Android Devices Research Articles

Plant pathology identification using local-global feature level based on transformer

Deep learning plays a crucial role in addressing the challenge of plant disease identification in the field of agriculture. Detecting diseases in plants requires extensive effort, along with a comprehensive understanding of various plant diseases and increased processing time. Balancing both speed and accuracy in predicting leaf diseases in plants can significantly improve crop production and reduce environmental damage. In this paper, we examined deseases on popular plants in agriculture. We proposed a novel model to predict crop pathology on a feature space of global-local based on transformer aggregation. Paticular, we use refined feature of different layer to correlate semantics from high-level feature and low-level feature. Besides, to capture the extended temporal scale across the entire image, we employ a transformer to discern long-range dependencies among frames. Subsequently, the enhanced features incorporating these dependencies are inputted into a classifier for preliminary crop pathology prediction. The plant village dataset and VietNam strawberry disease (VNStr) dataset were utilized for training and disease classification in the experiments. Extensive experiments show that the proposed method outperforms by 99.18% and 94.05% accuracy in plant village and VNStr, respectivly. The model after being judged was applied on Android devices and therefore is easy to use.

The Hearing Test App for Android Devices: Distinctive Features of Pure-Tone Audiometry Performed on Mobile Devices [Response to Letter

The Hearing Test App for Android Devices: Distinctive Features of Pure-Tone Audiometry Performed on Mobile Devices [Response to Letter

Pengenalan Presensi Kehadiran Menggunakan Kode Qr Berbasis Gawai Android

Presence recognition training using QR codes based on Android devices could be one of the trainings that can be developed by students because the competency gain from this training is quite promising. If students/santri after becoming alumni can later develop these competencies, it can be very profitable. If in the Islamic boarding school environment the alumni spread across their regions and try in various fields, of course knowledge of using the QR code scanner digital application on Android devices will be very useful, especially for the administration system. Partners in this PKM activity are teachers/administrative staff/students of Assaadah Puri Serpong Islamic High School within the Assaadah Puri Serpong Islamic Boarding School environment. The training on introducing attendance using QR codes based on Android devices was carried out with the stages of introduction, counseling and assistance in the practice of using it. Based on the results of observations and discussions with partners, there are several problems faced, especially related to the student attendance review system which still uses a manual/paper-based system, resulting in difficulties in organizing, processing and controlling student attendance data both at the teaching staff level and in the school administration. The lack of technical knowledge regarding the use of digital applications on Android devices, such as a QR code scanner application which can actually be used for student attendance applications, is one of the obstacles for school equipment to be able to manage a more efficient attendance administration system. The solutions carried out in this PKM activity related to existing problems are: 1. Technical aspect: this aspect includes things you need to know about a simple presence attendance application using a QR code based on an Android device. The PKM team helps with the above matters through counseling and training so that a good understanding of this aspect is obtained so that they are technically able to practice it. 2. Management Aspect: this aspect is related to the management of the presence data obtained. So far, data management is still carried out manually without the use of a good application system. For this reason, the PKM team helps to solve problems in the management aspect with training methods on how to manage student attendance percentage data that is more practical, accurate, effective and efficient.

Four Quadrant Operation of DC Motor Controlled by Android Application

Abstract: The project is designed to develop a four quadrant speed control system for a DC motor. The motor is operated in four quadrants i.e. clockwise; counter clock-wise, forward brake and reverse brake. It also has a feature of speed control. The four quadrant operation of the dc motor is best suited for industries where motors are used and as per requirement as they can rotate in clockwise, counter-clockwise and also apply brakes immediately in both the directions. In case of a specific operation in industrial environment, the motor needs to be stopped immediately. In such scenario, this proposed system is very apt as forward brake and reverse brake are its integral features. Instantaneous brake in both the directions happens as a result of applying a reverse voltage across the running motor for a brief period and the speed control of the motor can be achieved with the PWM pulses generated by the microcontroller. The microcontroller used in this project is from 8051 family. Remote operation is achieved by any smart-phone/Tablet etc., with Android OS, upon a GUI (Graphical User Interface) based touch screen operation. Bluetooth device is provided to connect with android application device for the operation of the motor which are interfaced to the microcontroller that provides an input signal to it and in turn controls the speed of the motor through a motor driver IC. This project can be enhanced by using higher power electronic devices to operate high capacity DC motors. Regenerative braking for optimizing the power consumption can also be incorporated

