Assessment of whole-body and regional body fat using abdominal quantitative computed tomography in Chinese women and men.

BACKGROUND: Being overweight or obese has become a serious public health concern, and accurate assessment of body composition is particularly important. More precise indicators of body fat composition include visceral adipose tissue (VAT) mass and total body fat percentage (TBF%). Study objectives included examining the relationships between abdominal fat mass, measured by quantitative computed tomography (QCT), and the whole-body and regional fat masses, measured by dual energy X-ray absorptiometry (DXA), as well as to derive equations for the prediction of TBF% using data obtained from multiple QCT slices. METHODS: Whole-body and regional fat percentage were quantified using DXA in Chinese males (n = 68) and females (n = 71) between the ages of 24 and 88. All the participants also underwent abdominal QCT measurement, and their VAT mass and visceral fat volume (VFV) were assessed using QCT and DXA, respectively. RESULTS: DXA-derived TBF% closely correlated with QCT abdominal fat percentage (r = 0.89-0.93 in men and 0.76-0.88 in women). Stepwise regression showed that single-slice QCT data were the best predictors of DXA-derived TBF%, DXA android fat percentage and DXA gynoid fat percentage. Cross-validation analysis showed that TBF% and android fat percentage could be accurately predicted using QCT data in both sexes. There were close correlations between QCT-derived and DXA-derived VFV (r = 0.97 in men and 0.93 in women). CONCLUSION: Clinicians can assess the TBF% and android and gynoid fat percentages of Chinese women and men by analysing existing abdominal CT-derived data using the QCT technique.

Validity of an android device for assessing mobility in people with chronic stroke and hemiparesis: a cross-sectional study.

BACKGROUND: Incorporating instrument measurements into clinical assessments can improve the accuracy of results when assessing mobility related to activities of daily living. This can assist clinicians in making evidence-based decisions. In this context, kinematic measures are considered essential for the assessment of sensorimotor recovery after stroke. The aim of this study was to assess the validity of using an Android device to evaluate kinematic data during the performance of a standardized mobility test in people with chronic stroke and hemiparesis. METHODS: This is a cross-sectional study including 36 individuals with chronic stroke and hemiparesis and 33 age-matched healthy subjects. A simple smartphone attached to the lumbar spine with an elastic band was used to measure participants' kinematics during a standardized mobility test by using the inertial sensor embedded in it. This test includes postural control, walking, turning and sitting down, and standing up. Differences between stroke and non-stroke participants in the kinematic parameters obtained after data sensor processing were studied, as well as in the total execution and reaction times. Also, the relationship between the kinematic parameters and the community ambulation ability, degree of disability and functional mobility of individuals with stroke was studied. RESULTS: Compared to controls, participants with chronic stroke showed a larger medial-lateral displacement (p = 0.022) in bipedal stance, a higher medial-lateral range (p < 0.001) and a lower cranio-caudal range (p = 0.024) when walking, and lower turn-to-sit power (p = 0.001), turn-to-sit jerk (p = 0.026) and sit-to-stand jerk (p = 0.001) when assessing turn-to-sit-to-stand. Medial-lateral range and total execution time significantly correlated with all the clinical tests (p < 0.005), and resulted significantly different between independent and limited community ambulation patients (p = 0.042 and p = 0.006, respectively) as well as stroke participants with significant disability or slight/moderate disability (p = 0.024 and p = 0.041, respectively). CONCLUSION: This study reports a valid, single, quick and easy-to-use test for assessing kinematic parameters in chronic stroke survivors by using a standardized mobility test with a smartphone. This measurement could provide valid clinical information on reaction time and kinematic parameters of postural control and gait, which can help in planning better intervention approaches.

flyDetect: An Android Application for Flight Detection.

