LSTM-based Multivariate Time-Series Analysis: A Case of Journal Visitors Forecasting

Software effort estimation (SEE) is an important process for predicting the effort required to develop or maintain software projects. It is considered one of the difficult challenges for software engineering because the more accurate the estimation, the greater the chances of success in developing software projects to complete and deliver them within the specified scheduling and budget. The diversity in software projects led to the use of many techniques to estimate the effort. The main objective of the research is to find the best technique to get the estimated effort as close to the real effort, using Machine learning Algorithms, artificial neural network Long Short-Term Memory(LSTM) and the artificial neural network Stacked Long Short-Term Memory (Stacked_LSTM), with six data sets are China, Kitchenham, Kemerer, Cocomo 81, Albrecht, Decharnais, and comparing the performance of the two machine learning algorithms performance, Neuralnet and Lasso from previous research, used the same data sets and using the same evaluation metrics, which are: the root mean square error (RMSE), mean absolute error (MAE) and R_Squared. The results demonstrated the superiority of the Stacked _LSTM algorithm by all metrics with the dataset of China, Kemerer and Albrecht, while in the data sets, Descharnais and Kitchenham, the LSTM algorithm outperformed the rest of the methods. While in the Cocomo 81 dataset, Neuralnet algorithm outperformed the rest of the techniques used, but the best rating was obtained. It is for Stacked _LSTM algorithm with China data.

Arctic sea ice and snow affect the energy balance of the global climate system through the radiation budget. Accurate determination of the snow cover over Arctic sea ice is significant for the retrieval of the sea ice thickness (SIT). In this study, we developed a new snow depth retrieval method over Arctic sea ice with a long short-term memory (LSTM) deep learning algorithm based on Operation IceBridge (OIB) snow depth data and brightness temperature data of AMSR-2 passive microwave radiometers. We compared climatology products (modified W99 and AWI), altimeter products (Kwok) and microwave radiometer products (Bremen, Neural Network and LSTM). The climatology products and altimeter products are completely independent of the OIB data used for training, while microwave radiometer products are not completely independent of the OIB data. We also compared the SITs retrieved from the above different snow depth products based on Cryosat-2 radar altimeter data. First, the snow depth spatial patterns for all products are in broad agreement, but the temporal evolution patterns are distinct. Snow products of microwave radiometers, such as Bremen, Neural Network and LSTM snow depth products, show thicker snow in early winter with respect to the climatology snow depth products and the altimeter snow depth product, especially in the multiyear ice (MYI) region. In addition, the differences in all snow depth products are relatively large in the early winter and relatively small in spring. Compared with the OIB and IceBird observation data (April 2019), the snow depth retrieved by the LSTM algorithm is better than that retrieved by the other algorithms in terms of accuracy, with a correlation of 0.55 (0.90), a root mean square error (RMSE) of 0.06 m (0.05 m) and a mean absolute error (MAE) of 0.05 m (0.04 m). The spatial pattern and seasonal variation of the SITs retrieved from different snow depths are basically consistent. The total sea ice decreases first and then thickens as the seasons change. Compared with the OIB SIT in April 2019, the SIT retrieved by the LSTM snow depth is superior to that retrieved by the other SIT products in terms of accuracy, with the highest correlation of 0.46, the lowest RMSE of 0.59 m and the lowest MAE of 0.44 m. In general, it is promising to retrieve Arctic snow depth using the LSTM algorithm, but the retrieval of snow depth over MYI still needs to be verified with more measured data, especially in early winter.

