Browsing by Author "Atia, Ayman"

Now showing 1 - 20 of 29

Amelio-rater: Detection and Classification of Driving Abnormal Behaviours for Automated Ratings and Real-Time Monitoring
(IEEE, 2018) El Masry, Noha; El-Dorry, Passant; El Ashram, Mariam; Atia, Ayman; Tanaka, Jiro
Real-time monitoring of the drivers may be a factor that would force them to drive safely. In this paper, we introduce a system named 'Amelio-Rater", that focuses on detection and classification of abnormal driving behaviours for automatically generating driver ratings and real-time monitoring. To reduce malicious ratings, the Amelio-rater introduces an automatic rating system which is calculated purely based on the driver's driving behaviours only. Each driver will be given his own Amelio-rater rate and a manual user rate. There are multiple types of driving abnormal behaviours monitored by the proposed system such as meandering, single weaves, sudden changing of lanes and speeding. The classification results achieved showed that the Amelio-rater reached an accuracy of 95%. Our experiments showed that the manual user rates given for the driving behaviour are not far from the rates given by Amelio-rater. Amelio-rater rates were very close to the actual rates given by the users
Anti-Bump: A Bump/Pothole Monitoring and Broadcasting System for Driver Awareness
(SPRINGER, 2013) Fekry, Mohamed; Hamdy, Aya; Atia, Ayman
This paper presents a system for bump detection and alarming system for drivers. We have presented an architecture that adopts context awareness and Bump location broadcasting to detect and save bumps locations. This system uses motion sensor to get the readings of the bump then we classify it using Dynamic Time Wrapping, Hidden Markov Model and Neural Network. We keep records for the bump location through tracking its geographic position. We developed a system that alarms the driver within appropriate profiled distance for bump occurrence. We conducted two experiments for testing the system in a street modeled architect with different kinds of bumps and potholes. The other experiment was on real street bumps. The results show that the system can detect bumps and potholes with reasonably accepted accuracy.
Applying Deep Learning to Track Food Consumption and Human Activity for Non-intrusive Blood Glucose Monitoring
(Institute of Electrical and Electronics Engineers, 04/12/2021) Samir, Mohamed Amr; Mohamed, Zeinab A; Hussein, Mona Abdelmotaleb A; Atia, Ayman
Blood glucose monitoring is a wide area of research as it plays a huge part in controlling diabetes and many of its symptoms. A common human disease 'Diabetes Mellitus' (DM), which is characterized by hyperglycemia, has a number of harmful complications. In addition, the low glucose level in blood caused by hypoglycemia is correlated to fatal brain failure and death. In this paper, we explore a variety of related research to have a grasp on some of the systems and concepts that can assist in forming an autonomous system for glucose monitoring, including deep learning techniques. The proposed system in this paper utilizes non-intrusive Continuous Glucose Monitoring (CGM) devices for tracking glucose levels, combined with food classification and Human Activity Recognition (HAR) using deep learning. We relate the preprandial and peak postprandial glucose levels extracted from CGM with the Glycimc Load (GL) present in food, which makes it possible to form an estimation of blood sugar increase as well as predict hyperglycemia. The system also relates human activity with decrease in blood glucose to warn against possible signs of hypoglycemia before it occurs. We have conducted 3 different experiments; two of which are comparison between deep learning models for food classification and HAR with good results achieved, as well as an experimental result that we obtained by testing hyperglycemia prediction on real data of diabetic patients. The system was able to predict hyperglycemia with an accuracy percentage of 93.2%. © 2021 IEEE.
Automatic Identification of Student’s Cognitive Style from Online Laboratory Experimentation using Machine Learning Techniques
(Institute of Electrical and Electronics Engineers, 04/12/2021) Yousef, Ahmed Mohamed Fahmy; Atia, Ayman; Youssef, Amira; Saad Eldien, Noha A; Hamdy, Alaa; Abd El-Haleem, Ahmed M; Elmesalawy, Mahmoud M
Online learning has emerged as powerful learning methods for the transformation from traditional education to open learning through smart learning platforms due to Covid-19 pandemic. Despite its effectiveness, many studies have indicated the necessity of linking online learning methods with the cognitive learning styles of students. The level of students always improves if the teaching methods and educational interventions are appropriate to the cognitive style of each student individually. Currently, psychological measures are used to assess students' cognitive styles, but about the application in virtual environment, the matter becomes complicated. The main goal of this study is to provide an efficient solution based on machine learning techniques to automatically identify the students' cognitive styles by analyzing their mouse interaction behaviors while carrying out online laboratory experiments. This will help in the design of an effective online laboratory experimentation system that is able to individualize the experiment instructions and feedback according to the identified cognitive style of each student. The results reveal that the KNN and SVM classifiers have a good accuracy in predicting most cognitive learning styles. In comparison to KNN, the enlarged studies ensemble the KNN, linear regression, neural network, and SVM reveal a 13% increase in overall total RMS error. We believe that this finding will enable educators and policy makers to predict distinct cognitive types in the assessment of students when they interact with online experiments. We believe that integrating deep learning algorithms with a greater emphasis on mouse location traces will improve the accuracy of our classifiers' predictions. © 2021 IEEE.