Over the past years, transport mode recognition has become a large field of research. However, flight as a type of transportation has been mostly overlooked. A system for flight detection might be useful for context-aware applications, but more importantly, it can be used to automatically manage airplane mode on smartphones. Smartphones transmit radio frequency signals which could potentially interfere with aircraft systems, and it is therefore important that devices enable airplane mode to avoid this problem. This paper proposes flyDetect, a method for automatic flight mode detection and an embodiment in the form of an app that demonstrates the viability of the method. Thus, the system uses the accelerometer and barometer in an Android smartphone, can detect the start and end of a flight, and notify other apps or systems on the device when this happens. Our evaluation shows that flyDetect meets the requirements set for the solution, and the results are very promising.

An Enhancement of Outdoor Location-Based Augmented Reality Anchor Precision through VSLAM and Google Street View.

Outdoor Location-Based Augmented Reality (LAR) applications require precise positioning for seamless integrations of virtual content into immersive experiences. However, common solutions in outdoor LAR applications rely on traditional smartphone sensor fusion methods, such as the Global Positioning System (GPS) and compasses, which often lack the accuracy needed for precise AR content alignments. In this paper, we introduce an innovative approach to enhance LAR anchor precision in outdoor environments. We leveraged Visual Simultaneous Localization and Mapping (VSLAM) technology, in combination with innovative cloud-based methodologies, and harnessed the extensive visual reference database of Google Street View (GSV), to address the accuracy limitation problems. For the evaluation, 10 Point of Interest (POI) locations were used as anchor point coordinates in the experiments. We compared the accuracies between our approach and the common sensor fusion LAR solution comprehensively involving accuracy benchmarking and running load performance testing. The results demonstrate substantial enhancements in overall positioning accuracies compared to conventional GPS-based approaches for aligning AR anchor content in the real world.

Security Evaluation of Companion Android Applications in IoT: The Case of Smart Security Devices.

Smart security devices, such as smart locks, smart cameras, and smart intruder alarms are increasingly popular with users due to the enhanced convenience and new features that they offer. A significant part of this convenience is provided by the device's companion smartphone app. Information on whether secure and ethical development practices have been used in the creation of these applications is unavailable to the end user. As this work shows, this means that users are impacted both by potential third-party attackers that aim to compromise their device, and more subtle threats introduced by developers, who may track their use of their devices and illegally collect data that violate users' privacy. Our results suggest that users of every application tested are susceptible to at least one potential commonly found vulnerability regardless of whether their device is offered by a known brand name or a lesser-known manufacturer. We present an overview of the most common vulnerabilities found in the scanned code and discuss the shortcomings of state-of-the-art automated scanners when looking at less structured programming languages such as C and C++. Finally, we also discuss potential methods for mitigation, and provide recommendations for developers to follow with respect to secure coding practices.

Lightweight Crypto-Ransomware Detection in Android Based on Reactive Honeyfile Monitoring.

Given the high relevance and impact of ransomware in companies, organizations, and individuals around the world, coupled with the widespread adoption of mobile and IoT-related devices for both personal and professional use, the development of effective and efficient ransomware mitigation schemes is a necessity nowadays. Although a number of proposals are available in the literature in this line, most of them rely on machine-learning schemes that usually involve high computational cost and resource consumption. Since current personal devices are small and limited in capacities and resources, the mentioned schemes are generally not feasible and usable in practical environments. Based on a honeyfile detection solution previously introduced by the authors for Linux and Window OSs, this paper presents a ransomware detection tool for Android platforms where the use of trap files is combined with a reactive monitoring scheme, with three main characteristics: (i) the trap files are properly deployed around the target file system, (ii) the FileObserver service is used to early alert events that access the traps following certain suspicious sequences, and (iii) the experimental results show high performance of the solution in terms of detection accuracy and efficiency.

Novel Multi-Classification Dynamic Detection Model for Android Malware Based on Improved Zebra Optimization Algorithm and LightGBM.

