With the rapid development and popularization of Internet of Things (IoT) devices, an increasing number of cyber-attacks are targeting such devices. It was said that most of the attacks in IoT environments are botnet-based attacks. Many security weaknesses still exist on the IoT devices because most of them have not enough memory and computational resource for robust security mechanisms. Moreover, many existing rule-based detection systems can be circumvented by attackers. In this study, we proposed a machine learning (ML)-based botnet attack detection framework with sequential detection architecture. An efficient feature selection approach is adopted to implement a lightweight detection system with a high performance. The overall detection performance achieves around 99% for the botnet attack detection using three different ML algorithms, including artificial neural network (ANN), J48 decision tree, and Naïve Bayes. The experiment result indicates that the proposed architecture can effectively detect botnet-based attacks, and also can be extended with corresponding sub-engines for new kinds of attacks.

The application of a large number of Internet of Things (IoT) devices makes our life more convenient and industries more efficient. However, it also makes cyber-attacks much easier to occur because so many IoT devices are deployed and most of them do not have enough resources (i.e., computation and storage capacity) to carry out ordinary intrusion detection systems (IDSs). In this study, a lightweight machine learning-based IDS using a new feature selection algorithm is designed and implemented on Raspberry Pi, and its performance is verified using a public dataset collected from an IoT environment. To make the system lightweight, we propose a new algorithm for feature selection, called the correlated-set thresholding on gain-ratio (CST-GR) algorithm, to select really necessary features. Because the feature selection is conducted on three specific kinds of cyber-attacks, the number of selected features can be significantly reduced, which makes the classifiers very small and fast. Thus, our detection system is lightweight enough to be implemented and carried out in a Raspberry Pi system. More importantly, as the really necessary features corresponding to each kind of attack are exploited, good detection performance can be expected. The performance of our proposal is examined in detail with different machine learning algorithms, in order to learn which of them is the best option for our system. The experiment results indicate that the new feature selection algorithm can select only very few features for each kind of attack. Thus, the detection system is lightweight enough to be implemented in the Raspberry Pi environment with almost no sacrifice on detection performance.

A content-based image retrieval system, as an Indonesian traditional woven fabric knowledge base, can be useful for artisans and trade promotions. However, creating an effective and efficient retrieval system is difficult due to the lack of an Indonesian traditional woven fabric dataset, and unique characteristics are not considered simultaneously. One type of traditional Indonesian fabric is ikat woven fabric. Thus, this study collected images of this traditional Indonesian woven fabric to create the TenunIkatNet dataset. The dataset consists of 120 classes and 4800 images. The images were captured perpendicularly, and the ikat woven fabrics were placed on different backgrounds, hung, and worn on the body, according to the utilization patterns. The feature extraction method using a modified convolutional neural network (MCNN) learns the unique features of Indonesian traditional woven fabrics. The experimental results show that the modified CNN model outperforms other pretrained CNN models (i.e., ResNet101, VGG16, DenseNet201, InceptionV3, MobileNetV2, Xception, and InceptionResNetV2) in top-5, top-10, top-20, and top-50 accuracies with scores of 99.96%, 99.88%, 99.50%, and 97.60%, respectively.

Sign language uses gestures instead of speech sound to communicate. However, it is rare that the normal people try to learn the sign language for interacting with deaf people. Therefore, the need for a translation from sign language to written or oral language becomes important. In this paper, we propose a prototype system that can recognize the hand gesture sign language in real time. We use HSV (Hue Saturation Value) color space combined with skin detection to remove the complex background and create segmented images. Then a contour detection is applied to localize and save hand area. Further, we use SURF algorithm to detect and extract key point features and recognize each hand gesture sign alphabet by comparing with these user image database. Based on the experiments, the system is capable to recognize hand gesture sign and translate to Alphabets, with recognize rate 63 % in average.

Sign language uses gestures instead of speech sounds to communicate. But in general, normal people rarely trying to learn sign language to interact with the deaf community. Recently, there are many sign language recognition system that had been developed. But most of them were implemented using desktop and laptop computer, which is impractical due to its weight and size. This paper presents a prototype of real time static Indonesian sign language recognition using the Android Smart Phone, so it can be used anywhere and anytime. YCrCb color space combined with skin color detection is used to remove the background image and form a segmented image. Detection contour with convex hull algorithms are used to localize and save an area of the hand. Convexity defect algorithms then are used to extract the hand gesture's features using a radiant line from the center of the palm to the fingertips. The classification of hand gesture that performs sign alphabets is accomplished using back propagation neural network algorithm in order to determine a suitable alphabet. The performance test of the system is done by recognizing some variation hand gesture poses for Indonesian sign language alphabet. The results show that the system can detect the position of the user's hand. Furthermore, the system can recognize the alphabet sign from user hand gesture input, reaching 91.66% success rate in testing using Android devices in real time.

Turnover is one of the factors that can cause the development of a company to be hampered, especially for startup. The high level of employee turnover caused by many things, one of them is employee dissatisfaction. Onboarding process is one of the ways that can be used to introduce the new employee to the culture and work environment so that it can develop job satisfaction and convenience. However, to get an effective result, onboarding process should also be done well and systematically. This paper describes how the onboarding process is done by the startups, especially those that specialize in software engineering. The study used literature review, interview and questionnaire methods. The interview was conducted with the leaders of six startups in Yogyakarta, while questionnaires were distributed to employee in each startup who have worked for about one year. The data of the questionnaire were analyzed using descriptive statistics. Based on the results, it was found that all startups have done the five aspects of onboarding on their new employees. But the average value on these five aspects is below 80%. The lowest average score of 67% is in the documentation aspect. While the lowest sub aspect is a sub aspect of developer-oriented documentation with an average value of 58.22% and this is included in enough criteria.