Short-term Memory Model Research Articles

Meteorological Anomalies During Earthquake Preparation: A Case Study for the 1995 Kobe Earthquake (M = 7.3) Based on Statistical and Machine Learning-Based Analyses

The purpose of this paper is to discuss the effect of earthquake (EQ) preparation on changes in meteorological parameters. The two physical quantities of temperature (T)/relative humidity (Hum) and atmospheric chemical potential (ACP) have been investigated with the use of the Japanese meteorological “open” data of AMeDAS (Automated Meteorological Data Acquisition System), which is a very dense “ground-based” network of meteorological stations with higher temporal and spatial resolutions than the satellite remote sensing open data. In order to obtain a clearer identification of any seismogenic effect, we have used the AMeDAS station data at local midnight (LT = 01 h) and our initial target EQ was chosen to be the famous 1995 Kobe EQ of 17 January 1995 (M = 7.3). Initially, we performed conventional statistical analysis with confidence bounds and it was found that the Kobe station (very close to the EQ epicenter) exhibited conspicuous anomalies in both physical parameters on 10 January 1995, just one week before the EQ, exceeding m (mean) + 3σ (standard deviation) in T/Hum and well above m + 2σ in ACP within the short-term window of one month before and two weeks after an EQ. When looking at the whole period of over one year including the day of the EQ, in the case of T/Hum only we detected three additional extreme anomalies, except in winter, but with unknown origins. On the other hand, the anomalous peak on 10 January 1995 was the largest for ACP. Further, the spatial distributions of the anomaly intensity of the two quantities have been presented using about 40 stations to provide a further support to the close relationship of this peak with the EQ. The above statistical analysis has been compared with an analysis with recent machine/deep learning methods. We have utilized a combinational use of NARX (Nonlinear Autoregressive model with eXogenous inputs) and Long Short-Term Memory (LSTM) models, which was successful in objectively re-confirming the anomalies in both parameters on the same day prior to the EQ. The combination of these analysis results elucidates that the meteorological anomalies on 10 January 1995 are considered to be a notable precursor to the EQ. Finally, we suggest a joint examination of our two meteorological quantities for their potential use in real short-term EQ prediction, as well as in the future lithosphere–atmosphere–ionosphere coupling (LAIC) studies as the information from the bottom part of LAIC.

THE COMPARISON OF LONG SHORT-TERM MEMORY AND BIDIRECTIONAL LONG SHORT-TERM MEMORY FOR FORECASTING COAL PRICE

Coal remains vital for global energy despite recent demand fluctuations due to the COVID-19 pandemic and geopolitical tensions. The International Energy Agency (IEA) projected a decline in global coal demand starting in early 2024, driven by increasing renewable energy adoption. As one of the top coal exporters, Indonesia must adjust to these changes. This study aims to forecast future coal prices using historical data from Indonesia's Ministry of Energy and Mineral Resources (KESDM), applying and comparing Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) models. While BiLSTM has shown advantages in other contexts and studies, its effectiveness for coal price forecasting remains underexplored. To ensure robust predictions, we employ walk-forward validation, which divides the data into six segments and evaluates 90 hyperparameter combinations across all segments. The BiLSTM model consistently outperforms the LSTM model, achieving lower average RMSE and MAPE values. Specifically, BiLSTM records an average MAPE of 7.847 and RMSE of 10.485, compared to LSTM's 10.442 and 11.993, respectively. The Diebold-Mariano (DM) test using squared error and absolute error loss functions further corroborates these findings, with most segments showing significant improvements in favor of BiLSTM, indicated by negative DM-test statistics and p-values below 0.01 or 0.10. This superior performance continues into the testing data, where BiLSTM maintains lower error metrics and a significant result of the DM test, underscoring its reliability for forecasting. In the final stage, the forecasts from both models indicate a nearly linear downward trend in coal prices over the next 18 months, aligning with the International Energy Agency's 2023 projection of a structural decline in coal demand driven by the sustained growth of clean energy technologies.