With the increasing popularity of Android smartphones, malware targeting the Android platform is showing explosive growth. Currently, mainstream detection methods use static analysis methods to extract features of the software and apply machine learning algorithms for detection. However, static analysis methods can be less effective when faced with Android malware that employs sophisticated obfuscation techniques such as altering code structure. In order to effectively detect Android malware and improve the detection accuracy, this paper proposes a dynamic detection model for Android malware based on the combination of an Improved Zebra Optimization Algorithm (IZOA) and Light Gradient Boosting Machine (LightGBM) model, called IZOA-LightGBM. By introducing elite opposition-based learning and firefly perturbation strategies, IZOA enhances the convergence speed and search capability of the traditional zebra optimization algorithm. Then, the IZOA is employed to optimize the LightGBM model hyperparameters for the dynamic detection of Android malware multi-classification. The results from experiments indicate that the overall accuracy of the proposed IZOA-LightGBM model on the CICMalDroid-2020, CCCS-CIC-AndMal-2020, and CIC-AAGM-2017 datasets is 99.75%, 98.86%, and 97.95%, respectively, which are higher than the other comparative models.

PsySuite: An android application designed to perform multimodal psychophysical testing.

In behavioral sciences, there is growing concern about the inflation of false-positive rates due to the amount of under-powered studies that have been shared in the past years. While problematic, having the possibility to recruit (lots of) participants (for a lot of time) is realistically not achievable for many research facilities. Factors that hinder the reaching of optimal sample sizes are, to name but a few, research costs, participants' availability and commitment, and logistics. We challenge these issues by introducing PsySuite, an Android app designed to foster a remote approach to multimodal behavioral testing. To validate PsySuite, we first evaluated its ability to generate stimuli appropriate to rigorous psychophysical testing, measuring both the app's accuracy (i.e., stimuli's onset, offset, and multimodal simultaneity) and precision (i.e., the stability of a given pattern across trials), using two different smartphone models. We then evaluated PsySuite's ability to replicate perceptual performances obtained using a classic psychophysical paradigm, comparing sample data collected with the app against those measured via a PC-based setup. Our results showed that PsySuite could accurately reproduce stimuli with a minimum duration of 7 ms, 17 ms, and 30 ms for the auditory, visual, and tactile modalities, respectively, and that perceptual performances obtained with PsySuite were consistent with the perceptual behavior observed using the classical setup. Combined with the high accessibility inherently supported by PsySuite, here we ought to share the app to further boost psychophysical research, aiming at setting it to a cheap, user-friendly, and portable level.

Utilization of android-based paediatric assessment triangle application as an emergency detection tool for children.

Objectives: To identify the effectiveness of an android-based paediatric assessment triangle application in emergency diagnostics. METHODS: The action research study was conducted in the emergency department of a hospital under the Ministry of Defence, Indonesia, located within the Ministry of Defence Rehabilitation Centre Complex, from April to December 2020 after approval from the ethics review committee of the Faculty of Nursing, Universitas Indonesia, Indonesia, employing quantitative and qualitative methods consisting of planning, acting, observing and reflecting stages. Emergency department nurses with at least D3 nursing graduation who were able to identify emergency status in children were included. The subjects were given training on paediatric assessment triangle application before using it in their professional life. The difference was noted through pre- and post-intervention tests. Qualitative data was collected using focus group discussion and system usability scale. RESULTS: Of the 9 nurses, 5(55.6%) were males, 4(44.4%) were females, 8(88.9%) were aged 26-35 years, and 2(22.2%) had professional experience 1-2 years. The mean baseline score was 36.1±11.4, while the mean post-intervention score was 70.9±14.4. The fastest application completion time was 13 seconds, while the slowest was 52 seconds. Qualitative data led to the emergence of 4 themes: time required to complete the application; preference for connectivity with the hospital's electronic record system; assessment of children's clinical status; and, unfamiliarity with the computerised system. The mean system usability scale score was 72.22±11.35 (range: 52.5-92.5). CONCLUSIONS: Paediatric assessment triangle application could be a valid tool for identifying emergency severity in patients during the triage process.

