Hathal Alwageed - Academia.edu (original) (raw)

Papers by Hathal Alwageed

Research paper thumbnail of Securing Software Development through People Maturity: A Fuzzy-AHP Decision Making Framework

Research paper thumbnail of Software reliability assessment: An architectural and component impact analysis

Tsinghua science and technology/Tsinghua Science and Technology, 2024

Research paper thumbnail of A High-Capacity Optical Metro Access Network: Efficiently Recovering Fiber Failures with Robust Switching and Centralized Optical Line Terminal

Sensors, Feb 7, 2024

This study proposes and presents a new central office (CO) for the optical metro access network (... more This study proposes and presents a new central office (CO) for the optical metro access network (OMAN) with an affordable and distinctive switching system. The CO's foundation is built upon a novel optical multicarrier (OMC) generation technique. This technique provides numerous frequency carriers that are characterized by a high tone-to-noise ratio (TNR) of 40 dB and minimal amplitude excursions. The purpose is to accommodate multiple users at the optical network unit side in the optical metropolitan area network (OMAN). The OMC generation is achieved through a cascaded configuration involving a single phase and two Mach Zehnder modulators without incorporating optical or electrical amplifiers or filters. The proposed OMC is installed in the CO of the OMAN to support the 1.2 Tbps downlink and 600 Gbps uplink transmission, with practical bit error rate (BER) ranges from 10 -3 to 10 -13 for the downlink and 10 -6 to 10 -14 for the uplink transmission. Furthermore, in the OMAN's context, optical fiber failure is a main issue. Therefore, we have proposed a possible solution for ensuring uninterrupted communication without any disturbance in various scenarios of main optical fiber failures. This demonstrates how this novel CO can rapidly recover transmission failures through robust switching a and centralized OLT. The proposed system is intended to provide users with a reliable and affordable service while maintaining high-quality transmission rates.

Research paper thumbnail of Optimization and Analysis of Spectral/Spatial Optical Code Division Multiple Access Passive Optical Network

AEU - International Journal of Electronics and Communications, Jan 31, 2024

Research paper thumbnail of A Data-Driven Artificial Neural Network Approach to Software Project Risk Assessment

IET Software, Dec 18, 2023

Research paper thumbnail of Efficient optical fiber communication in the metro access domain based on an optical multicarrier source

Microwave and Optical Technology Letters, Aug 30, 2023

Research paper thumbnail of Feasibility analysis of 2-dimensional permutation vector optical code division multiple access passive optical network

Research paper thumbnail of Modulation Classification Based on Signal Constellation Diagrams and Deep Learning

IEEE transactions on neural networks and learning systems, Mar 1, 2019

Deep learning (DL) is a new machine learning (ML) methodology that has found successful implement... more Deep learning (DL) is a new machine learning (ML) methodology that has found successful implementations in many application domains. However, its usage in communications systems has not been well explored. This paper investigates the use of the DL in modulation classification, which is a major task in many communications systems. The DL relies on a massive amount of data and, for research and applications, this can be easily available in communications systems. Furthermore, unlike the ML, the DL has the advantage of not requiring manual feature selections, which significantly reduces the task complexity in modulation classification. In this paper, we use two convolutional neural network (CNN)-based DL models, AlexNet and GoogLeNet. Specifically, we develop several methods to represent modulated signals in data formats with gridlike topologies for the CNN. The impacts of representation on classification performance are also analyzed. In addition, comparisons with traditional cumulant and ML-based algorithms are presented. Experimental results demonstrate the significant performance advantage and application feasibility of the DL-based approach for modulation classification.