COMPARING FORECASTS OF AGRICULTURAL SECTOR EXPORT VALUES USING SARIMA AND LONG SHORT-TERM MEMORY MODELS

Indonesia's agricultural sector plays a crucial role in the national economy, with significant export potential and supporting the livelihoods of the majority of the population. As part of the government's vision to make Indonesia the world's food barn by 2045, increasing the volume and value of agricultural product exports is a primary focus, making export value forecasting essential for supporting strategic decision-making. Sequential data analysis is an important approach in analyzing data collected over a specific period. This study aims to compare two popular methods in forecasting the export value of the agricultural sector, namely the Seasonal AutoRegressive Integrated Moving Average (SARIMA) model and the Long Short-Term Memory (LSTM) model. Monthly agricultural export data from West Java Province from January 2013 to February 2024 were used as the dataset. The best SARIMA model generated was (1,1,1)(0,1,1)12, while the optimal parameters for the LSTM model were neuron: 50, dropout rate: 0.3, number of layers: 2, activation function: relu, epochs: 500, batch size: 64, optimizer: Adam, and learning rate: 0.01. Evaluation was performed using the Root Mean Squared Error (RMSE) method to measure the accuracy of both models in forecasting the export value of the agricultural sector. The results showed that the LSTM model outperformed the SARIMA model, with a lower RMSE value (SARIMA: 4182.133 and LSTM: 1939.02). This research provides valuable insights for decision-makers in planning agricultural sector export strategies in the future. With this comparison, it is expected to provide better guidance in selecting forecasting methods suitable for the characteristics of the data.

MKER: multi-modal knowledge extraction and reasoning for future event prediction

Humans can predict what will happen shortly, which is essential for survival, but machines cannot. To equip machines with the ability, we introduce the innovative multi-modal knowledge extraction and reasoning (MKER) framework. This framework combines external commonsense knowledge, internal visual relation knowledge, and basic information to make inference. This framework is built on an encoder-decoder structure with three essential components: a visual language reasoning module, an adaptive cross-modality feature fusion module, and a future event description generation module. The visual language reasoning module extracts the object relationships among the most informative objects and the dynamic evolution of the relationship, which comes from the sequence scene graphs and commonsense graphs. The long short-term memory model is employed to explore changes in the object relationships at different times to form a dynamic object relationship. Furthermore, the adaptive cross-modality feature fusion module aligns video and language information by using object relationship knowledge as guidance to learn vision-language representation. Finally, the future event description generation module decodes the fused information and generates the language description of the next event. Experimental results demonstrate that MKER outperforms existing methods. Ablation studies further illustrate the effectiveness of the designed module. This work advances the field by providing a way to predict future events, enhance machine understanding, and interact with dynamic environments.

Arctic sea ice thickness prediction using machine learning: a long short-term memory model

Arctic sea ice thickness prediction using machine learning: a long short-term memory model

Prediction of Structural Vibration Induced by Subway Operations Using Hybrid Method Based on Improved LSTM and Spectral Analysis

With the rapid expansion of urban subway networks, vibrations induced by subway operations have become an increasingly significant concern for nearby structures. To assess the influence of subway-induced vibrations on nearby structures, it is essential to predict the vibration effects accurately prior to the construction of the subway system. By combining an improved Long Short-Term Memory (LSTM) model with a spectral analysis, this paper proposes a hybrid method to enhance the accuracy and efficiency of predicting structural vibrations induced by subway operations. The improved LSTM model is composed of BiLSTM, an attention mechanism, and the DBO algorithm. The symmetry inherent in the vibration propagation paths and the structural layouts of subway systems is leveraged to improve the feature extraction and modeling accuracy. Additionally, the hybrid method utilizes the symmetric properties of vibration signals in the spectral domain to enhance prediction robustness and efficiency. Then, the hybrid method is utilized to rapidly achieve highly accurate vibration responses induced by subway operations. The verification results demonstrate the following: (1) The improved LSTM model enhances the ability to recognize patterns in time-series vibration data, leading to improved model convergence and generalization. The improved LSTM mode has a significant improvement in prediction accuracy compared to the standard LSTM network. For numerical simulation and real-world measured signals, values of R2 increased by 3% and 49.37%. (2) The proposed hybrid method significantly reduces computational time while ensuring results consistent with those obtained from the time-history analysis method. Applying the proposed hybrid method for data augmentation enhances the accuracy of the spectral analysis. The hybrid method achieves an improvement of 7% for the prediction accuracy.

