Tech-E
Not a member yet
118 research outputs found
Sort by
PROTOTYPE WATER SPRAY OTOMATIS UNTUK PEMBERSIHAN DEBU BATUBARA PADA COAL CONVEYOR
No full textCoal dust generated during the transfer process via belt conveyors at PT Bukit Asam Tbk has significant negative impacts on the environment and the health of workers. The current manual method, involving direct water spraying, is ineffective in controlling airborne dust and increases safety risks due to water exposure and unstable working conditions. To overcome these challenges, this study developed a prototype of an Arduino-based automatic water spraying system as a safer and more efficient solution.The system employs a SHARP GP2Y1010AU0F dust sensor to monitor coal dust concentrations in real-time and an HC-SR04 ultrasonic sensor to regulate water spraying automatically, based on the detected levels. The prototype was tested under operational conditions and showed optimal performance, effectively reducing coal dust concentrations while improving health and safety standards in the workplace.This innovation offers a practical and sustainable approach to coal dust management, addressing the shortcomings of manual methods. By automating the process, it minimizes worker exposure to dust and eliminates hazards associated with direct water application. The system's efficient and safe operation highlights its potential for broader implementation in similar mining environments. This technology not only resolves critical issues in coal dust control but also introduces a forward-thinking solution that aligns with industry goals for improved occupational safety and environmental protection.Debu batubara yang dihasilkan selama proses pemindahan batubara melalui belt conveyor di PT Bukit Asam Tbk menimbulkan berbagai dampak negatif, baik terhadap lingkungan sekitar maupun kesehatan para pekerja yang terpapar. Dalam praktiknya, metode manual yang saat ini digunakan, yaitu penyemprotan air secara langsung di atas conveyor, terbukti kurang efektif dalam mengendalikan debu yang berterbangan, bahkan berpotensi membahayakan keselamatan pekerja akibat paparan air dan kondisi lingkungan kerja yang tidak stabil. Untuk mengatasi permasalahan ini, penelitian ini bertujuan untuk mengembangkan prototipe sistem penyemprotan air otomatis berbasis Arduino, yang diharapkan dapat memberikan solusi lebih aman dan efisien. Prototipe ini menggunakan sensor debu SHARP GP2Y1010AU0F untuk mendeteksi konsentrasi debu batubara secara real-time, serta sensor Ultrasonik HC-SR04 untuk mengontrol penyemprotan air secara otomatis sesuai kebutuhan. Hasil pengujian prototipe menunjukkan kinerja yang optimal, di mana sistem berhasil mengurangi tingkat konsentrasi debu batubara secara signifikan, sekaligus meningkatkan aspek kesehatan dan keselamatan kerja di area operasional. Dengan demikian, sistem ini tidak hanya menawarkan solusi praktis terhadap masalah debu batubara, tetapi juga berpotensi menjadi inovasi yang dapat diterapkan lebih luas di industri pertambangan serup
Designing Air Quality Detection Systems with Over-the-Air Firmware Update Methods for Performance Enhancement
Full text linkImplementing the Over-The-Air (OTA) system, which facilitates wireless and remote updates of software or firmware through internet connectivity, offers a significant advantage by saving both time and effort. This approach allows for firmware updates to be performed directly from any location, eliminating the need to physically visit each device. This is especially advantageous in the manufacturing of air quality monitoring devices, where adjustments to programs and software are often needed, particularly with seasonal changes. Updating firmware manually on numerous devices can be a time-consuming and labor-intensive process. To address this issue, the proposed device will be designed to support air quality readings and will utilize an internet connection to enable virtual firmware updates. The device will periodically check its program storage for new firmware versions. When a new version is detected, the device will automatically download and install the latest firmware available. This process reduces the need for manual intervention and improves operational efficiency. Additionally, deploying multiple devices across a large area is crucial for ensuring comprehensive coverage. This approach not only simplifies maintenance but also enhances the operational management of air quality monitoring systems. By leveraging OTA technology, the process of updating devices becomes more streamlined, scalable, and efficient, contributing to more effective environmental monitoring and management
Implementing and Monitoring Water Consumption Using IoT-Based Smart Dispensers
