Mayada Hadhoud - Academia.edu (original) (raw)

Papers by Mayada Hadhoud

Alexandria Engineering Journal, 2022

Studies in Computational Intelligence, 2021

Journal of Al-Azhar University Engineering Sector, 2018

2019 15th International Computer Engineering Conference (ICENCO)

This paper presents an approach for constructing ontology automatically from web pages thus migra... more This paper presents an approach for constructing ontology automatically from web pages thus migrating data from web into ontology. The proposed approach can be applied to web pages in any domain. It is a step towards utilizing the huge amount of data published on the web to automatically build ontology. The proposed approach first extracts the triples from web page. Next it utilizes natural language processing techniques to process the extracted triples. Finally it applies ontology design patterns before inserting triples into ontology. WEB2ONTO is compared with only fully automatic work (as our knowledge) and the results show that WEB2ONTO is close to cover all the information in the documents correctly. WEB2ONTO is better at reducing repeat rate where it doesn't insert the same object twice and doesn't repeat the relation between two concepts. Also WEB2ONTO ontology is simpler representation than other work.

European Journal of Engineering Science and Technology, 2019

Neuroevolution has been used to train neural networks for challenging deep Reinforcement Learning... more Neuroevolution has been used to train neural networks for challenging deep Reinforcement Learning (RL) problems like Atari, image hard maze, and humanoid locomotion. The performance is comparable to the performance of neural networks trained by algorithms like Q-learning and policy gradients. This work conducts a detailed comparative study of using neuroevolution algorithms in solving the self-driving car problem. Different neuroevolution algorithms are used to train deep neural networks to predict the steering angle of a car in a simulated environment. Neuroevolution algorithms are compared to the Double Deep Q-Learning (DDQN) algorithm. Based on the experimental results, the neuroevolution algorithms show better performance than DDQN algorithm. The Evolutionary Strategies (ES) algorithm outperforms the rest in accuracy in driving in the middle of the lane, with the best average result of 97.13%. Moreover, the Random Search (RS) algorithm outperforms the rest in terms of driving th...

ArXiv, 2021

Instance segmentation has gained recently huge attention in various computer vision applications.... more Instance segmentation has gained recently huge attention in various computer vision applications. It aims at providing different IDs to different objects of the scene, even if they belong to the same class. Instance segmentation is usually performed as a two-stage pipeline. First, an object is detected, then semantic segmentation within the detected box area is performed which involves costly up-sampling. In this paper, we propose Insta-YOLO, a novel one-stage end-to-end deep learning model for real-time instance segmentation. Instead of pixel-wise prediction, our model predicts instances as object contours represented by 2D points in Cartesian space. We evaluate our model on three datasets, namely, Carvana, Cityscapes and Airbus. We compare our results to the state-of-the-art models for instance segmentation. The results show our model achieves competitive accuracy in terms of mAP at twice the speed on GTX-1080 GPU.

The increasing deployment of the Convolutional Neural Networks (CNNs) in computer vision algorith... more The increasing deployment of the Convolutional Neural Networks (CNNs) in computer vision algorithms is because of the high accuracy of CNNs in image recognition jobs which makes CNNs of dominant use, but the huge number of parameters inside the CNN puts hurdles against the ease of deployment of the CNN in embedded systems, IoT chips and even mobile devices. Huge number of parameters means excessive computations and storage requirements which makes it infeasible to use in hardware chips with limited resources. In this paper a new hybrid algorithm for CNNs compression is proposed. This new algorithm combines pruning, quantization and compression techniques which are used to reduce the huge size of different CNNs while maintaining a similar accuracy percentage. The proposed algorithm is to combine the use of genetic algorithms (GA) to conduct the selection criteria of pruning of convolutional layers only and applying conventional pruning to the fully connected layers, Finally applying ...

Proceedings of the 11th International Joint Conference on Computational Intelligence, 2019

Dynamic flexible job shop scheduling is an optimization problem concerned with job assignment in ... more Dynamic flexible job shop scheduling is an optimization problem concerned with job assignment in dynamic production environments where future job arrivals are unknown. Job scheduling systems employ a pair of rules: a routing rule which assigns a machine to process an operation and a sequencing rule which determines the order of operation processing. Since hand-crafted rules can be time and effort-consuming, many papers employ genetic programming to generate optimum rule trees from a set of terminals and operators. Since the terminal set can be large, the search space can be huge and inefficient to explore. Feature selection techniques can reduce the terminal set size without discarding important information and they have shown to be effective for improving rule generation for dynamic job shop scheduling. In this paper, we extend a niching-based feature selection technique to fit the requirements of dynamic flexible job shop scheduling. The results show that our method can generate rules that achieves significantly better performance compared to ones generated from the full feature set.

Deep learning for procedural level generation has been explored in many recent works, however, ex... more Deep learning for procedural level generation has been explored in many recent works, however, experimental comparisons with previous works are either nonexistent or limited to the works they extend upon. This paper’s goal is to conduct an experimental study on four recent deep learning procedural level generation methods for Sokoban (size = 7 × 7) to explore their strengths and weaknesses and provide insights for possible research directions. The methods will be bootstrapping conditional generative models, controllable & uncontrollable procedural content generation via reinforcement learning (PCGRL) and generative playing networks. We will propose some modifications to either adapt the methods to the task or improve their efficiency and performance. For the bootstrapping method, we propose using diversity sampling to improve the solution diversity, auxiliary targets to enhance the models’ quality and Gaussian mixture models to improve the sample quality. The results show that diver...

