Convolutional Neural Network Long Short-term Memory Research Articles

CNN-LSTM Hybrid Model for Enhanced Malware Analysis and Detection

The ever-evolving tactics employed by malware authors to avoid detection pose challenges to the conventional static analysis method, which entails examining the malware code. These challenges arise from the authors’ capacity to obfuscate their code. To address this matter and enhance the identification of malware, integrating dynamic detection and machine learning has emerged as a highly promising approach. This methodology has demonstrated efficacy in identifying malware specifically engineered to circumvent established detection techniques. Behavioural analysis is a crucial component in ensuring endpoints’ security, with the CNN-LSTM algorithm being particularly notable for its effectiveness in identifying Zero-Day malware. This type of malware poses a substantial obstacle to conventional signature-based approaches. This paper aims to assess the efficacy of the Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model, emphasising its significance in tackling the continuously evolving realm of cybersecurity obstacles. The research highlights the significance of transitioning from traditional signature-based detection methods to behavioural analysis techniques. It suggests utilising deep learning approaches such as Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) to improve the ability to detect malware in an environment where threats constantly evolve. The malware detection system that has been developed encompasses a log parser analyser, API monitoring, and an extension checker module. The CNN-LSTM model demonstrates a commendable ability to accurately identify malicious behaviour, achieving a validation accuracy of 96%. This study demonstrates the efficacy of employing behavioural analysis and deep learning techniques to enhance cybersecurity, particularly in addressing sophisticated, evasive, and previously unknown malware risks.

Prediction and classification of IoT sensor faults using hybrid deep learning model

The quality and reliability of internet of thing (IoT) ecosystems heavily rely on accurate and dependable sensor data. However, resource limited sensors are prone to failure due to various factors like environmental disturbances and electrical noise in which they can produce erroneous and faulty measurements. These can have significant consequences across different domains, including a threat to safety in critical systems. Though many researches have been conducted, the existing literature primarily focuses on fault detection in the sensor data, while fault detection is useful, it is still a reactive approach that identifies the faults after they have occurred, meaning that actions are taken after the fault has already impacted the system, potentially leading to negative consequences. In this study, a proactive approach has been proposed by developing a two-stage solution. In the first stage, a hybrid convolutional neural network-long short term memory (CNN-LSTM) model was trained to forecast sensor measurements based on historical data, while in the second stage, the forecasted measurements were passed to a hybrid convolutional neural network-multi layer perceptron (CNN-MLP) model that has been trained to recognize different types of sensor faults and classify the new measurements accordingly. By passing the forecasted sensor values as input to the classification model and categorizing them as normal, bias, drift, random or poly-drift, anticipated the potential faults before they manifest. The publicly available Intel Lab data raw dataset is used, which has been annotated and fault-injected. For regression, gated recurrent unit (GRU), Long short term memory (LSTM), bidirectional long short term memory (BiLSTM), convolutional neural network-gated recurrent unit (CNN-GRU), convolutional neural network-long short term memory (CNN-LSTM), and convolutional neural network-bidirectional long short term memory (CNN-BiLSTM), were evaluated and compared their performance using root mean squared error (RMSE), mean squared error (MSE) and mean absolute error (MAE) with 2-split time series cross-validation. CNN-LSTM outperformed the other models with a Mean Absolute Error of 2.0957 for a 45 time steps forecast. For the classification task, convolutional neural network (CNN), multi-layer perceptron (MLP), and convolutional neural network-multi layer perceptron (CNN-MLP) evaluated using the metrics accuracy, precision, recall, and F1-score with 5 and tenfold cross-validations. CNN-MLP outperformed the others with accuracy of 96.11% for bias, 99.33% for drift, and 98.61% for random and 98.81% for poly-drift. The average accuracy across the 4 faults is 98.21%, which is a 0.3% increase from the baseline work 97.91%. By adopting a proactive approach to sensor fault prediction and classification, this research aims to enhance the reliability and efficiency of IoT systems, allowing for preventive measures to be taken before faults have a detrimental impact.