Penelitian ini bertujuan untuk merancang arsitektur model sistem pemantauan kualitas udara di Kota Bandung menggunakan empat parameter polutan utama: PM1.0, PM2.5, PM10, dan CO. Sistem ini dirancang dengan memanfaatkan algoritma Long Short-Term Memory (LSTM) untuk memprediksi kualitas udara harian berdasarkan data historis. Fokus penelitian meliputi perancangan desain arsitektur sistem, model data, dan metode prediksi, yang disusun berdasarkan analisis arsitektur sebelumnya serta kajian literatur. Salah satu elemen penting dan kebaruan dalam penelitian ini adalah penggunaan sensor ZH03B untuk pemantauan kualitas udara secara real-time yang memberikan solusi hemat biaya dan dapat diandalkan. Kombinasi antara sensor real-time dan algoritma LSTM menghasilkan tingkat akurasi prediksi kualitas udara sebesar 88%. Hasil evaluasi model menunjukkan nilai Root Mean Square Error (RMSE) sebesar 2,68 yang mencerminkan kinerja prediksi yang baik. Selain itu, pendekatan ini memberikan peningkatan signifikan dibandingkan metode konvensional yang sering kali kurang responsif terhadap perubahan kualitas udara secara dinamis. Penelitian ini memberikan dasar yang kuat untuk pengembangan sistem monitoring kualitas udara yang lebih akurat dan adaptif. Arsitektur yang diusulkan dapat menjadi acuan untuk pengembangan sistem monitoring kualitas udara di masa depan. Abstract This research aims to design the architecture of an air quality monitoring system model in Bandung City using four main pollutant parameters: PM1.0, PM2.5, PM10, and CO. The system is designed by utilising the Long Short-Term Memory (LSTM) algorithm to predict daily air quality based on historical data. The focus of the research includes the design of the system architecture, data model, and prediction method, which were developed based on previous architecture analysis and literature review. One important element and novelty in this research is the use of the ZH03B sensor for real-time air quality monitoring which provides a cost-effective and reliable solution. The combination of the real-time sensor and the LSTM algorithm resulted in an air quality prediction accuracy rate of 88%. The model evaluation results show a Root Mean Square Error (RMSE) value of 2.68 which reflects good prediction performance. In addition, this approach provides a significant improvement over conventional methods that are often less responsive to dynamic changes in air quality. This research provides a solid foundation for the development of a more accurate and adaptive air quality monitoring system. The proposed architecture can serve as a reference for the development of future air quality monitoring systems.

Accurate prediction of liquid transportation distance in LNG long-distance pipelines is critical for optimizing energy transportation efficiency and ensuring operational safety. However, traditional methods often struggle to capture the nonlinear temporal dependencies and complex flow dynamics inherent in pipeline systems. This paper proposes a novel prediction method based on the Long Short-Term Memory (LSTM) algorithm to address these challenges. By leveraging historical operational data, including pressure, temperature, flow rate, and pipeline terrain characteristics, the LSTM model is trained to learn spatiotemporal patterns and predict transportation distances under varying conditions. The proposed framework incorporates data preprocessing, feature selection, and hyperparameter optimization to enhance model robustness. Experimental results demonstrate that the LSTM-based method outperforms conventional models in terms of prediction accuracy, achieving a mean absolute error of 0.82 km and a root mean square error of 1.15 km over a 200 km test pipeline segment. The model’s ability to handle long-term dependencies and noisy data highlights its practical applicability for real-time monitoring and decision-making in LNG pipeline management. This study contributes to advancing intelligent solutions for energy infrastructure optimization.

