Comparative Analysis of ARIMA and LSTM Methods for Sea Surface Temperature Forecasting in the Sunda Strait

The rapid advancement of mobile apps has emerged as an important aspect of the routine of internet-connected users. In Indonesia, many companies are introducing their apps to improve the quality of service for users, and Alfamart is one of them. However, users have identified many shortcomings in these apps. This feedback is provided by users on the review feature of the Alfagift app on the Google Play Store. This research aims to apply a sentiment analysis approach to identify the application's shortcomings so that developers can understand the aspects that need to be improved to improve the quality of application services. The research stages include data collection, preprocessing, labeling, weighting, classification of LSTM and SVM methods, and performance evaluation using a confusion matrix. The dataset consists of 1000 reviews obtained through web scraping techniques. This research uses the Lexicon-based method to classify the dataset into positive, negative, and neutral categories. The analysis results show that 801 data are classified as positive sentiment, 77 as negative sentiment, and 122 as neutral sentiment. Based on testing, both SVM and LSTM methods show good performance. The best accuracy results were obtained using the SVM method, which amounted to 83.5%. Meanwhile, the LSTM method achieved an accuracy of 82%.

The harmonic reducer is a key component of the industrial robot. Its reliability has significant influence on the consecutive operation of the industrial robot. However, its failure rate is high due to the complicated internal structure and long-term working conditions of large load and high torque. To identify the fault type of the harmonic reducer under different working conditions, this article proposes the joint wavelet regional correlation threshold denoising (WRCTD) algorithm and convolutional neural network-long short term memory (CNN-LSTM) fault detection method. Firstly, the WRCTD algorithm utilizes the regional correlation of the wavelet decomposition coefficients and the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$3\sigma $ </tex-math></inline-formula> criterion to suppress noise in the raw sensor data. Then, the CNN-LSTM model could mine hidden features of the processed sensor data to identify fault correctly. To evaluate the proposed method, the vibration signals of the harmonic reducer under different working conditions are collected by establishing a test rig. Comparative experimental results show that the proposed WRCTD algorithm can significantly improve the accuracy of the fault detection method. The specific values for the CNN-LSTM method and the LSTM method are 9.5% and 12.2%, respectively. In addition, the proposed CNN-LSTM method has better performance than traditional methods. It achieves the fault detection over 94.0%, which is 1.5%, 2.0%, 2.0%, 1.9%, and, 1.9% higher than the highest accuracy values of CNN, LSTM, and SVM methods in five experiments.

Tembang is a pelagic fish which is important in Indonesia and the development on the Sunda Strait. The Indian Ocean Dipole could affect oceanography and at the same time will affect the population of fishes. The aim of this study was to determine the effect of IOD and oceanographic factors on the catch of Tembang fish. This research was conducted in the Sunda Strait waters by looking at the Dipole Mode Index (DMI) and oceanographic ocean conditions such as sea surface temperature and chlorophyll as well as the production of fish catches for 11 years from 2008-2018. IOD affects the catch of Tembang fish by 35.8%. Temperature influences the catch of Tembang fish in the Sunda Strait by 9.48%. Klorofil-a influences the catch of Tembang fish in Sunda Strait by 38.6%. DMI, Temperature, and Chlorophyll affect fish catches by 26.9%.