Mobile Tracking System Using SMTP Protocol

Abstract: The objective of this project is to enhance mobile security through a robust Android application capable of tracking, locking, and recovering lost or stolen mobile devices. Utilizing the capabilities of Android devices, the system offers real-time tracking, remote locking, device wiping, and geo fencing features. It supports Android OS and allows users to control their devices remotely via SMS commands or through a web-based dashboard using their account credentials. Users can track the location of their device, remotely lock it, and even manipulate the camera to capture images of the possessor. The rising incidence of mobile device theft, which often results in unauthorized access and personal data breaches, underscores the importance of this sophisticated Mobile Tracking System (MTS). This system addresses these security concerns by providing comprehensive functionalities that enhance user safety and device recovery.

A Robust License Plate Detection System Using Smart Device

The license plate recognition (LPR) system is widely employed in various applications. However, most research studies have used a fixed camera rather than a moving one. This is because the location of the vehicle plate is nearly static and easily estimated, making the use of a static camera simple for locating and detecting the scanned license plate. Images obtained with a moving camera are highly complex due to frequent background changes. Additionally, a challenge with car plates in Malaysia is their non-standardized nature. Car owners are permitted to use any font type for their license plate number, rendering existing license plate recognition systems from other countries incapable of effectively detecting license plates on Malaysian car plates. A traditional LPR system typically requires a high-quality camera and a powerful computer for costly and bulky processing. Nowadays, many smartphones come equipped with powerful processors and cameras. Android smartphones include various libraries for modifying hardware configurations such as the camera. This paper presents a robust method for detecting Malaysia's license plate number using a convolutional neural network (CNN). The CNN model from the pre-training process is imported to the Android device and tested in real-time in an on-road driving environment, resulting in an average recognition rate of 89.37%. A comprehensive Character Recognition Analysis is also presented to demonstrate the accuracy of each character. However, there is still room for improvement in recognizing the character Q.

A Model for Detection and Prevention of AndroRat in Mobile Devices

Android operating systems has gained increasing popularity in smart phones and other mobile intelligent terminals in recent years. Unpleasantly, the accumulation development and open nature of the platform has also attracted a vast number of malware developers. This dissertation presents a model for detecting and preventing AndroRat, a notorious Remote Administration Tool (RAT), on android devices. The research systematically pursued predefined objectives, leading to the development of a robust detection framework that utilizes the Outlier Technique. This framework significantly enhances the accuracy of AndroRat identification. Moreover, the dissertation introduces a preventive mechanism based on Recurrent Neural Network (RNN), fortifying Android phones against potential threats posed by RATs. By achieving the outlined objectives, this research makes a noteworthy contribution to the field of mobile device security. It demonstrates a practical application of machine learning techniques in mitigating evolving cybersecurity threats. A dataset was gathered for constructing the model. Object Oriented Analysis and Design (OOAD) was used as the research methodology and python was used as the programming language. The implementation of the Python Programming Language in this system not only ensured efficient execution but also established a versatile and accessible platform, laying the groundwork for future enhancements and adaptations. The comparative analysis conducted against existing systems highlights the effectiveness and innovation embedded in the proposed model, affirming its potential as a valuable addition to the realm of AndroRat detection and prevention with an accuracy of 99.99%. This dissertation not only addresses current security challenges but also establishes a foundation for continued advancements in mobile device security through the integration of cutting-edge technologies.

Drowsiness Detection and Alert System

Drowsiness detection is a solution for identifying signs of fatigue or sleepiness in individuals. One of the key features of our model is that it can detect drowsiness at night as well using Mobile cameras (infrared sensors). The system captures infrared images of the person's face and analyzes the physiological and behavioral cues related to drowsiness. Infrared sensors allow for drowsiness detection in low-light conditions, making it particularly useful for night-time scenarios such as night driving. The system can trigger alerts or interventions if drowsiness is detected, helping to prevent accidents or mistakes. We will be using libraries like OpenCV, TensorFlow, CNN, and VGG19 features in our model. By combining the accessibility of Android devices with the advanced capabilities of the Deep Learning algorithm, drowsiness detection using infrared sensors has the potential to greatly improve the safety and productivity of individuals in their daily lives.