Enhancing bridge performance assessment with a hybrid attention-based long short-term memory and hidden Markov model using sparse inspection data

Enhancing bridge performance assessment with a hybrid attention-based long short-term memory and hidden Markov model using sparse inspection data

Role of Rough Neutrosophic Attribute Reduction with Deep Learning-Based Enhanced Kidney Disease Diagnosis

The kidneys have an important role in keeping blood pressure, electrolyte sense, and acid-base sense of body balance to remove toxins from our body. Malfunction is responsible for irrelevant to life-threatening diseases, along with malfunction in the other functional organs. As a result, scholars worldwide have committed to finding methods for effectively diagnosing and accurately treating chronic kidney disease. As machine learning (ML) classifier is widely deployed in the healthcare field for diagnoses, also CKD is now involved in the collection of disorders that could be predicted through the ML classifier. Neutrosophic logic (NL) can be employed as a form of logic that expands classical, fuzzy, and intuitionistic fuzzy logic (IF) by integrating a third constituent: indeterminacy. It enables data handling and representation with three dissimilar membership functions: truth (T), indeterminacy (I), and false (F). The complete set is independent and may differ in the interval [0, 1], providing a convoluted strategy to handle, data incompleteness, vagueness and uncertainty. This makes NL especially relevant in complicated systems where data might be partially unknown, ambiguous, or inconsistent. This article employs a Rough Neutrosophic Attribute Reduction with Deep Learning based Enhanced Kidney Disease Diagnosis (RNSAR-DLKDD) technique. Initially, the RNSAR-DLKDD technique reduces the attributes via the RNSAR technique. Followed by, the detection and classification of kidney disease take place using long short-term memory (LSTM) model. Finally, the hyperparameter selection process is carried out via crow search algorithm (CSA). To highlight the performance of the RNSAR-DLKDD technique, a series of experiments were involved. The extensive results inferred the betterment of the RNSAR-DLKDD technique over other models

Finding the Efficiency of ConvBi-LSTM Over Anticipation of Adversaries in WBANs

Introduction: Wireless Body Area Networks (WBANs) are similar to custom Wireless Sensor Networks, so these networks are prone to adversaries through their activities, but in healthcare applications, security is necessary for the patient data. Moreover, providing reliable healthcare to patients is essential, and for the right treatment, correct patient data is required. For this purpose, we need to eliminate anomalies and irrelevant data created by malicious persons, attackers, and unauthorized users. However, existing technologies are not able to detect adversaries and are unable to maintain the data for a long duration while transferring it. Aims: This research aims to identify adversarial attacks and solutions for these attacks to maintain reliable smart healthcare services Methodology: We proposed a Convolutional-Bi-directional Long Short-Term Memory (ConvBiLSTM) model that provides a solution for the detection of adversaries and robustness against adversaries. Bi-LSTM (Bidirectional-Long Short Term Memory), where the hyperparameters of BiLSTM are tuned using the PHMS (Prognosis Health Monitoring System) to detect malicious or irrelevant anomalies data. Result: Thus, the empirical outcomes of the proposed model showed that it accurately categorizes a patient's health status founded on abnormal vital signs and is useful for providing the proper medical care to the patients. Furthermore, the Convolution Neural Networks (CNN) performance is also evaluated spatially to examine the relationship between the sensor and CMS (Central Monitoring System) or doctor’s device. The accuracy, recall, precision, loss, time, and F1 score metrics are used for the performance evaluation of the proposed model. Conclusion: Besides, the proposed model performance is compared with the existing approaches using the MIMIC (Medical Information Mart for Intensive Care) data set.

