Saroj Gopali
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Saroj Gopali has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Akbar Siami Namin
Department of Computer Science, Texas Tech University, Lubbock, TX, USA
8 shared publications - Faranak Abri
Department of Computer Science San Jose State University USA
4 shared publications - Keith S. Jones
Department of Psychological Sciences, Texas Tech University, Lubbock, TX, USA
2 shared publications Akbar S. Namin
Department of Computer Science, Texas Tech University, Lubbock, Texas, United States
1 shared publicationBabafela Awosile
Texas Tech University School of Veterinary Medicine, Amarillo, TX, United States
1 shared publication- Bimal Karki
Department of Computer Science 2 Texas Tech University
1 shared publication
Latest Publications
- Open Access
- 19 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 84016-84066
ACT: A Conceptual Framework for Understanding and Controlling Trustworthiness in Controllable AI
With the rapid advancement of AI and foundation models, several research directions have emerged which are active research focuses contributing to advancing and stabilizing the next generation of cutting-edge AI technologies. Instances of such research efforts are being explored through various concepts such as AI Alignment, Explainable AI and Transparency, AI Compliance, AI Ethics, Constitutional AI, and notably Controllable AI. Although the needs for all these research concepts and focuses are well-justified, there is little known how these areas contribute to trustworthiness in AI and whether there is any overlap or missing research gaps that need to be explored for addressing the hard-core research problems and concerns in trustworthy AI. Furthermore, it is also primitive to understand how trustworthiness can be addressed in the context of “agentic AI”, and more notably “controllable AI” where LLM-powered agents collaboratively reason and decide about workflows and tasks without human’s intervention. The key idea is that while “agentic AI” offers sophisticated technology and paradigm for the next generations of computing, the trustworthiness of such fascinating technology is still in its infancy, and therefore controllability of such agentic AI technology needs to be explored. This conceptual article intends to explore and view the research focuses in AI (e.g., AI Alignment, Explainability) in accordance with AI trustworthiness. More specifically, the work compares and contrasts these conceptual concepts with respect to the NIST Trustworthy AI framework that embodies seven criteria that include safety, security, explainability, privacy, fairness, validity, and accountability. The article provides a conceptual mapping between each of these concepts and the trustworthiness criteria listed in the NIST trustworthy framework. The paper introduces ACT, an Active framework for controlling trustworthiness criteria in AI systems.
- 19 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 84016-84066
Open AccessACT: A Conceptual Framework for Understanding and Controlling Trustworthiness in Controllable AI
With the rapid advancement of AI and foundation models, several research directions have emerged which are active research focuses contributing to advancing and stabilizing the next generation of cutting-edge AI technologies. Instances of such research efforts are being explored through various concepts such as AI Alignment, Explainable AI and Transparency, AI Compliance, AI Ethics, Constitutional AI, and notably Controllable AI. Although the needs for all these research concepts and focuses are well-justified, there is little known how these areas contribute to trustworthiness in AI and whether there is any overlap or missing research gaps that need to be explored for addressing the hard-core research problems and concerns in trustworthy AI. Furthermore, it is also primitive to understand how trustworthiness can be addressed in the context of “agentic AI”, and more notably “controllable AI” where LLM-powered agents collaboratively reason and decide about workflows and tasks without human’s intervention. The key idea is that while “agentic AI” offers sophisticated technology and paradigm for the next generations of computing, the trustworthiness of such fascinating technology is still in its infancy, and therefore controllability of such agentic AI technology needs to be explored. This conceptual article intends to explore and view the research focuses in AI (e.g., AI Alignment, Explainability) in accordance with AI trustworthiness. More specifically, the work compares and contrasts these conceptual concepts with respect to the NIST Trustworthy AI framework that embodies seven criteria that include safety, security, explainability, privacy, fairness, validity, and accountability. The article provides a conceptual mapping between each of these concepts and the trustworthiness criteria listed in the NIST trustworthy framework. The paper introduces ACT, an Active framework for controlling trustworthiness criteria in AI systems.
