LSTM-based Approach Research Articles

A Survey Paper on LSTM-Based Approach for DeepFake Video Detection

Abstract: This research studies the use of Long Short-Term Memory (LSTM) networks for detecting DeepFake videos. DeepFake technology presents serious problems for preserving the authenticity and integrity of digital media since it uses sophisticated deep learning techniques to alter video content. We created a model capable of accurately detecting synthetic media by leveraging LSTM networks' sequential processing capabilities. The study focuses on taking advantage of temporal irregularities that are frequently found in DeepFake films but are difficult to identify using static analysis.

A Quantum LSTM-based approach to cyber threat detection in virtual environment

A Quantum LSTM-based approach to cyber threat detection in virtual environment

Research on Vehicle-Driving-Trajectory Prediction Methods by Considering Driving Intention and Driving Style

With the rapid advancement of autonomous driving technology, the accurate prediction of vehicle trajectories has become a research hotspot. In order to accurately predict vehicles’ trajectory, this study comprehensively explores the impact of driving style and intention on trajectory prediction, proposing a novel prediction method. Firstly, the dataset AD4CHE was selected as the research data, from which the required trajectory data of vehicles were extracted, including 1202 lane-changing and 1137 car-following driving trajectories. Secondly, a long short-term memory (LSTM) network based on the Keras framework was constructed by using the TensorFlow deep-learning platform. The LSTM network integrates driving intention, driving style, and historical trajectory data as inputs to establish a vehicle-trajectory prediction model. Finally, the mean absolute error (MAE) and root-mean-square error (RMSE) were selected as the evaluation indicators for the models, and the prediction results of the models were compared under two conditions: not considering driving style and considering driving style. The results demonstrate that models incorporating driving style significantly outperformed those that did not, highlighting the critical influence of driving style on vehicle trajectories. Moreover, compared to traditional kinematic models, the LSTM-based approach exhibits notable advantages in long-term trajectory prediction. The prediction method that accounts for both driving intention and style effectively reduces RMSE, significantly enhancing prediction accuracy. The findings of this research provide valuable insights for vehicle-driving risk assessment and contribute positively to the advancement of autonomous driving technology and the sustainable development of road traffic.

Data-driven prediction of drilling strength ahead of the bit

This paper compares the performance of two data-driven methods, Signal-Matching Predictor (SMP) and Long Short-Term Memory (LSTM), for predicting drilling strength (Es) ahead of the bit based on drilling data from nearby offset wells. The comparison is based on the accuracy, applicability, complexity, and computational cost of the methods with the objective of suggesting the most appropriate tool for look-ahead drilling strength prediction. The methods were tested using data from offshore wells in Newfoundland. The SMP used a fixed-size sliding-window of real-time Es data from the target well to find a match in the offset well within similar geological formations and chose the scaled value from the offset well as the prediction. In the second approach, twelve LSTM models were trained using the drilling data of twelve offset wells, and the drilling data of the thirteenth well was used for blind testing. Results showed that the SMP achieved a coefficient of determination (R2) of 0.92, 0.92, and 0.79 for predicting 1.5, 3, and 5 feet ahead of the bit, respectively, while the LSTM reached an R2 of 0.95, 0.92, and 0.80 for the respective prediction intervals. The R2 of the LSTM models was further increased to 0.96, 0.94, and 0.83 after retraining it with weighted samples in formation transition zones. Also, a post-processing technique was proposed that further enhanced the R2 of the LSTM-based approach to 0.98, 0.97, and 0.93, respectively. The strength of the LSTM-based approach was to use measurable drilling parameters as the only inputs and not the Es itself. According to the results, the LSTM-based method can be reliably used to predict the Es ahead of the bit allowing drillers to identify upcoming drilling dysfunctions.