Research paper thumbnail of Green cloud computing adoption challenges and practices: a client’s perspective-based empirical investigation

Cognition, Technology & Work

Research paper thumbnail of A Hybrid Approach Using Survey and ISM Analysis for Security Coding Risks and Best Practices for GSD Enterprises

Global software development (GSD) offers quality results, cost-effectiveness, and uninterrupted p... more Global software development (GSD) offers quality results, cost-effectiveness, and uninterrupted project delivery. However, integrating security into GSD remains a challenge. This study aims to enhance security in GSD projects by developing a hybrid approach using an empirical survey and Interpretive Structural Model (ISM). Initially, we identified 13 major security-coding risks and 82 practices to mitigate these by conducting a systematic literature review and questionnaire survey with 50 GSD security experts. Moreover, 13 experts were invited to analyze the interrelationships among the practices using ISM. The ISM analysis revealed that out of the identified security-coding practices, “never submit security measures to illegitimate authority”, “avoiding buffer overflow and format string vulnerabilities”, “control the brute force attack”, and “identify a middleman attack” were considered fully dependent. While “avoid revealing information to achieve a secure design” is entirely inde...

Research paper thumbnail of An empirical study for prioritizing issue of software project management team

Cognition, Technology & Work

Research paper thumbnail of Investigating the Effectiveness of Novel Support Vector Neural Network for Anomaly Detection in Digital Forensics Data

Sensors

As criminal activity increasingly relies on digital devices, the field of digital forensics plays... more As criminal activity increasingly relies on digital devices, the field of digital forensics plays a vital role in identifying and investigating criminals. In this paper, we addressed the problem of anomaly detection in digital forensics data. Our objective was to propose an effective approach for identifying suspicious patterns and activities that could indicate criminal behavior. To achieve this, we introduce a novel method called the Novel Support Vector Neural Network (NSVNN). We evaluated the performance of the NSVNN by conducting experiments on a real-world dataset of digital forensics data. The dataset consisted of various features related to network activity, system logs, and file metadata. Through our experiments, we compared the NSVNN with several existing anomaly detection algorithms, including Support Vector Machines (SVM) and neural networks. We measured and analyzed the performance of each algorithm in terms of the accuracy, precision, recall, and F1-score. Furthermore,...

Research paper thumbnail of Dual Electro-Optic Comb Generator by Heterodyning Two Combs for Extending the Optical Bandwidth

IEEE Photonics Technology Letters

Research paper thumbnail of Green Cloud Computing Adoption Challenges and Practices: A Client's Perspective based Empirical Investigations

Context Over the last decade, the widespread adoption of cloud computing has spawned a new branch... more Context Over the last decade, the widespread adoption of cloud computing has spawned a new branch of the computing industry, known as green cloud computing. Cloud computing is improving, and data centers are increasing at regular frequencies to meet the demands of users. Cloud providers, on the other hand, pose major environmental risks because massive data centers use a large amount of energy and leave a carbon footprint. One possible solution to this issue is the use of green cloud computing. However, clients face significant difficulties in adopting green cloud computing. Objective This study aims to understand the problems faced by client organizations while considering green cloud computing. In addition, this study aims to empirically identify the solution to the challenges faced by green cloud computing practitioners. Method A questionnaire survey approach was used to get insight into green cloud computing practitioners concerning the challenges they faced and their solutions....

Research paper thumbnail of Prediction of Cardiovascular Disease on Self-Augmented Datasets of Heart Patients Using Multiple Machine Learning Models