Assessing Consciousness in Patients With Disorders of Consciousness Using a Musical Stimulation Paradigm and Verifiable Criteria.

Numerous studies have shown that musical stimulation can activate corresponding functional brain areas. Electroencephalogram (EEG) activity during musical stimulation can be used to assess the consciousness states of patients with disorders of consciousness (DOC). In this study, a musical stimulation paradigm and verifiable criteria were used for consciousness assessment. Twenty-nine participants (13 healthy subjects, 6 patients in a minimally conscious state (MCS) and 10 patients in a vegetative state (VS)) were recruited, and EEG signals were collected while participants listened to preferred and relaxing music. Fusion features based on differential entropy (DE), common spatial pattern (CSP), and EEG-based network pattern (ENP) features were extracted from EEG signals, and a convolutional neural network-long short-term memory (CNN-LSTM) model was employed to classify preferred and relaxing music.The results showed that the average classification accuracy for healthy subjects reached 85.58%. For two of the patients in the MCS group, the classification accuracies reached 78.18% and 66.14%, and they were diagnosed with emergence from MCS (EMCS) two months later. The accuracies of three patients in the VS group were 58.18%, 64.32% and 62.05%, with two patients showing slight increases in scale scores. Our study suggests that musical stimulation could be an effective method for consciousness detection, with significant diagnostic implications for patients with DOC.

Harnessing Deep Learning for Meteorological Drought Forecasts in the Northern Cape, South Africa

The National Disaster Management Center has declared a drought disaster in the Northern Cape, South Africa, due to persistent dry conditions that impact regions such as the Western, Eastern, and Northern Cape provinces. Accurate drought predictions are vital for decision‐making and planning in vulnerable areas. This study introduces a hybrid intelligence model, combining long short‐term memory (LSTM) and convolutional neural networks (CNNs), to forecast short‐term meteorological droughts using the Standardized Precipitation Evapotranspiration Index (SPEI). Applied to Kimberley and Upington in the Northern Cape, the model predicts 1‐month and 3‐month SPEI indices (SPEI‐1 and SPEI‐3). The hybrid model’s performance, compared to benchmark models such as artificial neural networks (ANNs), LSTM, and CNN, is measured through statistical analysis. In Kimberley, the CNN–LSTM model displayed a robust positive correlation of 0.901573 and a low mean absolute error (MAE) of 0.082513. Similarly, in Upington, the CNN–LSTM model exhibited strong performance, achieving a correlation coefficient of 0.894805 and a MAE of 0.085212. These results highlight the model’s remarkable precision and effectiveness in predicting drought conditions in both regions, underscoring its superiority over other forecasting techniques. SPEI, incorporating potential evapotranspiration and rainfall, is superior for drought analysis amidst climate change. The findings enhance understanding of drought patterns and aid mitigation efforts. The CNN–LSTM hybrid model demonstrated noteworthy results, outperforming ANN, CNN, and LSTM, emphasizing its potential for precise meteorological drought predictions.

A Systematic Evaluation of Adversarial Attacks against Speech Emotion Recognition Models

Speech emotion recognition (SER) has been constantly gaining attention in recent years due to its potential applications in diverse fields and thanks to the possibilities offered by deep learning technologies. However, recent studies have shown that deep learning models can be vulnerable to adversarial attacks. In this paper, we systematically assess this problem by examining the impact of various adversarial white-box and black-box attacks on different languages and genders within the context of SER. We first propose a suitable methodology for audio data processing, feature extraction, and convolutional neural network long short-term memory (CNN-LSTM) architecture. The observed outcomes highlighted the considerable vulnerability of CNN-LSTM models to adversarial examples (AEs). In fact, all the considered adversarial attacks are able to considerably reduce the performance of the constructed models. Furthermore, when assessing the efficacy of the attacks, minor differences were noted between the languages analyzed as well as between male and female speech. In summary, this work contributes to the understanding of the robustness of CNN-LSTM models, particularly in SER scenarios, and the impact of AEs. Interestingly, our findings serve as a baseline for (a) developing more robust algorithms for SER, (b) designing more effective attacks, (c) investigating possible defenses, (d) improved understanding of the vocal differences between different languages and genders, and (e) overall enhancing our comprehension of the SER task.

