Instant messaging applications (IMAs) rely on message encryption to preserve privacy and security, which makes network traffic inspection difficult. For better network monitoring and analysis, we explore network traffic signatures in IMAs. We develop a framework to automatically generate and capture traffic from seven popular IMAs. We discover patterns from text messaging behavior, such as synchronous and asynchronous as well as group and private communications. We analyze the resulting end-to-end encrypted traffic using a machine learning-based approach to traffic metadata without using deep packet inspection. The evaluations show that it is possible to identify between groups with different numbers of users for asynchronous and synchronous communication models. This, in turn, can help better plan and manage network operations for better quality of service.

This paper introduces the Encrypted Network Traffic Analysis (ENTA) platform, a scalable AI-driven system de-signed for traffic analysis with support for identifying encrypted VoIP traffic generated by instant messaging applications (IMAs). User behaviors, such as exchanging audio messages through different IMAs, are emulated, and the resulting network traffic is captured for analysis. The ENTA platform's capabilities are demonstrated in feature extraction, data pre-processing, AI model training and testing, and generating key performance indi-cators (KPIs) to assist network operations teams. This demonstration showcases the ENTA system's end-to-end functionality with a particular emphasis on accurately classifying and identifying IMA VoIP traffic.

The AI Virtual mouse project is a challenge for individuals with physical disabilities and those affected by autism. This project presents an innovative solution: an AI Virtual Mouse, powered by computer Vision and the MobileNet architecture. This system not only improves accessibility but also addresses the pressing need for contactless and touchless interactions in a world increasingly concerned about health and hygiene. By using the MobileNet architecture, this system accurately interprets hand gestures to control cursor movements, eliminating the need for physical contact. Designed with accessibility in mind, the AI Virtual Mouse empowers individuals with physical disabilities and those affected by autism to navigate computers effortlessly, fostering greater independence and inclusion. The contactless nature of the interface also aligns with the increasing demand for hygienic solutions, minimizing the risk of germ transmission in public and personal spaces. This technology represents a significant advancement in the realm of accessible computing, offering a practical and intuitive alternative to traditional input methods

Signature verification and forgery detection are crucial tasks in document authentication, banking, and legal proceedings. This abstract presents an innovative approach utilizing deep transfer learning with MobileNet Vision Transformer (ViT) architecture for automatic signature verification and forgery detection, integrated into a web application using Flask framework.The proposed system employs MobileNet Vision Transformer (ViT) with deep transfer learning for automatic signature verification and forgery detection. Utilizing transfer learning, MobileNet ViT extracts features from signature images efficiently, enhancing its ability to discern authenticity nuances. In signature verification, the system computes similarity scores between the queried and reference signatures, accommodating variations in style and speed via dynamic time warping. For forgery detection, discrepancies such as unnatural strokes or inconsistencies are analyzed. Integration with Flask facilitates deployment as a user-friendly web application, where users upload scanned signatures for real-time processing. The system provides verification results and flags suspicious signatures. This approach offers scalability and accessibility, reducing reliance on manual inspection and improving document authentication efficiency across industries

The escalating demand for user privacy and data encryption has significantly boosted the volume of encrypted traffic on the contemporary Internet. Nonetheless, there is a shortage of comprehensive research on the properties of Virtual Private Network traffic. In this paper, we explore Edge-Cloud Virtual Private Network traffic in order to understand usage patterns without deep packet inspection. To achieve this, we use a machine learning based approach to analyze traffic flows, and identify Virtual Private Network traffic captured from five applications that belong to four service categories. Our results demonstrate that we are not only able to identify the VPN traffic, but also able to identify the different applications and therefore service categories across different network locations and computing platforms.

Software plagiarism, the illegal copying of code, negatively impacts both open-source communities and legitimate companies. Notable incidents include Verizon being sued by the Free Software Foundation for distributing Busy box in its routers, and Skype's licensing issues with Joltid. Plagiarism is easy to execute but hard to detect, with a 2012 study indicating that 5%-13% of apps in third-party markets are copied from the official Android market. Challenges in detection arise from the lack of source code and advanced code obfuscation techniques. Researchers have developed methods like software birthmarking, which extracts unique characteristics from programs to identify them. Birthmarks can be static or dynamic; static birthmarks analyse syntactic features but struggle against obfuscations and packing techniques. Dynamic birthmarks, derived from runtime behaviours, are more accurate and robust. However, the rise of multithreaded programs poses a challenge to existing detection methods, which are optimized for sequential programs

Instant Messaging Applications (IMAs), such as WhatsApp and Messenger, have become one of the main communication tools for smartphone users. However, there is limited research analyzing the nature of encrypted network traffic produced by IMAs. In this paper, we employ a data driven approach using machine learning classification models to analyze and identify encrypted traffic from six different IMAs. Our results show that it is possible to distinguish the behaviour of different IMAs with high F1 scores.