- Open Access
- 10 December 2025
- Published by Frontiers Media SA in Frontiers in Veterinary Science
- Vol. 12
A data privacy and deep learning based AMR dashboard for rural and regional veterinary practices in Texas
Antimicrobial resistance (AMR) grows as a major worldwide health threat which affects treatment of both human and veterinary medicine. Practitioners working in rural and regional veterinary offices throughout Texas face difficulties obtaining real-time data tools which support making antimicrobial treatment decisions. This study introduces an AI-driven dashboard to address veterinary medicine needs by utilizing real-world AMR data collected over 14 years from veterinary labs throughout Texas. The dashboard employs deep learning models along with Long Short-Term Memory (LSTM) and Prophet with Recurrent Neural Networks (RNN) for prediction tasks and data imputation so practitioners can access insights utilizing visual elements such as heatmaps, Sankey plots, and MIC distributions and susceptibility tables. The dashboard empowers veterinarians with predictive analytics to perform empirical treatment selection and monitor resistance patterns to improve antimicrobial stewardship. Additionally, the dashboard integrates privacy-preserving fingerprinting techniques using steganographic marks, ensuring secure data sharing without compromising utility. Our novel approach addresses critical gaps in veterinary AMR data analysis, supporting antimicrobial stewardship and public health efforts through One Health frameworks. The findings demonstrate AI has proven its capacity to transform evidence-based veterinary medicine through data integrity and privacy.
- 10 December 2025
- Published by Frontiers Media SA in Frontiers in Veterinary Science
- Vol. 12
Open AccessA data privacy and deep learning based AMR dashboard for rural and regional veterinary practices in Texas
Antimicrobial resistance (AMR) grows as a major worldwide health threat which affects treatment of both human and veterinary medicine. Practitioners working in rural and regional veterinary offices throughout Texas face difficulties obtaining real-time data tools which support making antimicrobial treatment decisions. This study introduces an AI-driven dashboard to address veterinary medicine needs by utilizing real-world AMR data collected over 14 years from veterinary labs throughout Texas. The dashboard employs deep learning models along with Long Short-Term Memory (LSTM) and Prophet with Recurrent Neural Networks (RNN) for prediction tasks and data imputation so practitioners can access insights utilizing visual elements such as heatmaps, Sankey plots, and MIC distributions and susceptibility tables. The dashboard empowers veterinarians with predictive analytics to perform empirical treatment selection and monitor resistance patterns to improve antimicrobial stewardship. Additionally, the dashboard integrates privacy-preserving fingerprinting techniques using steganographic marks, ensuring secure data sharing without compromising utility. Our novel approach addresses critical gaps in veterinary AMR data analysis, supporting antimicrobial stewardship and public health efforts through One Health frameworks. The findings demonstrate AI has proven its capacity to transform evidence-based veterinary medicine through data integrity and privacy.
- Open Access
IoT Malware Network Traffic Detection using Deep Learning and GraphSAGE Models
This paper intends to detect IoT malicious attacks through deep learning models and demonstrates a comprehensive evaluation of the deep learning and graph-based models regarding malicious network traffic detection. The models particularly are based on GraphSAGE, Bidirectional encoder representations from transformers (BERT), Temporal Convolutional Network (TCN) as well as Multi-Head Attention, together with Bidirectional Long Short-Term Memory (BI-LSTM) Multi-Head Attention and BI-LSTM and LSTM models. The chosen models demonstrated great performance to model temporal patterns and detect feature significance. The observed performance are mainly due to the fact that IoT system traffic patterns are both sequential and diverse, leaving a rich set of temporal patterns for the models to learn. Experimental results showed that BERT maintained the best performance. It achieved 99.94% accuracy rate alongside high precision and recall, F1-score and AUC-ROC score of 99.99% which demonstrates its capabilities through temporal dependency capture. The Multi-Head Attention offered promising results by providing good detection capabilities with interpretable results. On the other side, the Multi-Head Attention model required significant processing time like BI-LSTM variants. The GraphSAGE model achieved good accuracy while requiring the shortest training time but yielded the lowest accuracy, precision, and F1 score compared to the other models
Open AccessIoT Malware Network Traffic Detection using Deep Learning and GraphSAGE Models