Improving wave height prediction accuracy with deep learning

A novel convolutional neural network-long short-term memory (CNN-LSTM) model is proposed for wave height prediction. The model effectively extracts relevant features such as wind speed, wind direction, wave height, latitude, and longitude. The proposed model outperforms traditional machine learning algorithms such as multi-layer perceptron (MLP), support vector machine (SVM), random forest and LSTM, especially for extreme values and fluctuations. The model has a significantly lower average root mean square error (RMSE) of 71.1%, 72.8%, 71.9% and 72.2% for MLP, SVM, random forest and LSTM, respectively. Our model is computationally more efficient than traditional numerical simulations, making it suitable for real-time applications. Moreover, it has better long-term robustness compared to traditional models. The integration of CNN and LSTM techniques improves wave height prediction accuracy while enhancing its efficiency and robustness. The proposed CNN-LSTM model provides a promising tool for effective wave height prediction, making a valuable contribution to coastal disaster prevention and mitigation. Future research should aim to improve long-term prediction accuracy, and we believe that the CNN-LSTM model plays a crucial role in developing real-time coastal disaster prevention and mitigation measures. Overall, our study represents a significant step towards achieving more accurate and efficient wave height prediction using machine learning techniques.

Convolutional Neural Network‐Long Short‐Term Memory‐Based State of Health Estimation for Li‐Ion Batteries under Multiple Working Conditions

The state of health (SOH) for lithium‐ion batteries is an important indicator to ensure the safety and reliability of battery energy storage systems. Aiming at the difficulty of accurately estimating the SOH of lithium‐ion batteries under different working conditions, this article proposes a method based on a hybrid convolutional neural network‐long short‐term memory (CNN‐LSTM) model. First, the battery health indicators and capacity data under different operating conditions are extracted from the public dataset to form a new dataset. Second, the CNN has multiple one‐dimensional convolutional layers to improve the efficiency of feature extraction from new datasets, and the resulting features are used as inputs to the LSTM to predict SOH. Finally, the CNN‐LSTM model integrates a fully connected layer that outputs the estimation of SOH for different operating conditions. The results show that the mean absolute error of the SOH estimation results is within 2.33% and 3.01% for the same and different working conditions, respectively.

A surface electromyography based hand gesture recognition framework leveraging variational mode decomposition technique and deep learning classifier

Deciphering and classifying surface electromyography (sEMG) signals is highly essential in rehabilitation robotics, myoelectric prosthetic control, sign languages and human–computer-interface. Researchers have generally focused on utilizing multi-channel sEMG signals for gesture classification. However, in case of amputees, the residual muscles are limited and the gesture classification needs to be reframed with minimum sEMG channels. Moreover, another key problem in the gesture classification system is the nonlinear and non-stationary nature of sEMG signals, leading to poor generalization ability. Hence, to address the aforementioned problems, this study puts forward a novel deep learning classifier framework which leverages the potentials of variational mode decomposition (VMD) technique and a hybrid convolutional neural network–long short term memory (CNN–LSTM) classifier model to recognize the hand gestures from single channel sEMG signals. Collecting the sEMG signals from forearm muscles of 25 intact subjects for ten functional and grasping actions, this work implements a VMD technique to identify the prominent frequency modes in the sEMG signals. From the decomposed modes of sEMG signals, the prominent intrinsic mode functions (IMFs) are extracted through spectral analysis to minimize the computation burden on the hybrid classifier model. Furthermore, as the muscle contractions result in substantial temporal dependencies, this work exploits the potentials of CNN and LSTM networks and extracts the spatiotemporal features of the sEMG signals for various hand gestures. The experimental results corroborate that the proposed classifier framework can achieve an average classification accuracy of 98.04% and provide 3% improvement in the classification accuracy compared to conventional CNN classifier.

