Papers by Shawkat Guirguis
Face Detection Based on Skin Color Segmentation and SVM Classification
2008 Second International Conference on Secure System Integration and Reliability Improvement, 2008
This paper proposes an improved version of our previously introduced face detection system based ... more This paper proposes an improved version of our previously introduced face detection system based on skin color segmentation and neural networks. The new system uses a support vector machine (SVM) based method for verification.
Journal of Advanced Research in Applied Sciences and Engineering Technology, Feb 28, 2024
To train a machine to "sense" a users' feelings through writings (sentiment analysis) has become ... more To train a machine to "sense" a users' feelings through writings (sentiment analysis) has become a crucial process in several domains: marketing, research, surveys and more. Nevertheless in times of crisis like COVID. Typo is one of the underestimated challenges processing user-generated text (comments, tweets, ..etc), it affects both learning and evaluation processes. Word tokenization outcome changes drastically even with a single character change, hence as expected, experiments have shown significant accuracy decreases due to typo. Adding a spelling correction as preprocessing layer, building one for every language, is a very time and resources expensive solution, a huge challenge against large data and real-time processing. Alternatively, a CNN model consuming the same text, once tokenized on characters level and once on words level while inducing typo, showed that as the typo percentage approaches 10% of the text, the results with characters tokens surpasses words tokens. Finally, on %30 typo of the text, the model consuming characters tokenization outperformed itself with the word level by a significant %22.3 in accuracy and %24.9 in F1-Score, using the same exact model. This approach in solving the inevitable typo challenge in NLP proved to be of significant practicality, saving huge resources versus using a spelling-correction model beforehand. It also removes a blocker challenge in front of real-time processing of user-generated text while preserving acceptable accuracy results.
European Journal of Engineering and Technology Research, Oct 3, 2022
In alignment with today's online market needs, this study is concerned with a major topic present... more In alignment with today's online market needs, this study is concerned with a major topic present in any purchasing interaction, namely price prediction. It is of critical importance to both the buyer and seller to be able to estimate the proper price of the prospective merchandise with accuracy to ensure maximum profit and avoid any possible fraud situations. The purpose of our work is to test the deep learning network used in previous literature to predict prices from image data only, on an image data set of a more complex application, namely real estate listings. Also, a hybrid model is designed to improve price prediction accuracy by combining both numerical and image data predictions. The proposed model has achieved a Mean Squared Logarithmic Error (MSLE) of 0.05 and a R² of 0.91.
Review of artificial intelligence for enhancing intrusion detection in the internet of things
Engineering Applications of Artificial Intelligence
This paper is the first attempt to improve the quality of investing in the highly volatile Egypti... more This paper is the first attempt to improve the quality of investing in the highly volatile Egyptian Stock Exchange (ESE) by combining the concepts of statistical process control and artificial intelligence. Control charts were used to construct a statistically controlled stock market prediction model to support the decision of stock investors. The suggested model is mainly based on the concepts of Case-based Reasoning (CBR) which is an artificial intelligent methodology that imitates the human problem-solving and reasoning behavior. Hit rate was applied as a performance measure of the quality of prediction for the suggested model. Results of predicting 900 next day stock predictions during January 2012 had a mean absolute prediction error of 2.096 LE and a hit ratio of 67%. After using the quality controlled process, the mean absolute prediction error was reduced to 1.92 L.E. and the hit ratio increased to 72%.
<title>Multimedia modeling of autonomous mobile robots</title>
Proceedings of SPIE, Sep 22, 1997
Modeling of autonomous mobile robots (AMRs) is sought to enable the designers to investigate vari... more Modeling of autonomous mobile robots (AMRs) is sought to enable the designers to investigate various aspects of the design before the actual implementation takes place. Simulation techniques are undoubtedly enriching the design tools, by which the designer would be able to vary the design parameters as appropriate until achieving some optimal performance point. Although they are general purpose, multimedia tools, especially authoring tools, can give the AMR designer some degree of assistance in fulfilling his simulation task as fast as possible. This rapid prototyping tool is rather cost effective, and allow the designer to interactively manipulate his design in simple steps. In this paper, a multimedia environment has been constructed to enable designers to simulate AMRs in order to investigate aspects concerning their kinematics and dynamics. It is also sought that these design experiences can be gathered and categorized in a tutoring system that could be used by practitioners and students enrolled in highly technical courses such as robotics. The rich multimedia environment can assist the learner in so many ways by devising examples, suggesting solutions and design tradeoffs that have been experienced before.