No full textConventional dispensers have limitations in providing drinking water tailored to user preferences and do not focus on efficient resource use. This research aims to address these issues by designing and implementing a smart, efficient automatic dispenser. An experimental method was used to develop an Arduino-based prototype consisting of several components: flow sensor, color sensor, fingerprint sensor, proximity sensor, DC pump, motor driver, NodeMCU, and LCD. The flow sensor measures water volume, the color sensor detects glass color, the fingerprint sensor identifies the user, and the proximity sensor detects the presence of the glass. The DC pump flows water from the tank to the glass, relays and solenoids control the water flow, NodeMCU processes sensor data and connects to IoT, and the LCD displays the required information. A battery backup ensures functionality during power outages. The research results show that the automatic dispenser performs well and meets the research objectives. It provides drinking water according to user preferences: warm water for red glasses, cold water for blue glasses, and room temperature water for green glasses. Additionally, it identifies users through fingerprints and sends notifications via Telegram chatbots. This smart dispenser offers a more efficient and user-friendly solution compared to conventional dispensers
PERANCANGAN PROTOTYPE SMART HOME MENGGUNAKAN MIKROKONTROLER ESP32 BERBASIS IOT DAN TELEGRAM
No full textSmarthome is a combination of internet of things (IoT). The use of a smarthome controlled using telegram functions to provide better comfort, provide efficiency in activities and save on electrical energy use. That way, there will be no more forgetting to turn off the AC or turning on or off the lights, watering house plants and forgetting to lock the door because by using a Smarthome device at home or in an office building, electrical equipment will be drained. able to work automatically according to user needs. Users can also control electrical devices indoors and outdoors using communication channels such as via the internet network. The aim of creating this smarthome is to provide better comfort, make it easier to control home electronic devices so that activities become more efficient. The development model used in this research is design to look for research that is similar to the tools that will be used then analysis to study things related to the research after that design to make a miniature room as clear as possible and implementation aims to examine and find out each whether each system is functioning as desired or whether an error has occurred. Based on the results of system testing, it can be concluded that the tool can work as expected.Smarthome adalah kombinasi internet of things (IoT). Penggunaan smarthome yang dikontrol menggunakan telegram berfungsi memberikan kenyamanan yang lebih baik, memberikan efisiensi dalam beraktivitas dan menghemat penggunaan energi listrik. Dengan begitu, tidak akan ada lagi kelupaan mematikan AC atau menyalakan atau mematikan lampu, menyiram tanaman rumah dan lupa mengunci pintu karena dengan menggunakan perangkat Smarthome di rumah atau di gedung perkantoran, peralatan listrik akan terkuras habis. . mampu bekerja secara otomatis sesuai kebutuhan pengguna. Pengguna juga dapat mengontrol perangkat listrik di dalam maupun di luar ruangan menggunakan saluran komunikasi seperti melalui jaringan internet. Tujuan diciptakannya smarthome ini adalah untuk memberikan kenyamanan yang lebih baik, memudahkan dalam mengontrol perangkat elektronik rumah sehingga aktivitas menjadi lebih efisien. Model pengembangan yang digunakan dalam penelitian ini adalah desain untuk mencari penelitian yang serupa dengan alat yang akan digunakan kemudian analisis untuk mempelajari hal-hal yang berhubungan dengan penelitian setelah itu desain untuk membuat miniatur ruangan sejelas mungkin dan implementasi bertujuan untuk mengkaji dan mengetahui masing-masing apakah setiap sistem berfungsi sesuai yang diinginkan atau telah terjadi kesalahan. Berdasarkan hasil pengujian sistem dapat disimpulkan bahwa alat dapat bekerja sesuai dengan yang diharapkan
Penerapan Metode Logika Fuzzy Sugeno Pada Prediksi Stok Bahan Baku Kulit Pie
No full textAccurate prediction of raw material stocks is essential for cost management and effective production planning in the food industry. The Sugeno fuzzy logic method is employed to predict the stock levels of pie leather raw materials. This method aims to offer a reliable prediction system that enhances stock management, thereby minimizing the risks associated with overstocking or stock shortages. The performance of the model is evaluated using the average error percentage test, which yielded a result of 3.94%. This indicates an accuracy level of 96.06%, demonstrating a high degree of precision. The findings suggest that the Sugeno fuzzy logic method is a highly effective tool for predicting raw material requirements in the pie leather production