Journal of Sensors, Dec 23, 2022

About 26 million people worldwide experience its effects each year. Both cardiologists and surgeo... more About 26 million people worldwide experience its effects each year. Both cardiologists and surgeons have a tough time determining when heart failure will occur. Classification and prediction models applied to medical data allow for enhanced insight. Improved heart failure projection is a major goal of the research team using the heart disease dataset. The probability of heart failure is predicted using data mined from a medical database and processed by machine learning methods. It has been shown, through the use of this study and a comparative analysis, that heart disease may be predicted with high precision. In this study, researchers developed a machine learning model to improve the accuracy with which diseases like heart failure (HF) may be predicted. To rank the accuracy of linear models, we find that logistic regression (82.76 percent), SVM (67.24 percent), KNN (60.34 percent), GNB (79.31 percent), and MNB (72.41) perform best. These models are all examples of ensemble learning, with the most accurate being ET (70.31%), RF (87.03%), and GBC (86.21%). DT (ensemble learning models) achieves the highest degree of precision. CatBoost outperforms LGBM, HGBC, and XGB, all of which achieve 84.48% accuracy or better, while XGB achieves 84.48% accuracy using a gradient-based gradient method (GBG). LGBM has the highest accuracy rate (86.21 percent) (hypertuned ensemble learning models). A statistical analysis of all available algorithms found that CatBoost, random forests, and gradient boosting provided the most reliable results for predicting future heart attacks.

Research paper thumbnail of Real-Time Detection Schemes for Memory DoS (M-DoS) Attacks on Cloud Computing Applications

IEEE Access

Memory Denial of Service (M-DoS) attacks refer to a class of cyber-attacks that aim to exhaust th... more Memory Denial of Service (M-DoS) attacks refer to a class of cyber-attacks that aim to exhaust the memory resources of a system, rendering it unavailable to legitimate users. This type of attack is particularly dangerous in cloud computing environments, where multiple users share the same resources. Detection and mitigation of M-DoS attacks in real-time is a challenging task, as they often involve a large number of low-rate requests, making it difficult to distinguish them from legitimate traffic. Several real-time detection schemes have been proposed to identify and mitigate M-DoS attacks in cloud computing environments. These schemes can be broadly classified into two categories: signature-based and anomaly-based detection. Signature-based detection methods rely on the identification of specific patterns or characteristics of known M-DoS attack techniques, while anomaly-based detection methods identify abnormal behaviour that deviates from the normal pattern of usage. This study presents a hybrid model for real-time detection of cloud and MDOS attacks using SVM-KNN-LR. The dataset used in this study was collected from various sources and pre-processed to extract relevant features for attack detection. A feature selection process was also applied to identify the most important features for attack detection. The hybrid model achieved an accuracy of 96%, outperforming other individual models such as SVM, KNN, LR, Naive Bayes, Decision Trees, Extra Trees, Bagging Trees, and Random Forests. Confusion matrices were also used to evaluate the performance of each model. In the discussion section, we examined the performance of the hybrid model in detecting MDOS attacks and found that it had a high precision score of 0.97. However, the recall score was lower at 0.87, indicating that the model was not able to detect all instances of MDOS attacks.

Research paper thumbnail of Cyber Security against Intrusion Detection Using Ensemble-Based Approaches

Security and Communication Networks

The attacks of cyber are rapidly increasing due to advanced techniques applied by hackers. Furthe... more The attacks of cyber are rapidly increasing due to advanced techniques applied by hackers. Furthermore, cyber security is demanding day by day, as cybercriminals are performing cyberattacks in this digital world. So, designing privacy and security measurements for IoT-based systems is necessary for secure network. Although various techniques of machine learning are applied to achieve the goal of cyber security, but still a lot of work is needed against intrusion detection. Recently, the concept of hybrid learning gives more attention to information security specialists for further improvement against cyber threats. In the proposed framework, a hybrid method of swarm intelligence and evolutionary for feature selection, namely, PSO-GA (PSO-based GA) is applied on dataset named CICIDS-2017 before training the model. The model is evaluated using ELM-BA based on bootstrap resampling to increase the reliability of ELM. This work achieved highest accuracy of 100% on PortScan, Sql injection...

