Bahtiar Saleh Abbas’s research while affiliated with Binus University and other places

This paper proposes the implementation of Bidirectional Long Short-Term Memory (LSTM) model for forecasting crop pest attack based on multivariate inputs of weather data. To enhance the model performance, the efforts implemented include optimizing the training process by applying sliding-windows methods and setting appropriate parameters. After obtaining the best settings, the proposed model was then compared with two other variants of the LSTM model, namely Vanilla LSTM and Stack LSTM. The model performance evaluation was done by finding Mean Square Error (MSE) and root mean square error values from training and testing process. The results show that there were increased performances from using sliding-windows method to optimize the training process and the appropriate parameter setting. Bidirectional LSTM model, along with the treatments implemented, gave the best performance compared to the two other models.

Climate anomalies are considered as an important factor closely related to many disasters causing many human losses, such as airline crash, wildfires, drought and flooding in many areas. Many researchers have projected that the rising global temperature will increase the draught, especially in the mid-latitude areas. Taking those problems into account, studies on anomaly detection in climate are crucial. While climate prediction aims to analyze and model regular pattern of climate, climate anomaly studies aim to model climate deviation from its previous general patterns. Long Short Term Memory (LSTM) is a method employed in this research because it has been proven to work effectively in several anomaly detection studies, especially for data with similar characteristics. This paper presents empirical results of using Basic LSTM, Densely Connected (DC) LSTM, and Stacked-DC LSTM models to detect temperature anomaly as a manifestation of climate change in Semarang City. The results show that Stacked DC LSTM produced higher accuracy in detecting anomaly than the other two methods.

Web applications continue to grow however web attacks are also increasing, this shows an increase in web application vulnerabilities. Several methods have been used to detect vulnerabilities in web applications such as black-box testing, dynamic analysis, and static analysis. In this article, we propose a framework for detecting web application vulnerabilities by combining all three methods. The strengths of one method are used to overcome the weaknesses of another method. This framework is believed to provide better results than if each method was used separately.

We would like to measured the information system of Pamulang University library through the usability evaluation. The method in this study uses the adoption of the Knowledge Management System Life Cycle (KMSLC) life cycle. Where the stages used consist of Evaluation of Existing Infrastructure Analysis, Capture Knowledge, Implementing the KM system, Evaluation. The steps taken are system analysis, knowledge mapping in the application, implementation results and evaluation using usability. The questionnaire was conducted on 20 respondents, including 10 students and 10 Pamulang University lecturers. The questionnaire was conducted in 3 categories namely effectiveness, efficiency and satisfaction with 10 questions each so that there were 60 questions and 3 linkers namely 4 if they all agreed, 2 if they did not know and 0 did not agree. The results of the SUMI questionnaire against the Library are 90; 75; 75; 87.5; 90; 75. The usability evaluation results are above average, meaning that the usability in the UNPAM Library system is already in the good category.

Tourism is the main driving force of the Indonesian economy. So far, Indonesia's maritime economic potential has not been optimally developed, especially in Natuna. The area of Natuna Sea is 99.25%, so it is very potential to develop marine tourism. Natuna is also included in the planning of the Global Maritime Fulcrum and is given the authority to manage tourism. Natuna Geopark has also been inaugurated by UNESCO in 2019. The presence of a geopark in Natuna will have an impact on the movement of foreign tourists. Thus, it is necessary to prepare human resources for tour guides to welcome foreign tourists. This study describes the design of Natuna Tourism application with an emphasis on mobile-assisted language learning (MALL) to introduce Natuna tourism in Indonesian, English and Mandarin. Through this application, students can learn independently. This application also features pictures and sounds with a quiz that helps learners to memorize vocabulary. Before designing this application, researchers first conducted interviews with the Natuna tourism service and religious high schools. From the interviews, the application was designed using the Mnemonic method. Researchers hope that with applications on smartphones that can be used offline, the Natuna tourism agency will develop and can contribute to improving the maritime economyfishermen, fish processing technology and illegal fishing. Whereas the obstacle in the field of goods distribution is the Sea Toll Program which is of little help due to the trip schedules of ships which are only twice a month. The fishermen's catch has become no longer fresh and cannot be sold at high prices. There should be special treatment for Natuna by developing a model of economic integration of Maritime and tourism.