Abstract: This research is driven by the challenges faced by Universitas Lancang Kuning (UNILAK) in attracting applicants amidst intense competition, especially after the government's policy opened independent pathways to State Universities (PTN) from 2022-2023, which impacted private university applicant numbers. To address this and support strategic planning, this study aims to predict the trend of prospective students applying to all study programs at UNILAK for the period 2025-2027. Two time series models were employed: ARIMA (AutoRegressive Integrated Moving Average) and LSTM (Long Short-Term Memory). Applicant data from 2019 to 2024 was used to build the model. The Augmented Dickey-Fuller (ADF) test confirmed the data's stationarity with a p-value of 0.0. ACF and PACF analyses determined the ARIMA parameters as p=1, d=1, q=1. The LSTM model was trained to capture more complex data patterns. ARIMA predictions for 2025, 2026, and 2027 are 3298.66, 3362.33, and 3371.30, respectively. LSTM predictions for the same years are 3335.64, 3476.52, and 3518.42. Evaluation using Root Mean Squared Error (RMSE) showed ARIMA (RMSE=588.72) to be more accurate than LSTM (RMSE=653.96). Nevertheless, LSTM provided a more optimistic prediction. This study concludes that ARIMA is better suited for short-term planning, while LSTM can be used for more ambitious long-term strategies. Keywords: arima; LSTM; applicants; prediction; university Abstrak: Penelitian ini didorong oleh tantangan Universitas Lancang Kuning (UNILAK) dalam menarik pendaftar di tengah persaingan ketat, khususnya setelah kebijakan pemerintah membuka jalur mandiri ke Perguruan Tinggi Negeri (PTN) sejak 2022-2023, yang menyebabkan penurunan jumlah pendaftar di universitas swasta. Untuk mendukung perencanaan strategis, studi ini bertujuan memprediksi tren jumlah calon mahasiswa yang mendaftar ke seluruh program studi di UNILAK untuk periode 2025-2027.Dua model deret waktu digunakan: ARIMA (AutoRegressive Integrated Moving Average) dan LSTM (Long Short-Term Memory). Data jumlah pendaftar dari 2019 hingga 2024 digunakan untuk membangun model. Uji Augmented Dickey-Fuller (ADF) menunjukkan data stasioner dengan p-value 0,0. Analisis ACF dan PACF menentukan parameter ARIMA sebagai p=1, d=1, q=1. Model LSTM dilatih untuk menangkap pola data yang lebih kompleks.Prediksi ARIMA untuk 2025, 2026, dan 2027 adalah 3298.66, 3362.33, dan 3371.30. Prediksi LSTM untuk tahun yang sama adalah 3335.64, 3476.52, dan 3518.42. Evaluasi menggunakan Root Mean Squared Error (RMSE) menunjukkan ARIMA (RMSE=588.72) lebih akurat daripada LSTM (RMSE=653.96). Meskipun demikian, LSTM memberikan prediksi yang lebih optimis. Studi ini menyimpulkan ARIMA lebih cocok untuk perencanaan jangka pendek, sementara LSTM dapat digunakan untuk strategi jangka panjang yang ambisius. Kata kunci: arima; LSTM; pendaftar; prediksi; universitas

Wind speed is a crucial parameter alongside coastal areas, especially Indonesia. Above average wind speed can cause harmful effects on human activities. This study uses wind speed data from Berakit Bay, Bintan Island is a potential location for coastal community settlement, fisheries, and tourist activities. The wind parameter then predicted using the Long Short-Term Memory or LSTM algorithm. This algorithm is able to study long-term dependencies by converting simple nervous system designs into specialized blocks containing cells. It is suitable to be applied to long-term wind predictions where the wind speed at this time is very influential with the wind speed in the future. In preparing the LSTM, the data preprocessing and the architecture used will determine the prediction results. In this study, four different architectures were made in order to determine the most optimal architecture. The results show that the LSTM architecture is able to obtain a relatively good RMSE value of 1.87 and an accuracy of 39.40% with the use of two LSTM layers, 256 units in the first layer and 128 in the second layer. The LSTM algorithm in predicting wind can also be applied to other areas in Indonesia.

The growing demand for energy efficiency in smart homes necessitates accurate short-term load forecasting to enable adaptive scheduling and optimal resource allocation. Traditional forecasting models, such as Random Forest, have demonstrated limited capability in capturing sequential dependencies, especially under fluctuating consumption behaviors typical of residential environments. This study aims to compare the forecasting performance of RF and Long Short-Term Memory (LSTM) models in predicting household energy consumption, to identify the most suitable approach for intelligent energy management systems. A quantitative experimental design was adopted using a publicly available dataset, which underwent preprocessing including time normalization and unit conversion. Both models were evaluated using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) to assess forecasting accuracy. The LSTM model achieved a lower MAE of 3.2 and RMSE of 4.1, significantly outperforming the RF model, which recorded an MAE of 6.5 and RMSE of 8.4. Additionally, during peak load conditions, LSTM achieved 89.7% accuracy, compared to 72.4% for RF, further emphasizing its superior adaptability to time-sensitive variations. The results confirm that LSTM is more effective in modeling temporal patterns and handling volatility in household energy usage. This research contributes to the field by reinforcing the applicability of deep learning for real-time energy forecasting, offering valuable insights for the development of smart home systems. Future studies may expand this work by integrating hybrid optimization techniques and exploring multi-household scenarios for broader scalability.

