I have been a lecturer since January 2020 but am not actively writing papers. Since last year, I have been interested in researching AIoT, which combines Machine learning and IoT to develop some hardware implementation that embeds model AI inside it. Those are lists of my research paper related to machine learning and IoT.
2023
Best Machine Learning Model For Face Recognition in Home Security Application
Istiqomah, Faqih Alam, Achmad Rizal
Abstract: Particularly since the COVID-19 outbreak, Indonesia has seen an annual surge in criminal prosecutions. To increase home security, many technological advances have been made. Face recognition served as the main form of security for almost all of them. Face detection, face segmentation, and face recognition are the three steps in the face recognition process. To avoid misclassification and increase system dependability, accurate recognition of faces becomes crucial in security systems. The optimization tool Grid Search CV produces using a number of machine learning methods that are proposed. Each machine learning has been created using its best model and has attained accuracy levels of at least 90%. The most effective strategy is SVM, which has 100% accuracy rates. A technique for choosing the best model is an alternative. The computation time will be compared to that of more complex systems before these results are eventually communicated to the real system.
Keywords: Face Recognition, Machine Learning, Home Security
Individual Recognition Based on Gait Using Multi-Distance Signal Level Difference Sample Entropy
Istiqomah, Achmad Rizal, Ratih Dwi Atmaja
Abstract: The way a person walks has unique characteristics for each individual and can be used to recognize them. There are various ways to classify characteristics for gait of each individual, one of them is the inertia sensor. The inertia sensor is used to collect data gait signals, which are angular velocity variations caused by human walking movements. Multi-distance Signal Level Difference Sample Entropy is proposed in this study as a feature extraction before classifying individual gaits. MSLD is used to measure the co-occurrence of two signal samples at a distance d, and SampEn quantizes signal complexity. The MSLD Entropy produce 60 features in the form of SampEn at distances of 1 until 20 from the three-axis. The testing procedure is carried out on the MSLD Entropy result signal for each classifier with a feature in the form of SampEn at distances of d=1–20, d=1–15, d=1–10, and d=1–5. Softmax regression as a classifier and feature at distance 1 until 20, the test results produce the greatest accuracy of 98.3%. Because a person’s gait can be identified not just from one but three directions, using only one axis results in lesser accuracy than using data from all three axes.
Keywords: individual recognition, gait, inertia sensor, MSLD entropy