Leveraging Blockchain and Machine Learning to Improve IoT Security for Smart Cities
Lecture notes on data engineering and communications technologies, 2023
Reducing Redundant Association Rules Using Type-2 Fuzzy Logic
Studies in computational intelligence, Sep 24, 2020
Data mining (DM) is an analysis extensive data in order to gain the novel and hidden information.... more Data mining (DM) is an analysis extensive data in order to gain the novel and hidden information. DM is vital to research domains like statistics, artificial intelligence, machine learning, and soft computing. Association Rule Mining (ARM) in enormous databases is a fundamental topic of DM. Discovering frequent itemsets are an underlying process in ARM. Frequent itemsets are employed using statistical measures like Support (Sup) and Confidence (Conf). ARM is practiced to produce association rules (ARs) from frequent itemsets. Such rules reveal a connection between items in the actual world. Numerous algorithms have submitted to attain these rules. However, such algorithms suffer from troubles of redundancy and a sizable count of derived ARs, which renders algorithms inefficient and renders it complicated for end-users to grasp created rules. Due to these motives, this paper adopts the type-2 fuzzy association rules mining technique (T2FARM) to attain frequent items, locate all relationships among items and AR which fulfill minimum support (min sup) and minimum confidence (min conf) values in addition to prune redundant rules in. Empirical evaluations display that the proposed technique improves redundant rules pruning of DM compared to traditional fuzzy association rules (FARs).
Lecture notes on software engineering, 2015
Mobile ad hoc network (MANET) is a self-configuring infrastructure less network of mobile nodes c... more Mobile ad hoc network (MANET) is a self-configuring infrastructure less network of mobile nodes connected by wireless links -the union of which form a random topology. There are several IP routing protocols, with competing features, developed for wireless ad hoc networks. These protocols have varying qualities for different wireless routing aspects. It is due to this reason that choice of a correct routing protocol is critical. In this paper, two main questions are addressed. The first is 'Which routing protocol provides a better performance in mobile ad hoc Networks?' This question addresses the overall performance of each routing protocol investigated in this paper. The second question addresses the factors that influence the performance of these routing protocols. In this paper, Three protocols ad hoc on-Demand Distance Vector Routing (AODV) , Dynamic Source Routing (DSR), and Destination-Sequenced Distance Vector (DSDV) were compared in terms of Average End-to-End Delay, Average Throughput, Packet Delivery Ratio, Total Dropped Packets, and Normalized Routing Load in different environment; varying number of nodes and simulation Time. All simulation result implement at network simulator-2 (NS-2.35). Index Terms-Ad hoc on-demand distance vector routing (AODV), destination-sequenced distance vector (DSDV), dynamic source routing (DSR), and mobile ad hoc network (MANET), and network simulator 2 (NS2.35).
Hybrid Neural Predictive-Fuzzy Controller for Motorized Robot Arm
In this study, a design methodology is introduced that blends the neural predictive and fuzzy log... more In this study, a design methodology is introduced that blends the neural predictive and fuzzy logic controllers in an intelligent way developing a new intelligent hybrid controller has been achieved. In this design methodology, the fuzzy logic controller works in parallel with neural predictive controller and adjusts the output of the predictive controller in order to enhance system predicted input. The performance of our proposal controller is demonstrated on the motorized robot arm with disturbances. The simulation shows that the new hybrid neural predictive-fuzzy controller provides better system response in terms of transient and steady-state performance when compared to neural predictive or fuzzy logic controller applications. The simulation is performed on MATLAB/Simulink toolbox to illustrate the efficiency of the proposed method.
Haar Wavelet Transform of The Signal Representation of DNA Sequences
Abstract: Complex sequences of DNA nucleotides and their associated search techniques can be rela... more Abstract: Complex sequences of DNA nucleotides and their associated search techniques can be relatively simplified when presented as a digital signal. This approach applies known signal processing techniques for the analysis of genomic information. We present a set of tools ...
Journal of Soil Sciences and Agricultural Engineering (Print), Jun 1, 2005
Hybrid Neural-Fuzzy Controller for Motorized Robot Arm
Advanced Materials Research, Nov 1, 2011
In this study, a design methodology is introduced that blends the neural and fuzzy logic controll... more In this study, a design methodology is introduced that blends the neural and fuzzy logic controllers in an intelligent way developing a new intelligent hybrid controller. In this design methodology, the fuzzy logic controller works in parallel with the neural controller and adjusting the output of the neural controller. The performance of our proposed controller is demonstrated on a motorized robot arm with disturbances. The simulation results shows that the new hybrid neural -fuzzy controller provides better system response in terms of transient and steady-state performance when compared to neural or fuzzy logic controller applications. The development and implementation of the proposed controller is done using the MATLAB/Simulink toolbox to illustrate the efficiency of the proposed method.
