Pening memenuhi kriteria baku mutu air dengan sebagian besar berada pada kelas I dan sebagaian kecil berada kelas II, III, dan IV. Konsentrasi tertinggi menggunakan perhitungan algoritma ratio band 4/6 pada tahun 2021 sebesar 0 – 258,91 mg/L dan terendah pada tahun 2020 sebesar 0 – 6,13 mg/L.
{"title":"ANALISIS PERUBAHAN KONSENTRASI TOTAL SUSPENDED SOLID SECARA MULTITEMPORAL MENGGUNAKAN CITRA SENTINEL 2A (STUDI KASUS: DANAU RAWA PENING, JAWA TENGAH)","authors":"Bandi Sasmito, Nurhadi Bashit, Erliza Rachmadiana","doi":"10.14710/teknik.v43i2.46469","DOIUrl":"https://doi.org/10.14710/teknik.v43i2.46469","url":null,"abstract":"AbstrakDanau Rawa Pening merupakan danau alami yang termasuk danau prioritas utama untuk dilakukan restorasi karena pertumbuhan eceng gondok yang tinggi. Pertumbuhan eceng gondok menyebabkan tertutupnya permukaan air danau dan penumpukan sedimen di dasar perairan. Sedimentasi adalah salah satu faktor penyebab munculnya Total Suspended Solid (TSS) yang menggambarkan kualitas perairan. Pemantauan perubahan kualitas perairan dapat dilakukan dengan melakukan pemetaan menggunakan metode pengindraan jauh. Pada penelitian ini pemetaan TSS dilakukan guna mencari algoritma empiris yang sesuai dengan kondisi Danau Rawa Pening dan menganalisis sebaran konsentrasi TSS melalui algoritma yang didapat. Metode yang digunakan dalam analisis konsentrasi TSS adalah pembangunan model algoritma melalui regresi data reflektan Citra Sentinel 2A tahun 2021 band 1 – 8A yang memiliki kemungkinan tinggi dalam penyerapan dan hamburan balik dari objek air dengan data TSS in situ. Percobaan penerapan regresi dipakai jika nilai ≥ 0,5 yang menunjukkan adanya hubungan keterkaitan yang kuat antara variabel TSS in situ dan nilai reflektans band. Hasil dari penelitian ini berupa 2 model dengan nilai ≥ 0,5 yaitu model persamaan regresi berganda menggunakan ratio band , nilai sebesar 0,620 dan persamaan regresinya . Sebaran konsentrasi TSS di Danau Rawa Pening memenuhi kriteria baku mutu air dengan sebagian besar berada pada kelas I dan sebagaian kecil berada kelas II, III, dan IV. Konsentrasi tertinggi menggunakan perhitungan algoritma ratio band 4/6 pada tahun 2021 sebesar 0 – 258,91 mg/L dan terendah pada tahun 2020 sebesar 0 – 6,13 mg/L. ","PeriodicalId":30795,"journal":{"name":"Teknik","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43250936","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}
Plastic has many advantages due to flexibility, unaffordable, transparent, and toughness. Plastics can size into small sizes (microplastics) or large sizes (macroplastics). Microbeads are granules of plastic or fiber that can often be utilized in many personal care products with sizes below 1 mm. These size of microbeads affect to environmental. Microbeads cannot be filtered by the sewage treatment system resulting microbeads go through to end up in water bodies and become a dangerous pollutant. Therefore any efforts must be conducted to replace the use of plastics microbeads. The microbeads can be prepared from with organic materials having easily degradation with stand the same functions. One of the ways can be accomplished through preparation of bacterial cellulose from sago waste since liquid waste can be used to produce bacterial cellulose. Bacterial cellulose is highly potential to be developed into microbeads as it has advantages of high purity, good tissue structure, high degradation ability, mechanical strength, and easy degradability. The utilization of sago liquid waste is very beneficial because it can reduce environmental pollution and production costs. Additionally, antibacterial properties in microbeads can introduce chitosan, eucalyptus filtrate, celery leaf extract, basil, and cinnamon. The use of chitosan as an additive in the preparation of microbeads will reduce the rate of water adsorption, improve mechanical properties, and reduce the moisture in the microbeads that would promote the ability of microbeads to against bacteria.
