Hasil Pencarian  ::  Simpan CSV :: Kembali

"This fundamental work explains in detail the driver assistance systems for active safety and driver assistance, considering both their structure and their function. These include the well-known standard systems such as Anti-lock braking system (ABS), Electronic Stability Control (ESC) or Adaptive Cruise Control (ACC). But it includes also new systems for protecting collisions protection, for changing the lane, or for convenient parking.The book aims at giving a complete picture focusing on the entire system. First, it describes the components which are necessary for assistance systems, such as sensors, actuators, mechatronic subsystems, and control elements. Then, it explains key features for the user-friendly design of human-machine interfaces between driver and assistance system. Finally, important characteristic features of driver assistance systems for particular vehicles are presented: Systems for commercial vehicles and motorcycles."

"Dalam proses berkendara, pengemudi memiliki keterbatasan akan informasi selain dari panel instrumen (dashboard) dan penglihatan mereka, sehingga selalu terdapat resiko bahwa pengemudi lengah dan melakukan kesalahan. Untuk membantu pengemudi, salah satu pengembangan terkini di industri otomotif adalah Driver Assistence System atau DAS, yang ditujukan untuk membantu dengan cara memberikan informasi yang komprehensif mengenai kondisi kendaraan maupun kondisi sekitar kendaraan. Informasi yang didapatkan dapat berupa data kendaraan melalui sensor internal, serta data sensor eksternal seperti Kamera. Sebuah kendala dalam menelaah informasi dari Kamera adalah kemampuan untuk mendeteksi jalan dan mengidentifikasi objek yang ada di sekitar, yang umumnya memerlukan biaya komputasi yang cukup besar, sehingga masih tergolong kurang aksesibel.Dalam penelitian ini, dikembangkan sebuah rancangan sistem gabungan perangkat elektronik dan software, dengan kemampuan membaca data internal kendaraan melalui Sensor Grabber, serta menerima dan menelaah data visual dari Kamera. Algoritma deteksi jalan dan pendeteksian objek dikembangkan menggunakan teknik Image Processing serta Deep Neural Network atau Deep Learning. Data kemudian dapat ditampilkan secara visual melalui Graphical User Interface (GUI) yang dikembangkan dengan bahasa Python.Sistem dilatih dengan sampel berjumlah 816 gambar. Setelah melakukan pengujian, data internal kendaraan dapat diperoleh secara real-time, pendeteksian jalan dapat dilakukan dengan tingkat akurasi sebesar 84.96%, dan objek di sekitar kendaraan dapat diprediksi serta diketahui jarak dan posisinya menggunakan Deep Learning dengan tingkat kepresisian hingga 63.6%, dengan waktu komputasi total 121.68ms.

---

During driving, the driver does not have much information regarding the vehicle and its surroundings aside from the instrument panel and their own eyes, therefore there is always the risk of getting caught off-guard and making a mistake. To assist the driver, one of the current breakthroughs in the industry is Driver Assistance System (DAS), which is meant to help drivers by giving them comprehensive information regarding their vehicle or its surroundings. The given information can be the vehicle's data from internal sensors, and data from external sensors such as Cameras. A problem regarding analyzing visual data is how to detect road edges and identify the surrounding objects, which usually requires a sizable amount of computing power, therefore causing the technology to still remain less accessible to the public.

In this research, a system consisting of Electronics and software with the ability to retrieve vehicle data via a Sensor Grabber, as well as obtain and analyze visual data via a camera is designed. A Road Edge Detection an Object Detection Algorithm is developed with Image Processing and Deep Neural Network or Deep Learning Techniques. The data is then visualized through a Graphical User Interface (GUI) developed in Python.

The system is trained using a sample of 816 images. After a testing process, the internal data of the vehicle can be retrieved in real-rime, road edge detection can be achieved with 84.96% accuracy, and object detection with distance calculation using Deep Learning can be done with 63.6% accuracy, using total computation time of only 121.68ms.

