Education is one of the activities carried out by students and students in order to obtain a title. The process that is common in edification method in Indonesia is a legal action that is done via academic credit at school institutions and must be completed if you want to get recognition in the issuance of a diploma. In Indonesia, a learning activity is full of semi-computer processes but not all educational institutions have implemented this technology. In cases like this, an individual may look for loopholes to commit fraud, such as falsifying diplomas. To find a solution to the problems above, we need to digitize, what is it? Digitization is one of the system that can offer a sense of security and can minimize bureaucracy in the document legal action of ratification with savings on retention and manpower used. A tips passed by students before receiving an academic diploma at one of the universities are starting with the registration process, after all the registration processes are completed, a student is officially accepted at the university and can directly participate in teaching and learning activities , at the time of graduation, it is certain that a student must pass all courses and have completed all the tasks that have been given until he is officially declared graduated. Problems that often occur in the field of education, especially when it is in the registration process, are data falsification, data manipulation, and even the worst case is data loss, this fraud is usually carried out by irresponsible parties. This journal aims to submit a proposal for the schoolboy registry process of school institute in digitalization education method in Indonesia using Blockchain technology. This study resulted in a student enrollment model in an educational institution using Blockchain to supply transparent and validated data in educational process.
Drones or quadcopters have been widely used in various fields based on deep learning, especially object detection. However, drone vision characteristics such as occlusion and small objects are still being explored for performance in terms of accuracy and speed detection. The YOLO architecture is very commonly used for cases requiring high-speed detection. To overcome the limitations of drone vision, in this paper, we explore the size of the YOLOv5s backbone kernel in the shallowest convolutional layer to achieve better performance. The kernel is a filter that has a main role in the feature map, and it defines the size of the convolution matrix, and the resulting features in the shallowest convolutional layer are more representative of the case of object detection and recognition. The techniques can be divided into three major categories: (1) data preprocessing, which involves augmentation and normalization of the data, (2) kernel size exploration in the shallowest convolutional layer of the YOLOv5s, and (3) model implementation in the real environment using the quadcopter. The dataset consisted of four classes representing dragon fruit, snake fruit, banana, and pineapple, with a total of 8000 data. Exploration results with kernel size give promising results. Kernel sizes 5 and 7 give an mAP of 0.988. Through these results, modification of the kernel size provides an opportunity for more in-depth investigations, such as with the epoch parameter, padding scheme, and other optimization techniques.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.