DXA Android-to-Gynoid Ratio and Cardiovascular Risk Assessment in Age and BMI Propensity-Matched Early Postmenopausal Women.

Background and Objectives: The literature suggests that physiological menopause (MP) seems linked with increased adiposity with a preference for intra-abdominal fat accumulation, greater than what can be attributed only by aging, which could magnify this period's increased cardiovascular risk. Materials and Methods: We retrospectively analyzed two age and body mass index (BMI) propensity-matched subgroups each formed of 90 clinically healthy, 40-60-year-old postmenopausal women, within the first 5 and 5-10 years of MP. The 10-year ASCVD risk was assessed using medical history, anthropometric data, and lipid profile blood tests. The android-to-gynoid (A/G) ratio was computed using Lunar osteodensitometry lumbar spine and hip scans. Results: The A/G ratio was significantly higher for the subgroup evaluated in years 5-10 of MP than in the first 5 years of MP, even after controlling for BMI (1.05 vs. 0.99, p = 0.005). While displaying a significant negative correlation with HDL cholesterol (r = 0.406), the A/G ratio also had positive correlations with systolic blood pressure (BP) values (r = 0.273), triglycerides (r = 0.367), and 10-year ASCVD risk (r = 0.277). After adjusting for smoking, hypertension treatment, and type 2 diabetes, the 10-year ASCVD risk became significantly different for women in the first 5 years (3.28%) compared to those in years 5-10 of MP (3.74%), p = 0.047. Conclusions: In women with similar age and BMI, the A/G ratio appears to vary based on the number of years since menopause onset and correlates with either independent cardiovascular risk parameters like BP, triglycerides, and HDL cholesterol or with composite scores, such as 10-year ASCVD risk.

The association of fasting plasma thiol fractions with body fat compartments, biomarker profile, and adipose tissue gene expression.

People with high plasma total cysteine (tCys) have higher fat mass and higher concentrations of the atherogenic apolipoprotein B (apoB). The disulfide form, cystine, enhanced human adipogenesis and correlated with total fat mass in a Middle-Eastern cohort. In 35 European adults with overweight (88.6% women) and with dual-X-ray absorptiometry measurements of regional fat, we investigated how cystine compared to other free disulfides in their association with total regional adiposity, plasma lipid and glucose biomarkers, and adipose tissue lipid enzyme mRNA (n = 19). Most total plasma homocysteine (tHcy) (78%) was protein-bound; 63% of total glutathione (tGSH) was reduced. tCys was 49% protein-bound, 30% mixed-disulfide, 15% cystine, and 6% reduced. Controlling for age and lean mass, cystine and total free cysteine were the fractions most strongly associated with android and total fat: 1% higher cystine predicted 1.97% higher android fat mass (95% CI 0.64, 3.31) and 1.25% (0.65, 2.98) higher total fat mass (both p = 0.005). A positive association between tCys and apoB (ß: 0.64%; 95% CI 0.17, 1.12%, p = 0.009) was apparently driven by free cysteine and cystine; cystine was also inversely associated with the HDL-associated apolipoprotein A1 (ß: -0.57%; 95% CI -0.96, -0.17%, p = 0.007). No independent positive associations with adiposity were noted for tGSH or tHcy fractions. Plasma cystine correlated with CPT1a mRNA (Spearman's r = 0.68, p = 0.001). In conclusion, plasma cystine-but not homocysteine or glutathione disulfides-is associated with android adiposity and an atherogenic plasma apolipoprotein profile. The role of cystine in human adiposity and cardiometabolic risk deserves investigation. ClinicalTrials.gov identifiers: NCT02647970 and NCT03629392.

The association of body composition and fat distribution with hypertension in community-dwelling older adults: the Bushehr Elderly Health (BEH) program.