A deep learning LSTM-based approach for AMD classification using OCT images

Age-related macular degeneration (AMD) is an age-related, persistent, painless eye disease that impairs central vision. The central area (macula) of the retina, located at the back of the eye, sustains damage that is the cause of loss of vision. The early detection of AMD can increase the probability of treatment and prevent vision loss. The AMD can be classified into dry and wet AMD based on the absence of neovascularization. This study introduces a new methodology for the classification of AMD using optical coherence tomography (OCT) retinal images. The proposed methodology is based on three stages. The first stage is the data preparation stage for resizing and normalizing the used images. The second stage is the image processing stage for enhancing the image quality as contrast and resolution these enhancements have been checked by the weighted peak signal-to-noise ratio (WPSNR) methodology. The third stage is the deep feature extraction and classification stage, which consists of two sub-models. The first model is MobileNet V1 which has been used as a deep feature extractor. The second model is LSTM (long short-term memory), fed with deep features to classify the AMD stages. A multi-classification with six separate trials has been employed with the proposed methodology, and compared with other models like DenseNet201 and InceptionV3. The proposed model has been tested on a sample of benchmark data with 4005 grayscale images labeled into three classes. The proposed methodology has achieved an accuracy of 98.85%, a sensitivity of 99.09%, and a specificity of 99.1%. To ensure the effectiveness of the proposed methodology, a comparative analysis has been established with previous approaches in the related field, and the results demonstrated the superiority of the proposed system in AMD multi-classification.

Long-short term memory networks aided fault detection of power facilities

In recent years, long-short term memory (LSTM) networks have emerged as a promising tool for time-series analysis, offering the ability to capture temporal dependencies effectively, especially for the fault detection in power facilities which is crucial for maintaining operational integrity and ensuring continuous power supply. This paper presents a study on the utilization of LSTM networks for fault detection in power facilities, focusing on evaluating the detection accuracy as a performance metric. We propose a novel LSTM-based fault detection framework that utilizes historical operational data to identify abnormal patterns indicative of faults or anomalies. The framework is trained on labeled data to learn the normal operational behavior of the power facility, enabling it to detect deviations from expected patterns in practical data streams. To assess the effectiveness of the proposed approach, extensive experiments are conducted using real-world operational data from diverse power facilities. We systematically evaluate the detection accuracy of the LSTM-based fault detection system under various operating conditions, including different types of faults and levels of noise in the data. Comparative analyses are performed against traditional fault detection methods to demonstrate the superiority of the LSTM-based approach in terms of accuracy. Moreover, sensitivity analyses are conducted to investigate the impact of key parameters, such as network architecture and training data size, on the detection performance. The results illustrate the robustness and effectiveness of the proposed LSTM-based fault detection framework, highlighting its potential for enhancing the reliability and efficiency of power facility operations.

Sign Language Detection Using Action Recognition LSTM Deep Learning Model

Sign language serves as a vital communication medium for the Deaf and Hard of Hearing (DHH) community, yet its recognition by computational systems remains a complex challenge. This research paper presents a novel approach to sign language detection utilizing action recognition principles through a Long Short-Term Memory (LSTM) deep learning model. Leveraging the temporal dynamics and sequential nature of sign language gestures, the LSTM model is trained to accurately identify and classify signs from video data. The proposed system processes video sequences to extract key frame features, which are then input into the LSTM network. The model's architecture is designed to capture the temporal dependencies and nuanced movements characteristic of sign language. We utilize a comprehensive dataset comprising diverse sign language gestures to train and evaluate the model. Our experimental results demonstrate that the LSTM-based approach achieves high accuracy in sign language detection, outperforming traditional static frame-based methods. The system's performance is evaluated through various metrics, including precision, recall, and F1-score, showcasing its robustness in real-world scenarios. Keywords: Gesture Recognition, Deep Learning(DL), Sign Language Recognition(SLR), TensorFlow, Matplotlib, Mediapipe, opencv-python, numpy.