Instant Messaging Applications (IMAs), such as Discord and WhatsApp, have become one of the main communication tools for mobile device users. Network traffic analysis is a method of monitoring network activity to identify operational and security issues. There is limited research on network traffic analysis of IMAs on mobile devices due to the challenges of end-to-end encryption, user privacy, and dynamic port usage. In this paper, we design, develop and evaluate a framework to generate end-to-end IMA traffic on mobile devices, employ feature selection and conduct traffic analysis that can cope with encrypted traffic while identifying different IMAs. Results show a performance evaluation workbench as well as highlight the key characterictis of six popular IMAs.

Contеnt-Basеd Imagе Rеtriеval (CBIR) and imagе captioning havе gainеd significant attеntion in rеcеnt yеars duе to thеir potеntial applications in various fiеlds, including law еnforcеmеnt and criminal invеstigations. This projеct aims to dеvеlop an intеlligеnt systеm that combinеs thе powеr of dееp lеarning modеls, VGG19 and RеsNеt50, to facilitatе thе rеtriеval and captioning of criminal imagеs basеd on thеir visual contеnt. Thе proposеd systеm will consist of two main componеnts: a ContеntBasеd Imagе Rеtriеval (CBIR) systеm and an imagе captioning modulе. Thе CBIR systеm will bе built using thе VGG19 and RеsNеt50 dееp convolutional nеural nеtworks, prе-trainеd on largе-scalе imagе datasеts. Thеsе modеls havе shown еxcеptional pеrformancе in fеaturе еxtraction and rеprеsеntation lеarning, making thеm idеal candidatеs for imagе rеtriеval tasks. In addition to imagе rеtriеval, thе projеct will also focus on gеnеrating dеscriptivе captions for criminal imagеs using thе captioning modulе. This modulе will еmploy an attеntion-basеd mеchanism to еmphasizе rеlеvant imagе rеgions whilе gеnеrating captions. Thе captioning modеl will bе trainеd on a largе-scalе captionеd imagе datasеt to lеarn thе corrеlation bеtwееn visual fеaturеs and tеxtual dеscriptions. Thе intеgration of thе CBIR systеm and thе imagе captioning modulе will rеsult in a comprеhеnsivе tool that not only rеtriеvеs similar criminal imagеs but also providеs dеscriptivе captions, aiding invеstigators in undеrstanding thе contеxt and contеnt of thе rеtriеvеd imagеs. This combinеd approach will significantly еnhancе thе еfficiеncy and еffеctivеnеss of criminal imagе analysis and hеlp law еnforcеmеnt agеnciеs in idеntifying suspеcts and potеntial connеctions bеtwееn diffеrеnt criminal activitiеs

Instant Messaging Applications (IMAs) have become the leading communication tool for smartphone users. While it is insightful for network operators and security researchers to monitor and analyze the network traffic of their organization, there is a lack of research on IMA encrypted traffic analysis. In a companion work [1], we introduced a flow-based encrypted IMA traffic analysis using a data driven approach. Given the lack of publicly available data in this area, a new encrypted IMA traffic generation system is designed and implemented to automatically generate and label encrypted IMA traffic including Discord, Facebook Messenger, Signal, Microsoft Teams, Telegram, and WhatsApp. The new system utilizes a combination of open-source tools to emulate user behavior, to capture, filter and label the resulting traffic directly on an Android device. This demonstration shows the functionality of the proposed system via data generation, capture, and analysis of the six IMAs.

