Amira T. Mahmoud, A. A. Muhammad, A. Yousef, Walaa Medhat, Hala H. Zayed, Sahar Selim
{"title":"Compiler-based Web Services code conversion model for different languages of mobile application","authors":"Amira T. Mahmoud, A. A. Muhammad, A. Yousef, Walaa Medhat, Hala H. Zayed, Sahar Selim","doi":"10.1109/IMSA58542.2023.10217471","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10217471","url":null,"abstract":"Mobile applications are very popular nowadays. The two most common platforms depend on different languages to have native performance. Most trans-compiler-based converters between those languages didn’t take webservices conversion into consideration. However, in recent years, mobile applications developers have used web services for lighter and more dynamic mobile applications. Therefore, it becomes crucial to include web services mapping to the trans-compiler-based code converters for mobile applications code. In this paper, we present a model for web service trans-compiler code mapper from swift for iOS to java for Android to be integrated to previous trans-pilers. The testing for the conversion accuracy is done for six different web services functions. The average accuracy of converting webservice calling from iOS to Android is 89.3%. In addition, due to the rise of generative language models and their capability to generate code, we compare OpenAI’s chatGPT to our tool, evaluating its capabilities for code translation and exploring the potential of prompt engineering for seamless integration into our trans-compiler tool.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114358507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Salma AlWardany, Salma Hossam, Kareem Moussa, M. Darweesh
{"title":"Emotion to Detect: Facial Expression Recognition by CNN","authors":"Salma AlWardany, Salma Hossam, Kareem Moussa, M. Darweesh","doi":"10.1109/IMSA58542.2023.10217748","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10217748","url":null,"abstract":"Recognizing and analyzing body language is one of the major fields, and one branch of it is Face expression recognition. In this paper, we present a machine learning model based on a convolutional neural network (CNN) to predict the face expressions, using libraries of TensorFlow and the ‘FER 2013' dataset that consists of 34,034 48×48 greyscale images gathered in a CSV file. There are seven main reactions (classes): Angry, Disgust, Fear, Happy, Sad, Surprise, and Neutral. We intend to discover how the image gets processed from the input layer in the CNN to be recognized as a face and its emotion at the output layer. We intend to apply CNN to output a high accuracy in prediction to be later used to improve the prediction of real-life applications. The model can predict the reactions with 83.55% testing accuracy and an average F1-score of 0.84. This model can be used in several ways, such as: giving suggestions to the customers according to their reactions, as it is considered the primary model that can serve many fields.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"1999 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134571211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Comparative Study of Alzheimer’s disease Classification using Transfer Learning Models","authors":"Habiba Mohamed, Abdelaziz Ashraf, Abdelrahman Ezzeldin Nagib","doi":"10.1109/IMSA58542.2023.10217654","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10217654","url":null,"abstract":"In this study, deep learning models used to detect and classify Alzheimer’s disease through the utilization of knowledge acquired from pre-existing trained models—including MobileNet, Inception, VGG16, DenseNet121, and Xception—are investigated. The dataset consisted of brain MRI scans from both healthy individuals and individuals diagnosed with Alzheimer’s disease used in this investigation. The findings demonstrate that the Xception model outperformed other models in terms of accuracy, achieving a 98.8% accuracy in training and a 94.9% accuracy in testing. According to the study, the Xception model has significant potential for this role and may be utilised to classify Alzheimer’s disease successfully.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134501162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A framework for exploring incentive methods towards reducing phishing susceptibility in Healthcare: Based on a review and In-the-wild-field study approach","authors":"P. Yeng, Bian Yang, M. Fauzi, P. Nimbe","doi":"10.1109/IMSA58542.2023.10217499","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10217499","url":null,"abstract":"Phishing remains a significant and ever-growing threat in our digitalized society. Its impact on industries crucial to human welfare, such as healthcare, can be devastating and even life-threatening. This paper presents a comprehensive exploration of various types of simulated phishing exercises in the healthcare sector, encompassing incentive methods, tools, risks, and ethical considerations through a scoping review.In this study, a total of six phishing simulation studies and sixteen simulated phishing tools were identified. Among the three types of simulated phishing studies (survey, lab-based experiment, in-the-wild study), a combination of survey and in-the-wild-field study, or a hybrid approach, has been commonly employed for conducting phishing simulations in healthcare settings. While the protection motivation theory has been examined to enhance phishing practices, no measures of incentives have been evaluated to improve resistance against phishing attacks.Regarding risk and ethics, the contentious issue of deception in research has sparked considerable debate across various communities. Nevertheless, employing the \"to deceive\" approach in in-the-wild-field studies has proven to be the most effective and efficient. However, it is imperative to adopt appropriate ethical measures to mitigate the risks associated with deceitfulness in such studies.Based on the findings of this review, a framework has been developed to guide future studies focusing on effective incentive-related approaches to reduce susceptibility among healthcare workers. This framework serves as a valuable resource for researchers and practitioners aiming to address the ongoing threat of phishing in the healthcare industry.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128501554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"OilSpillNet: Deep Learning Model for Synthetic Aperture Radar Imagery Oil Spill Detection","authors":"Touka Wael Ghonaime, Ahmed Farouk Al-Sadek","doi":"10.1109/IMSA58542.2023.10217532","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10217532","url":null,"abstract":"The objective of this study is to enhance the precision of oil spill identification and division utilizing the benefits of Synthetic Aperture Radar (SAR) imagery. The capacity of SAR imagery to function around the clock makes it an ideal tool for constant oil spill surveillance. Unaffected by factors such as weather conditions, cloud obstruction, or lack of light, SAR can penetrate oil layers to detect spills beneath the surface that might be undetectable with conventional optical images or hyper-spectral imaging. This study presents a method that serves as a significant resource for identifying and tracking oil spills, and evaluating their effect on marine habitats and coastal ecosystems. It can greatly contribute to the field of oil spill detection and surveillance research. Furthermore, this research tackles the challenge of imbalanced datasets through the use of a UNet model with a densenet encoder, enhancing the classification of oil spills and the surrounding environment. The method suggested was successful, achieving an f1-score of 80.31 % and an 76.84 % mean IoU on testing set of 110 images. Additionally, the model received high scores for categories like sea surface, ship, and land, proving its proficiency in identifying and classifying oil spills and their environmental context.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132226876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Norah Saud Al-Musibe, Hédi Hamdi, A. A. Abd El-Aziz
{"title":"A Secured Technique for Executing Queries over Multidimensional Encrypted Data","authors":"Norah Saud Al-Musibe, Hédi Hamdi, A. A. Abd El-Aziz","doi":"10.1109/IMSA58542.2023.10217376","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10217376","url":null,"abstract":"In new computing architectures, data is outsourced and sensitive data becomes vulnerable in various areas. Owners must guarantee that their data are secure from breaches and unauthorized users and available anytime. Various techniques have been proposed to maintain a certain degree of privacy in the database and to allow efficient execution of queries on cloud computing. These methods cannot securely support queries over encrypted data without leaking private data. Therefore, in this paper, a secure technique was proposed for executing queries over encrypted data, and the proposed technique was based on the design of CryptDB. This technique eliminates the limitations of CryptDB to perform server-side computations on cryptographic data of different principles. The proposed technique attempts to overcome CryptDB’s limitations by encrypting with different keys in multidimensional mode and running each query on the corresponding data encrypted by the same key.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132268128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}