Alexandria Engineering Journal, 2022

Studies in Computational Intelligence, 2021

Journal of Al-Azhar University Engineering Sector, 2018

2019 15th International Computer Engineering Conference (ICENCO)

This paper presents an approach for constructing ontology automatically from web pages thus migra... more This paper presents an approach for constructing ontology automatically from web pages thus migrating data from web into ontology. The proposed approach can be applied to web pages in any domain. It is a step towards utilizing the huge amount of data published on the web to automatically build ontology. The proposed approach first extracts the triples from web page. Next it utilizes natural language processing techniques to process the extracted triples. Finally it applies ontology design patterns before inserting triples into ontology. WEB2ONTO is compared with only fully automatic work (as our knowledge) and the results show that WEB2ONTO is close to cover all the information in the documents correctly. WEB2ONTO is better at reducing repeat rate where it doesn't insert the same object twice and doesn't repeat the relation between two concepts. Also WEB2ONTO ontology is simpler representation than other work.

European Journal of Engineering Science and Technology, 2019

Neuroevolution has been used to train neural networks for challenging deep Reinforcement Learning... more Neuroevolution has been used to train neural networks for challenging deep Reinforcement Learning (RL) problems like Atari, image hard maze, and humanoid locomotion. The performance is comparable to the performance of neural networks trained by algorithms like Q-learning and policy gradients. This work conducts a detailed comparative study of using neuroevolution algorithms in solving the self-driving car problem. Different neuroevolution algorithms are used to train deep neural networks to predict the steering angle of a car in a simulated environment. Neuroevolution algorithms are compared to the Double Deep Q-Learning (DDQN) algorithm. Based on the experimental results, the neuroevolution algorithms show better performance than DDQN algorithm. The Evolutionary Strategies (ES) algorithm outperforms the rest in accuracy in driving in the middle of the lane, with the best average result of 97.13%. Moreover, the Random Search (RS) algorithm outperforms the rest in terms of driving th...

ArXiv, 2021

Instance segmentation has gained recently huge attention in various computer vision applications.... more Instance segmentation has gained recently huge attention in various computer vision applications. It aims at providing different IDs to different objects of the scene, even if they belong to the same class. Instance segmentation is usually performed as a two-stage pipeline. First, an object is detected, then semantic segmentation within the detected box area is performed which involves costly up-sampling. In this paper, we propose Insta-YOLO, a novel one-stage end-to-end deep learning model for real-time instance segmentation. Instead of pixel-wise prediction, our model predicts instances as object contours represented by 2D points in Cartesian space. We evaluate our model on three datasets, namely, Carvana, Cityscapes and Airbus. We compare our results to the state-of-the-art models for instance segmentation. The results show our model achieves competitive accuracy in terms of mAP at twice the speed on GTX-1080 GPU.

The increasing deployment of the Convolutional Neural Networks (CNNs) in computer vision algorith... more The increasing deployment of the Convolutional Neural Networks (CNNs) in computer vision algorithms is because of the high accuracy of CNNs in image recognition jobs which makes CNNs of dominant use, but the huge number of parameters inside the CNN puts hurdles against the ease of deployment of the CNN in embedded systems, IoT chips and even mobile devices. Huge number of parameters means excessive computations and storage requirements which makes it infeasible to use in hardware chips with limited resources. In this paper a new hybrid algorithm for CNNs compression is proposed. This new algorithm combines pruning, quantization and compression techniques which are used to reduce the huge size of different CNNs while maintaining a similar accuracy percentage. The proposed algorithm is to combine the use of genetic algorithms (GA) to conduct the selection criteria of pruning of convolutional layers only and applying conventional pruning to the fully connected layers, Finally applying ...

Proceedings of the 11th International Joint Conference on Computational Intelligence, 2019

Dynamic flexible job shop scheduling is an optimization problem concerned with job assignment in ... more Dynamic flexible job shop scheduling is an optimization problem concerned with job assignment in dynamic production environments where future job arrivals are unknown. Job scheduling systems employ a pair of rules: a routing rule which assigns a machine to process an operation and a sequencing rule which determines the order of operation processing. Since hand-crafted rules can be time and effort-consuming, many papers employ genetic programming to generate optimum rule trees from a set of terminals and operators. Since the terminal set can be large, the search space can be huge and inefficient to explore. Feature selection techniques can reduce the terminal set size without discarding important information and they have shown to be effective for improving rule generation for dynamic job shop scheduling. In this paper, we extend a niching-based feature selection technique to fit the requirements of dynamic flexible job shop scheduling. The results show that our method can generate rules that achieves significantly better performance compared to ones generated from the full feature set.

Deep learning for procedural level generation has been explored in many recent works, however, ex... more Deep learning for procedural level generation has been explored in many recent works, however, experimental comparisons with previous works are either nonexistent or limited to the works they extend upon. This paper’s goal is to conduct an experimental study on four recent deep learning procedural level generation methods for Sokoban (size = 7 × 7) to explore their strengths and weaknesses and provide insights for possible research directions. The methods will be bootstrapping conditional generative models, controllable & uncontrollable procedural content generation via reinforcement learning (PCGRL) and generative playing networks. We will propose some modifications to either adapt the methods to the task or improve their efficiency and performance. For the bootstrapping method, we propose using diversity sampling to improve the solution diversity, auxiliary targets to enhance the models’ quality and Gaussian mixture models to improve the sample quality. The results show that diver...