Patient no-show for a booked medical appointment is a significant problem that negatively impacts healthcare resource utilization, cost, efficiency, quality, and patient outcomes. This paper developed a machine learning framework to predict pediatric patients' no-shows to medical appointments accurately. Thirty months of outpatient visits data were extracted from data warehouse from January 2017 to July 2019 of the Ministry of National Guard Health Affairs (MNGHA), Saudi Arabia. The researchers retrieved the data from all healthcare facilities in the central region, and more than 100 attributes were generated. The data includes over 100,000 pediatric patients and more than 3.7 million visits. Five machine learning algorithms were deployed, where Gradient Boosting (GB) algorithm outperformed the other four machine learning algorithms: decision tree, random forest, logistic regression, and neural network. The study evaluated and compared the performance of the five models based on five evaluations criteria. GB achieved a Receiver Operating Characteristic (ROC) score of 97.1%. Furthermore, this research paper identified the factors that have massive potential for effecting patients' adherence to scheduled appointments.

This study aims to develop an accurate machine learning model for predicting no-shows in pediatric outpatient clinics at King Faisal Specialist Hospital and Research Centre (KFSH&RC), and understand pediatric patients' characteristics who are most likely will not show to their scheduled appointments. Appointment no-show data collected from KFSH&RC data warehouse over the period (01 Jan – 31 Dec 20...

Introduction: Patient no-shows are defined as patients who missed outpatient appointments, either for diagnostic or clinic tests. Identifying those patients is necessary for clinicians and healthcare settings to utilize the resources and improve healthcare efficiency appropriately. This research paper aims to develop a predictive model based on machine learning algorithms to predict patients' failure to attend scheduled appointments. A public data set was divided into training and testing data sets. Two machine learning algorithms, namely decision trees and AdaBoost, were evaluated based on Precision, Recall, True Positive Rate, False Negative Rate, F-measure, and Receiver Operating Characteristic (ROC). Results showed that the decision tree outperformed AdaBoost. The most significant predictors were age and lead time.

Background: Patient satisfaction is one of the primary Key Performance Indicator (KPI) goal of health care service, and it creates many reasons for implementing research, plans, and innovations to achieve it for a better quality of life. Cutting Patient waiting time would increase patient satisfaction. Objective: A healthcare framework has been constructed utilizing a machine learning approach to construct an early predicting preparation model of pharmacy prescriptions and the worthiness of changing the outpatient pharmacy workflow. Methods: Data sets were retrieved between Januarys and June 2019 from Prince Sultan Military Medical City, Riyadh, KSA, for all patients who visited the clinics or discharged with pharmacy prescriptions. Included (1048575) instances and composed of (11) attributes. The evaluation criteria to compare the four algorithms were based on precision, Recall, True Positive Rate, False Negative Rate, F-measure, and Area under the curve. Results: Overall, 94.88% of patient’s shows at the pharmacy, female represents 58.89% of the data set while male represents 41.1%. RT gives the highest accuracy, with 97.22% in comparison to the other algorithms. Conclusion: The suggestion to change the pharmacy workflow is worth increasing patient satisfaction and overall the quality of the care.

Digitalization of healthcare delivery is rapidly fostering development of precision medicine. Multiple digital technologies, known as telehealth or eHealth tools, are guiding individualized diagnosis and treatment for patients, and can contribute significantly to the objectives of precision medicine. From a basis of "one-size-fits-all " healthcare, precision medicine provides a paradigm shift to deliver a more nuanced and personalized approach. Genomic medicine utilizing new technologies can provide precision analysis of causative mutations, with personalized understanding of mechanisms and effective therapy. Education is fundamental to the telehealth process, with artificial intelligence (AI) enhancing learning for healthcare professionals and empowering patients to contribute to their care. The Gulf Cooperation Council (GCC) region is rapidly implementing telehealth strategies at all levels and a workshop was convened to discuss aspirations of precision medicine in the context of pediatric endocrinology, including diabetes and growth disorders, with this paper based on those discussions. GCC regional investment in AI, bioinformatics and genomic medicine, is rapidly providing healthcare benefits. However, embracing precision medicine is presenting some major new design, installation and skills challenges. Genomic medicine is enabling precision and personalization of diagnosis and therapy of endocrine conditions. Digital education and communication tools in the field of endocrinology include chatbots, interactive robots and augmented reality. Obesity and diabetes are a major challenge in the GCC region and eHealth tools are increasingly being used for management of care. With regard to growth failure, digital technologies for growth hormone (GH) administration are being shown to enhance adherence and response outcomes. While technical innovations become more affordable with increasing adoption, we should be aware of sustainability, design and implementation costs, training of HCPs and prediction of overall healthcare benefits, which are essential for precision medicine to develop and for its objectives to be achieved.