Mobile banking and mobile payment are currently always used by customers for financial payments. With customer payments, it is usually easier to make payments with mobile payment, because it is more practical and direct than mobile banking. However, is the privacy of both platforms understood by the customer? Research questions to be answered: 1) What are the factors that influence privacy issues in mobile banking? 2) What are the factors that influence privacy issues with mobile payments? 3) What are the factors that influence confidence in mobile banking? 4) What are the factors that influence confidence in mobile payments? 5) Does the privacy factor influence the perceived privacy? 6) Does the confidence factor influence the perceived privacy? There are two research models and 12 (twelve) hypotheses for each model. Privacy risk, subjective norm, information management factors positive influence on privacy interest, and trust. Care about privacy and trust have a positive influence on mobile payment.

In this preliminary descriptive study, the authors highlight a problem occurring in Indonesia. They reveal that Indonesia's "Digital Islands" are the largest internet user-base in the Southeast Asian region (150 million internet users in 2018), generate the largest internet economy ($27 billion in the year 2018) and operate the fastest-growing internet economy in Southeast Asia. However, the use of E-commerce itself in the sector of small and medium enterprises (SMEs) in Indonesia is still only between 9-15 %. The objective of this review is to establish a theoretical model that links digital business adoption, organizational innovation, frugal innovation type, and firm performance. A systematic literature review (SLR) is the method used for the critical review. The critical result of the review is used as the basis for the development of the concept. More than 864,000 publications released between 2014 and 2019 were screened using the keywords: digital business adoption, e-business adoption, e-commerce adoption, type of innovation, frugal innovation, organisational innovation, and firm performance. Eventually, for this study, 23 journals were included. Based on the analysis, the conceptual model has four possible connections: (1) The positive relationship between digital business adoption and SME achievements; (2) the good relationship between the adoption of digital businesses and organisational innovation; (3) the positive direct impacts of organizational innovations on company performance; and (4) a positive relationship exists between digital business adoption and frugal innovation type and organizational innovation. This study contributes a conceptual framework that digital business adoption, frugal innovation type, and organisational innovation might have important roles in the performance of SMEs.

The combination of gamma-ray irradiation treatment and somaclonal variation may cause morphological changes in vitro culture of rodent tuber. In vitro shoots were irradiated with several gamma-ray doses. Rodent tuber plantlets were irradiated with the doses of 20 Gy. The plantlets were subcultured up to 5 times then produced MV1 to MV5. Plantlets MV4 and MV5 were acclimatized and transplanted at the greenhouse. The purpose of this study was to analyze the morphological characteristics in the fourth mutant vegetative propagation (MV4) and the fifth mutant vegetative propagation (MV5) of rodent tuber from the combination of gamma-ray irradiation and somaclonal variation. Subcultures were performed to regenerate from MV1 to MV5 with optimal MS (Murashige & Skoog) medium. Subcultures were done at eight weeks. The morphological measurement in MV4 with the average number of shoots, number of leaves and plant height, i.e. 5.21, 14.41 and 5.52 cm, respectively. The highest average number of shoots, number of leaves and plant height was generated in MV5, i.e. 5.23, 16.54 and 5.18 cm, respectively. Pre-acclimatization were successfully produced in the greenhouse of about 30% (MV4) and 39.5% (MV5). Post acclimatization was obtained 100% in control, MV4, and MV5 at the greenhouse. MV5 had better morphological characteristics. The morphological changes were occurring in MV4 and MV5 compared with controls due to the combination of gamma-ray irradiation and somaclonal variation.

It is necessary to study technical factors such as bait used, oceanographic conditions of fishing areas and skipjack tuna trade patterns ( Katsuwonus pelamis ) as well as other factors in Sulawesi Fisheries. Supporting data to study these technical factors need to be obtained so that it can be improved throughout the year as a skipjack fishing standard with weights taken by the skipjack weights. Therefore, drones and underwater drones with cameras with high-resolution video and images to be fed and processed by computer vision. These drones are operated via Huhate ships which are then used to test efficient technical factors as expected, can be used in determining the size, shape, and colour as well as the analysis of skipjack fish that are in the Fish Aggregating Devices (FADs or Rumpon) in order to manage the management of fisheries managed in Indonesia.

Tuna fishing in Indonesia is excessive and if left unchecked, some types of tuna will become extinct within 3-10 years. There is an urgent need to help MMAF for producing more accurate fish catches data. This paper proposed a system that utilizes computer vision, fuzzy logic and Global Positioning System (GPS) for supporting a sustainableIndonesian fishery by recognizing and measuring fish length, determine fish age and where is the catch location. The system can help authority to manage sustainable fisheries management in Indonesia.