No abstract

The security of a network might be threatened by an intrusion aim to steal classified data or to find weaknesses on the network. In general, network main security systems use a firewall to control and monitor both incoming and outgoing network traffic. Intrusion Detection System can be used to strengthen network security. Several data mining methods have been used to solve Intrusion Detection System (IDS) problem on a network. On this paper we will use Naïve Bayes Classifier along with Particle Swarm Optimization (PSO) as the feature selection method specifically on one of the benchmark dataset on IDS problem, KDD CUP’99. The dataset consists of more than 40 features with more than 400 thousands records. To solve IDS problem on the dataset, it needs a quite expensive cost either on time computation or memory usage hence the use of PSO as the feature selection method. The best classification result was reached when we use 38 features where the accuracy is 99.12%. Particle Swarm Optimization method has several parameters that may affect the classification performance. For future improvement, it is possible to use a parameter optimization method to ensure the best classifier performance.

Polarization imaging can be used to improve the image quality by reducing the effects of the unwanted light reflection, enhancing the quality of images taken in non-ideal conditions, such as foggy weather, or reconstructing the 3D form of an object based on the shape from polarization. Reconstructing a 3D form requires the acquisition of multiple images and inference of the polarization parameters, such as the degree of polarization and angle of polarization, from these experimental data. The light polarization extraction process should begin by performing the photometric calibration to improve the performance of the polarize instrument measurements by reducing the measurement errors and improving the consistency between measurements. We propose an algorithm based on the kernel ridge regression method to estimate both the polarization parameters and the measurement (angle) errors in the placement of the polarizer. The algorithm was tested on four different sets of images containing different objects based on their responses to light and polarization. The algorithm that uses the mixed kernel function gives the best results. INDEX TERMS Calibration, kernel ridge regression, polarization, polarizer.

Researches involving Artificial Neural Network (ANN) or its derivative have been published all around the world, spesifically to solve data mining problem, classification, clusterinf, or detection problems. Recurrent Neural Network is a class of ANN with Long Short Term Memory (LSTM) as its one of the architecture that commonly used in deep learning problems. On this paper, we use LSTM to detect hate speech on social media related with Indonesia President Election on 2019. There are several steps on this research, we start with literature study, data collection, data preprocessing, training step, and testing step.  The dataset consist of 950 sentences, while the testing data consist of 190 comments on Facebook. The best model performance was reached with recall value 0.7021, which menas that from the whole relevant instances on the testing data, 70.21% were categorized as relevant, on this case as hate speech (HS). The other performance parameter value as in accuracy and precision still quite low due to the testing data that comes directly from social media which highly possible consist of inconsistent choises of words, informal words, or contains grammatically error sentences.

No abstract