CLAID: Closing the Loop on AI & Data Collection — A cross-platform transparent computing middleware framework for smart edge-cloud and digital biomarker applications

The increasing number of edge devices with enhanced sensing capabilities, such as smartphones, wearables, and IoT devices equipped with sensors, holds the potential for innovative smart-edge applications in healthcare. These devices generate vast amounts of multimodal data, enabling the implementation of digital biomarkers which can be leveraged by machine learning solutions to derive insights, predict health risks, and allow personalized interventions. Training these models requires collecting data from edge devices and aggregating it in the cloud. To validate and verify those models, it is essential to utilize them in real-world scenarios and subject them to testing using data from diverse cohorts. Since some models are too computationally expensive to be run on edge devices directly, a collaborative framework between the edge and cloud becomes necessary. In this paper, we present CLAID, an open-source cross-platform middleware framework based on transparent computing compatible with Android, iOS, WearOS, Linux, macOS, and Windows. CLAID enables logical integration of devices running different operating systems into an edge-cloud system, facilitating communication and offloading between them, with bindings available in different programming languages. We provide Modules for data collection from various sensors as well as for the deployment of machine-learning models. Furthermore, we propose a novel methodology, ML-Model in the Loop for verifying deployed machine learning models, which helps to analyze problems that may occur during the migration of models from cloud to edge devices. We verify our framework in three different experiments and achieve 100% sampling coverage for data collection across different sensors as well as an equal performance of a cough detection model deployed on both Android and iOS devices. Additionally, we compare the memory and battery consumption of our framework across the two mobile operating systems.

Teaching three-phase half-wave power electronic rectifier with gamified augmented reality support

This paper presents a support tool designed for instructors in technical education within engineering programs, focusing specifically on power electronics and laboratory procedures related to the three-phase half-wave rectifier. The Augmented Reality (AR) application was developed for Android devices using Unity+Vuforia, employing a gamification-based approach. The application allows students to evaluate their knowledge and skills in real-time and offers an interactive learning environment. It provides learning diagnostics and sends each student's evaluation to a database stored on Google-Forms that is accessible by the instructor or assessor in question. It's important to note that this APP is freely accessible through the Android APP store. The learning strategy is around a game that tests players on their knowledge of measuring devices and theoretical concepts. Additionally, there is a puzzle task that encourages learners to correctly arrange the waveforms in a rectifier. Students can also connect the half-wave rectifier's essential connections and the transformer's delta-star connections through touch interaction. A comparison study between traditional teaching methods and the innovative AR-based approach has been conducted. This educational proposal itself is an innovative solution that will be especially helpful for laboratories lacking useful equipment in Mexican colleges. To test the effect of AR application on student success, an experimental study was conducted on two groups of students (a control group [non-using AR] and a test group [using AR]). To determine significant difference in acquired learning, an ANOVA statistical analysis was conducted using independent sample tests. According to tests result, there is a significant difference in the acquired knowledge for those who used the designed tool. The probability value (p = 1e-5 <0.05) for the use of AR is found. They increase their initial average grade from 27.08% to 72.3%, in contrast to the control group with no significant increasing learning, reporting an initial average grade of 28.75–43.33%. These results show that the use of AR in electronic practice makes a significant difference in student success.

Analysis of Elfan Bookless Library System Innovation at the Barru Regency Library and Archives Office

This qualitative study explores the innovation of the Elfan Bookless Library System at the Barru Regency Library and Archives Office. Data were collected through observation, interviews, and documentation, with validity ensured via triangulation, negative case analysis, member checking, and extended observations. The findings reveal that the Elfan Bookless Library System enhances the reading experience by providing its own Wi-Fi network, allowing online book access. While the system effectively meets visitors' needs, its Wi-Fi coverage is limited to 500 meters, posing a connectivity challenge beyond this range. Despite this, the system is accessible without special requirements; visitors only need a cellphone or Android device. User guidance is provided through tutorials on billboards and banners, and library staff offers additional support. This study highlights the Elfan Bookless Library System's potential to innovate public library services, offering valuable insights into its advantages and limitations. These findings contribute to understanding how digital library systems can be optimized to improve user experience and accessibility in public libraries.