BACKGROUND: A significant proportion of the global burden of disability and premature mortality has caused by hypertension. It seems that the relationship between obesity and hypertension is not only associated with excessive body fat mass (FM) but also with body adipose distribution patterns. The present study investigated the association between regional fat distribution using dual-energy X-ray absorptiometry and hypertension in older adults. METHODS: This cross-sectional study was performed using the data from Bushehr Elderly Health Program (BEH) on a total of 2419 participants aged 60 and over. Hypertension was defined as SBP of at least 140 mmHg and/or DBP of at least 90 mmHg. SBP between 120 and 139 mmHg and/or a DBP between 80 and 89 mmHg were considered prehypertension. Participants underwent body composition measurement by dual-energy x-ray absorptiometry to analyze FM, fat-free mass (FFM) in trunk and extremities composition. RESULTS: The results showed that 460 (19.02%) of participants had prehypertension, and 1,818 (75.15% ) had hypertension. The odds of having prehypertension (OR: 1.06, 95%CI: 1.01-1.12) and hypertension (OR: 1.08, 95%CI: 1.03-1.13) increased with a rise in total body FM percentage. Moreover, people with a higher FM to FFM ratio had increased odds of being prehypertensive (OR: 9.93, 95%CI: 1.28-76.99) and hypertensive (OR: 16.15, 95%CI: 2.47-105.52). Having a higher android to gynoid FM ratio was related to increased odds of being prehypertensive and hypertensive. CONCLUSIONS: This study showed that a higher body FM, particularly in the android region, is associated with higher odds of having hypertension in older adults.

How can social robot use cases in healthcare be pushed - with an interoperable programming interface.

INTRODUCTION: Research into current robot middleware has revealed that most of them are either too complicated or outdated. These facts have motivated the development of a new middleware to meet the requirements of usability by non-experts. The proposed middleware is based on Android and is intended to be placed over existing robot SDKs and middleware. It runs on the android tablet of the Cruzr robot. Various toolings have been developed, such as a web component to control the robot via a webinterface, which facilitates its use. METHODS: The middleware was developed using Android Java and runs on the Cruzr tablet as an app. It features a WebSocket server that interfaces with the robot and allows control via Python or other WebSocket-compatible languages. The speech interface utilizes Google Cloud Voice text-to-speech and speech-to-text services. The interface was implemented in Python, allowing for easy integration with existing robotics development workflows, and a web interface was developed for direct control of the robot via the web. RESULTS: The new robot middleware was created and deployed on a Cruzr robot, relying on the WebSocket API and featuring a Python implementation. It supports various robot functions, such as text-to-speech, speech-to-text, navigation, displaying content and scanning bar codes. The system's architecture allows for porting the interface to other robots and platforms, showcasing its adaptability. It has been demonstrated that the middleware can be run on a Pepper robot, although not all functions have been implemented yet. The middleware was utilized to implement healthcare use cases and received good feedback. CONCLUSION: Cloud and local speech services were discussed in regard to the middleware's needs, to run without having to change any code on other robots. An outlook on how the programming interface can further be simplified by using natural text to code generators has been/is given. For other researchers using the aforementioned platforms (Cruzr, Pepper), the new middleware can be utilized for testing human-robot interaction. It can be used in a teaching setting, as well as be adapted to other robots using the same interface and philosophy regarding simple methods.

Combination of a DC Motor Controller and Telemetry System to Optimize Energy Consumption.

The paper introduces the development stages of a MOSFET-based controller for a DC brush motor. The main objective was to design a controller that could be integrated with the existing telemetry system, offering full configurability through an Android application. This controller aims to provide real-time analysis of data collected from the measurement system, including motor revolutions and current draw. Based on the analyzed data and the conditions set in the Android application, the controller adjusts the motor's operational characteristics accordingly. The paper provides a comprehensive description of the controller system's functioning. The proposed control system is particularly relevant in applications where minimizing energy consumption for driving a DC motor is of utmost importance.