Evaluation of the impact of intensive PM2.5 reduction policy in Seoul, South Korea using machine learning

The average PM2.5 concentration in South Korea decreased steadily, but the monthly average PM2.5 concentration in January–March increased over time. The Seasonal Fine Dust Management System (hereafter, seasonal management) was implemented from December 2019 to March 2020 in order to reduce high PM2.5 concentrations. This study evaluated the effect of seasonal management using machine learning algorithms, long–short term memory (LSTM), convolutional neural network–LSTM (CNN–LSTM), and ensemble models (Random forest and extreme gradient boosting), and the business–as–usual (BAU) approach. The CNN–LSTM model was defined as four models (multi-headed model 1 and model 2; single-headed model 1 and model 2) according to the method of handling independent variables and the composition of layers. All models performed well; however, the single-headed CNN–LSTM model 1 outperformed the other models. In the BAU period, the observed PM2.5 concentration was 31.98 μg/m3 and the seasonal management reduced PM2.5 concentrations to between 1.09 μg/m3 and 2.73 μg/m3. Overall, the change in PM2.5 concentrations through the seasonal management was apparent during the BAU period, and the machine learning algorithms and BAU approach can be used for the evaluation of policy impact.

A rapid analysis framework for seismic response prediction and running safety assessment of train-bridge coupled systems

With high-speed railway lines increasing gradually, the running safety assessment (RSA) of train-bridge coupled (TBC) systems has become an indispensable part of railway seismic design. However, the modeling of TBC systems is difficult and computationally complex. Therefore, it is difficult to conduct real-time assessment and response analysis rapidly. With this in mind, this paper integrates a surrogate framework based on deep learning methods and can help rapid-diagnose the seismic response and RSA. Meanwhile, real-time information feedback is performed to determine the safe speed of the train. To this end, a convolutional neural network-long short-term memory (CNN-LSTM) model with excellent time-series data processing capability is newly used for the seismic response analysis of the TBC system. Furthermore, response data obtained are processed and input to an interpretable adaptive network-based fuzzy inference system (ANFIS). The ANFIS derives a series of fuzzy rules while conducting the RSA, and these rules can help non-specialists understand the assessment process. Finally, parameter inversion is performed by the ANFIS to determine a safe threshold of train speed. According to the tests, the proposed rapid analysis framework can be applied to seismic response analysis and RSA with high efficiency and accuracy in multiple engineering scenarios. The framework may be helpful for railway design and make it possible to realize real-time data analysis for TBC systems.

Classification of crop disease-pest questions based on BERT-BiGRU-CapsNet with attention pooling.

Crop disease-pest question classification is an essential part of pest knowledge intelligent question answering system. A crop disease-pest question classification method is proposed on the basis of bidirectional encoder representations from transformers (BERT), bidirectional gated unit (BiGRU), capsule network (CapsNet), and BERT-BiGRU-CapsNet with attention pooling (BBGCAP). In BBGCAP, the unstructured text data are preprocessed vectorically using BERT, BiGRU is used to extract the deep features of the text, attention pooling is used to assign the corresponding weights to the extracted deep information, and CapsNet is used to route the right alternative. BBGCAP is a synthetic model by integrating the advantages of BERT, BiGRU, CapsNet, and attention pooling. The experimental results on the cucumber-pest question database show that the proposed method is superior to the methods based on traditional template matching, support vector machines (SVM), and convolutional neural network-long short-term memory (LSTM), and the accuracy rates of precision, recall, and F1 are all above 902.15%. This method provides technical support for intelligent question answering system of crop disease-pests.

Hyperspectral Image Analysis using LSTM and 2D CNN and its Application in Remote Sensing

The land cover classification in urban areas is described in this research work. The use of hyperspectral image analysis is growing in popularity because it performs better than conventional machine learning techniques. Hypercubes, a type of three-dimensional dataset with two spatial dimensions and one spectral dimension, make up the Hyperspectral imaging (HSI). An overview of HSI's uses in remote sensing applications and the methods for classifying it are given in this research. In the field of HSI, numerous experiments are conducted with various deep learning methods for analysis and classification. The main components of this research is convolutional neural network (CNN)and long short-term memory (LSTM) that shows to be more effective than alternative models. In this case, spectral and spatial features are extracted using CNN and LSTM, respectively, and the results are then classified using support vector machines (SVM). The datasets utilized in this study were gathered using a ROSIS sensor/spectrometer at Pavia University and Indian Pines.