Research paper thumbnail of Human Activity Recognition Based on Deep-Temporal Learning Using Convolution Neural Networks Features and Bidirectional Gated Recurrent Unit With Features Selection

IEEE Access

Recurrent Neural Networks (RNNs) and their variants have been demonstrated tremendous successes i... more Recurrent Neural Networks (RNNs) and their variants have been demonstrated tremendous successes in modeling sequential data such as audio processing, video processing, time series analysis, and text mining. Inspired by these facts, we propose human activity recognition technique to proceed visual data via utilizing convolution neural network (CNN) and Bidirectional-gated recurrent unit (Bi-GRU). Firstly, we extract deep features from frames sequence of human activities videos using CNN and then select most important features from the deep appearances to improve performance and decrease computational complexity of the model. Secondly, to learn temporal motions of frames sequence, we design Bi-GRU and feed those deep-important features extracted from frames sequence of human activities to Bi-GRU which learn temporal dynamics in forward and backward direction at each time step. We conduct extensive experiments on realistic videos of human activity recognition datasets YouTube11, HMDB51 and UCF101. Lastly, we compare the obtained results with existing methods to show the competence of our proposed technique. INDEX TERMS Human activity recognition, recurrent neural networks (RNNs), convolution neural networks (CNNs), bidirectional-gated recurrent unit (Bi-GRU), deep learning.

Research paper thumbnail of AHP-Based Systematic Approach to Analyzing and Evaluating Critical Success Factors and Practices for Component-Based Outsourcing Software Development

Mathematics, Oct 26, 2022

This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

Research paper thumbnail of Effect of Feature Selection on the Accuracy of Music Popularity Classification Using Machine Learning Algorithms

Electronics

This research aims to analyze the effect of feature selection on the accuracy of music popularity... more This research aims to analyze the effect of feature selection on the accuracy of music popularity classification using machine learning algorithms. The data of Spotify, the most used music listening platform today, was used in the research. In the feature selection stage, features with low correlation were removed from the dataset using the filter feature selection method. Machine learning algorithms using all features produced 95.15% accuracy, while machine learning algorithms using features selected by feature selection produced 95.14% accuracy. The features selected by feature selection were sufficient for classification of popularity in established algorithms. In addition, this dataset contains fewer features, so the computation time is shorter. The reason why Big O time complexity is lower than models constructed without feature selection is that the number of features, which is the most important parameter in time complexity, is low. The statistical analysis was performed on t...

Research paper thumbnail of Securing Software Development through People Maturity: A Fuzzy-AHP Decision Making Framework

Research paper thumbnail of Software reliability assessment: An architectural and component impact analysis

Tsinghua science and technology/Tsinghua Science and Technology, 2024

Research paper thumbnail of A High-Capacity Optical Metro Access Network: Efficiently Recovering Fiber Failures with Robust Switching and Centralized Optical Line Terminal

Sensors, Feb 7, 2024

This study proposes and presents a new central office (CO) for the optical metro access network (... more This study proposes and presents a new central office (CO) for the optical metro access network (OMAN) with an affordable and distinctive switching system. The CO's foundation is built upon a novel optical multicarrier (OMC) generation technique. This technique provides numerous frequency carriers that are characterized by a high tone-to-noise ratio (TNR) of 40 dB and minimal amplitude excursions. The purpose is to accommodate multiple users at the optical network unit side in the optical metropolitan area network (OMAN). The OMC generation is achieved through a cascaded configuration involving a single phase and two Mach Zehnder modulators without incorporating optical or electrical amplifiers or filters. The proposed OMC is installed in the CO of the OMAN to support the 1.2 Tbps downlink and 600 Gbps uplink transmission, with practical bit error rate (BER) ranges from 10 -3 to 10 -13 for the downlink and 10 -6 to 10 -14 for the uplink transmission. Furthermore, in the OMAN's context, optical fiber failure is a main issue. Therefore, we have proposed a possible solution for ensuring uninterrupted communication without any disturbance in various scenarios of main optical fiber failures. This demonstrates how this novel CO can rapidly recover transmission failures through robust switching a and centralized OLT. The proposed system is intended to provide users with a reliable and affordable service while maintaining high-quality transmission rates.