Survey on Blockchain-Based Data Storage Security for Android Mobile Applications.

This research paper investigates the integration of blockchain technology to enhance the security of Android mobile app data storage. Blockchain holds the potential to significantly improve data security and reliability, yet faces notable challenges such as scalability, performance, cost, and complexity. In this study, we begin by providing a thorough review of prior research and identifying critical research gaps in the field. Android's dominant position in the mobile market justifies our focus on this platform. Additionally, we delve into the historical evolution of blockchain and its relevance to modern mobile app security in a dedicated section. Our examination of encryption techniques and the effectiveness of blockchain in securing mobile app data storage yields important insights. We discuss the advantages of blockchain over traditional encryption methods and their practical implications. The central contribution of this paper is the Blockchain-based Secure Android Data Storage (BSADS) framework, now consisting of six comprehensive layers. We address challenges related to data storage costs, scalability, performance, and mobile-specific constraints, proposing technical optimization strategies to overcome these obstacles effectively. To maintain transparency and provide a holistic perspective, we acknowledge the limitations of our study. Furthermore, we outline future directions, stressing the importance of leveraging lightweight nodes, tackling scalability issues, integrating emerging technologies, and enhancing user experiences while adhering to regulatory requirements.

Developing a Smartwatch-Based Healthcare Application: Notes to Consider.

Wearable devices and fitness trackers have gained popularity in healthcare and telemedicine as tools to reduce hospitalization costs, improve personalized health management, and monitor patients in remote areas. Smartwatches, particularly, offer continuous monitoring capabilities through step counting, heart rate tracking, and activity monitoring. However, despite being recognized as an emerging technology, the adoption of smartwatches in patient monitoring systems is still at an early stage, with limited studies delving beyond their feasibility. Developing healthcare applications for smartwatches faces challenges such as short battery life, wearable comfort, patient compliance, termination of non-native applications, user interaction difficulties, small touch screens, personalized sensor configuration, and connectivity with other devices. This paper presents a case study on designing an Android smartwatch application for remote monitoring of geriatric patients. It highlights obstacles encountered during app development and offers insights into design decisions and implementation details. The aim is to assist programmers in developing more efficient healthcare applications for wearable systems.

An Android Malware Detection Approach to Enhance Node Feature Differences in a Function Call Graph Based on GCNs.

The smartphone has become an indispensable tool in our daily lives, and the Android operating system is widely installed on our smartphones. This makes Android smartphones a prime target for malware. In order to address threats posed by malware, many researchers have proposed different malware detection approaches, including using a function call graph (FCG). Although an FCG can capture the complete call-callee semantic relationship of a function, it will be represented as a huge graph structure. The presence of many nonsensical nodes affects the detection efficiency. At the same time, the characteristics of the graph neural networks (GNNs) make the important node features in the FCG tend toward similar nonsensical node features during the propagation process. In our work, we propose an Android malware detection approach to enhance node feature differences in an FCG. Firstly, we propose an API-based node feature by which we can visually analyze the behavioral properties of different functions in the app and determine whether their behavior is benign or malicious. Then, we extract the FCG and the features of each function from the decompiled APK file. Next, we calculate the API coefficient inspired by the idea of the TF-IDF algorithm and extract the sensitive function called subgraph (S-FCSG) based on API coefficient ranking. Finally, before feeding the S-FCSG and node features into the GCN model, we add the self-loop for each node of the S-FCSG. A 1-D convolutional neural network and fully connected layers are used for further feature extraction and classification, respectively. The experimental result shows that our approach enhances the node feature differences in an FCG, and the detection accuracy is greater than that of models using other features, suggesting that malware detection based on a graph structure and GNNs has a lot of space for future study.

Android Ransomware Detection Using Supervised Machine Learning Techniques Based on Traffic Analysis.