IoT intrusion detection system using ensemble classifier and hyperparameter optimization using tuna search algorithm

<p>The Internet of Things (IoT) is a dynamic and delightful research field in this emerging technology. It can be globally connected with many IoT devices and exchange a large amount of data. However, the threats also developed and misguided the entire network’s behaviour. This article proposes an Intrusion Detection System (IDS) using the proposed ensemble classifier along with the Tuna Swarm Optimization (TSO) to fine-tune the hyperparameters and help to enhance the detection accuracy of attacks that take place in IoT environment. Here, the publicly available message queue telemetry transport (MQTT) network dataset is used to classify the given data into the following categories: SlowlTe, malformed, brute force, flood, DoS, and legitimate. Initially, the dataset is pre-processed to remove possible outliers, then data balancing is performed using the Synthetic Minority Oversampling Technique (SMOTE) technique and features are extracted with the help of Recursive Feature Elimination (RFE). Finally, ensemble classifier along with the optimized parameters using TSO helps in detecting the attacks in IoT attacks. The proposed TSO-ensemble classifier achieved a classification accuracy of 99.12%. In contrast, the classification accuracy of the existing Improved Vulture Starvation-based African Vultures Optimization (IVS-AVOA) and Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) have achieved a classification accuracy of 96.61% and 98.94% respectively.</p>

Separating climate change and human activities' effects on flow regime with hydrological model error correction

Climate change and human activities have markedly altered flow regimes, leading to deleterious consequences for riverine ecosystems. The widely employed hydrological modeling restoration method for conducting flow regime attribution often tends to underemphasize the impact of simulation errors on attribution outcomes. Moreover, the issue of ambiguous attribution targets in flow regime attribution remains a critical concern. This study presented a flow regime attribution framework integrated the hydrological model error correction. Indicators of hydrologic alteration (IHA) simulated by the XAJ and GR4J hydrological models and corrected using the quantile-mapping (QM) and convolutional neural network-long short term memory (CNN-LSTM) error correction methods, were employed to create 6 scenarios for assessing the impacts of climate change and human activities on flow regime changes. A case study was conducted in the Xitiaoxi basin, located in the upper reaches of Lake Tai in China. The results demonstrated that CNN-LSTM's superior performance over QM in correcting IHA metrics simulated by both XAJ and GR4J. The mean flow regime attribution results obtained from XAJ and GR4J simulations following the application of CNN-LSTM correction, mitigated the underestimation of contributions from the primary driving factors, in contrast to uncorrected or QM-corrected IHA metrics attribution results. Additionally, the regime attribution findings revealed all 33 IHA metrics experienced changes, with 73 % of them attributing human activities as the predominant driving forces. Substantial variations in IHA metrics exerted a certain degree of pressure on riverine habitats, particularly impacting the spawning and reproductive activities of piscine species.

Flood Forecasting Using Hybrid LSTM and GRU Models with Lag Time Preprocessing

Climate change and urbanization have increased the frequency of floods worldwide, resulting in substantial casualties and property loss. Accurate flood forecasting can offer governments early warnings about impending flood disasters, giving them a chance to evacuate and save lives. Deep learning is used in flood forecasting to improve the timeliness and accuracy of flood water level predictions. While various deep learning models similar to Long Short-Term Memory (LSTM) have achieved notable results, they have complex structures with low computational efficiency, and often lack generalizability and stability. This study applies a spatiotemporal Attention Gated Recurrent Unit (STA-GRU) model for flood prediction to increase the models’ computing efficiency. Another salient feature of our methodology is the incorporation of lag time during data preprocessing before the training of the model. Notably, for 12-h forecasting, the STA-GRU model’s R-squared (R2) value increased from 0.8125 to 0.9215. Concurrently, the model manifested reduced root mean squared error (RMSE) and mean absolute error (MAE) metrics. For a more extended 24-h forecasting, the R2 value of the STA-GRU model improved from 0.6181 to 0.7283, accompanied by diminishing RMSE and MAE values. Seven typical deep learning models—the LSTM, the Convolutional Neural Networks LSTM (CNNLSTM), the Convolutional LSTM (ConvLSTM), the spatiotemporal Attention Long Short-Term Memory (STA-LSTM), the GRU, the Convolutional Neural Networks GRU (CNNGRU), and the STA-GRU—are compared for water level prediction. Comparative analysis delineated that the use of the STA-GRU model and the application of the lag time pre-processing method significantly improved the reliability and accuracy of flood forecasting.