Research paper thumbnail of Optimization and Analysis of Spectral/Spatial Optical Code Division Multiple Access Passive Optical Network

AEU - International Journal of Electronics and Communications, Jan 31, 2024

Research paper thumbnail of A Data-Driven Artificial Neural Network Approach to Software Project Risk Assessment

IET Software, Dec 18, 2023

Research paper thumbnail of Efficient optical fiber communication in the metro access domain based on an optical multicarrier source

Microwave and Optical Technology Letters, Aug 30, 2023

Research paper thumbnail of Feasibility analysis of 2-dimensional permutation vector optical code division multiple access passive optical network

Research paper thumbnail of Modulation Classification Based on Signal Constellation Diagrams and Deep Learning

IEEE transactions on neural networks and learning systems, Mar 1, 2019

Deep learning (DL) is a new machine learning (ML) methodology that has found successful implement... more Deep learning (DL) is a new machine learning (ML) methodology that has found successful implementations in many application domains. However, its usage in communications systems has not been well explored. This paper investigates the use of the DL in modulation classification, which is a major task in many communications systems. The DL relies on a massive amount of data and, for research and applications, this can be easily available in communications systems. Furthermore, unlike the ML, the DL has the advantage of not requiring manual feature selections, which significantly reduces the task complexity in modulation classification. In this paper, we use two convolutional neural network (CNN)-based DL models, AlexNet and GoogLeNet. Specifically, we develop several methods to represent modulated signals in data formats with gridlike topologies for the CNN. The impacts of representation on classification performance are also analyzed. In addition, comparisons with traditional cumulant and ML-based algorithms are presented. Experimental results demonstrate the significant performance advantage and application feasibility of the DL-based approach for modulation classification.

Research paper thumbnail of Green cloud computing adoption challenges and practices: a client’s perspective-based empirical investigation

Cognition, Technology & Work

Research paper thumbnail of A Hybrid Approach Using Survey and ISM Analysis for Security Coding Risks and Best Practices for GSD Enterprises

Global software development (GSD) offers quality results, cost-effectiveness, and uninterrupted p... more Global software development (GSD) offers quality results, cost-effectiveness, and uninterrupted project delivery. However, integrating security into GSD remains a challenge. This study aims to enhance security in GSD projects by developing a hybrid approach using an empirical survey and Interpretive Structural Model (ISM). Initially, we identified 13 major security-coding risks and 82 practices to mitigate these by conducting a systematic literature review and questionnaire survey with 50 GSD security experts. Moreover, 13 experts were invited to analyze the interrelationships among the practices using ISM. The ISM analysis revealed that out of the identified security-coding practices, “never submit security measures to illegitimate authority”, “avoiding buffer overflow and format string vulnerabilities”, “control the brute force attack”, and “identify a middleman attack” were considered fully dependent. While “avoid revealing information to achieve a secure design” is entirely inde...

Research paper thumbnail of An empirical study for prioritizing issue of software project management team

Cognition, Technology & Work

Research paper thumbnail of Investigating the Effectiveness of Novel Support Vector Neural Network for Anomaly Detection in Digital Forensics Data

Sensors

As criminal activity increasingly relies on digital devices, the field of digital forensics plays... more As criminal activity increasingly relies on digital devices, the field of digital forensics plays a vital role in identifying and investigating criminals. In this paper, we addressed the problem of anomaly detection in digital forensics data. Our objective was to propose an effective approach for identifying suspicious patterns and activities that could indicate criminal behavior. To achieve this, we introduce a novel method called the Novel Support Vector Neural Network (NSVNN). We evaluated the performance of the NSVNN by conducting experiments on a real-world dataset of digital forensics data. The dataset consisted of various features related to network activity, system logs, and file metadata. Through our experiments, we compared the NSVNN with several existing anomaly detection algorithms, including Support Vector Machines (SVM) and neural networks. We measured and analyzed the performance of each algorithm in terms of the accuracy, precision, recall, and F1-score. Furthermore,...