A Transformer and LSTM-Based Approach for Blind Well Lithology Prediction

Petrographic prediction is crucial in identifying target areas and understanding reservoir lithology in oil and gas exploration. Traditional logging methods often rely on manual interpretation and experiential judgment, which can introduce subjectivity and constraints due to data quality and geological variability. To enhance the precision and efficacy of lithology prediction, this study employed a Savitzky–Golay filter with a symmetric window for anomaly data processing, coupled with a residual temporal convolutional network (ResTCN) model tasked with completing missing logging data segments. A comparative analysis against the support vector regression and random forest regression model revealed that the ResTCN achieves the smallest MAE, at 0.030, and the highest coefficient of determination, at 0.716, which are indicative of its proximity to the ground truth. These methodologies significantly enhance the quality of the training data. Subsequently, a Transformer–long short-term memory (T-LS) model was applied to identify and classify the lithology of unexplored wells. The input layer of the Transformer model follows an embedding-like principle for data preprocessing, while the encoding block encompasses multi-head attention, Add & Norm, and feedforward components, integrating the multi-head attention mechanism. The output layer interfaces with the LSTM layer through dropout. A performance evaluation of the T-LS model against established rocky prediction techniques such as logistic regression, k-nearest neighbor, and random forest demonstrated its superior identification and classification capabilities. Specifically, the T-LS model achieved a precision of 0.88 and a recall of 0.89 across nine distinct lithology features. A Shapley analysis of the T-LS model underscored the utility of amalgamating multiple logging data sources for lithology classification predictions. This advancement partially addresses the challenges associated with imprecise predictions and limited generalization abilities inherent in traditional machine learning and deep learning models applied to lithology identification, and it also helps to optimize oil and gas exploration and development strategies and improve the efficiency of resource extraction.

Detection of Questions from Text Data Using LSTM-Deep Learning Model

This paper discusses the importance of detecting questions in textual data for various applications in natural language processing (NLP), such as question answering and chatbot creation. The proposed approach employs long short-term memory (LSTM) models to accurately identify questions by leveraging the sequential nature of language.The paper highlights that LSTM models address challenges like ambiguous language and varying sentence structures. They allow the model to learn from sequential patterns, crucial for understanding the intent behind the text. The preprocessing steps, including tokenization, embedding, and padding, are detailed to prepare the data for training and testing. The study investigates the impact of hyperparameters like hidden layers, hidden states, and optimizer choice on the LSTM algorithm’s performance. In experiments on benchmark datasets, the proposed LSTM-based approach consistently outperforms conventional machine learning models, achieving a remarkable accuracy of 99.25% on the test dataset. The paper concludes by suggesting future directions, including applyingthe approach to other NLP tasks like named entity recognition, sentiment analysis, and text classification. Further optimization for specific datasets or domains is also encouraged. Overall, this research contributes to robust question detection models in NLP, with potential applications in various fields.

Time-aware MADDPG with LSTM for multi-agent obstacle avoidance: a comparative study

AbstractIntelligent agents and multi-agent systems are increasingly used in complex scenarios, such as controlling groups of drones and non-player characters in video games. In these applications, multi-agent navigation and obstacle avoidance are foundational functions. However, problems become more challenging with the increased complexity of the environment and the dynamic decision-making interactions among agents. The Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm is a classical multi-agent reinforcement learning algorithm successfully used to improve agents’ performance. However, it ignores the temporal message hidden in agents’ interaction with the environment and needs to be more efficient in scenarios with many agents due to its training technique. To address the limitations of MADDPG, we propose to explore modified algorithms of MADDPG for multi-agent navigation and obstacle avoidance. By combining MADDPG with Long Short-Term Memory (LSTM), we obtain the MADDPG-LSTMactor algorithm, which leverages continuous observations over time as input for the policy network, enabling the LSTM layer to capture hidden temporal patterns. Moreover, by simplifying the input of the critic network, we obtain the MADDPG-L algorithm for efficiency improvement in scenarios with many agents. Experimental results demonstrate that these algorithms outperform existing networks in the OpenAI multi-agent particle environment. We also conducted a comparative study of the LSTM-based approach with Transformer and self-attention models in the task of multi-agent navigation and obstacle avoidance. The results reveal that Transformer and self-attention do not consistently outperform LSTM. The LSTM-based model exhibits a favorable tradeoff across varying sequence lengths. Overall, this work addresses the limitations of MADDPG in multi-agent navigation and obstacle avoidance tasks, providing insights for developing intelligent agents and multi-agent systems.

Detecting cyberbullying text using the approaches with machine learning models for the low-resource Bengali language

The rising usage of social media sites and the advances in communication technologies have led to a considerable increase in cyberbullying events. Here, people are intimidated, harassed, and humiliated via digital messaging. To identify cyberbullying texts, several research have been undertaken in English and other languages with abundant resources, but relatively few studies have been conducted in low-resource languages like Bengali. This research focuses on Bengali text to find cyberbullying material by experimenting with pre-processing, feature selection, and three types of machine learning (ML) models: classical ML, deep learning (DL), and transformer learning. In classical ML, four models, support vector machine (SVM), multinomial Naive Bayes (MNB), random forest (RF), and logistic regression (LR) are used. In DL, three models, long short term memory (LSTM), Bidirectional LSTM, and convolutional neural network with bidirectional LSTM (CNN-BiLSTM) are employed. As the transformerbased pre-trained model, bidirectional encoder representations from transformers (BERT) is utilized. Using our proposed pre-processing tasks, the MNB-based approach achieves the best accuracy of 78.816% among the other classical ML models, the LSTM-based approach gains the highest result of 77.804% accuracy among the DL models, and the BERT-based approach outperforms both with 80.165% accuracy.