Hybrid deep learning model for wearable sensor‐based stress recognition for Internet of Medical Things (IoMT) system

SummaryThere are numerous, interrelated, and multi‐dimensional aspects that influence a person's mental health, one of them being stress. Smart wearable technology having physiological and motion sensors has paved the way for real‐time data collection to deliver cutting‐edge information about the stress of individuals. It is now possible to build an Internet of Medical Things (IoMT) system that can recognise the user's stress, revealing the elements that cause stress. However, there are significant gaps in the existing system for stress recognition. To begin with, stress recognition is primarily studied for a specific set of people, such as occupational stress among office working persons or hospital staff during emergency duties, and so forth. Second, most past work on stress recognition has focused on extracting handcrafted traits, which necessitates human interaction and skill. To overcome above mentioned challenges, this work proposes a novel IoMT framework for continuous stress recognition for mental well‐being. This paper presents a hybrid deep learning (DL) approach for automatically retrieving features and classification into various stress states for the IoMT system to address these difficulties. The proposed expanded system gathers data from wearable physiological sensors and feeds it into a convolutional neural network–long short‐term memory (CNN‐LSTM), a hybrid DL classifier. The suggested approach has been tested on the wearable stress and affect detection (WESAD) dataset. It has a reported accuracy of 90.45%, which is higher than previously reported accuracies from existing machine learning (ML) and DL approaches.

Bidirectional Encoder Representations Transformers for Improving CNN-LSTM Covid-19 Disease Detection Classifier

Early identification of COVID-19 diseased persons is crucial to avoid and prevent the transmission of the SARS-CoV-2 virus. To achieve this, lung Computed Tomography (CT) scan segmentation and categorization models have been broadly developed for COVID-19 diagnosis. Amongst, Multi-Scale function learning with an Attention-based UNet and Marginal Space Deep Ambiguity-attentive Transfer Learning (MS-AUNet-MSDATL) framework is developed to concurrently segment the COVID-19 infected regions and classify their risk levels from the CT/Chest X-Ray (CXR) scans. This model utilizes Convolutional Neural Network–Long Short Term Memory (CNN-LSTM) as a classifier for proper recognition. Although CNN-LSTM efficiently learns the spatial and temporal data, but it highly ignores the pixels and their adjacent information which results in lower classification rate. So, in this paper, Bidirectional Encoder Representations from Transformers (BERT) is introduced along with CNN-LSTM in MS-AUNet-MSDATL model to resolve the above mentioned issues for efficient COVID-19 risk level classification. Initially, the segmented CT and CXR images from MS-AUNet is given as input to the BERT model. BERT structure consist of stack of transformer encoder layers which extracts fixed features from a pre-trained models to obtain the numerical representation of the given image. Then, the numerical expressions from the BERT are transformed to pre-learned CNN model for selecting the important features from the given representations. The LSTM model receives the CNN output and generates a new representation based on the data order. In addition, Fully Connected Layer (FCL) maps the CNN-LSTM results into categorization classes to learn pixels and their adjacent information for COVID-19 risk level detection and diagnosis. The complete work is termed as MS-AUNet-EMSDATL. Finally, the test findings shows that the MS-AUNet-MS-B-DATL achieves accuracy of 98.67% and 98.55% on CT and CXR images compared to the other existing frameworks.