Brain computer interfacing: Applications and
(Elsevier, 2015-07) Mostafa, Mostafa-Sami M.; Atia, Ayman; Abdulkader, Sarah N.
Brain computer interface technology represents a highly growing field of research with application systems. Its contributions in medical fields range from prevention to neuronal rehabil- itation for serious injuries. Mind reading and remote communication have their unique fingerprint in numerous fields such as educational, self-regulation, production, marketing, security as well as games and entertainment. It creates a mutual understanding between users and the surrounding sys- tems. This paper shows the application areas that could benefit from brain waves in facilitating or achieving their goals. We also discuss major usability and technical challenges that face brain sig- nals utilization in various components of BCI system. Different solutions that aim to limit and decrease their effects have also been reviewed. - 2015 Production and hosting by Elsevier B.V. on behalf of Faculty of Computers and Information,
Can pose classification be used to teach Kickboxing?
(Institute of Electrical and Electronics Engineers Inc, 2021-12) Wessa, Eriny; Ashraf, Abdelaziz; Atia, Ayman
Kickboxing is a combat sport, based on kicking, punching, Knee and elbow strikes and defence moves. Every kickboxing technique needs to be preformed a specific way, As there is correct postures and wrong postures to every technique. In this paper, we offer a system that can facilitate the beginners trainees to learn kickboxing. The system uses a camera to estimate poses and then, classify them into 'correct techniques' and their common mistakes or 'wrong pose' using ANN. Live feedback is offered by the system. Whenever the classifier recognize a wrong pose, a message is shown to indicate how to correct the posture. Our hypothesis is that, when trainees have the ability to see and recognize their wrong posters, they learn faster. We evaluate the progress of the trainees based on the time it takes to complete a simple kickboxing exercise. Two types of experiments were conducted. The first calculated the progress of trainees everyday, the other calculated the progress of trainees through three training sessions in the span on two hours. Our results show that time taken by users to preform the moves decrease with each time they use our system. This paper focuses on 3 kickboxing techniques, which are slipping, jab and front kick. © 2021 IEEE.
Chicken Behavior Analysis for Surveillance in Poultry Farms
(Science and Information Organization, 2023-03) Mohialdin, Abdallah Mohamed; Elbarrany, Abdullah Magdy; Atia, Ayman
Poultry farming is an important industry that provides food for a growing population. However, the welfare of the birds is a major concern, as poor living conditions leads to abnormal behavior that affects the health and productivity of the flock. In order to monitor and improve the welfare of the birds, it is important to have a surveillance system in place that monitors the behavior of the chickens and alert farmers to potential issues. This paper reviews the current state of the art in behavior analysis for surveillance in poultry farms and discuss potential future directions for research in this area. This paper presents a computer-vision-based system that detects and monitors the behaviors of the chickens in poultry farms. The system classifies three behaviors which are eating, walking and sleeping. The system takes videos as input and then classifies the behavior of the chicken. The proposed system produces an accuracy of 94.7% using Light Gradient Boosting Machine on a collected data-set of chickens, and a 98.4% accuracy on a benchmarked Human Activity Recognition data-set.
