In manufacturing practice, manufacturers always strive to achieve both quality and productivity targets simultaneously. In the first part, this study examines the relationship between input factors, including cutting speed, depth of cut, and feed rate, and the output response, which is surface roughness, when milling hardened SKD11 alloy steel under minimum coolant lubrication conditions using SiO2 nanofluid. The input parameters are divided into four levels to determine their influence on surface roughness and to find the optimal conditions for achieving the minimum surface roughness. The experimental design was conducted using an L16 array. A second-order regression model was developed to describe the relationship between the input variables and the output response. In the second part, multi-objective optimization was performed to simultaneously achieve the minimum surface roughness and the maximum material removal rate (MRR). The Response Surface Methodology (RSM) was employed in this study. The results indicated that to achieve the minimum surface roughness, machining should be performed at a cutting speed of 100 m/min, a cutting depth of 0.2 mm, and a feed rate of 0.01 mm/tooth. With these settings, the predicted surface roughness could reach 0.0451 µm. On the other hand, for the multi-objective optimization, to achieve the minimum surface roughness and the maximum MRR simultaneously, machining should be carried out at a cutting speed of 100 m/min, a cutting depth of 0.36 mm, and a feed rate of 0.0168 mm/tooth. With this cutting condition, the predicted surface roughness could reach 0.1069 µm, and the predicted MRR could reach 775.06 mm3/min

Automatic traffic sign recognition is essential in researching and developing driver assistance systems and autonomous vehicles. This paper presents the research and development of an automated traffic sign recognition module in Vietnam. The recognition model is developed based on the deep learning model YOLOv5 and incorporates architectural modifications to reduce computational complexity, increase inference speed, and meet real-time requirements for embedded system applications. The model is trained using a custom dataset collected by the research team from real-world street environments in Vietnam, encompassing diverse locations, times, and weather conditions. The trained recognition model is deployed on the Jetson embedded system, yielding high-quality recognition results and meeting real-time recognition needs.