"

"Sebagai salah satu ibukota terpadat di dunia, Jakarta mengalami kenaikan populasi yang cepat setiap tahunnya yang sejalan dengan pertumbuhan jumlah kendaraan bermotor. Masalah muncul ketika Jakarta dinobatkan sebagai salah satu kota yang tidak nyaman dalam hal mengemudi berdasarkan Indeks Kepuasaan Pengemudi yang dirilis oleh Waze (3,37 dari 10) dan sekitar 98 ribu kecelakaan terjadi sepanjang tahun 2017. Advanced Driver Assistance Systems (ADAS) bertujuan untuk meningkatkan performa pengemudi dan keselamatan berkendara. ADAS dapat memberikan peringatan dan melakukan intervensi yang dibutuhkan ketika menghadap situasi tertentu. Dua dari fitur yang diangkat pada penelitian ini adalah Forward Collision Warning (FCW) dan Lane Departure Warning (LDW). Oleh karena itu, tujuan penelitian ini adalah untuk mengukur penerimaan pengemudi terhadap penggunaan sistem dan mengetahui faktor-faktor yang mempengaruhi keinginan pengemudi untuk mengadopsi suatu teknologi. Melalui hasil penelitian didapatkan tiga variabel laten dengan dua belas variabel terukur yang menjadi faktor pengaruh terhadap keinginan pengemudi untuk menggunakan sistem. Rekomendasi untuk meningkatkan penerimaan pengemudi menjadi bagian akhir yang didapatkan berdasarkan evaluasi terhadap variabel yang tidak signifikan.

---

As one of the most populous capitals in the world, Jakarta experiences rapid population growth every year which is followed by increasing number of vehicles rapidly too. The problem arise when Jakarta was named as one of the cities not comfortable to drive based on Driver Satisfaction Index 2016 released by Waze (3,37 out of 10) and around 98 thousands accidents occurred in 2017. Advanced Driver Assistance Systems (ADAS) aims to enhance driver performance and improve safety. ADAS can alert and intervene as needed when facing certain situations. Two systems were investigated in this study, Forward Collision Warning and Lane Departure Warning. Therefore, the purpose of this research was to measure driver acceptance using these systems and discovered the factors that affecting behavioral intention to adopt the systems. Through the results of the study found three latent variables with twelves measured variables that are influential factors on the driver`s intention to use the systems. Recommendations for increasing driver acceptance become the final part obtained based on evaluation of variables that are not significant."

"This book consists of two closely intertwined parts. The first, theoretical part defines the concept of an information system, followed by an explanation of action regulation as well as cognitive theories to describe man information system interaction. A comprehensive description of information ergonomics concludes the theoretical approach. In the second, practically oriented part of this book authors from industry as well as from academic institutes illustrate the variety of current information systems taken from different fields of transportation, i.e. aviation, automotive, and railroad. "

"Peningkatan angka kecelakaan kerja di Indonesia menuntut adanya suatu pengembangan pendekatan manajemen kesehatan dan keselamatan kerja bagi para pegawai. Nyatanya, penyebab dari suatu kecelakaan kerja masih didominasi akibat kesalahan tindakan manusia (human error). Human error sangat erat dikaitkan dengan kecelakaan industri dan dalam kasus ini human error yang terjadi pada proses fabrikasi kendaraan khusus (armoured vehicle) yang memiliki lingkungan kerja yang ekstrem. Bercermin pada hal tersebut maka dibutuhkan suatu penelitian untuk mengurangi resiko kecelakaan kerja dengan pendekatan analisis identifikasi dan pengurangan human error. Sebuah pendekatan sistematis yang mengkombinasikan teknik identifikasi serta pengukuran pada human error yang dimulai dengan mengidentifikasi mengidentifikasi setiap task-task yang berlangsung pada proses fabrikasi kendaraan khusus. Kemudian dilakukan identifikasi kegagalan kerja menggunakan metode Systematic Human Error Risk Prediction and Analysis untuk memetakan resiko serta dampak dari setiap rangkaian-rangkaian pekerjaan. Selanjutnya dilakukan pengukuran human error terhadap task-task tersebut dengan menggunakan metode Human Error Analysis and Reduction Technique (HEART) serta metode Standardized Plant Analysis Risk Human Reliability Assessment (SHERPA) yang masing-masing memiliki pendekatan yang relevan dalam menganalisis kondisi serta faktor yang mempengaruhi kegagalan dari sebuah pekerjaan. Terakhir dilakukan analisa pola kecelakaan kerja dengan metode Fault Tree Analysis (FTA). Pendekatan ini menghasilkan identifikasi kegagalan kerja secara mendetail, pengukuran human error yang relevan, serta memberikan rekomendasi dan prioritas penanggulangan kecelakaan kerja dalam manajemen kesehatan dan keselamatan kerja pada fabrikasi kendaraan khusus.