Image security using quantum Rivest-Shamir-Adleman cryptosystem algorithm and digital watermarking
Authentication and integrity are very essential security requirements for a secure transaction. T... more Authentication and integrity are very essential security requirements for a secure transaction. To achieve these security goals, we use a combined technology of Rivest-Shamir-Adleman cryptosystem algorithm and digital watermarking. This work proposes the Rivest-Shamir-Adleman cryptosystem algorithm to work with quantum computing idea as simulation to encrypt the image and the goal of the quantum idea is to speed the process of the encryption. After that, the encrypted image is embedded in the cover image using its least significant bit. Digital watermarking is the process of embedding information into a digital signal. This paper uses the hybrid discrete wavelet transform and singular value decomposition algorithms for embedding and extracting process of digital watermarking. This scheme favorably preserves the quality for both the sender and receiver. The experimental results showed the efficiency of the proposed system in terms of time, integrity, and the authentication. The results showed the accelerate of the encryption process using RSA with quantum ideas compared with using RSA only, the results showed the histogram for both the sender or decrypted image and the receiver or the watermark image is the same. From the histogram diagrams, it is observed that they are quite similar and the difference is insignificant which the human eye cannot easily differentiate. Also the results showed the correlation coefficient between the original watermark and received watermark. The correlation coefficient has the value one if the two images are absolutely identical, has the value zero if the two images are completely uncorrelated. From the correlation coefficient results, it is observed that they are nearly one. This model maintains the image quality is good.
Data mining (DM) is an analysis extensive data in order to gain the novel and hidden information.... more Data mining (DM) is an analysis extensive data in order to gain the novel and hidden information. DM becomes vital to a lot of research domain like soft computing, artificial intelligence, statistics and machine learning. One of the important topics of DM is Association Rule Mining (ARM) in mega databases where it is used to discover frequent itemsets using statistical metrics such as support (Sup) and confidence (Conf) which is an essential process in ARM. Also ARM is practiced to produce association rules (ARs) from frequent itemsets. Such ARs reveal a link between items in the real world. Several algorithms have been submitted to achieve these ARs. However, these algorithms suffer from redundancy problems and a large number of derived ARs, which makes the algorithms ineffective and complicated them for the end users to understand the rules that were created. Because of these motives, this paper uses the type-2 fuzzy association rules mining technique (T2FARM) to achieve frequent ...
Multimedia modeling of autonomous mobile robots
SPIE Proceedings, 1997
Modeling of autonomous mobile robots (AMRs) is sought to enable the designers to investigate vari... more Modeling of autonomous mobile robots (AMRs) is sought to enable the designers to investigate various aspects of the design before the actual implementation takes place. Simulation techniques are undoubtedly enriching the design tools, by which the designer would be able to vary the design parameters as appropriate until achieving some optimal performance point. Although they are general purpose, multimedia tools, especially authoring tools, can give the AMR designer some degree of assistance in fulfilling his simulation task as fast as possible. This rapid prototyping tool is rather cost effective, and allow the designer to interactively manipulate his design in simple steps. In this paper, a multimedia environment has been constructed to enable designers to simulate AMRs in order to investigate aspects concerning their kinematics and dynamics. It is also sought that these design experiences can be gathered and categorized in a tutoring system that could be used by practitioners and students enrolled in highly technical courses such as robotics. The rich multimedia environment can assist the learner in so many ways by devising examples, suggesting solutions and design tradeoffs that have been experienced before.
WIT Transactions on Information and Communication Technologies, 1970
In this paper the problem of designing and implementing a large software system is addressed. Sev... more In this paper the problem of designing and implementing a large software system is addressed. Several considerations have been taken into account, namely : user friendliness, reliability, modiflability, maintainability and security. The case study was to model and automate the student management activities in Alexandria University, where the system has been applied to the student management section in the Faculty of Law as a model with characteristics general enough to be applicable to all faculties since the bylaws governing their activities are almost the same. The paper describes the use of CASE tools to reduce the software implementation life cycle along with ensuring sufficient software quality. during operation. Bearing in mind that the users are the employees of the student management -with little or no experience in computing -the system has been designed to be user-friendly and self-contained.
Evaluation of Tree-Based Machine Learning Algorithms for Network Intrusion Detection in the Internet of Things
IT Professional
Deeper Understanding of Software Change
IT Professional, Mar 1, 2023
Enhancing IoT security is a corner stone for building trust in its technology and driving its gro... more Enhancing IoT security is a corner stone for building trust in its technology and driving its growth. Limited resources and diversified nature of IoT devices make them vulnerable to attacks. Botnet attacks compromise the IoT systems and can pose significant security challenges. Numerous investigations have utilized machine learning and deep learning techniques to identify botnet attacks in IoT. However, achieving high detection accuracy with reasonable computational requirements is still a challenging research considering the particularity of IoT. This paper aims to analytically study the performance of the tree based machine learning in detecting botnet attacks for IoT ecosystems. Through an empirical study performed on a public botnet dataset of IoT environment, basic decision tree algorithm in addition to ensemble learning of different bagging and boosting algorithms are compared. The comparison covers two perspectives: IoT botnet detection capability and computational performanc...
Uploads
Papers by Shawkat Guirguis