process. The study underscores the potential of fuzzy logic methods in supply management, ensuring smooth production operations. By implementing this method, manufacturers can achieve better inventory control, leading to more efficient production planning and cost savings. The results validate the application of Sugeno fuzzy logic as a robust approach for inventory prediction, capable of significantly improving the overall management of raw material stocks in the food industry. This research highlights the practical benefits of advanced predictive models in optimizing supply chains, supporting continuous production flow, and enhancing the overall efficiency of production systems. Consequently, the use of fuzzy logic methods can play a critical role in streamlining production processes and maintaining optimal inventory levels, ultimately contributing to the success and sustainability of food manufacturing operations.Prediksi yang akurat dari persediaan bahan baku sangat penting untuk manajemen biaya dan perencanaan produksi yang efektif di industri makanan. Metode logika rumit Sugeno digunakan untuk memprediksi tingkat stok bahan baku kulit kue. Tujuan dari metode ini adalah untuk memberikan sistem prediksi yang dapat diandalkan yang dapat meningkatkan manajemen stok dan mengurangi risiko kelebihan stok atau kekurangan stok. Tes persentase kesalahan rata-rata digunakan untuk menguji kinerja model, hasilnya adalah 3,94%, yang sesuai dengan tingkat akurasi 96.06%. Hasil ini menunjukkan tingkat akurasi yang tinggi, yang menunjukkan bahwa Sugeno Fuzzy Logic Method adalah alat yang layak dan efektif untuk memprediksi kebutuhan bahan baku dalam proses produksi kulit kue. Studi ini menunjukkan bahwa metode logika kabur dapat membantu dalam manajemen pasokan dan memastikan operasi produksi yang lancar
Pengembangan Website Berbasis Machine Lerning untuk Klasifikasi Kesehatan Pasien Diabetes
No full textThis research aims to develop a website utilizing the Support Vector Machine (SVM) algorithm for diabetes detection. The primary objective is to assist medical personnel in diagnosing diabetes efficiently by collecting and analyzing patient data to provide accurate health classifications. The SVM algorithm was chosen due to its high accuracy in managing complex and multidimensional medical data, making it ideal for diabetes detection. The website integrates SVM to process patient information and deliver precise predictions about their health status. By enhancing the diabetes diagnosis process, the system supports healthcare providers in making informed decisions and encourages patients to maintain regular check-ups. Additionally, the website features notifications for follow-up examinations, ensuring timely medical interventions and improving patient care and diabetes management. Its user-friendly interface allows medical staff to input and retrieve patient information with ease. This integration of advanced algorithms and intuitive design creates a valuable tool for both medical professionals and patients. By streamlining data collection and analysis, the website contributes to more accurate and timely diagnoses, fostering better health outcomes. This research highlights the potential of combining machine learning with healthcare to develop innovative solutions for chronic disease management, emphasizing the importance of regular monitoring and early detection in preventative healthcare.Penelitian ini mengembangkan sebuah website untuk mendeteksi diabetes menggunakan algoritma Support Vector Machine (SVM). Website ini bertujuan untuk membantu tenaga medis dalam mendiagnosis diabetes dengan mengumpulkan data pasien secara efisien dan memberikan klasifikasi kesehatan yang akurat. Algoritma SVM dipilih karena akurasinya yang tinggi dalam menangani data medis yang kompleks dan multidimensional, sehingga cocok untuk deteksi diabetes. Website ini mengintegrasikan SVM untuk memproses informasi pasien dan memberikan prediksi yang tepat mengenai status kesehatan mereka. Sistem ini memperbaiki proses diagnosis diabetes, membantu penyedia layanan kesehatan membuat keputusan yang tepat, dan mendorong pasien untuk menjalani pemeriksaan rutin. Kemampuan website untuk memberi notifikasi kepada pasien untuk pemeriksaan lanjutan memastikan intervensi medis tepat waktu, yang pada akhirnya meningkatkan perawatan pasien dan manajemen diabetes
Online Criminal Record Monitoring System for Issuance Certificates of Good Conduct, Life, and Morals in Bukavu