Oversharing the super safe stuff: “Privacy-washing” in Apple iPhone and Google Pixel commercials

Inspired by the ever-evolving concerns surrounding data privacy, this study analyzes Apple’s and Google’s ads for their iPhone and Android devices, respectively, as well as each company’s privacy policies. Findings via critical discourse analysis reveal that the ads conflate privacy with security, relying on powerful imageries that depict the phones as safes from which data cannot travel. These depictions, however, do not align with the policies that provide separate sections for privacy and security. With these findings in mind, I propose a widespread adoption of “privacy-washing” to promote a newfound literacy of granular data types.

BraNet: a mobil application for breast image classification based on deep learning algorithms

Mobile health apps are widely used for breast cancer detection using artificial intelligence algorithms, providing radiologists with second opinions and reducing false diagnoses. This study aims to develop an open-source mobile app named “BraNet” for 2D breast imaging segmentation and classification using deep learning algorithms. During the phase off-line, an SNGAN model was previously trained for synthetic image generation, and subsequently, these images were used to pre-trained SAM and ResNet18 segmentation and classification models. During phase online, the BraNet app was developed using the react native framework, offering a modular deep-learning pipeline for mammography (DM) and ultrasound (US) breast imaging classification. This application operates on a client–server architecture and was implemented in Python for iOS and Android devices. Then, two diagnostic radiologists were given a reading test of 290 total original RoI images to assign the perceived breast tissue type. The reader’s agreement was assessed using the kappa coefficient. The BraNet App Mobil exhibited the highest accuracy in benign and malignant US images (94.7%/93.6%) classification compared to DM during training I (80.9%/76.9%) and training II (73.7/72.3%). The information contrasts with radiological experts’ accuracy, with DM classification being 29%, concerning US 70% for both readers, because they achieved a higher accuracy in US ROI classification than DM images. The kappa value indicates a fair agreement (0.3) for DM images and moderate agreement (0.4) for US images in both readers. It means that not only the amount of data is essential in training deep learning algorithms. Also, it is vital to consider the variety of abnormalities, especially in the mammography data, where several BI-RADS categories are present (microcalcifications, nodules, mass, asymmetry, and dense breasts) and can affect the API accuracy model.Graphical abstract

The Hearing Test App for Android Devices: Distinctive Features of Pure-Tone Audiometry Performed on Mobile Devices [Letter

The Hearing Test App for Android Devices: Distinctive Features of Pure-Tone Audiometry Performed on Mobile Devices [Letter

Android Pattern Bypass using Microcontroller

Abstract: The goal is to exploit a potential security vulnerability in Android devices by using a microcontroller which goes by the name ATTiny85 connected via USB. The objective is to bypass the lock patterns or security measures typically in place on Android devices, which are designed to prevent unauthorized access. This could involve manipulating the USB connection to take control of the device's data or functions, potentially compromising the device's security. Such actions are unethical and illegal without proper authorization. It’s really important to acknowledge the amount of loss these attacks incur. The primary aim is to capitalize on a potential security vulnerability inherent in Android devices through the utility provided by microcontroller. This strategy is devised to circumvent the established lock patterns and security protocols usually implemented on Android devices, serving as a deterrent against unauthorized access. This approach may entail manipulating the USB connection to infiltrate the device's data or functionalities, posing a significant threat. It is crucial to emphasize that engaging in such activities is not only unethical but also illegal without explicit authorization. This underscores the paramount importance of upholding robust security measures on Android devices to proactively thwart any attempts at exploitation.

A Survey of Mobile Application Based Collision Detection Alert System for Motor Vehicles

Accidents involving motor vehicles are a big problem on a global scale, and they frequently result in terrible deaths. Responding to emergencies in a timely manner is absolutely necessary in order to improve survival rates in instances like these. Alternatively, this reaction time is dependent upon the presence of automatic in-vehicle crash detection and reporting approaches, which are commonly seen in high-end or luxury automobiles. Due of this, there is a gap in safety, particularly in low-end automobiles, which are widespread in developing nations. Original equipment manufacturers (OEMs) do not often install such devices in their vehicles. This research provides a unique way to solve this important issue, which is an autonomous collision detection system which uses smartphones. Our method makes use of the sensor capabilities of cellphones, such as Accelerometer, Gyroscope,GPS and GSM , in order to correctly detect collisions. This is accomplished despite the limits of the sensors, which includes range and sensitivity. As a result of this, this system presents an option that is more cost-effective than the expensive collision detection systems that are combined with the premium automobiles. In addition, this method eliminates the cost barrier, which enables it to be compatible with Android devices whereas it was previously only compatible with iPhones. The focus of this approach is mainly placed on the significance of minimising reaction times in the event of traffic accidents. It highlights the disparity between different car categories in terms of safety features and provides the solution that is based on smartphones.