Detecting Abnormal Fish Behavior Using Motion Trajectories In Ubiquitous Environments
(Elsevier Ltd, 2020-01) Anas, Omar; Wageeh, Youssef; Mohamed, Hussam El-Din; Fadl, Ali; El Masry, Noha; Nabil, Ayman; Atia, Ayman
Monitoring fish farms as controlling water quality and abnormal fish behaviors inside fish pond are one of the most costly and difficult task to do for fish farmers. Fish farmers normally do these tasks manually, which requires them to dedicate lots of time and money. Way for detecting fish behaviors is presented in this paper by identifying the fish and analyzing their trajectories in a difficult water environment. First of all, we used an image enhancement algorithm to color-enhance water pictures and to enhance fish detection. We then used an algorithm for object detection to identify fish. Finally, we used a classification algorithm to detect fish abnormal behavior. Our aim is making an automated system that monitors the fish farm to reduce costs and time for the fish farmers and provide them with more efficient and easy ways to perform their operations
Development of interactive 3D imaging system for hepatic angiography
(IEEE, 2013) A Rashed, Essam; M Ghanem, Ahmed; Amin, Ahmad; Atia, Ayman; al-Shatouri, Mohammad; Kudo, Hiroyuki
Egypt is witnessing over the next decade many challenges in the field of healthcare, especially with regard to the spread of hepatitis and coincides with the spread of liver hepatocellular carcinoma. Because most cases of liver cancer in Egypt are detected in very late stages, the use of surgical resection, liver transplantation and percutaneous ablative therapies constitutes unsuitable therapeutic options either due to high recurrence rate or unfeasibility. Therapy sessions can be made through the introduction of chemotherapy using a catheter directly into the hepatic artery supplying the tumor guided by angiography imaging system. This method of treatment known to prevent the patient from different problems associated with surgical treatment, but it is still needs to be further improved to maximize the benefits and minimize the risks. Hepatic angiography is an x-ray study of the blood vessels that supply the liver. The procedure uses a catheter that is placed into a blood vessel through a small incision. The catheter is guided using the x-ray images obtained through the interventional session. During angiography, hepatic arterial supply is usually displayed in one, two or three projections. Mental 3D interpretation of the anatomy is not an easy task. Reaching the target supply artery by the catheter tip is mandatory to obtain satisfactory tumor response and reduce complications and recurrence. This work aims to develop an interactive 3D imaging system of hepatic angiography. The developed system uses a set of 2D images measured over few view angles to reconstruct a full 3D volume of the hepatic arteries. The problem can be thought as a combination of three main approaches. (1) Image reconstruction of 3D artery volume from few number of projections (each is presented as 2D image), (2) automatic detection of the catheter roadmap to the labeled artery which feed the tumor, and (3) interactive system to control and display images using simple gestures of the physician..
Embodied learning via tangible user interfaces: the impact of physical interaction on learning performance
(Inderscience Publishers, 2022-04) Neila, Chettaoui; Atia, Ayman; Bouhlel, Med Salim
Tangible user interfaces have been introduced as a form of Human-Computer Interaction to promote embodied learning pedagogy. This interaction modality offers the possibility to support students' cognitive development through manipulating objects in the social and physical environment of the classroom. This article presents a study of tangible user interfaces supporting children (aged 9 to 11) while learning of the solar system concepts. A controlled study was performed at a primary school with 18 participants to evaluate the educational potential of manipulating abstract concepts in the physical world, compared to tablet-based learning. The results highlighted a significant difference in terms of the learning performance between both groups, as determined by one-way ANOVA (F (1,16) = 4.49, p =.033), in favour of the tangible user interfaces. These findings draw some implications for the adoption of the tangible interaction to extend embodied learning pedagogy and cognitive development of children. © 2022 Inderscience Enterprises Ltd
Exam Cheating Detection System with Multiple-Human Pose Estimation
(Institute of Electrical and Electronics Engineers, 19/11/2021) Samir, Mohamed Amr; Maged, Youssef; Atia, Ayman
Cheating in exams is a persistent problem that contributes to academic dishonesty. In this paper we explore a variety of related work proposed as a solution for exam cheating, then we propose an exam cheating detection system that works for both on-site and online examinations. The proposed system applies Human Pose Estimation that includes both single-user and multiple-user tracking algorithms. Based on video footage, the system can detect whether or not a student is cheating by continuously validating their head posture and hand movement conditions during the exam. The system doesn't fully imply a student is cheating, instead, we use the term 'warning' for the output to indicate that the student has met an abnormal condition that is similar to cheating behavior. At last, we validate the system usage in real-life examination environments through two different experiments that resulted in accuracy numbers of 92%-97% in cheating detection.