This paper intends to detect IoT malicious attacks through deep learning models and demonstrates a comprehensive evaluation of the deep learning and graph-based models regarding malicious network traffic detection. The models particularly are based on GraphSAGE, Bidirectional encoder representations from transformers (BERT), Temporal Convolutional Network (TCN) as well as Multi-Head Attention, together with Bidirectional Long Short-Term Memory (BI-LSTM) Multi-Head Attention and BI-LSTM and LSTM models. The chosen models demonstrated great performance to model temporal patterns and detect feature significance. The observed performance are mainly due to the fact that IoT system traffic patterns are both sequential and diverse, leaving a rich set of temporal patterns for the models to learn. Experimental results showed that BERT maintained the best performance. It achieved 99.94% accuracy rate alongside high precision and recall, F1-score and AUC-ROC score of 99.99% which demonstrates its capabilities through temporal dependency capture. The Multi-Head Attention offered promising results by providing good detection capabilities with interpretable results. On the other side, the Multi-Head Attention model required significant processing time like BI-LSTM variants. The GraphSAGE model achieved good accuracy while requiring the shortest training time but yielded the lowest accuracy, precision, and F1 score compared to the other models
- Open Access
- 27 November 2024
- Published by Elsevier in Natural Language Processing Journal
- Vol. 9
The performance of the LSTM-based code generated by Large Language Models (LLMs) in forecasting time series data
- 27 November 2024
- Published by Elsevier in Natural Language Processing Journal
- Vol. 9
Open AccessThe performance of the LSTM-based code generated by Large Language Models (LLMs) in forecasting time series data
- Open Access
The Performance of the LSTM-based Code Generated by Large Language Models (LLMs) in Forecasting Time Series Data
As an intriguing case is the goodness of the machine and deep learning models generated by these LLMs in conducting automated scientific data analysis, where a data analyst may not have enough expertise in manually coding and optimizing complex deep learning models and codes and thus may opt to leverage LLMs to generate the required models. This paper investigates and compares the performance of the mainstream LLMs, such as ChatGPT, PaLM, LLama, and Falcon, in generating deep learning models for analyzing time series data, an important and popular data type with its prevalent applications in many application domains including financial and stock market. This research conducts a set of controlled experiments where the prompts for generating deep learning-based models are controlled with respect to sensitivity levels of four criteria including 1) Clarify and Specificity, 2) Objective and Intent, 3) Contextual Information, and 4) Format and Style. While the results are relatively mix, we observe some distinct patterns. We notice that using LLMs, we are able to generate deep learning-based models with executable codes for each dataset seperatly whose performance are comparable with the manually crafted and optimized LSTM models for predicting the whole time series dataset. We also noticed that ChatGPT outperforms the other LLMs in generating more accurate models. Furthermore, we observed that the goodness of the generated models vary with respect to the ``temperature'' parameter used in configuring LLMS. The results can be beneficial for data analysts and practitioners who would like to leverage generative AIs to produce good prediction models with acceptable goodness.
Open AccessThe Performance of the LSTM-based Code Generated by Large Language Models (LLMs) in Forecasting Time Series Data
As an intriguing case is the goodness of the machine and deep learning models generated by these LLMs in conducting automated scientific data analysis, where a data analyst may not have enough expertise in manually coding and optimizing complex deep learning models and codes and thus may opt to leverage LLMs to generate the required models. This paper investigates and compares the performance of the mainstream LLMs, such as ChatGPT, PaLM, LLama, and Falcon, in generating deep learning models for analyzing time series data, an important and popular data type with its prevalent applications in many application domains including financial and stock market. This research conducts a set of controlled experiments where the prompts for generating deep learning-based models are controlled with respect to sensitivity levels of four criteria including 1) Clarify and Specificity, 2) Objective and Intent, 3) Contextual Information, and 4) Format and Style. While the results are relatively mix, we observe some distinct patterns. We notice that using LLMs, we are able to generate deep learning-based models with executable codes for each dataset seperatly whose performance are comparable with the manually crafted and optimized LSTM models for predicting the whole time series dataset. We also noticed that ChatGPT outperforms the other LLMs in generating more accurate models. Furthermore, we observed that the goodness of the generated models vary with respect to the ``temperature'' parameter used in configuring LLMS. The results can be beneficial for data analysts and practitioners who would like to leverage generative AIs to produce good prediction models with acceptable goodness.