BANKS SHORT MESSAGE SERVICE THREATS NOTIFICATION SYSTEM ON ANDROID BASED PHONE

This research is carried out for the development and implementation of an end-to-end encrypted Short Message Service (SMS) App, utilizing a hybrid cipher algorithm, driven by the notable insecurity observed in SMS communications on mobile devices. SMS is a widely used communication method, and the primary goal of this study is to create a system (App) for end-to-end encrypted SMS. Loss of phones is becoming vulnerable for threats, because we store vital records in android and these records are secret such that no other third party is required to see them, such as Bank SMS, Event Notification etc. Also this information can be compromised if android phone is been lost and found by the criminals. Kidnapping activity is serious case happening in northern part of Nigeria, so if a phone is being lost and discovered how financed he is (the device holder), there is any means of bank account compromisation as that would allow the bank to give some information about the account because of the registered SIM card inserted in android devices (phones). This system is aimed to secure Bank SMS by not allowing an unauthorized person to views the banks SMS, but all other SMS can be view. Whenever the Banks SMS is received by the Android phone, the system will encrypt it and can only be viewed if using correct decryption key, a notification will be sent to the owner other phone if more than two attempt to view the message is made, using a Hybrid Cipher...

Desktop Stream

Abstract: The "Desktop Stream" approach is all about breaking barriers between Android devices and desktop computers. It lets you easily access your desktop from your Android, wherever you are. By combining Python for the desktop side and Java for Android, it brings mobility, accessibility, and multi-device collaboration to a whole new level. It uses screen sharing, allowing multiple Android devices to peek at your desktop at the same time. Thanks to a middleware server powered by Firebase and Ngrok, you can work together in real-time, share stuff, and get things done. This approach is perfect for today's world, where remote work and teamwork are crucial. It's built to be user-friendly, secure, and scalable. It turns your desktop into a super-portable resource that you can access from anywhere. "Desktop Stream" is not just a cool idea; it's a practical solution that makes remote desktop access a breeze. In this report, we'll dive into how it works, how we made it happen, and why it's a game-changer for remote collaboration.

Gamificação na prevenção de queimaduras: desenvolvimento de um jogo infantil

Burns are a public health problem and result in physical, psychological as well as social repercussions, leading to death. The objective of this study is to develop a game that can distribute information, with the focus on burn prevention and serving as an alternative for health education. This is technological research for the experimental development of a game focusing on the prevention of childhood burns and using the problematization method based on the Maguerez Arch. Gamification is an innovative alternative for training and for behavioral changing and health education is a strategic tool that helps and strengthens care. The game was made for children aged six to ten years old and will be made available in a virtual environment for Android devices. Assistance from a programming language professional was required to program the game. Nowadays, it is necessary to keep up with innovations and technologies, improving interaction with children.

Garbage Collection Android Application

Abstract: The "Android Garbage Collection Application" stands as an innovative solution tailored for Android devices, with the objective of revolutionizing waste management in smart cities. Conventional waste collection methods frequently result in missed pickups, litter accumulation, and potential public health risks. This project harnesses seamless integration with Firebase to create a user-friendly Android app. It provides real-time notifications to residents as garbage collection trucks approach their locations. A central feature of this app is its live tracking system, enabling users to monitor the precise location of the garbage truck in real-time. Additionally, it offers estimated arrival times, effectively reducing waiting times for residents and optimizing the waste collection process. What truly sets this application apart is its focus on community engagement. By actively involving residents in the waste management process, it encourages shared responsibility and cooperation among city dwellers, fostering a cleaner environment and ensuring timely and efficient waste collection. Furthermore, this project serves as a testament to the transformative power of modern technology in enhancing traditional municipal services. It exemplifies how integrating cuttingedge technology can effectively address longstanding challenges and enhance the quality of life for residents in smart cities. The scalability and adaptability of this application make it a valuable asset for optimizing waste management in various urban settings. Its data analytics capabilities provide city officials with valuable insights, enabling more informed decision-making and a proactive approach to waste management