Enhancing Cybersecurity Attack Detection Using Multiplayer Battle Game Optimizer with Hybridization of Deep Learning Models

Cybersecurity is advancing and the rate of cybercrime, which is always rising. Advanced attacks are measured as the novel normal as they are one of the more normal and extensive. Cybersecurity threats have risen promptly in many areas like healthcare, smart homes, energy, automation, agriculture, and industrial processes. An intrusion detection system (IDS) discovers intrusions by analyzing attack designs or mining signatures from system packets. To assess an IDS model, use Machine Learning (ML) and deep learning (DL) approaches for recognizing data traffic into malicious and healthy. ML and DL techniques has earned an extensive interest on countless applications and domains of study, mostly in Cybersecurity. With computing power and hardware becoming more available, ML and DL systems can be employed in order to classify and analyze corrupt actors from a massive group of accessible data. This manuscript presents an Enhancing Detection of Cybersecurity Attack Using Multiplayer Battle Game Optimizer with Hybrid Deep Learning (EDCA-MBGOHDL) technique. The main intention of the EDCA-MBGOHDL technique is to provide a robust framework for cyberattack detection using deep learning integrated with a hyperparameter tuning approach. At first, the feature selection process is implemented by applying improved Harris hawk optimization (IHHO) algorithm for ensuring that only the most relevant features are fed into the model. Furthermore, the hybrid of convolutional neural network, bidirectional long short-term memory and attention mechanism (CNN-BiLSTM-AM) model is employed for the classification of cybersecurity threats. Eventually, the multiplayer battle game optimizer (MBGO) algorithm adjusts the hyperparameter values of the CNN-BiLSTM-AM classifier optimally and outcomes in greater classification performance. The wide range of analysis of the EDCA-MBGOHDL technique takes place using a benchmark dataset. The outcomes pointed out the superior performance of the EDCA-MBGOHDL system across existing models

Archimedes assisted LSTM model for blockchain based privacy preserving IoT with smart cities

Presently, the emergence of internet of things (IoT) has significantly improved the processing, analysis, and management of the substantial volume of big data generated by smart cities. Among the various applications of smart cities, notable ones include location-based services, urban design and transportation management. These applications, however, come with several challenges, including privacy concerns, mining complexities, visualization issues and data security. The integration of blockchain (BC) technology into IoT (BIoT) introduces a novel approach to secure smart cities. This work presents an Archimedes assisted long short-term memory (LSTM) model intrusion detection for BC based privacy preserving (PP) IoT with smart cities. After the stage of pre-processing, the LSTM is utilized for automated feature extraction and classification. At last, the Archimedes optimizer (AO) is utilized to optimize the LSTM’s hyper-parameters. In addition, the BC technology is utilized for securing the data transmission.

Optimizing county-level infectious respiratory disease forecasts: a pandemic case study integrating social media-based physical and social connectivity networks

ABSTRACT Forecasting infectious respiratory diseases is crucial for effective prevention and intervention strategies. However, existing time series forecasting models that incorporate human mobility data have faced challenges in making localized predictions on a large scale across the country due to data costs and constraints. Using the COVID-19 pandemic as a case study, this research explores whether integrating social media-based place and social connectivity networks can improve predictions of disease transmission at the county level across various regions. Place connectivity networks, derived from Twitter users and tweets, and social connectivity networks, based on Facebook interactions, were used to map spatial and social linkages between locations. These networks were integrated into weekly COVID-19 incidence data across 2,927 U.S. counties using Long Short-Term Memory (LSTM) models. The combined connectivity-weighted model significantly enhanced prediction accuracy, reducing Mean Absolute Percentage Error (MAPE) by 49.38% across 96.62% of the counties, with the greatest improvements observed in urban and Northeastern counties. The results demonstrate that combining connectivity networks enhances prediction accuracy, offering a scalable and sustainable solution for localized disease forecasting on a large scale across diverse geographic areas using publicly accessible social media data.