Exploring and Classifying Beef Retail Cuts Using Transfer Learning
(Institute of Electrical and Electronics Engineers Inc., 2022-09) Abuzaid, Abdallah; Atia, Ayman
An evaluation of the deep learning neural network in artificial intelligence (AI) technologies is proposed to provide a rapid recognition and immediate proper classification of the different beef retail cuts (Liver, Roast Beef, Beef Chuck, Beef Round, Strip-Lion, Round Fillet, Beef Flank) to classify them accordingly. The problem is that many of the modern consumers face difficulties in recognizing the different retail beef cuts. Thus, a solution was created through collecting a dataset for retail cuts and creating an algorithm to classify them. A dataset, which is available for public, of 7 different beef retail cuts was proposed. This dataset includes colored images from our own image library, a total of 1638 images for validation testing and training are used for this project. The deep learning neural network algorithm-based model was able to identify specific beef retail cuts. 5 models were used in this paper to reach the highest accuracy for the classification of our dataset (MobileNet, ResNet50, InceptionV3, EfficientNetB0 and our customized model). EffecientNetB0 pretrained model is one of the best and easiest pretrained models in Keras CNN. The employment of this model, after training and data augmentation techniques, was able to achieve the highest accuracy by a 99.81%. Based on our trained model and the huge results, deep learning technology evidently showed a promising effort for beef cuts recognition in the meat science industry. © 2022 IEEE.
Exploring the Impact of Interaction Modality on Students’ Learning Performance
(SAGE Publications Inc., 2021) Chettaoui, Neila; Atia, Ayman; Bouhle, Med Salim
Embodied learning pedagogy highlights the interconnections between the brain, body, and the concrete environment. As a teaching method, it provides means of engaging the physical body in multimodal learning experiences to develop the students’ cognitive process. Based on this perspective, several research studies intro- duced different interaction modalities to support the implementation of an embod- ied learning environment. One such case is the use of tangible user interfaces and motion-based technologies. This paper evaluates the impacts of motion-based, tan- gible-based, and multimodal interaction merging between tangible interfaces and motion-based technology on improving students’ learning performance. A controlled study was performed at a primary school with 36 participants (aged 7 to 9), to evaluate the educational potential of embodied interaction modalities compared to tablet-based learning. The results highlighted a significant difference in the learning gains between all groups, as determined by one-way ANOVA [F (3,32) ¼ 6.32, p ¼.017], in favor of the multimodal learning interface. Findings revealed that a multimodal learning interface supporting richer embodied interaction that took advantage of affording the power of body movements and manipulation of physical objects might improve students’ understanding of abstract concepts in edu- cational contexts.
Forensic Handwritten Signature Identification Using Deep Learning
(Institute of Electrical and Electronics Engineers Inc., 2022-09) Tarek, Omara; Atia, Ayman
Forgery is a type of fraud defined as the act of forging a copy or an imitation of a document, signature, or banknote which is considered a form of illegal criminal activity. In this paper, we are focusing on the identification and detection of handwritten signature forgeries inside documents. The proposed system uses contemporary methods that utilize a deep learning approach of CNNs (Convolutional Neural Networks) for binary image classification and aims to help forensic examiners measure the genuineness of handwritten signatures. We considered using a number of five different classification models of CNN which are, VGG-16, ResNet50, Inception-v3, Xception, and Our CNN model. The purpose for using these different CNN models is to determine and study which model is best at identifying images containing text data containing similar resemblances. Upon comparing these CNN models, we concluded that the ResNet50 model was able to reach the highest score at identifying handwritten signatures with an accuracy of 82.3% and 86% when tested on datasets of 300 images and 140 images respectively. Regarding future work, this is a required step that determines what model to focus on for more in-depth analysis and classification of the characteristics of handwritten signatures. © 2022 IEEE.
Fruit Disease's Identification and Classification Using Deep Learning Model
(IEEE, 2022-06) Matboli, Mohammed Ahmed; Atia, Ayman
Now days Fruits is being produced from alot of countries as the global fruit production reached up to 2914.27 production in thousand metric tons and in the upcoming years a lot of countries want to increase the production. However, some challenges and problems persist to exist through the fruits production like the quality of the fruit, the cost of the production, the quality of the seed and the illness of the fruit itself. There are types of recognized Diseases in the apples such as blotch, scab, and rotten diseases, and for the citrus, Black spot, Scab Citrus, and Citrus Canker. In this project, Our aim is to identify the best transfer learning model that is able to achieve the most extraordinary accuracy through the early detection of fruit diseases. Five different types of transfer learning models are presented, and they are being used in this proposed solution as the customized CNN model achieved the highest accuracy that reached up to 99.16%. © 2022
A futuristic design vision of tangible user interfaces on enhancing Montessori
(Taylor and Francis Ltd., 10/10/2021) Ali, Sara Ahmed Sayed; Chettaoui, Neila; Atia, Ayman; Bouhlel, Med. Salim; Abdel Mohaiman, Dalia Mohamed
Montessori considers as an effective method that is commonly used in nurseries to improve the mental performance and develop the cognitive skills toward children. Tangible user interfaces (TUI) is an effective tool that allows interaction with physical objects in a way that makes this interaction augmented through embedded computation. This paper proposed a new concept of Montessori, which is Interactive Technological Montessori (ITM) using TUI. It aims to measure the impact of using TUI on enhancing the effectiveness of Montessori and make a new futuristic design vision for Montessori activities to motivate children positively. The findings of this paper revealed that Merging TUI with ITM has a great potential to increase the efficiency of Montessori. In addition to considering the appropriate design principles and Multi aging group work help children to be motivated positively to interact with the Montessori activities.
