Artificial intelligence (AI) has recently been used frequently, especially concerning the Internet of Things (IoT). However, IoT devices cannot work alone, assisted by Low Power Wide Area Network (LPWAN) for long-distance communication and Short-Range Network for a short distance. However, few reviews about AI can help LPWAN and Short-Range Network. Therefore, the author took the opportunity to do this review. This study aims to review LPWAN and Short-Range Networks AI papers in systematically enhancing IoT performance. Reviews are also used to systematically maximize LPWAN systems and Short-Range networks to enhance IoT quality and discuss results that can be applied to a specific scope. The author utilizes selected reporting items for systematic review and meta-analysis (PRISMA). The authors conducted a systematic review of all study results in support of the authors' objectives. Also, the authors identify development and related study opportunities. The author found 79 suitable papers in this systematic review, so a discussion of the presented papers was carried out. Several technologies are widely used, such as LPWAN in general, with several papers originating from China. Many reports from conferences last year and papers related to this matter were from 2020-2021. The study is expected to inspire experimental studies in finding relevant scientific papers and become another review.

There are indisputable research supporting scientific argument that propagation of (tsunami) wave from intermediate depth towards shallower coastal area needs dispersive wave model. For tsunami wave simulation, efficiency of the numerical scheme is an important issue. In this paper, the two-layer non-hydrostatic model as developed previously in Pudjaprasetya et al. [2017] “A non-hydrostatic two-layer staggered scheme for transient waves due to anti-symmetric seabed thrust,” J. Earthquake Tsunami  11, 1–17, to study tsunami generation and propagation, is adopted. Restricting to 1+1 dimension, here, we focus on the performance of the scheme in simulating wave propagation in coastal areas, in particular predicting the run-up height. First, we conducted a simulation of harmonic wave over a sloping beach to conform the analytical shoreline motion by Carrier and Greenspan [1958] “Water waves of finite amplitude on a sloping beach,” J. Fluid Mech.  4, 97–109. The ability of the scheme in accommodating dispersion and non-linearity were shown via simulation of a solitary wave that propagates over a flat bottom. This solitary wave simulation provides an evaluation of the convergence aspect of the model. Further, several benchmark tests were conducted; a solitary wave over a sloping beach to mimic the experimental data by Synolakis [1986] “The run-up of solitary waves,” J. Fluid Mech.  185, 523–545, as well as solitary wave over a composite beach. Good agreement with laboratory data was obtained in terms of wave signal, whereas for relatively low amplitude, the solitary run-up height conforms the analytical formula. Moreover, the scheme is tested for simulating the Beji–Battjes experiment Beji, S. and Battjes, J. A. [1993] “Experimental investigation of wave propagation over a bar,” Coast. Eng.  19, 151–162. As well as wave focusing experiment by Kurnia et al. [2015] “Simulations for design and reconstruction of breaking waves in a wavetank,” Proc. ASME 2015 34th Int. Conf. Ocean, Offshore and Arctic Engineering, Newfoundland, Canada, 31 May–5 June 2015, pp. 2–7.

Nowadays, conventional marketing techniques have changed to online (digital) marketing techniques requiring internet access. Online marketing techniques have many advantages, especially in terms of cost efficiency and fast information delivery to the public. Therefore, many companies are interested in online marketing and advertising on social media platforms and websites. However, one of the challenges for companies in online marketing is determining the right target consumers since if they target consumers who are not interested in buying the product, the advertising costs will be high. One use of online advertising is clicks on ads which is a marketing measurement of how many users click on the online ad. Thus, companies need a click prediction system to know the right target consumers. And different types of advertisers and search engines rely on modeling to predict ad clicks accurately. This paper constructs the customer ad clicks prediction model using the machine learning approach that becomes more sophisticated in effectively predicting the probability of a click. We propose two classification algorithms: the logistic regression (LR) classifier, which produces probabilistic outputs, and the k-nearest neighbors (k-NN) classifier, which produces non-probabilistic outputs. Furthermore, this study compares the two classification algorithms and determines the best algorithm based on their performance. We calculate the confusion matrix and several metrics: precision, recall, accuracy, F1-score, and AUC-ROC. The experiments show that the logistic regression algorithm performs best on a given dataset.

In conducting water wave simulations, the correct implementation of boundary conditions is important to obtain accurate wave dynamics in the computational domain. For assessment of coastal structures such as breakwaters, where both transmitted and reflected waves are present in the computational domain, we often need to observe simulation behavior for a somewhat long period of time. In this case, applying a transparent boundary condition is necessary, a condition that allows transmitted wave propagates to the right, whereas reflected waves propagates to the left at all times. In this paper, we propose a transparent boundary condition which derives from the embedded wave generation method of Liam et al. [5]. In this paper, the method is implemented to the momentum conservative scheme of the shallow water equations, and conduct several wave simulations. First, we use a monochromatic wave to demonstrate the implementation of embedded wave generation for constructing transparent boundary condition. Second, we show how this method has an effect on the backward and onward shoreline motion of Carrier-Greenspan [2] simulation. Finally, we consider a simulation of wave reduction due to a submerged breakwater with a certain dimension.

No abstract