Financial institutions have a large amount of data on their borrowers, which can be used to predict the probability of borrowers defaulting their loan or not. Some of the models that have been used to predict individual loan defaults include linear discriminant analysis models and extreme value theory models. These models are parametric in nature since they assume that the response being investigated takes a particular functional form. However, there is a possibility that the functional form used to estimate the response is very different from the actual functional form of the response. The purpose of this research was to analyze individual loan defaults in Kenya using the logistic regression model. The data used in this study was obtained from equity bank of Kenya for the period between 2006 to 2016. A random sample of 1000 loan applicants whose loans had been approved by equity bank of Kenya during this period was obtained. Data obtained was on the credit history, purpose of the loan, loan amount, nature of the saving account, employment status, sex of the applicant, age of the applicant, security used when acquiring the loan and the area of residence of the applicant (rural or urban). This study employed a quantitative research design, it deals with individual loans defaults as group characteristics of a borrower. The data was pre-processed by seeding using R- Software and then split into training dataset and test data set. The train data was used to train the logistic regression model by employing Supervised machine learning approach. The R-statistical software was used for the analysis of the data. The test data set was used to do cross-validation of the developed logistic model which later was used for analysis prediction of individual loan defaults. This study focused on the analysis of individual loan defaults in Kenya using the logistic regression model in Machine learning. The logistic regression model predicted 303 defaults from train data set, 122 non-defaults and misclassified loans were 56 and 69. The model had an accuracy of 0.7727 with the train data and 0.7333 with the test data. The logistic regression model showed a precision of 0.8440 and 0.8244 with the train and test data respectively. The performance of the model with both the train and test data was illustrated using a plot of train errors and test errors against sample size on the same axes. The plot showed that the performance of the model increases with an increase in sample size. The study recommended the use of logistic regression in conjunction with supervised machine learning approach in loan default prediction in financial institutions and also more research should be carried out on ensemble methods of loan defaults prediction in order to increase the prediction accuracy.

The growing population and industrialization have resulted in an increased demand for energy, which has worsened environmental problems such as pollution and climate change. Renewable energy sources are considered a promising solution due to their environmental benefits and limited potential. This study examines the use of neural networks and time series analysis to predict electricity generation rates from renewable energy sources in Turkey. We use the LSTM, NNAR, and ELM models, all of which utilize the backpropagation algorithm for neural network forecasting. Additionally, we apply ARIMA, Holt’s trend, linear regression, mean, and exponential smoothing models for time series analysis. We evaluate the performance using the mean absolute error and root mean square error on the training and test data. The study showed that LSTM models outperformed the ARIMA (1,2,1), ARIMA (2,2,1), ARIMA (3,2,1), and NNAR methods in forecasting accuracy. Although the NNAR model initially had the lowest error, its linear predictions made it less suitable for practical applications. This study highlights the effectiveness of neural networks and time series analysis in predicting renewable energy sources. The ARIMA (1,2,1), LSTM and ARIMA (3,2,1) modeling methods are useful for optimizing the planning and management of Turkey's renewable energy future, contributing to a more sustainable energy landscape.

Extreme weather modeling is a challenge for modeling experts in Indonesia and the world. Extreme weather prediction is a complex problem because the chances of it happening are very small, so the developed models often have a low level of accuracy. The purpose of this research is to combine the classic model, Autoregressive Integrated Moving Average (ARIMA), recurrent neural network (RNN) model using Adam and SGD estimation (RNN-Adam and RNN-SGD) with the reLU, tanh, sigmoid and gaussian activation functions. In addition, the ARIMA-RNN mix model was also demonstrated in this study. These models are applied to monthly period extreme weather data obtained from the Meteorology, Climatology and Geophysics Agency (BMKG) of West Sulawesi Province which are converted into training data and test data. The RMSE value is used to see the level of prediction accuracy in both training data and test data. Based on the research results, the best model obtained for modeling Indonesia’s extreme weather is the ARIMA-RNN-Adam mix model with the reLU activation function based on the RMSE value on the training and test data. At n = 50, the smallest RMSE and MSE values of the third model are the ARIMA-RNN-Adam model which is 0.23212 using the reLU activation function, then the ARIMA-RNN-SGD model which is 0.25432 with the same activation function, while the ARIMA value is 0.3270. At n=100 it can be seen that the smallest RMSE and MSE values of the three models are the ARIMA-RNN-Adam model which is equal to 0.25149 using the reLU activation function, then the ARIMA-RNN-SGD model which is equal to 0.25256 with the same activation function, while the ARIMA value is 0.2644.