{"title":"Non-Microplastic Microbeads From Sago Liquid Waste With The Addition Of Chitosan as Antibacterial Function: A Review","authors":"S. Silviana, Fakhri Santo Khoirudin, Ferris Andhika Pratama, Rizky Putri Adelina Harahap, Alfi Hasanah, Queen Ruhmaningrum, L. Khoiriyah, Saskia Vianova, Michelle Nabillarisa Qori Santoso, Yoga Anugra Guslamari, Cantika Aulia Salsabila","doi":"10.14710/teknik.v43i2.40855","DOIUrl":"https://doi.org/10.14710/teknik.v43i2.40855","url":null,"abstract":"Plastic has many advantages due to flexibility, unaffordable, transparent, and toughness. Plastics can size into small sizes (microplastics) or large sizes (macroplastics). Microbeads are granules of plastic or fiber that can often be utilized in many personal care products with sizes below 1 mm. These size of microbeads affect to environmental. Microbeads cannot be filtered by the sewage treatment system resulting microbeads go through to end up in water bodies and become a dangerous pollutant. Therefore any efforts must be conducted to replace the use of plastics microbeads. The microbeads can be prepared from with organic materials having easily degradation with stand the same functions. One of the ways can be accomplished through preparation of bacterial cellulose from sago waste since liquid waste can be used to produce bacterial cellulose. Bacterial cellulose is highly potential to be developed into microbeads as it has advantages of high purity, good tissue structure, high degradation ability, mechanical strength, and easy degradability. The utilization of sago liquid waste is very beneficial because it can reduce environmental pollution and production costs. Additionally, antibacterial properties in microbeads can introduce chitosan, eucalyptus filtrate, celery leaf extract, basil, and cinnamon. The use of chitosan as an additive in the preparation of microbeads will reduce the rate of water adsorption, improve mechanical properties, and reduce the moisture in the microbeads that would promote the ability of microbeads to against bacteria.","PeriodicalId":30795,"journal":{"name":"Teknik","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42498347","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 : 2022-07-20DOI: 10.14710/teknik.v43i2.43301
Y. Y. Tanoto, Vincensius Filbert, Ronaldo Febrian, Nicholas Adriel
[Title: Multi response Optimazion In 3D Printing ABS Materials With Taguchi-PCR Topsis Method] The use of 3D printing technology, commonly referred to as additive manufacturing, is increasingly widespread as a rapid prototyping method. Acrylonitrile butadiene styrene (ABS) is one type of material whose use is quite massive in 3D printing technology. In this study, nine experiments were carried out using the experimental design method orthogonal arrays L9 ( 3 3 ), and three process parameters were used, namely nozzle temperature, base plate/bed temperature, and orientation, as well as with three levels of variation for each process parameter (230oC, 240oC, 250oC, 90oC, 100oC, 110oC, 0o, 45o, 90o). This study aimed to find the optimal process parameters for the processing response time, mechanical properties of flexural strength, and dimensional accuracy. Thus, a combination of the Taguchi and PCR-TOPSIS methods was used to solve the multiresponse problem. Based on the results of ANOVA analysis, the parameter with the level that produces the most optimal combined response is located in the third condition specimen (that is, the nozzle temperature value is 230°C; the base plate/bed temperature is 110°C, and the printing orientation direction is 90°). The results of the PCR-Topsis analysis on three process parameters shows that the parameters that have the highest influence in sequence are orientation at 33%, bed temperature at 28%, and nozzle temperature at 18%.
{"title":"Optimasi Multirespon pada Proses 3D Printing Material ABS dengan Metode Taguchi-PCR Topsis","authors":"Y. Y. Tanoto, Vincensius Filbert, Ronaldo Febrian, Nicholas Adriel","doi":"10.14710/teknik.v43i2.43301","DOIUrl":"https://doi.org/10.14710/teknik.v43i2.43301","url":null,"abstract":"[Title: Multi response Optimazion In 3D Printing ABS Materials With Taguchi-PCR Topsis Method] The use of 3D printing technology, commonly referred to as additive manufacturing, is increasingly widespread as a rapid prototyping method. Acrylonitrile butadiene styrene (ABS) is one type of material whose use is quite massive in 3D printing technology. In this study, nine experiments were carried out using the experimental design method orthogonal arrays L9 ( 3 3 ), and three process parameters were used, namely nozzle temperature, base plate/bed temperature, and orientation, as well as with three levels of variation for each process parameter (230oC, 240oC, 250oC, 90oC, 100oC, 110oC, 0o, 45o, 90o). This study aimed to find the optimal process parameters for the processing response time, mechanical properties of flexural strength, and dimensional accuracy. Thus, a combination of the Taguchi and PCR-TOPSIS methods was used to solve the multiresponse problem. Based on the results of ANOVA analysis, the parameter with the level that produces the most optimal combined response is located in the third condition specimen (that is, the nozzle temperature value is 230°C; the base plate/bed temperature is 110°C, and the printing orientation direction is 90°). The results of the PCR-Topsis analysis on three process parameters shows that the parameters that have the highest influence in sequence are orientation at 33%, bed temperature at 28%, and nozzle temperature at 18%.","PeriodicalId":30795,"journal":{"name":"Teknik","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42841824","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：