- Open Access
- 18 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 136451-136465
The Applicability of LLMs in Generating Textual Samples for Analysis of Imbalanced Datasets
In machine learning class imbalance is a pressing issue, where the model is biased towards the majority classes and underperforms in the minority classes. In textual data, the natural language processing (NLP) model bias significantly reduces overall accuracy, along with poor performance in minority classes. This paper investigates and compares the performance of transformer-based models, such as Multi-head Attention with the data levels and algorithmic levels approaches and BERT (Bidirectional Encoder Representations from Transformers) with LLM-based data augmentation. The research utilized the approaches, such as Random Over Sampler, Synthetic Minority Over-sampling Technique (SMOTE), SMOTEENN, data augmentation at word level, class weights, L2 regularization and leveraging GPT-3.5-Turbo’s for data augmentation to create additional data samples in imbalance dataset. The results from the experiment demonstrate that the LLM-based data augmentation with Multi-head Attention and BERT in the Myers-Briggs Type Indicator (MBTI) dataset (a highly skewed dataset) achieves the highest precision, recall and F1 score of 0.76 across terms. It indicates that the LLM-based data augmentation has significant improvements in dealing with class imbalance and improves the model’s accuracy in minority class types in the MBTI dataset.
- 18 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 136451-136465
Open AccessThe Applicability of LLMs in Generating Textual Samples for Analysis of Imbalanced Datasets
In machine learning class imbalance is a pressing issue, where the model is biased towards the majority classes and underperforms in the minority classes. In textual data, the natural language processing (NLP) model bias significantly reduces overall accuracy, along with poor performance in minority classes. This paper investigates and compares the performance of transformer-based models, such as Multi-head Attention with the data levels and algorithmic levels approaches and BERT (Bidirectional Encoder Representations from Transformers) with LLM-based data augmentation. The research utilized the approaches, such as Random Over Sampler, Synthetic Minority Over-sampling Technique (SMOTE), SMOTEENN, data augmentation at word level, class weights, L2 regularization and leveraging GPT-3.5-Turbo’s for data augmentation to create additional data samples in imbalance dataset. The results from the experiment demonstrate that the LLM-based data augmentation with Multi-head Attention and BERT in the Myers-Briggs Type Indicator (MBTI) dataset (a highly skewed dataset) achieves the highest precision, recall and F1 score of 0.76 across terms. It indicates that the LLM-based data augmentation has significant improvements in dealing with class imbalance and improves the model’s accuracy in minority class types in the MBTI dataset.
- Open Access
- 21 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 155423-155436
A Comparative Multivariate Analysis of VAR and Deep Learning-Based Models for Forecasting Volatile Time Series Data
The existing literature on forecasting time series data is primarily based on univariate analysis and techniques such as Univariate Autoregressive (UAR), Univariate Moving Average (UMA), Simple Exponential Smoothing (SES), deep learning models, and, most notably, univariate Long Short-Term Memory (LSTM) built based on univariate variable where the next lag of time series is leveraged for forecasting the next cycle of data. This paper takes this line of research to the next level by focusing on forecasting time series data based on “multivariate” modeling and analysis. To have a better insight of the performance of various deep learning-based models when multivariate analysis is performed, the paper builds and reports the forecasting accuracy for techniques such as the Transformer-based Multi-head Attention network, Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BI-LSTM), Temporal Convolution Network (TCN), and conventional Vector Autoregressive (VAR) models. The findings revealed that the TCN model achieved the average lowest RMSE values of 0.0589 for stock data and 0.1554 for cryptocurrency data. Notably, the Multi-Head Attention model achieved average R 2 values of 0.92 for stock data and −1.98 for cryptocurrency data with respect to five variables (i.e., open, high, low, close and volume). According to the empirical studies conducted and reported in this paper, the transformer-based Multi-head Attention network outperformed other models such as LSTM, BI-LSTM, and more importantly conventional Vector Auto-Regression Models (VAR) in stocks and cryptocurrencies time series data where several variables were leveraged in building these multivariate-based models.