Passive sensing applications are limited by their inability to determine who is using a device, a critical concern in child mobile device use research, where devices are often shared between siblings or between a child and their parent. Our previous work leveraged behavioral biometrics to identify a target child user; however, it is unknown what type of training data is necessary for optimal model performance. This study evaluated model performance across different characteristics of training data. Thirty-six children (11.3 ± 0.9 years, 56% female) self-selected a video or a game on iPads for 10 min while laying and for another 5 min while sitting. The SensorLog application captured iPad accelerometer and gyroscope data while the child interacted with the device. Machine learning algorithms including Neural Network (NN), Random Forest (RF), k-Nearest Neighbors (k-NN), and SwipeFormer were applied to determine the most important aspects of training data to optimize model performance. The aspects of training data evaluated included (1) varying the length (i.e., seconds of training data), (2) varying the user position (i.e., sitting, laying), and (3) varying the time proximity between training and testing data. F1 score was used to evaluate model performance. The SwipeFormer F1 scores were lowest when the training data was further from the test data (0 when training data was 11 min away from test data) and highest when training data was close to test data (0.91 when training data was the minute preceding test data). The SwipeFormer F1 scores were highest when predicting the user laying from laying (0.97) and sitting from sitting (0.94), and lowest when predicting the user sitting from laying (0) and laying from sitting (0). The length of training data had little impact on performance, with a SwipeFormer F1 score of 0.91 when training on one minute of data and a SwipeFormer F1 score of 0.94 when training on twelve minutes of data. Because researchers would likely be predicting users at different timepoints than their training data, research should focus on improving model performance for identifying users independent of time proximity for training and test data.

Automated monitoring of the movements and behaviour of animals is a valuable research tool. Recently, machine learning tools were applied to many species to classify units of behaviour. For the monitoring of wild species, collecting enough data for training models might be problematic, thus we examine how machine learning models trained on one species can be applied to another closely related species with similar behavioural conformation. We contrast two ways to calculate accuracies, termed here as overall and threshold accuracy, because the field has yet to define solid standards for reporting and measuring classification performances. We measure 21 dogs and 7 wolves, and find that overall accuracies are between 51 and 60% for classifying 8 behaviours (lay, sit, stand, walk, trot, run, eat, drink) when training and testing data are from the same species and between 41 and 51% when training and testing is cross-species. We show that using data from dogs to predict the behaviour of wolves is feasible. We also show that optimising the model for overall accuracy leads to similar overall and threshold accuracies, while optimizing for threshold accuracy leads to threshold accuracies well above 80%, but yielding very low overall accuracies, often below the chance level. Moreover, we show that the most common method for dividing the data between training and testing data (random selection of test data) overestimates the accuracy of models when applied to data of new specimens. Consequently, we argue that for the most common goals of animal behaviour recognition overall accuracy should be the preferred metric. Considering, that often the goal is to collect movement data without other methods of observation, we argue that training data and testing data should be divided by individual and not randomly.

One of the efforts to suppress the increasing number of COVID-19 cases is the government's provision of a COVID-19 vaccine. This study examines the effect of the number of people who have been vaccinated, the first dose of vaccine, on the addition of new cases and cured cases. The three variables were analysed simultaneously using the help of the Vector Autoregressive (VAR) model. The data is on the number of new, recovered cases and people vaccinated per day from January 13 to December 30, 2021, in West Kalimantan Province. The main steps in this study are order identification, parameter estimation, and interpretation of the results. In this study, the order selection of the VAR model is limited to a maximum of the fourth order. Parameter estimation uses the Ordinary Least Square (OLS) method from several possible orders. Furthermore, the model selection is based on the smallest AIC and BIC values. The result is that the second-order VAR model has the smallest AIC and BIC values, so this model is said to be the best model. The interpretation of the equation obtained is that 74.1% of the factors adding new cases, the number of people being vaccinated, and the addition of cured cases at one and two last times affect the addition of new cases on that day. Meanwhile, the addition of new cases today was only influenced by 42.2% by new cases, the number of people being vaccinated, and the addition of recovered cases in the previous one and two days.