Harnessing Cognitively Inspired Predictive Models to Improve Investment Decision-Making

In the last years, researchers and practitioners have focused on defining portfolio optimization approaches. This task aims to identify a suitable distribution of assets for maximizing profits and minimizing risks, also offering protection against unexpected market behaviors. Nevertheless, the state-of-the-art approaches encounter significant limitations due to the complex nature of the task: (1) forecasting of non-stationary, non-linearity and volatile stock price; (2) budget allocation over different stocks satisfying multi-objective objective function; (3) risk costs can significantly affect the effectiveness of the designed approaches. In this paper, we propose a cognitively inspired framework for portfolio optimization by integrating deep learning-based stock forecasting for maximizing the revenue and portfolio diversification and Shape Ratio for minimizing the risk. Furthermore, the cognitively inspired forecasting module relies on the LSTM-based approach which combines historical financial data and technical indicators. Hence, this approach addresses the portfolio optimization task with the aim of designing more and more cognitive agents that perform autonomous actions for supporting decision-making. To make these agents cognitive, we further integrate stock forecasting into the portfolio optimization model, also investigating the main factors affecting both stock forecasting and portfolio optimization tasks. The proposed framework has been evaluated in two stages on a real-world dataset, composed of four years of information about stocks from six different areas. Firstly, we compare the proposed forecasting models based on LSTM and GRU, pointing out that the former achieves higher effectiveness results although the latter has a shorter training time. Finally, the proposed framework has been compared with different baselines, obtaining a net difference of $168 at the maximum. Finally, we compare the proposed approach w.r.t. several baselines in terms of total revenue, also providing an ablation analysis to investigate how stock prediction might support investors in dealing with portfolio optimization task.

Recurrent Neural Networks and Three-Point Bending Test on the Identification of Material Hardening Parameters

The continuous evolution of metallic alloys in the automotive industry has led to the development of more advanced and flexible constitutive models that attempt to accurately describe the various fundamental properties and behavior of these materials. These models have become increasingly complex, incorporating a larger number of parameters that require an accurate calibration procedure to fit the constitutive parameters with experimental data. In this context, machine learning (ML) methodologies have the potential to advance material constitutive modeling, enhancing the efficiency of the material parameter calibration procedure. Recurrent neural networks (RNNs) stand out among various learning algorithms due to their ability to process sequential data and overcome limitations imposed by nonlinearities and multiple parameters involved in phenomenological models. This study explores the modeling capabilities of long short-term memory (LSTM) structures, a type of RNN, in predicting the hardening behavior of a sheet metal material using the results of a standardized experimental three-point bending test, with the aim of extending this methodology to other experimental tests and constitutive models. Additionally, a variable analysis is performed to select the most important variables for this experimental test and assess the influence of friction, material thickness, and elastic and plastic properties on the accuracy of predictions made by neural networks. The required data for designing and training the network solutions are collected from numerical simulations using finite element methodology (FEM), which are subsequently validated by experiments. The results demonstrate that the proposed LSTM-based approach outperforms traditional identification techniques in predicting the material hardening parameters. This suggests that the developed procedure can be effectively applied to efficiently characterize different materials, especially those extensively used in industrial applications, ranging from mild steels to advanced high-strength steels.