Sunshine duration is a critical meteorological parameter with significant applications in climate studies, agriculture, and renewable energy, particularly solar energy systems. Accurate prediction of sunshine duration is crucial for optimizing solar energy utilization and addressing gaps in regions with limited radiation data. This study evaluates the performance of Long Short-Term Memory (LSTM), a deep learning model known for its ability to handle time series data, in predicting sunshine duration. The research utilizes a dataset comprising sunshine duration and related meteorological parameters, including temperature, humidity, wind speed, and precipitation. Initial correlation analysis using Spearman’s method identifies temperature and humidity as the most influential factors associated with sunshine duration. Three prediction models are developed by varying the input parameters, and their performances are evaluated using metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Pearson correlation coefficient. The best model, incorporating all meteorological parameters, achieves an RMSE of 1.02, MAE of 0.77, and Pearson correlation of 0.84, demonstrating the robustness of LSTM in capturing nonlinear relationships in complex datasets. These results underline the potential of LSTM as a reliable tool for sunshine duration prediction and provide insights into its applicability in solar energy planning and other meteorological studies.

The electrical equipment of offshore oil support ships operates in harsh marine environments with high failure rates, posing challenges to the development of preventive maintenance strategies. To address this issue, this article proposes an intelligent platform based on Long Short Term Memory (LSTM) algorithm to optimize preventive maintenance strategies for electrical equipment. Firstly, operational data of ship electrical equipment is collected, and data preprocessing and key feature extraction are carried out; subsequently, a prediction model based on LSTM is constructed to make real-time predictions on the health status of the equipment; then, the predictive model is integrated into the intelligent platform to achieve real-time monitoring of device status and dynamic optimization of maintenance strategies. The experimental results show that the LSTM based prediction model outperforms support vector regression (SVR) and random forest methods in terms of prediction accuracy and robustness. The average monthly failure rate of the equipment is 0.67 times, and the maintenance cost for 12 months is only $4750. In the above data conclusions, the intelligent platform based on LSTM algorithm can significantly improve the effectiveness of preventive maintenance strategies for marine oil support ship electrical equipment, highlighting the advantages of the proposed method.

The objective of this research is to develop a Deep Learning model to forecast the stock price, by using the variant of Long Short-Term Memory. This model predicts the close price of the stock for the future selected date, choosing as inputs the following data: open, high, low, adj close and close prices. This model shows a comparative analysis between three different LSTM networks: Long Short-Term Memory (LSTM), Stacked Long Short-Term Memory (Stacked LSTM), and Stacked Bi-directional Long Short-Term Memory (Stacked Bidirectional LSTM) concluding which one is the best and implementing the model using that variant. We have used the historical stock prices data from yahoo’s financial website over 5 years, by choosing multiple datasets: Apple, Amazon, Google, Meta, Microsoft and Tesla (daily values). In order to get effective in the forecasting model, we have tested the network with different iterations and epochs. The model represents Multiple Graphs for data visualization in different comparisons. We have estimated the effectiveness of our proposed model by using the following performance indicators: the Mean Square Error (MSE), the Root Mean Square Error (RMSE), and the R-Squared of the model. The experimental results clearly show that our Stacked Bi-LSTM model has the highest accuracy values when comparing with the LSTM and Stacked LSTM Models. Hence, we can conclude that our Stacked Bi-LSTM Model is suitable for accurate prediction of the stock market time series. Key Words: stock price prediction, Machine Learning, stacked LSTM, Bi-directional LSTM, Deep Learning, Data pre-processing techniques, Data normalization, Data Visualization, Training and Testing Set, Financial Time Series, Future prediction