Knowledge of the underlying anatomy of the left atrium can promote improved diagnostic protocols and clinical interventions; therefore, automatic segmentation of the left atrium on magnetic resonance imaging (MRI) can support diagnosis, treatment and surgery planning of the heart. Due to the small size of the left atrium with respect to the whole MRI volume, most of the current deep learning approaches are based on cropping or cascading networks. Dense V-Network is an encoder-decoder model designed for volumetric images by introducing a specialised dense feature stack to the standard V-Net model. A minor manipulation in parameters of the Dense V-Network can make it suitable for the fast and efficient segmentation of the left atrium. We present a brief review showing the ability of the Dense V-Network to deal with the issue of class imbalance and the unavailability of a large dataset of left atrium segmentation. We conclude that Dense V-Network can be tailored to left atrium MRI segmentation showing the accuracy that can surpass current methods, potentially supporting cardiac diagnosis and surgery.

BACKGROUND:Predicting the risk of glycated hemoglobin (HbA1c) elevation can help identify patients with the potential for developing serious chronic health problems, such as diabetes. Early preventive interventions based upon advanced predictive models using electronic health records data for identifying such patients can ultimately help provide better health outcomes.OBJECTIVE:Our study investigated the performance of predictive models to forecast HbA1c elevation levels by employing several machine learning models. We also examined the use of patient electronic health record longitudinal data in the performance of the predictive models. Explainable methods were employed to interpret the decisions made by the black box models.METHODS:This study employed multiple logistic regression, random forest, support vector machine, and logistic regression models, as well as a deep learning model (multilayer perceptron) to classify patients with normal (<5.7%) and elevated (≥5.7%) levels of HbA1c. We also integrated current visit data with historical (longitudinal) data from previous visits. Explainable machine learning methods were used to interrogate the models and provide an understanding of the reasons behind the decisions made by the models. All models were trained and tested using a large data set from Saudi Arabia with 18,844 unique patient records.RESULTS:The machine learning models achieved promising results for predicting current HbA1c elevation risk. When coupled with longitudinal data, the machine learning models outperformed the multiple logistic regression model used in the comparative study. The multilayer perceptron model achieved an accuracy of 83.22% for the area under receiver operating characteristic curve when used with historical data. All models showed a close level of agreement on the contribution of random blood sugar and age variables with and without longitudinal data.CONCLUSIONS:This study shows that machine learning models can provide promising results for the task of predicting current HbA1c levels (≥5.7% or less). Using patients' longitudinal data improved the performance and affected the relative importance for the predictors used. The models showed results that are consistent with comparable studies.

Diabetes is a salient issue and a significant health care concern for many nations. The forecast for the prevalence of diabetes is on the rise. Hence, building a prediction machine learning model to assist in the identification of diabetic patients is of great interest. This study aims to create a machine learning model that is capable of predicting diabetes with high performance. The following study used the BigML platform to train four machine learning algorithms, namely, Deepnet, Models (decision tree), Ensemble and Logistic Regression, on data sets collected from the Ministry of National Guard Hospital Affairs (MNGHA) in Saudi Arabia between the years of 2013 and 2015. The comparative evaluation criteria for the four algorithms examined included; Accuracy, Precision, Recall, F-measure and PhiCoefficient. Results show that the Deepnet algorithm achieved higher performance compared to other machine learning algorithms based on various evaluation matrices.

Patients' no-show is one of the leading causes of increasing financial burden for healthcare organizations and is an indicator of healthcare systems' quality and performance. Patients' no-show affects healthcare delivery, workflow, and resource planning. The study aims to develop a prediction model predict no-show visits using a machine learning approach. A large volume of data was extracted from electronic health records of patient visits in outpatient clinics under the umbrella of large medical cities in Saudi Arabia. The data consists of more than 33 million visits, with an 85% no-show rate. A total of 29 features were utilized based on demographic, clinical, and appointment characteristics. Nine features were an original data element, while data elements derived 20 features. This study used and compared three machine learning algorithms; Deep Neural Network (DNN), AdaBoost, and Naive Bayes (NB). Results revealed that the DNN performed better in comparison to NB and AdaBoost. DNN achieved a weighted average of 98.2% and 94.3% of precision and recall, respectively. This study shows that machine learning has the potential to improve the efficiency and effectiveness of healthcare. The results are considered promising, and the model can be an excellent candidate for implementation.