Research paper thumbnail of Dual Electro-Optic Comb Generator by Heterodyning Two Combs for Extending the Optical Bandwidth

IEEE Photonics Technology Letters

Research paper thumbnail of Green Cloud Computing Adoption Challenges and Practices: A Client's Perspective based Empirical Investigations

Context Over the last decade, the widespread adoption of cloud computing has spawned a new branch... more Context Over the last decade, the widespread adoption of cloud computing has spawned a new branch of the computing industry, known as green cloud computing. Cloud computing is improving, and data centers are increasing at regular frequencies to meet the demands of users. Cloud providers, on the other hand, pose major environmental risks because massive data centers use a large amount of energy and leave a carbon footprint. One possible solution to this issue is the use of green cloud computing. However, clients face significant difficulties in adopting green cloud computing. Objective This study aims to understand the problems faced by client organizations while considering green cloud computing. In addition, this study aims to empirically identify the solution to the challenges faced by green cloud computing practitioners. Method A questionnaire survey approach was used to get insight into green cloud computing practitioners concerning the challenges they faced and their solutions....

Research paper thumbnail of Prediction of Cardiovascular Disease on Self-Augmented Datasets of Heart Patients Using Multiple Machine Learning Models

Journal of Sensors, Dec 23, 2022

About 26 million people worldwide experience its effects each year. Both cardiologists and surgeo... more About 26 million people worldwide experience its effects each year. Both cardiologists and surgeons have a tough time determining when heart failure will occur. Classification and prediction models applied to medical data allow for enhanced insight. Improved heart failure projection is a major goal of the research team using the heart disease dataset. The probability of heart failure is predicted using data mined from a medical database and processed by machine learning methods. It has been shown, through the use of this study and a comparative analysis, that heart disease may be predicted with high precision. In this study, researchers developed a machine learning model to improve the accuracy with which diseases like heart failure (HF) may be predicted. To rank the accuracy of linear models, we find that logistic regression (82.76 percent), SVM (67.24 percent), KNN (60.34 percent), GNB (79.31 percent), and MNB (72.41) perform best. These models are all examples of ensemble learning, with the most accurate being ET (70.31%), RF (87.03%), and GBC (86.21%). DT (ensemble learning models) achieves the highest degree of precision. CatBoost outperforms LGBM, HGBC, and XGB, all of which achieve 84.48% accuracy or better, while XGB achieves 84.48% accuracy using a gradient-based gradient method (GBG). LGBM has the highest accuracy rate (86.21 percent) (hypertuned ensemble learning models). A statistical analysis of all available algorithms found that CatBoost, random forests, and gradient boosting provided the most reliable results for predicting future heart attacks.

Research paper thumbnail of Real-Time Detection Schemes for Memory DoS (M-DoS) Attacks on Cloud Computing Applications

IEEE Access

Memory Denial of Service (M-DoS) attacks refer to a class of cyber-attacks that aim to exhaust th... more Memory Denial of Service (M-DoS) attacks refer to a class of cyber-attacks that aim to exhaust the memory resources of a system, rendering it unavailable to legitimate users. This type of attack is particularly dangerous in cloud computing environments, where multiple users share the same resources. Detection and mitigation of M-DoS attacks in real-time is a challenging task, as they often involve a large number of low-rate requests, making it difficult to distinguish them from legitimate traffic. Several real-time detection schemes have been proposed to identify and mitigate M-DoS attacks in cloud computing environments. These schemes can be broadly classified into two categories: signature-based and anomaly-based detection. Signature-based detection methods rely on the identification of specific patterns or characteristics of known M-DoS attack techniques, while anomaly-based detection methods identify abnormal behaviour that deviates from the normal pattern of usage. This study presents a hybrid model for real-time detection of cloud and MDOS attacks using SVM-KNN-LR. The dataset used in this study was collected from various sources and pre-processed to extract relevant features for attack detection. A feature selection process was also applied to identify the most important features for attack detection. The hybrid model achieved an accuracy of 96%, outperforming other individual models such as SVM, KNN, LR, Naive Bayes, Decision Trees, Extra Trees, Bagging Trees, and Random Forests. Confusion matrices were also used to evaluate the performance of each model. In the discussion section, we examined the performance of the hybrid model in detecting MDOS attacks and found that it had a high precision score of 0.97. However, the recall score was lower at 0.87, indicating that the model was not able to detect all instances of MDOS attacks.

