There are around 650 million people from all over the world who lived with disabilities. One of the fundamental rights of people with disabilities is the existence of a companion to supervise his activity. Meanwhile, the use of mobile phones for monitoring the activities of people with disabilities has been widely carried out. The human activity monitoring mobile application requires human activity recognition methods that provide high accuracy, precision, and recall to reduce the error rate of the activity estimation. Some researches use machine learning algorithms like K-Nearest Neighbour (k-NN) algorithm, Artificial Neural Networks (ANN), Support Vector Machine (SVM), and Random Forest for human activity recognition methods. However, the results of these studies have not been compared apples to apples. Therefore, this study presents a performance comparison of SVM, KNN, and Random Forest machine learning methods. Based on our findings, the SVM method with Support Vector Classifier (SVC) and Radial Basis Function (RBF) kernels can achieve the highest precision and recall, 87% and 85% respectively. The fastest processing time is obtained using the SVM method with the Stochastic Gradient Descent. However, in general, the best performance is shown by Random Forest. The Random Forest method with a depth of 100 and 300 trees can reach an accuracy of 96% within 0.45 minutes.

This paper presents UKARA, a fast and simple automatic short-answer scoring system for Bahasa Indonesia. Automatic short-answer scoring holds an important role in speeding up automatic assessment process. Although this area has been widely explored, only very limited number of previous work have studied Bahasa Indonesia. One of the major challenges in this field is the different type of questions which require different assessments. We are addressing this problem by implementing a combination of Natural Language Processing (NLP) and supervised machine learning techniques. Our system works by training a classifier model on human-labeled data. Using three different types of Programme for International Student Assessment (PISA) student responses, our system successfully produced the F1-score above 97% and 70% on dichotomous and polytomous scoring types respectively. Moreover, UKARA provides a user-friendly interface which is simple and easy to use. UKARA offers a flexibility for human grader to do re-scoring and retraining the model until the optimal performance is obtained.

Besides specification and price, smartphone reviews can affect on consumer interest buying. This study aims to use the value of smartphone review sentiment as one of the attributes/criterias in addition to specifications and prices on the calculation of Decision Support System using MOORA method to generate smartphone recommendations. Sentiment value is obtained from sentiment analysis using SentiWordNet. There are two approaches of MOORA method used in this research, Ratio System and Reference Point Approach. Testing has been done by comparing the results of smartphone recommendations between approaches on the MOORA method, with or without sentiment analysis, on smartphone rankings based on the number of smartphone fans on the GSM Arena site. The test results show that the method of MOORA with Ratio System approach without sentiment analysis has the best accuracy among other approaches. Intisari-Selain spesifikasi dan harga, review smartphone dapat memengaruhi minat beli konsumen. Makalah ini bertujuan untuk menggunakan nilai sentimen review smartphone sebagai salah satu atribut/kriteria, selain spesifikasi dan harga, pada perhitungan Sistem Pendukung Keputusan menggunakan metode MOORA untuk menghasilkan rekomendasi smartphone. Nilai sentimen diperoleh dari sentiment analysis menggunakan SentiWordNet. Terdapat dua pendekatan dari metode MOORA yang digunakan pada makalah ini, yaitu pendekatan Ratio System dan Reference Point. Pengujian dilakukan dengan membandingkan hasil rekomendasi smartphone antar pendekatan pada metode MOORA, dengan atau tanpa sentiment analysis, terhadap ranking smartphone berdasarkan jumlah fan smartphone pada situs GSM Arena. Hasil pengujian menunjukkan bahwa metode MOORA dengan pendekatan Ratio System tanpa sentiment analysis memiliki akurasi paling bagus di antara metode-metode lain.

Web applications are the objects most targeted by attackers. The technique most often used to attack web applications is SQL injection. This attack is categorized as dangerous because it can be used to illegally retrieve, modify, delete data, and even take over databases and web applications. To prevent SQL injection attacks from being executed by the database, a system that can identify attack patterns and can learn to detect new patterns from various attack patterns that have occurred is required. This study aims to build a system that acts as a proxy to prevent SQL injection attacks using the Hybrid Method which is a combination of SQL Injection Free Secure (SQL-IF) and Naïve Bayes methods. Tests were carried out to determine the level of accuracy, the effect of constants (K) on SQL-IF, and the number of datasets on Naïve Bayes on the accuracy and efficiency (average load time) of web pages. The test results showed that the Hybrid Method can improve the accuracy of SQL injection attack prevention. Smaller K values and larger dataset will produce better accuracy. The Hybrid Method produces a longer average web page load time than using only the SQL-IF or Naïve Bayes methods.

Understanding the principles of animation is an important factor and determines the quality of animation that can be produced. However, explanation of the principles of animation in many book are still specifically to traditional animation, not 3D computer animation that mostly used today. Students have difficulty applying traditional animation principles to 3D computer animation principles. Therefore, the purpose of this research is to develop thirteen instructional videos for the topic of Principle of 3D Computer Animation and to determine the effectiveness of these videos on student understanding. Video development uses the Research and Development Four-D model (Define, Design, Develop, and Disseminate). Based on the results of product testing, these thirteen learning videos were declared “very good”. The paired t-test results showed that the product developed was effective in increasing students’ understanding of the Principle of 3D Computer Animation.