Non-Intrusive Load Monitoring (NILM) allows load identification of appliances through a single sensor. By using NILM, users can monitor their electricity consumption, which is beneficial for energy efficiency or energy saving. In advance NILM systems, identification of appliances on/off events should be processed instantly. Thus, it is necessary to use an extremely short period signal of appliances to shorten the time delay for users to acquire event information. However, acquiring event information from a short period signal raises another problem. The problem is target load feature to be easily mixed with background load. The more complex the background load has, the noisier the target load occurs. This issue certainly reduces the appliance identification performance. Therefore, we provide a novel methodology that leverages Generative Adversarial Network (GAN) to generate noise distribution of background load then use it to generate a clear target load. We also built a Convolutional Neural Network (CNN) model to identify load based on single load data. Then we use that CNN model to evaluate the target load generated by GAN. The result shows that GAN is powerful to denoise background load across the complex load. It yields a high accuracy of load identification which could reach 92.04%.

No abstract

Deep neural networks (DNNs), especially those used in computer vision, are highly vulnerable to adversarial attacks, such as adversarial perturbations and adversarial patches. Adversarial patches, often considered more appropriate for a real-world attack, are attached to the target object or its surroundings to deceive the target system. However, most previous research employed adversarial patches that are conspicuous to human vision, making them easy to identify and counter. Previously, the spatially localized perturbation GAN (SLP-GAN) was proposed, in which the perturbation was only added to the most representative area of the input images, creating a spatially localized adversarial camouflage patch that excels in terms of visual fidelity and is, therefore, difficult to detect by human vision. In this study, the use of the method called eSLP-GAN was extended to deceive classifiers and object detection systems. Specifically, the loss function was modified for greater compatibility with an object-detection model attack and to increase robustness in the real world. Furthermore, the applicability of the proposed method was tested on the CARLA simulator for a more authentic real-world attack scenario.

Dalam pengawasan lalu lintas, pengenalan nomor pelat kendaraan menjadi penting untuk dilakukan. Hal ini dikarenakan pengenalan nomor pelat kendaraan memiliki banyak tujuan seperti identifikasi kendaraan curian, identifikasi kendaraan yang melanggar tata tertib, manajemen perparkiran, pengecekan keluar masuk kendaraan, dan lain sebagainya. Sayangnya jumlah kendaraan yang semakin tinggi membuat hal ini tidak bisa lagi dilakukan secara manual. Maka dari itu dibutuhkan sebuah machine vision yang dapat mengenali nomor pelat kendaraan dengan cepat dan akurasi yang tinggi. Pada penelitian ini dikembangkan sistem pengenalan nomor pelat kendaraan menggunakan jaringan syaraf tiruan backpropagation (JST BP). Sistem ini mencari model terbaik JST BP yang mampu melakukan pengenalan karakter-karakter pada pelat dengan waktu tercepat namun dengan akurasi yang tetap tinggi. Dari model terbaik yang didapatkan, sistem pengenalan nomor pelat kendaraan ini memiliki persentase keberhasilan sebesar  99.80% pada data pelat yang digunakan sebagai pembentuk model dan sebesar 96.10% pada data verifikasi.