Hypertensive disorders of pregnancy (HDP) cause adverse maternal and fetal outcomes, and establishing an early prediction method for HDP is needed. Existing methods based on serum markers require blood sampling. Therefore, we aimed to develop and validate a noninvasive HDP prediction model based on home blood pressure monitoring. In a development cohort, home blood pressure monitoring data from 443 pregnant women including 65 HDPs were divided into training data (n=365) and test data (n=78) to develop a logistic regression-based prediction model. Normal blood pressure variations depending on season and gestational age were subtracted. At each time point, 4 features were calculated for the last 4 weeks of data: average systolic blood pressure, average diastolic blood pressure, correlation coefficient between systolic blood pressure and diastolic blood pressure, and upward trend of systolic blood pressure against day. In a validation cohort, HBPM data from 264 pregnant women including 33 HDPs were collected prospectively and used to validate the model. The area under the receiver operating characteristic curve was 0.949 (95% CI, 0.890-1.000), 0.884 (95% CI, 0.807-0.961), and 0.845 (95% CI, 0.759-0.930) for the training, test, and validation data, respectively. Sensitivity, specificity, positive predictive value, and negative predictive value were 0.923, 0.888, 0.387, and 0.993 for the training data; 0.667, 0.897, 0.867, and 0.729 for the test data; 0.758, 0.766, 0.316, and 0.957 for the validation data. Our HDP prediction model based on home blood pressure monitoring showed high negative predictive values and may contribute to reducing medical consultations.

We present a model that estimates the spectral phytoplankton absorption coefficient () of four phytoplankton groups (picophytoplankton, nanophytoplankton, dinoflagellates, and diatoms) as a function of the total chlorophyll-a concentration (C) and sea surface temperature (SST). Concurrent data on (at 12 visible wavelengths), C and SST, from the surface layer (<20 m depth) of the North Atlantic Ocean, were partitioned into training and independent validation data, the validation data being matched with satellite ocean-colour observations. Model parameters (the chlorophyll-specific phytoplankton absorption coefficients of the four groups) were tuned using the training data and found to compare favourably (in magnitude and shape) with results of earlier studies. Using the independent validation data, the new model was found to retrieve total with a similar performance to two earlier models, using either in situ or satellite data as input. Although more complex, the new model has the advantage of being able to determine for four phytoplankton groups and of incorporating the influence of SST on the composition of the four groups. We integrate the new four-population absorption model into a simple model of ocean colour, to illustrate the influence of changes in SST on phytoplankton community structure, and consequently, the blue-to-green ratio of remote-sensing reflectance. We also present a method of propagating error through the model and illustrate the technique by mapping errors in group-specific using a satellite image. We envisage the model will be useful for ecosystem model validation and assimilation exercises and for investigating the influence of temperature change on ocean colour.

Industrial sector exports have a large contribution to total exports in the Indonesian economy. A forecasting model is needed that is able to forecast the export value of the industrial sector well. The data used in this study are monthly data on the Export Value of Indonesian Footwear. The ARIMA method can forecast data well linearly but has a decrease in accuracy for data with nonlinear components. Lee's Fuzzy Time Series method is good for nonlinear data and has a level of accuracy that is easy to understand. The ARIMA method requires assumptions to be met such as the data must be stationary, then the Fuzzy Time Series Lee method can be used for non-stationary data, because the Fuzzy Time Series Lee does not require certain assumptions to be met. The results of forecasting the value of Indonesian footwear exports using ARIMA have a MAPE value of 18.5% with good criteria, the Fuzzy Time Series Lee method has a MAPE value of 18.2% with good criteria, so it can be used to forecast the value of Indonesian footwear exports for the August 2023 period of 46,563,984 USD. The forecasting results can be a reference for future policy making.