Travel planning is a process that allows users to obtain maximum benefit from their time, cost and energy. When planning a route from one place to another, it is an important option to present alternative travel areas on the route. This study proposes a travel route planning (TRP) architecture using a Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost) model to improve both travel efficiency and environmental sustainability in route selection. This model incorporates carbon emissions directly into the route planning process by unifying user preferences, location recommendations, route optimization, and multimodal vehicle selection within a comprehensive framework. By merging environmental sustainability with user-focused travel planning, it generates personalized, practical, and low-carbon travel routes. The carbon emissions observed with TRP’s artificial intelligence (AI) recommendation route are presented comparatively with those of the user-determined route. XGBoost, Random Forest (RF), Categorical Boosting (CatBoost), Light Gradient Boosting Machine (LightGBM), (Extra Trees Regressor) ETR, and Multi-Layer Perception (MLP) models are applied to the TRP model. LSTM is compared with Recurrent Neural Networks (RNNs) and Gated Recurrent Unit (GRU) models. Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Squared Error (MSE), and Normalized Root Mean Square Error (NRMSE) error measurements of these models are carried out, and the best result is obtained using XGBoost and LSTM. TRP enhances environmental responsibility awareness within travel planning by integrating sustainability-oriented parameters into the decision-making process. Unlike conventional reservation systems, this model encourages individuals and organizations to prioritize eco-friendly options by considering not only financial factors but also environmental and socio-cultural impacts. By promoting responsible travel behaviors and supporting the adoption of sustainable tourism practices, the proposed approach contributes significantly to the broader dissemination of environmentally conscious travel choices.

The purpose of this study is to predict the decade rainfall in Semarang City using two main methods, namely Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMAX) and Long Short Term Memory (LSTM). The methodology of this study begins with data pre-processing, which includes data deletion analysis using dropna and data normalization using Min-Max Scaling to reduce scale the to between 0 and 1. The dataset is then divided into 80% training data and 20% test data. The validity of the data (X_test, Y_test) using the best 56-epoch data validation (val_loss) is better than the validity of the training data (loss). On the other hand, SARIMAX uses the (2,1,2), (2,1,2,36) model, and its validation techniques include Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Coefficient of Determination (R2). Specifically, the RMSE of the LSTM model is 19.6, and its RMSE of the SARIMAX is 31.05. The MAE of LSTM is 15.0, SARIMAX is 24.5, and the R2 of LSTM is 0.814, and SARIMAX is 0.52. Lower RMSE and MAE values indicate lower prediction errors, but a higher R2 value of 1 indicates that LSTM can explain 81% of the actual data variation, which is better than SARIMAX, which is only about 52%. The main finding of this study is that the LSTM model performs better when recommending rainfall datasets.