An LSTM-based approach to detect transition to lean blowout in swirl-stabilized dump combustion systems

Lean combustion is environment friendly with low NOX emissions providing better fuel efficiency in a combustion system. However, approaching towards lean combustion can make engines more susceptible to an undesirable phenomenon called lean blowout (LBO) that can cause flame extinction leading to sudden loss of power. During the design stage, it is quite challenging for the scientists to accurately determine the optimal operating limits to avoid sudden LBO occurrences. Therefore, it is crucial to develop accurate and computationally tractable frameworks for online LBO prediction in low NOX emission engines. To the best of our knowledge, for the first time, we propose a deep learning approach to detect the transition to LBO in combustion systems. In this work, we utilize a laboratory-scale swirl-stabilized combustor to collect acoustic data for different protocols. For each protocol, starting far from LBO, we gradually move towards the LBO regime, capturing a quasi-static time series dataset at different conditions. Using one of the protocols in our dataset as the reference protocol, we find a transition state metric for our trained deep learning model to detect the imminent LBO in other test protocols. We find that our proposed approach is more precise and computationally faster than other baseline models to detect the transition to LBO. Therefore, we endorse this technique for monitoring the operation of lean combustion engines in real time.

LSTM-Based Approach for Stable Identification of Modal Damping Ratio in Building Structures

Modal parameters are used as safety assessment indicators for evaluating the structural integrity of buildings in various ways. In particular, the modal damping ratio plays a crucial role in accurately predicting the serviceability and safety of buildings, starting from the initial design stage. However, the identification results of the modal damping ratio can become unstable due to measurement time, initial configuration conditions used in the analysis, and nonstationary responses included in the structural response. To address the instability issue, this study proposes a long short-term memory-based frequency domain decomposition (FDD-LSTM) method. The FDD-LSTM method utilizes the acceleration response of the building as input data and the modal damping ratio obtained from the FDD method as output data, constructing an LSTM network model for the relationship between the acceleration response and modal damping ratio. The FDD-LSTM method exhibited a discrepancy of less than 0.02% compared to the reference value of the modal damping ratio obtained through free vibration response. Furthermore, when applied to data acquired from an actual building, the method demonstrated a variance of approximately 5%. The proposed FDD-LSTM method is validated for stability performance using a three-degree-of-freedom numerical analysis model, a 3-story steel frame structure model, and a 117-story high-rise building. The FDD-LSTM method, trained on a large dataset, enables generalized estimation and addresses instability issues related to modal damping ratio.

Early Energy Consumption Prediction as a Key Element in Smart City Sustainability

In the era of smart cities, the pursuit of sustainability stands as a paramount goal, with energy management playing a central role. This paper is dedicated to the exploration of early energy consumption prediction as a linchpin in the realization of sustainable smart cities. Employing advanced long short-term memory (LSTM) networks, we introduce a potent predictive model tailored to anticipate energy consumption patterns within urban environments. Notably, our model achieves remarkable performance metrics, with a root mean square error of 547.71 and a strikingly low mean absolute percentage error (MAPE) of 1.22. Through meticulous comparisons against baseline models, our LSTM-based approach emerges as a beacon of accuracy, reliability, and sustainability. Beyond predictive analytics, our research offers actionable insights for urban planners and policymakers, fostering the creation of greener, more sustainable, and ecologically responsible smart cities that harmonize technological innovation with environmental stewardship. As smart cities continue to evolve, our work lays the foundation for a future where sustainability is not merely a goal but a reality.

A Novel Scheduling Algorithm for Improved Performance of Multi-Objective Safety-Critical Wireless Sensor Networks Using Long Short-Term Memory

The multiple objective optimisation (MOO) challenges encountered in the context of wireless sensor networks (WSNs) present a formidable NP-hard problem. These issues primarily arise from the constraints imposed by critical factors such as connectivity, coverage, and, most notably, energy consumption. Simultaneously fulfilling these three requirements is no longer considered the standard approach for enhancing system dependability. To illustrate, a prospective solution may optimise one or two of these requirements while bolstering overall network energy efficiency. Nonetheless, prior endeavours documented in the extant literature reveal unexplored avenues for enhancement. Hence, this paper introduces a new methodology aimed at alleviating MOO concerns and thereby enhancing the quality of service (QoS) in WSNs. A long short-term memory (LSTM) model is proposed as an analytical tool to deliver an energy-efficient scheduling solution that aligns and optimises WSN parameters, striving to attain the most favourable system performance. The LSTM algorithm’s effectiveness is assessed through the iterative application of periods, confirming the desired QoS levels. The unique feature of LSTM lies in its capability to observe specific event sequences and subsequently establish them as the system’s default configuration for its entire operational lifespan. Once these favourable parameters are identified, LSTM automatically ensures consistent service availability and reliability throughout the network’s lifespan. The results obtained demonstrate the superiority of the proposed LSTM-based scheduling algorithm in comparison to the self-organising map (SOFM)-based node scheduling algorithm. The LSTM-based approach outperforms the SOFM-based alternative by a remarkable 75% in terms of coverage and exhibits a 20% enhancement in network lifetime, all while maintaining equivalent levels of connectivity (i.e., 99%) in both algorithms.