The convergent margin of the central Sunda Arc in Indonesia was the target of a reflection and refraction seismic survey conducted in 1998 and 1999. Along two seismic lines across the subduction complex off southern Sumatra and off Sunda Strait, coincident multichannel and wide-angle data were collected, complemented by two refraction strike-lines in the forearc basin off Sumatra. The combined analysis of the acquired data allows us to present a detailed model of the subduction zone where initiation of strain partitioning occurs due to the onset of oblique subduction. The dip of the subducted plate is well defined along both dip-lines and a lateral increase from 5° to 7° from beneath the outer high off Sumatra to Sunda Strait is supported by complementary gravity modelling. The downgoing slab is traced to a depth of more than 30km. On both reflection dip-lines, a clearly developed backstop structure underlying a trench slope break defines the landward termination of the active accretionary prism and separates it from the outer high. Active subduction accretion is supported by laterally increasing velocities between the deformation front and the active backstop structure. Seismic velocities of the outer high are moderate along both lines (<5.8kms−1 at 20km depth), suggesting a sedimentary composition. Reduced reflectivity beneath a rugged top basement traced along the outer high of both dip-lines supports a high degree of deformation and material compaction. Several kilometres of sediment has accumulated in the forearc domain, although a distinct morphological basin is only recognized off southern Sumatra and is not developed off Sunda Strait. The bathymetric elevation of the Java shelf that is encountered in the southern Sunda Strait corresponds to increased velocities of a basement high there and is connected to extensional structures of the Sunda Strait transtensional basin. Differences observed in the morphology of the forearc domain are also reflected in the lower crustal structure. Off southern Sumatra, the velocity–depth model clearly indicates a continental-type crust underlying the forearc basin, whereas lower velocities are found beneath the Sunda Strait forearc domain. Off Sumatra, some 3-D constraint on the upper plate structure is gained from the refraction strike-lines, which in addition is supported by synthetic data modelling.

Occupancy rate is a critical factor in a hotel because it is used to measure the operational success of a hotel. The higher the hotel occupancy rate, the more successful the hotel business is in generating revenue. In the hospitality business, occupancy rates are very important to monitor and analyse as marketing strategies and pricing policies. This study compares the forecasting of occupancy rates at Hotel X using neural network method and decision tree method. The dataset used in this study is room available, room sold, and available occupancy percentage data at Hotel X from April 2018 to June 2023. The simulation was carried out by dividing the data into training data and testing data with a percentage ratio of 70:30, 75:25, 80:20, 85:15, and 90:10. The forecasting results that have been carried out using a neural network with one hidden layer have an optimal RSME result of 0.010 for split data of 70%:30% and 80%:20% while using a neural network with two hidden layers the optimal result of RSME is 0.013 for split data of 75%:25%. Forecasting results using decision tree RSME optimal results of 0.022 for split data 85%:15% and 90%:10%. From this forecasting, the most optimal results use a neural network with one hidden layer for data splits of 70%:30% and 80%:20% with RSME results of 0.010. The results of the research can be used by Hotel X as a policy determination in the next hotel management.

SummaryAccurate prediction of the solubility of chemical substances in solvents remains a challenge. The sparsity of high-quality solubility data is recognized as the biggest hurdle in the development of robust data-driven methods for practical use. Nonetheless, the effects of the quality and quantity of data on aqueous solubility predictions have not yet been scrutinized. In this study, the roles of the size and the quality of data sets on the performances of the solubility prediction models are unraveled, and the concepts of actual and observed performances are introduced. In an effort to curtail the gap between actual and observed performances, a quality-oriented data selection method, which evaluates the quality of data and extracts the most accurate part of it through statistical validation, is designed. Applying this method on the largest publicly available solubility database and using a consensus machine learning approach, a top-performing solubility prediction model is achieved.