Advanced Long Short-Term Memory (LSTM) Models for Forecasting Indonesian Stock Prices

Advanced Long Short-Term Memory (LSTM) Models for Forecasting Indonesian Stock Prices

Prediction of Earthquakes in Nepal and the Adjoining Regions Using LSTM

This study applies Long Short-Term Memory (LSTM) model to predict earthquake magnitudes in the frequently earthquake-affected Himalayan country Nepal and the adjoining region. The seismic data on the mb scale, from September 1964 to August 2024, were taken from the International Seismological Centre (ISC) catalogue, spanning rectangular boundary of latitudes 26.30°N to 30.50°N and longitudes 80.00°E to 88.30°E. The methodology involved extensive data preprocessing, feature engineering, and the implementation of a deep learning model. The LSTM network demonstrated moderate predictive power, achieving a Mean Absolute Error (MAE) of 0.2789, Root Mean Square Error (RMSE) of 0.3728, and coefficient of determination (R²) score of 0.4294. The model effectively captured overall seismic trends and showed consistent performance over time. A limitation of the model is its tendency to predict magnitudes within the range of 3.5 to 5.0, resulting in the underestimation of strong earthquakes and slight overestimation of weaker ones.

A multivariate soil temperature interval forecasting method for precision regulation of plant growth environment.

Foliage plants have strict requirements for their growing environment, and timely and accurate soil temperature forecasts are crucial for their growth and health. Soil temperature exhibits by its non-linear variations, time lags, and coupling with multiple variables, making precise short-term multi-step forecasts challenging. To address this issue, this study proposes a multivariate forecasting method suitable for soil temperature forecasting. Initially, the influence of various environmental factors on soil temperature is analyzed using the gradient boosting tree model, and key environmental factors are selected for multivariate forecasting. Concurrently, a point and interval forecasting model combining the Neural Hierarchical Interpolation for Time Series Forecasting (N-HiTS) and Gaussian likelihood function is proposed, providing stable soil temperature forecasting for the next 20 to 120 minutes. Finally, a multi-objective optimization algorithm is employed to search for optimal initial parameters to ensure the best performance of the forecasting model. Experiments have demonstrated that the proposed model outperforms common models in predictive performance. Compared to Long Short-Term Memory (LSTM) model, the proposed model reduces the Mean Absolute Error (MAE) for forecasting soil temperatures over the next 20, 60, and 120 minutes by 0.065, 0.138, and 0.125, respectively. Moreover, the model can output stable forecasting intervals, effectively mitigating the instability associated with multi-step point forecasts. This research provides a scientific method for precise regulation and disaster early warning in facility cultivation environments.

A novel data-driven bridge monitoring data prediction framework using improved intelligent optimization-assisted deep learning

Bridge monitoring data prediction plays a crucial role in maintaining the serviceability and safety of bridges. To assess the performance of bridge structures in advance, an accurate and robust prediction model for measurement data prediction is needed. In this context, this paper presents a novel hybrid prediction model called IGWO-VMD-IGWO-LSTM, which aims to improve the accuracy and generalization ability of bridge monitoring data prediction. First, the proposed model incorporates variational mode decomposition (VMD) and an improved gray wolf optimization (IGWO) algorithm to decompose the measured data into several intrinsic mode functions (IMFs) to capture the signal’s features comprehensively. Then, long short-term memory (LSTM) models are established individually for each IMF, with hyperparameters optimization using the IGWO algorithm. Finally, the integrated reconstructed subsequences yield the prediction results of the proposed IGWO-VMD-IGWO-LSTM model. Thus, the proposed framework avoids exploring the complex internal mechanism of bridge behavior evolution. The measurement data collected from a real bridge demonstrates the feasibility of the proposed prediction method, and different deep learning models are used for comparison. The results demonstrate a significant improvement in prediction performance comparison with the other concerned models, highlighting the strong generalization ability and robustness of the proposed IGWO-VMD-IGWO-LSTM model.

Business process overhaul in dairy supply chains: An integrated approach of advanced forecasting and vehicle routing techniques

The study explores improving opportunities of forecasting accuracy from the traditional method through advanced forecasting techniques. This enables companies to optimize inventory management, production planning, and reducing the travelling time thorough vehicle route optimization. The article introduced a holistic framework by deploying advanced demand forecasting techniques i.e., AutoRegressive Integrated Moving Average (ARIMA) and Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM) models, and the Vehicle Routing Problem with Time Windows (VRPTW) approach. The actual milk demand data came from the company and two forecasting models, ARIMA and RNN-LSTM, have been deployed using Python Jupyter notebook and compared them in terms of various precision measures. VRPTW established not only the optimal routes for a fleet of six vehicles but also tactical scheduling which contributes to a streamlined and agile raw milk collection process, ensuring a harmonious and resource-efficient operation. The proposed approach succeeded on dropping about 16% of total travel time and capable of making predictions with approximately 2% increased accuracy than before.