- 21 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 155423-155436
Open AccessA Comparative Multivariate Analysis of VAR and Deep Learning-Based Models for Forecasting Volatile Time Series Data
The existing literature on forecasting time series data is primarily based on univariate analysis and techniques such as Univariate Autoregressive (UAR), Univariate Moving Average (UMA), Simple Exponential Smoothing (SES), deep learning models, and, most notably, univariate Long Short-Term Memory (LSTM) built based on univariate variable where the next lag of time series is leveraged for forecasting the next cycle of data. This paper takes this line of research to the next level by focusing on forecasting time series data based on “multivariate” modeling and analysis. To have a better insight of the performance of various deep learning-based models when multivariate analysis is performed, the paper builds and reports the forecasting accuracy for techniques such as the Transformer-based Multi-head Attention network, Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BI-LSTM), Temporal Convolution Network (TCN), and conventional Vector Autoregressive (VAR) models. The findings revealed that the TCN model achieved the average lowest RMSE values of 0.0589 for stock data and 0.1554 for cryptocurrency data. Notably, the Multi-Head Attention model achieved average R 2 values of 0.92 for stock data and −1.98 for cryptocurrency data with respect to five variables (i.e., open, high, low, close and volume). According to the empirical studies conducted and reported in this paper, the transformer-based Multi-head Attention network outperformed other models such as LSTM, BI-LSTM, and more importantly conventional Vector Auto-Regression Models (VAR) in stocks and cryptocurrencies time series data where several variables were leveraged in building these multivariate-based models.
- Open Access
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1064-1066
The Performance of Sequential Deep Learning Models in Detecting Phishing Websites Using Contextual Features of URLs
Cyber attacks continue to pose significant threats to individuals and organizations, stealing sensitive data such as personally identifiable information, financial information, and login credentials. Hence, detecting malicious websites before they cause any harm is critical to preventing fraud and monetary loss. To address the increasing number of phishing attacks, protective mechanisms must be highly responsive, adaptive, and scalable. Fortunately, advances in the field of machine learning, coupled with access to vast amounts of data, have led to the adoption of various deep learning models for timely detection of these cyber crimes. This study focuses on the detection of phishing websites using deep learning models such as Multi-Head Attention, Temporal Convolutional Network (TCN), BI-LSTM, and LSTM where URLs of the phishing websites are treated as a sequence. The results demonstrate that Multi-Head Attention and BI-LSTM model outperform some other deep learning-based algorithms such as TCN and LSTM in producing better precision, recall, and F1-scores.
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1064-1066
Open AccessThe Performance of Sequential Deep Learning Models in Detecting Phishing Websites Using Contextual Features of URLs
Cyber attacks continue to pose significant threats to individuals and organizations, stealing sensitive data such as personally identifiable information, financial information, and login credentials. Hence, detecting malicious websites before they cause any harm is critical to preventing fraud and monetary loss. To address the increasing number of phishing attacks, protective mechanisms must be highly responsive, adaptive, and scalable. Fortunately, advances in the field of machine learning, coupled with access to vast amounts of data, have led to the adoption of various deep learning models for timely detection of these cyber crimes. This study focuses on the detection of phishing websites using deep learning models such as Multi-Head Attention, Temporal Convolutional Network (TCN), BI-LSTM, and LSTM where URLs of the phishing websites are treated as a sequence. The results demonstrate that Multi-Head Attention and BI-LSTM model outperform some other deep learning-based algorithms such as TCN and LSTM in producing better precision, recall, and F1-scores.
- Open Access
A Survey on Blockchain-Based Federated Learning and Data Privacy
Federated learning is a decentralized machine learning paradigm that allows multiple clients to collaborate by leveraging local computational power and the models transmission. This method reduces the costs and privacy concerns associated with centralized machine learning methods while ensuring data privacy by distributing training data across heterogeneous devices. On the other hand, federated learning has the drawback of data leakage due to the lack of privacy-preserving mechanisms employed during storage, transfer, and sharing, thus posing significant risks to data owners and suppliers. Blockchain technology has emerged as a promising technology for offering secure data-sharing platforms in federated learning, especially in Industrial Internet of Things (IIoT) settings. This survey aims to compare the performance and security of various data privacy mechanisms adopted in blockchain-based federated learning architectures. We conduct a systematic review of existing literature on secure data-sharing platforms for federated learning provided by blockchain technology, providing an in-depth overview of blockchain-based federated learning, its essential components, and discussing its principles, and potential applications. The primary contribution of this survey paper is to identify critical research questions and propose potential directions for future research in blockchain-based federated learning.