A deep learning LSTM-based approach for forecasting annual pollen curves: Olea and Urticaceae pollen types as a case study

Airborne pollen can trigger allergic rhinitis and other respiratory diseases in the synthesised population, which makes it one of the most relevant biological contaminants. Therefore, implementing accurate forecast systems is a priority for public health. The current forecast models are generally useful, but they falter when long time series of data are managed. The emergence of new computational techniques such as the LSTM algorithms could constitute a significant improvement for the pollen risk assessment. In this study, several LSTM variants were applied to forecast monthly pollen integrals in Málaga (southern Spain) using meteorological variables as predictors. Olea and Urticaceae pollen types were modelled as proxies of different annual pollen curves, using data from the period 1992–2022. The aims of this study were to determine the LSTM variants with the highest accuracy when forecasting monthly pollen integrals as well as to compare their performance with the traditional pollen forecast methods. The results showed that the CNN-LSTM were the most accurate when forecasting the monthly pollen integrals for both pollen types. Moreover, the traditional forecast methods were outperformed by all the LSTM variants. These findings highlight the importance of implementing LSTM models in pollen forecasting for public health and research applications.

Deep Learning for Software Defect Prediction: An LSTM-based Approach

Software defect prediction is an important aspect of software development, as it helps developers and organizations to identify and resolve bugs in the software before they become major issues. In this paper, we explore the use of machine learning algorithms for software defect prediction. We discuss the different types of machine learning algorithms that have been used for software defect prediction and their advantages and disadvantages. We also provide a comprehensive review of recent studies that have used machine learning algorithms for software defect prediction. The paper concludes with a discussion of the challenges and opportunities in using machine learning algorithms for software defect prediction and the future directions of research in this field. This paper surveys the existing literature on software defect prediction, focusing specifically on deep learning techniques. Compared to existing surveys on the topic, this paper offers a more in-depth analysis of the strengths and weaknesses of deep learning approaches for software defect prediction. It explores the use of LSTMs for this task, which have not been extensively studied in previous surveys. Additionally, this paper provides a comprehensive review of recent research in the field, highlighting the most promising deep learning models and techniques for software defect prediction. The results of this survey demonstrate that LSTM-based deep learning models can outperform traditional machine learning approaches and achieve state-of-the-art results in software defect prediction. Furthermore, this paper provides insights into the challenges and limitations of deep learning approaches for software defect prediction, highlighting areas for future research and improvement. Overall, this paper offers a valuable resource for researchers and practitioners interested in using deep learning techniques for software defect prediction..

Deep Learning for Software Defect Prediction: An LSTM-based Approach

Software defect prediction is an important aspect of software development, as it helps developers and organizations to identify and resolve bugs in the software before they become major issues. In this paper, we explore the use of machine learning algorithms for software defect prediction. We discuss the different types of machine learning algorithms that have been used for software defect prediction and their advantages and disadvantages. We also provide a comprehensive review of recent studies that have used machine learning algorithms for software defect prediction. The paper concludes with a discussion of the challenges and opportunities in using machine learning algorithms for software defect prediction and the future directions of research in this field. This paper surveys the existing literature on software defect prediction, focusing specifically on deep learning techniques. Compared to existing surveys on the topic, this paper offers a more in-depth analysis of the strengths and weaknesses of deep learning approaches for software defect prediction. It explores the use of LSTMs for this task, which have not been extensively studied in previous surveys. Additionally, this paper provides a comprehensive review of recent research in the field, highlighting the most promising deep learning models and techniques for software defect prediction. The results of this survey demonstrate that LSTM-based deep learning models can outperform traditional machine learning approaches and achieve state-of-the-art results in software defect prediction. Furthermore, this paper provides insights into the challenges and limitations of deep learning approaches for software defect prediction, highlighting areas for future research and improvement. Overall, this paper offers a valuable resource for researchers and practitioners interested in using deep learning techniques for software defect prediction..