In today's digitalized era, the usage of Android devices is being extensively witnessed in various sectors. Cybercriminals inevitably adapt to new security technologies and utilize these platforms to exploit vulnerabilities for nefarious purposes, such as stealing users' sensitive and personal data. This may result in financial losses, discredit, ransomware, or the spreading of infectious malware and other catastrophic cyber-attacks. Due to the fact that ransomware encrypts user data and requests a ransom payment in exchange for the decryption key, it is one of the most devastating types of malicious software. The implications of ransomware attacks can range from a loss of essential data to a disruption of business operations and significant monetary damage. Artificial intelligence (AI)-based techniques, namely machine learning (ML), have proven to be notable in the detection of Android ransomware attacks. However, ensemble models and deep learning (DL) models have not been sufficiently explored. Therefore, in this study, we utilized ML- and DL-based techniques to build efficient, precise, and robust models for binary classification. A publicly available dataset from Kaggle consisting of 392,035 records with benign traffic and 10 different types of Android ransomware attacks was used to train and test the models. Two experiments were carried out. In experiment 1, all the features of the dataset were used. In experiment 2, only the best 19 features were used. The deployed models included a decision tree (DT), support vector machine (SVM), k-nearest neighbor (KNN), ensemble of (DT, SVM, and KNN), feedforward neural network (FNN), and tabular attention network (TabNet). Overall, the experiments yielded excellent results. DT outperformed the others, with an accuracy of 97.24%, precision of 98.50%, and F1-score of 98.45%. Whereas, in terms of the highest recall, SVM achieved 100%. The acquired results were thoroughly discussed, in addition to addressing limitations and exploring potential directions for future work.

Detection of Android Malware in the Internet of Things through the K-Nearest Neighbor Algorithm.

Predicting attacks in Android malware devices using machine learning for recommender systems-based IoT can be a challenging task. However, it is possible to use various machine-learning techniques to achieve this goal. An internet-based framework is used to predict and recommend Android malware on IoT devices. As the prevalence of Android devices grows, the malware creates new viruses on a regular basis, posing a threat to the central system's security and the privacy of the users. The suggested system uses static analysis to predict the malware in Android apps used by consumer devices. The training of the presented system is used to predict and recommend malicious devices to block them from transmitting the data to the cloud server. By taking into account various machine-learning methods, feature selection is performed and the K-Nearest Neighbor (KNN) machine-learning model is proposed. Testing was carried out on more than 10,000 Android applications to check malicious nodes and recommend that the cloud server block them. The developed model contemplated all four machine-learning algorithms in parallel, i.e., naive Bayes, decision tree, support vector machine, and the K-Nearest Neighbor approach and static analysis as a feature subset selection algorithm, and it achieved the highest prediction rate of 93% to predict the malware in real-world applications of consumer devices to minimize the utilization of energy. The experimental results show that KNN achieves 93%, 95%, 90%, and 92% accuracy, precision, recall and f1 measures, respectively.

Distributed Detection of Malicious Android Apps While Preserving Privacy Using Federated Learning.

Recently, deep learning has been widely used to solve existing computing problems through large-scale data mining. Conventional training of the deep learning model is performed on a central (cloud) server that is equipped with high computing power, by integrating data via high computational intensity. However, integrating raw data from multiple clients raises privacy concerns that are increasingly being focused on. In federated learning (FL), clients train deep learning models in a distributed fashion using their local data; instead of sending raw data to a central server, they send parameter values of the trained local model to a central server for integration. Because FL does not transmit raw data to the outside, it is free from privacy issues. In this paper, we perform an experimental study that explores the dynamics of the FL-based Android malicious app detection method under three data distributions across clients, i.e., (i) independent and identically distributed (IID), (ii) non-IID, (iii) non-IID and unbalanced. Our experiments demonstrate that the application of FL is feasible and efficient in detecting malicious Android apps in a distributed manner on cellular networks.