---

The increasing number of work accidents in Indonesia demands a developed approach to management of occupational health and safety. In fact, the cause of an accident is still dominated by the improper work of human actions (human error). Human error is always related to industrial accidents, and in this case the human error that occurs in the fabrication process of armored vehicle that has an extreme working environment. Referring from that condition, a research to reduce the risk of workplace accidents with identification and reduction of human error analysis approaches must be needed.

A systematic approaches that combine identification technique to human error start from identification of every tasks in fabrication process of armoured vehicle. Then, work failure is identified by using Systematic Human Error Risk Prediction and Analysis method to measure the risk and impact from every tasks sequences. Then, assessment of human error conducted for every tasks with Human Error Analysis and Reduction Technique (HEART) method and Standardized Plant Analysis Risk Human Reliability Assessment (SHERPA) method that have their own relevant approaches in order to analyze the conditions and factors that influence the failure of a tasks.

Last step is to mapping the pattern of work accident using Fault Tree Analysis (FTA). This approaches resulting in detailed work failure identification, relevant human error measurement, and finding out the recommendation dan prioritize remedial action for reducing the work accident in occupational health and safety management for fabrication process of armoured vehicle."

"This book introduces concepts and technologies of Intelligent Transportation Systems (ITS). It describes state of the art safety communication protocol called Dedicated Short Range Communication (DSRC), currently being considered for adoption by the USDOT and automotive industry in the US. However, the principles of this book are applicable even if the underlying physical layer protocol of V2X changes in the future, e.g. V2X changes from DSRC to cellular-based connectivity.Fundamental ITS concepts include topics like global positioning system; Vehicle to Vehicle (V2V), Vehicle to Pedestrian (V2P), and Vehicle to Infrastructure (V2I) communications; human-machine interface; and security and privacy. Fundamental concepts are sometimes followed by the real-life test experimental results (such as in V2P Chapter) and description of the performance metrics used to evaluate the results. This book also describes equations and math used in the development of the individual parts of the system.This book surveys current and previous publications for trending research in the ITS domain. It also covers state of the art standards that are in place for the DSRC in the US, starting from the application layer defined in SAE J2735 all the way to physical layer defined in IEEE 802.11.The authors provide a detailed discussion on what is needed to extend the current standards to accommodate future needs of the vehicle communications, such as needs for future autonomous vehicles. Programs and code examples accompany appropriate chapters, for example, after describing remote vehicle target classification function a pseudo code and description is provided. In addition, the book discusses current topics of the technology such as spectrum sharing, simulation, security, and privacy.The intended audience for this book includes engineering graduate students, automotive professionals/engineers, researchers and technology enthusiasts."

"ABSTRAK

Untuk menunjang pemantauan konsentrasi manusia, perlu adanya pemahaman mengenai respon sinyal dari EEG terhadap dua kondisi manusia ya itu saat sedang konsentrasi penuh dan konsentrasi tidak penuh (adanya distraksi). Dalam mengolah data sinyal EEG tersebut, dibutuhkan metode algoritma dan klasifikasi sinyal untuk mendapatkan hasil data sinyal dari dua kondisi tersebut. Pada penelitian ini akan dijelaskan tentang sistem perancangan pendeteksian konsentrasi manusia berdasarkan sinyal EEG. Metode yang digunakan adalah Fast Fourier Transform (FFT) dan Discrete Wavelet Transform (DWT) sedangkan dalam algoritma klasifikasinya menggunakan Support Vector Machine (SVM). Hasil yang telah didapatkan dalam pengujian ini adalah SVM lebih mampu untuk mengklasifikasikan sistem dengan kernel RBF menggunakan 30% holdout validation. Keakurasian dari sistem ini adalah 91% pada metode DWT dan 72% pada metode FFT. Sehingga, dari kedua ekstraksi metode FFT dan DWT, yang memiliki nilai ekstraksi terbaik adalah DWT.

---

ABSTRACTTo support the monitoring focused human concentration, there is a need to understand the response of signals from EEG in two conditions which are when human is in full concentration and less concentration (presence of distraction).  To process those EEG signal data, an algorithm method and classification is needed to get the results of signal data from these two conditions In this research, the system of detecting design of human concentration levels based on EEG signals will be explained. The used methods are Fast Fourier Transform (FFT) and Discrete Wavelet Transform (DWT) while the classification algorithm uses Support Vector Machine (SVM).  The result of this research shows that by using SVM, a much more reliable result is achieved when a kernel RBF is used with 30% holdout validation. The result of the aforementioned method yields a 91% accuracy with DWT method and a 72% accuracy with FFT. 

 

"