Search

Traffic sign recognition is a computer vision technique to recognize the traffic signs put on the road. In this paper, a traffic sign dataset with approximately 5000 images is collected. This paper presents an ablation analysis of Multilayer Perceptron and Convolutional Neural Networks in traffic sign recognition. The ablation analysis studies the effects of different architectures of Multilayer Perceptron and Convolutional Neural Networks, batch normalization, and dropout. A total of 8 different models are reviewed and their performance is studied. The experimental results demonstrate that Convolutional Neural Networks outperform Multilayer Perceptron in general. Leveraging dropout layer and batch normalization is effective in improving the stability of the model and achieved 98.62% accuracy in traffic sign recognition.

Deciding on the most suitable university program to pursue after completing secondary education is a major step for school-leavers as it sets the tone of the career path they will embark on in the future. Undeniably, deciding on the university program is a sophisticated problem that involves a broad range of factors, such as geographic location, overall cost, campus security, personality, etc. Most of these factors, for instance, geographic location and campus security only have temporary impact on the school-leavers while they are attending to university. Nevertheless, the personality factor appears to be the long-term and the most crucial determinant of the success in their professional life. When choosing the university program, school-leavers often make the mistake of following friends' footsteps or adhering to parents' decisions, only to realize years later that it is not what suits their personality or what they want. Considering these challenges, this work studies on the Holland's Personality Test to examine the personality of school-leavers. There are six personality types in Holland's Personality Test, represented as RIASEC code or Holland code. On top of that, this work also compiles a comprehensive list of university programs with their corresponding Holland code. An expert system is then engineered to encode the information into the knowledge base. Upon taking the Holland Personality Test, the expert system will update the facts list based on the answers given. Subsequently, the inference engine activates the production rules if the conditions are fulfilled. Ultimately, the personality type and recommended university program are presented to the school-leavers.