Full text linkIn the Democratic Republic of the Congo, the Ministry of Justice maintains criminal records for individuals with legal antecedents. However, certificates of good conduct, life, and morals are issued by local or district authorities without prior verification of the applicant's criminal record. This is due to the lack of a shared information system between the Ministry of Justice and these authorities. This paper describes the implementation of a platform that allows the Ministry of Justice to share criminal record information with local and district authorities. The system was modeled using the UP7 methodology and the Unified Modeling Language (UML). This platform ensures the reliability of the information provided on certificates of good conduct, life, and morals. Thanks to this new system, anyone with a criminal record is no longer able to hide their past by obtaining a certificate of good conduct, life, and morals that does not mention their criminal record. The results of the tests confirm that the system is user-friendly and meets the requirements of the users
Type 2 Diabetes Mellitus Diagnosis Model Using the C4.5 Algorithm
Full text linkType 2 Diabetes Mellitus (DM) is a metabolic disorder characterized by elevated blood sugar resulting from decreased insulin secretion by pancreatic beta cells and/or impaired insulin function (insulin resistance). Over the last 50 years, there has been a rapid increase in the prevalence of diabetes, paralleling the rise in obesity rates. This study aims to develop a diagnostic model for type 2 DM using C4.5, incorporating feature selection and analyzing age and gender parameters of Type II DM patients. The research employs the Cross-Industry Standard Process for Data Mining (CRISP-DM). Based on the dataset used, the C4.5 model demonstrated superior performance compared to SVM and Random Forest, achieving an AUC value of 72.5%, indicating a reasonably good classification level. The predominant gender among Type II DM patients is female, comprising 210 patients or 54.8% in the age range of 18-94 years, while 173 male patients or 45.2% fall within the age range of 23-80 years
Design and Analysis of a Knowledge Management System for Sawit Seberang Health Center Using the Inukshuk Methodology
Full text linkThe Sawit Seberang Health Center as the technical implementation unit of the health service is responsible for carrying out health development in the Sawit Seberang area, both in terms of health services and providing health knowledge that is useful for medical personnel in particular and the community in general. The problem faced by the Community Health Center is the unavailability of a computer-based system that can be accessed online as a medium for storing and sharing knowledge and information about health, both knowledge for fellow medical personnel and knowledge for the community. This problem can be solved with the KMS application which can be accessed online. The method used is the Inukshuk KM Model Method. The Inukshuk Knowledge Management model is a framework that has been refined from the SECI model (socialization, externalization, combination and internalization) with the addition of components such as leadership, culture and technology. The relationship with Knowledge Management is that it can provide information about Tacit and Explicit Knowledge in the organization. The result of this research is the KMS Puskesmas application which can be accessed online as a medium for storing and sharing knowledge for fellow medical personnel as well as a medium for information and knowledge for the community
PENERAPAN MACHINE LEARNING PADA DIFERENSIASI KUAH MENGANDUNG LEMAK BABI DAN LEMAK AYAM MENGGUNAKAN UV LED FLUORESCENCE IMAGING SYSTEM
No full textIn Indonesia, individuals have been found engaging in fraud for selling soupy dishes by adding pork fat to the broth. It is quite challenging to identify the pork fat contaminated soup from other halal broth. Using Machine learning, this studi attemps to identify and differentiating between RGB (Red Green Blue) values in picture of broth tainted with chicken and pork fat. The successful detection and differentiation of RGB values in broth contaminated with pork fat and chicken fat have been achieved. The broth samples were detected using a high-power UV-LED (Ultra Violet-Light Emitting Diode) Fluorescence Imaging System, while differentiation was accomplished through the implementation of a machine learning system. The data were processed using RapidMiner software with the K-NN algorithm. Detection was successfully performed through the spectrum of RGB values generated, while differentiation achieved a accuracy of 100%, precision of 100%, recall of 100%, and an AUC of 1.0.Telah berhasil dilakukan deteksi dan differensiasi nilai RGB pada kuah terkontaminasi minyak babi dan kuah mengandung minyak ayam. Sampel kuah dideteksi menggunakan alat high power UV-LED Fluorescence imaging sedangkan differensiasi dilakukan melalui penerapan machine learning system. . Data diolah menggunakan software RapidMiner dengan algoritma KNN. Deteksi berhasil dilakukan melalui spektrum nilai RGB yang dihasilkan, sedangkan diferensiasi berhasil dilakukan dengan nilai akurasi 100 %, presisi 100 %, recall 100% serta AUC 1.0