Analysis of Rice Yield Prediction with Mlpregressor and Long Short-Term Memory Models

This research aims to analyse and compare the accuracy of rice productivity prediction using Multi-Layer Perceptron Regressor (MLPRegressor) and Long Short-Term Memory (LSTM) models. The data used comes from the Badan Pusat Statistik (BPS) for the period 2018-2023, covering rice productivity from 34 provinces in Indonesia. The study employed six different architectural models for each model, with training data using the 2018-2020 period and testing data for 2021-2023. The results show that the LSTM model with 2-42-42-42-1 architecture achieved the highest accuracy rate of 94.12% with MSE 0.00305660, while the MLPRegressor model with 2-22-1 architecture achieved 91.18% accuracy with MSE 0.00471975. These results indicate that LSTM performs slightly better in predicting rice productivity, which can be used as a reference for agricultural planning and food policy in Indonesia.

Occupant-Aware Energy Consumption Prediction in Smart Buildings Using a LSTM Model and Time Series Data

Accurate energy consumption prediction in commercial buildings is a challenging research task. Energy prediction plays a crucial role in energy efficiency, management, planning, sustainability, risk management, diagnosis, and demand response. Although many studies have been conducted on building energy predictions, the impact of occupancy on energy prediction models for office-type commercial buildings remains insufficiently explored, despite its potential to improve energy efficiency by 20%. This study investigates energy prediction using a Long Short-Term Memory (LSTM) model that incorporates time-series power consumption data and considers occupancy. A real-world dataset containing the per-minute electricity consumption of various appliances in an office building in Houston, TX, USA, is utilized. The proposed machine learning models forecast future energy consumption based on hourly, 3-hourly, daily, and quarterly predictions for individual appliances and total energy usage. The model’s performance is evaluated using the following three metrics: Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). The results demonstrate the superiority of the proposed system.

Transferable deep learning with coati optimization algorithm based mitotic nuclei segmentation and classification model

Image processing and pattern recognition methods have recently been extensively implemented in histopathological images (HIs). These computer-aided techniques are aimed at detecting the attentive biological markers for assisting the final cancer grading. Mitotic count (MC) is a significant cancer detection and grading parameter. Conventionally, a pathologist examines the biopsy image physically by employing higher-power microscopy. The MC cells have been marked physically at every analysis, and total MC must be utilized as a major aspect for the cancer ranking and considered as the initiative of cancers. Numerous pattern recognition algorithms for cell-sized objects in HIs depend upon segmentation to assess features. The correct description of the segmentation has been difficult, and feature outcomes can be highly complex to the segmentation. The MC cells are an essential element in many cancer grading methods. Extraction of the MC cell from the HI is a highly challenging assignment. This manuscript proposes the Coati Optimization Algorithm with Deep Learning-Driven Mitotic Nuclei Segmentation and Classification (COADL-MNSC) technique. The major aim of the COADL-MNSC technique is to utilize the DL model to segment and classify the mitotic nuclei (MN). In the preliminary stage, the COADL-MNSC approach implements median filtering (MF) for pre-processing. Besides, the COADL-MNSC approach utilizes the Hybrid Attention Fusion U-Net (HAU-UNet) model to segment the MN. Moreover, the capsule network (CapsNet) model is employed for the feature extraction method, and its hyperparameters are adjusted by utilizing the COA model. At last, the classification procedure is performed using the bidirectional long short-term memory (BiLSTM) model. Extensive simulations are performed under the MN image dataset to exhibit the excellent performance of the COADL-MNSC methodology. The experimental validation of the COADL-MNSC methodology portrayed a superior accuracy value of 98.89% over existing techniques under diverse measures.