Hexart: Smart Merged Touch Tables
(SPRINGER, 2016) Sami, Ahmed; Essam, Alaa; Mohamed, Esraa; Ahmed, Saleh; M Zakzouk, Abdallah; Attia, Moustafa; Atia, Ayman
Hexart is a multi-touch tables system based on FTIR utilizing hexagon shaped tables, We designed Hexart for people needs in a group activities. Our paper illustrates the proposed system to eliminate common challenges in facing group activities problems such as time wasting, Lack of communication and the most crucially was the inability to integrate different work parts correctly. It also introduces two major cooperation concepts supported which are the merging and splitting. The Merging concept allows users to merge tables together in order to form a large multi-touch table, Whilst the Splitting concept allows users to split a table display into several private areas where each user has their own personal work space. Users can interact together through private areas or a public area which is accessible to all users. Finally, An experiment conducted to measure users’ satisfaction and usability of hexagonal multi-touch tables. It showed that such an approach can yield an implementation that was extremely competitive
Interaction With Tilting Gestures In Ubiquitous Environments
(International Journal Of UbiComp, 2010) Atia, Ayman
In this paper, we introduce a tilting interface that controls direction based applications in ubiquitous environments. A tilt interface is useful for situations that require remote and quick interactions or that are executed in public spaces. We explored the proposed tilting interface with different application types and classified the tilting interaction techniques. Augmenting objects with sensors can potentially address the problem of the lack of intuitive and natural input devices in ubiquitous environments. We have conducted an experiment to test the usability of the proposed tilting interface to compare it with conventional input devices and hand gestures. The experiment results showed greater improvement of thetilt gestures in comparison with hand gestures in terms of speed, accuracy, and user satisfaction.
Interactive Gestures for Liver Angiography Operation
(SPRINGER, 2016) A Elmanakhly, Dina; Atia, Ayman; A Rashed, Essam; M Mostafa, Mostafa-Samy
The main challenge of creating large interactive displays in the operating rooms (ORs) is in the definition of ways that are efficient and easy to learn for the physician. Apart from traditional input methods such as mouse and keyboard, we have developed a multimodal system with two different vision based human-computer interaction (HCI) systems that can simplify the way surgeons interact with the medical images shown on the LCD display. The purpose of this work is to construct a gesture recognition system with a fast, accurate, and easily attainable method. The first system is a laser pointer interaction framework that supports a 2D stroke gesture interface. The recorded laser gestures are recognized using two different algorithms: dynamic time warping (DTW) and one dollar (1$) recognizer. Our experimental results showed that the DTW algorithm performs better with an overall accuracy of 90 %. The second prototype presents an intuitive HCI to manipulate images using freehand gestures. In order to strengthen the gesture recognition process, the system incorporates contextual information to determine the intent of the user of interacting with the large display. Two cameras are used to observe the surgeon’s hand movements to continuously determine and monitor what the surgeon intends to perform. Experimental results showed that the system accuracy is 95 % for recognition with the effect of contextual integration
IPingPong: A Real-time Performance Analyzer System for Table Tennis Stroke’s Movements
(Elsevier Ltd, 2020-01) Hegazy, Habiba; Abdelsalam, Mohamed; Hussien, Moustafa; Elmosalamy, Seif; M.I Hassan, Yomna; Nabil, Ayman M.; Atia, Ayman
Assisting table tennis coaching using modern technologies is one of the most trending researches in the sports field. In this paper, we present a methodology to identify and recognize the wrong strokes executed by players to improve the training experience by the usage of an IR depth camera. The proposed system focuses mainly on the errors in table tennis player’s strokes and evaluating them efficiently and based on the analysis and classification of the data obtained from an IR depth camera using multiple algorithms. This paper is a continuation of our previous work [10], focusing more on identifying common wrong strokes in table tennis by utilizing IR depth camera classification algorithms. The classification of the mistakes that took place while playing can be classified based on each player dependently or independently for all players.