With the in-depth implementation of China’s “National Strategy for Building a Strong Transportation Network,” the scale of expressway construction has continued to expand. As a result, the number of high-fill and deep-cut subgrade projects under complex geological conditions has increased significantly, leading to a surge in landslide-related issues. Consequently, accurate prediction of slope displacement is of critical importance for early warning and prevention of landslide disasters. This study proposes a hybrid prediction model, VMD-MPA-LSSVM-LSTM (VMLL), which integrates Variational Mode Decomposition (VMD), Marine Predators Algorithm (MPA), Least Squares Support Vector Machine (LSSVM), and Long Short-Term Memory (LSTM) networks. Using monitoring data from the high-fill embankment slope at Hongtuyao as the research subject, the VMLL model is employed to predict slope displacement based on small-sample data. The objective is to provide a more accurate method for early warning of slope displacement. Firstly, the original monitoring data are decomposed into trend displacement components and fluctuation displacement components using Variational Mode Decomposition (VMD). Subsequently, the trend component and the fluctuation component are predicted using Least Squares Support Vector Machine (LSSVM) and Long Short-Term Memory (LSTM) networks, respectively. Finally, the Marine Predators Algorithm (MPA) is employed to optimize the hyperparameters of the predictive models. Based on this framework, a VMLL-based slope displacement prediction model is constructed. To verify the superiority of the VMLL model, a comparative analysis was conducted against LSSVM, LSTM, and the VMD-LSSVM-LSTM models. The results demonstrate that the VMLL model achieves the highest prediction accuracy, with a Mean Absolute Percentage Error (MAPE) of 0.4022%, a Mean Absolute Error (MAE) of 0.016 mm, a Root Mean Square Error (RMSE) of 0.0206 mm, a coefficient of determination (R²) of 94.08%, and a Variance Accounted For (VAF) of 96.5%. Compared with the other three models, the VMLL model reduces the MAPE, MAE, and RMSE by 30.41–67.62%, 30.38–67.40%, and 27.32–71.00%, respectively. Meanwhile, it improves the R² and VAF by 5.95–217.51% and 0.38–11.48%, respectively. These improvements clearly demonstrate that the VMLL model outperforms the other models, indicating its significant advantage over single prediction models. Furthermore, three additional datasets were used to evaluate the model’s performance. The average values of the performance evaluation metrics for these datasets were 0.6207% (MAPE), 0.0238 mm(MAE), 0.0273 mm(RMSE), 90.33%(R²), and 96.81%(VAF), respectively. These results demonstrate the high accuracy and strong robustness of the proposed model in predicting both horizontal displacement and vertical settlement of slopes, providing a reliable methodological framework for slope stability assessment and landslide disaster early warning.

Stock price modeling and prediction is a challenging task due to its non-stationary and dynamic nature of data. Developing an accurate stock prediction method can help investors in making profitable decisions by reducing the investment risks. This paper proposes a deep learning-based method for significantly improving the stock prediction accuracy using deep learning-based methods. Two well-known methods were investigated, namely one dimensional Convolutional Neural Network (1D-CNN) and the Long Short-Term Memory (LSTM). In addition, we also investigated the effect of dimensionality reduction using principal component analysis (PCA) on the prediction accuracy of both 1D-CNN and LSTM. Two separate experiments were performed for each method, one with PCA and one without PCA. The experimental results indicated that LSTM with PCA produced the best results with mean absolute error (MAE) of 0.032, 0.084, and 0.044 while a root mean square error (RMSE) of 0.0643, 0.172, 0.079 on Apple Inc., Amerisource Bergen Corporation, and Cardinal Health datasets. The LSTM network with PCA took an average of 421.8s for training. Contrarily, 1D-CNN model with PCA performed better in terms of computational time as it took only 37s for training and attained MAE of 0.039 and RMSE of 0.0706 on Apple Inc. dataset. Similarly, 1D-CNN took 36.5s for training while achieving 0.099 MAR and 0.2021 RMSE on Amerisource Bergen Corporation dataset, while 37.5s for training that secured 0.067 MAE and 0.1037 RMSE on Cardinal Health dataset.

To solve the problem of high root mean square error (RMSE) caused by the Graph Convolution with Graph Attention Network for Matrix Completion (GCGAT), which cannot fully utilize the node's feature information and temporal information. In this paper, we propose an LSTM-based GCGAT algorithm (GCGAT based on LSTM, GCGAT-LSTM) to solve this problem: the linear processing part of the encoder in GCGAT is replaced by long short-term memory algorithm (LSTM). Two LSTM layers are used to process user's and item's feature information separately, named GCGAT -LSTM. This paper conducted several experiments on MovieLens-100K and MovieLens-1M datasets. The experimental results show that GCGAT -LSTM performs better than the GCGAT algorithm, effectively improving the performance of GCGAT and making more accurate recommendations. Compared with the RMSE in the previous GCGAT algorithm, the RMSE of GCGAT-LSTM is reduced by about 0.03 on both datasets. Therefore, the GCGAT-LSTM method proposed in this paper can better use node's feature information and temporal information to make more accurate predictions and thus obtain better recommendation results. However, the GCGAT-LSTM also has some limitations: the LSTM requires sequential processing over time and therefore has low efficiency and high time complexity for the input sequence.