Research paper thumbnail of Cyber Security against Intrusion Detection Using Ensemble-Based Approaches

Security and Communication Networks

The attacks of cyber are rapidly increasing due to advanced techniques applied by hackers. Furthe... more The attacks of cyber are rapidly increasing due to advanced techniques applied by hackers. Furthermore, cyber security is demanding day by day, as cybercriminals are performing cyberattacks in this digital world. So, designing privacy and security measurements for IoT-based systems is necessary for secure network. Although various techniques of machine learning are applied to achieve the goal of cyber security, but still a lot of work is needed against intrusion detection. Recently, the concept of hybrid learning gives more attention to information security specialists for further improvement against cyber threats. In the proposed framework, a hybrid method of swarm intelligence and evolutionary for feature selection, namely, PSO-GA (PSO-based GA) is applied on dataset named CICIDS-2017 before training the model. The model is evaluated using ELM-BA based on bootstrap resampling to increase the reliability of ELM. This work achieved highest accuracy of 100% on PortScan, Sql injection...

Research paper thumbnail of Human Activity Recognition Based on Deep-Temporal Learning Using Convolution Neural Networks Features and Bidirectional Gated Recurrent Unit With Features Selection

IEEE Access

Recurrent Neural Networks (RNNs) and their variants have been demonstrated tremendous successes i... more Recurrent Neural Networks (RNNs) and their variants have been demonstrated tremendous successes in modeling sequential data such as audio processing, video processing, time series analysis, and text mining. Inspired by these facts, we propose human activity recognition technique to proceed visual data via utilizing convolution neural network (CNN) and Bidirectional-gated recurrent unit (Bi-GRU). Firstly, we extract deep features from frames sequence of human activities videos using CNN and then select most important features from the deep appearances to improve performance and decrease computational complexity of the model. Secondly, to learn temporal motions of frames sequence, we design Bi-GRU and feed those deep-important features extracted from frames sequence of human activities to Bi-GRU which learn temporal dynamics in forward and backward direction at each time step. We conduct extensive experiments on realistic videos of human activity recognition datasets YouTube11, HMDB51 and UCF101. Lastly, we compare the obtained results with existing methods to show the competence of our proposed technique. INDEX TERMS Human activity recognition, recurrent neural networks (RNNs), convolution neural networks (CNNs), bidirectional-gated recurrent unit (Bi-GRU), deep learning.

Research paper thumbnail of AHP-Based Systematic Approach to Analyzing and Evaluating Critical Success Factors and Practices for Component-Based Outsourcing Software Development

Mathematics, Oct 26, 2022

This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

Research paper thumbnail of Effect of Feature Selection on the Accuracy of Music Popularity Classification Using Machine Learning Algorithms

Electronics

This research aims to analyze the effect of feature selection on the accuracy of music popularity... more This research aims to analyze the effect of feature selection on the accuracy of music popularity classification using machine learning algorithms. The data of Spotify, the most used music listening platform today, was used in the research. In the feature selection stage, features with low correlation were removed from the dataset using the filter feature selection method. Machine learning algorithms using all features produced 95.15% accuracy, while machine learning algorithms using features selected by feature selection produced 95.14% accuracy. The features selected by feature selection were sufficient for classification of popularity in established algorithms. In addition, this dataset contains fewer features, so the computation time is shorter. The reason why Big O time complexity is lower than models constructed without feature selection is that the number of features, which is the most important parameter in time complexity, is low. The statistical analysis was performed on t...