State-of-health and remaining-useful-life estimations of lithium-ion battery based on temporal convolutional network-long short-term memory

Accurate estimations in state of health (SOH) and remaining useful life (RUL) are significant for safe and efficient operation of batteries. With the development of big data and deep learning technology, the neural network method has been widely used for SOH and RUL estimations because of its excellent nonlinear mapping performance, adaptive performance and self-learning performance. In this paper, a novel hybrid model based on temporal convolutional network-long short-term memory (TCN-LSTM) for SOH and RUL estimations is proposed. The hyperparameters of each layer in the model are optimized using Bayesian optimization algorithm. Three different models, including convolutional neural network-long short-term memory (CNN-LSTM) model, temporal convolutional network (TCN) model and long short-term memory (LSTM) model, are adopted as comparisons to evaluate the performance of the proposed model. All the models are tested using two public battery datasets from National Aeronautics and Space Administration (NASA dataset) and Oxford University (OX dataset). In SOH task, the TCN-LSTM model achieves an accuracy improvement of >16 % and 14 % in NASA and OX datasets, respectively. In RUL task, the accuracies of the TCN-LSTM model and the CNN-LSTM model are superior to other models in NASA dataset; while the LSTM model and the CNN-LSTM model have better performance in OX dataset.

Integrating Temporal Fluctuations in Crop Growth with Stacked Bidirectional LSTM and 3D CNN Fusion for Enhanced Crop Yield Prediction

Optimizing farming methods and guaranteeing a steady supply of food depend critically on accurate predictions of crop yields. The dynamic temporal changes that occur during crop growth are generally ignored by conventional crop growth models, resulting in less precise projections. Using a stacked bidirectional Long Short-Term Memory (LSTM) structure and a 3D Convolutional Neural Network (CNN) fusion, we offer a novel neural network model that accounts for temporal oscillations in the crop growth process. The 3D CNN efficiently recovers spatial and temporal features from the crop development data, while the bidirectional LSTM cells capture the sequential dependencies and allow the model to learn from both past and future temporal information. Our model's prediction accuracy is improved by combining the LSTM and 3D CNN layers at the top, which better captures temporal and spatial patterns. We also provide a novel label-related loss function that is optimized for agricultural yield forecasting. Because of the relevance of temporal oscillations in crop development and the dynamic character of crop growth, a new loss function has been developed. This loss function encourages our model to learn and take advantage of the temporal trends, which improves our ability to estimate crop yield. We perform comprehensive experiments on real-world crop growth datasets to verify the efficacy of our suggested approach. The outcomes prove that our unified strategy performs far better than both baseline crop growth prediction algorithms and cutting-edge applications of deep learning. Improved crop yield prediction accuracy is achieved with the integration of temporal variations via the merging of bidirectional LSTM and 3D CNN and a unique loss function. This study helps move the science of estimating crop yields forward, which is important for informing agricultural policy and ensuring a steady supply of food.

CHP Engine Anomaly Detection Based on Parallel CNN-LSTM with Residual Blocks and Attention.

The extreme operating environment of the combined heat and power (CHP) engine is likely to cause anomalies and defects, which can lead to engine failure; thus, detecting engine anomalies is essential. In this study, we propose a parallel convolutional neural network-long short-term memory (CNN-LSTM) residual blocks attention (PCLRA) anomaly detection model with engine sensor data. To our knowledge, this is the first time that parallel CNN-LSTM-based networks have been used in the field of CHP engine anomaly detection. In PCLRA, spatiotemporal features are extracted via CNN-LSTM in parallel and the information loss is compensated using the residual blocks and attention mechanism. The performance of PCLRA is compared with various hybrid models for 15 cases. First, the performances of serial and parallel models are compared. In addition, we evaluated the contributions of the residual blocks and attention mechanism to the performance of the CNN-LSTM hybrid model. The results indicate that PCLRA achieves the best performance, with a macro f1 score (mean ± standard deviation) of 0.951 ± 0.033, an anomaly f1 score of 0.903 ± 0.064, and an accuracy of 0.999 ± 0.002. We expect that the energy efficiency and safety of CHP engines can be improved by applying the PCLRA anomaly detection model.