Open AccessA Survey on Blockchain-Based Federated Learning and Data Privacy
Federated learning is a decentralized machine learning paradigm that allows multiple clients to collaborate by leveraging local computational power and the models transmission. This method reduces the costs and privacy concerns associated with centralized machine learning methods while ensuring data privacy by distributing training data across heterogeneous devices. On the other hand, federated learning has the drawback of data leakage due to the lack of privacy-preserving mechanisms employed during storage, transfer, and sharing, thus posing significant risks to data owners and suppliers. Blockchain technology has emerged as a promising technology for offering secure data-sharing platforms in federated learning, especially in Industrial Internet of Things (IIoT) settings. This survey aims to compare the performance and security of various data privacy mechanisms adopted in blockchain-based federated learning architectures. We conduct a systematic review of existing literature on secure data-sharing platforms for federated learning provided by blockchain technology, providing an in-depth overview of blockchain-based federated learning, its essential components, and discussing its principles, and potential applications. The primary contribution of this survey paper is to identify critical research questions and propose potential directions for future research in blockchain-based federated learning.
- Open Access
- 6 October 2022
- Published by MDPI AG in Electronics
- Vol. 11 (19) , 3205
Deep Learning-Based Time-Series Analysis for Detecting Anomalies in Internet of Things
Anomaly detection in time-series data is an integral part in the context of the Internet of Things (IoT). In particular, with the advent of sophisticated deep and machine learning-based techniques, this line of research has attracted many researchers to develop more accurate anomaly detection algorithms. The problem itself has been a long-lasting challenging problem in security and especially in malware detection and data tampering. The advancement of the IoT paradigm as well as the increasing number of cyber attacks on the networks of the Internet of Things worldwide raises the concern of whether flexible and simple yet accurate anomaly detection techniques exist. In this paper, we investigate the performance of deep learning-based models including recurrent neural network-based Bidirectional LSTM (BI-LSTM), Long Short-Term Memory (LSTM), CNN-based Temporal Convolutional (TCN), and CuDNN-LSTM, which is a fast LSTM implementation supported by CuDNN. In particular, we assess the performance of these models with respect to accuracy and the training time needed to build such models. According to our experiment, using different timestamps (i.e., 15, 20, and 30 min), we observe that in terms of performance, the CuDNN-LSTM model outperforms other models, whereas in terms of training time, the TCN-based model is trained faster. We report the results of experiments in comparing these four models with various look-back values.
- 6 October 2022
- Published by MDPI AG in Electronics
- Vol. 11 (19) , 3205
Open AccessDeep Learning-Based Time-Series Analysis for Detecting Anomalies in Internet of Things
Anomaly detection in time-series data is an integral part in the context of the Internet of Things (IoT). In particular, with the advent of sophisticated deep and machine learning-based techniques, this line of research has attracted many researchers to develop more accurate anomaly detection algorithms. The problem itself has been a long-lasting challenging problem in security and especially in malware detection and data tampering. The advancement of the IoT paradigm as well as the increasing number of cyber attacks on the networks of the Internet of Things worldwide raises the concern of whether flexible and simple yet accurate anomaly detection techniques exist. In this paper, we investigate the performance of deep learning-based models including recurrent neural network-based Bidirectional LSTM (BI-LSTM), Long Short-Term Memory (LSTM), CNN-based Temporal Convolutional (TCN), and CuDNN-LSTM, which is a fast LSTM implementation supported by CuDNN. In particular, we assess the performance of these models with respect to accuracy and the training time needed to build such models. According to our experiment, using different timestamps (i.e., 15, 20, and 30 min), we observe that in terms of performance, the CuDNN-LSTM model outperforms other models, whereas in terms of training time, the TCN-based model is trained faster. We report the results of experiments in comparing these four models with various look-back values.