Mobile Platform Research Articles (Page 1)

Today, there is a high demand for remote rehabilitation using mobile robotic complexes all over the world. They offer a wide range of options for convenient and effective therapy at home to patients and the elderly, especially those bedridden after musculoskeletal injuries. In this case, modern approaches to the development of exoskeletons for the rehabilitation of the lower extremities are especially relevant for the effective restoration of lost motor functions. Taking into account the advantages and features of robotic rehabilitation, this work is devoted to the development of a prototype exoskeleton for the ankle joint and experimental studies of the remote control module. The proposed new exoskeleton prototype design was integrated with a mobile wireless communication platform, allowing remote control of the position of the exoskeleton foot using a remote control device. As a result of functional testing, the root mean square error (RMSE) was 23.9° for dorsiflexion/plantarflexion movements and 12.8° for inversion and eversion movements, as well as an average signal transmission delay of about 100 ms and packet loss of 0.6%. These results reflect the technical feasibility of remote control at a distance of up to 10 m. The developed system is mobile, autonomous, and easy to use, which confirms its suitability as a laboratory platform for functional verification and testing of module consistency.

Like to most Kenyan sub-counties, the economy of Kitui County is supported by small and medium-sized enterprises that also contribute greatly to employment in the country and gross domestic product. However, most of the businesses are faced with challenges such as slow usage of technology that inhibits their capacity to grow and compete. The paper set out to discuss the adoption and growth of small and medium enterprises in the context of technology in Kitui County. Three theories were used to support the research: diffusion of innovations, technology acceptance model (TAM) and resource-based view. A descriptive study was adopted to target 4,088 SME owners across different industries. A stratified random sampling process was applied to get a sample size of 365 SMEs. Data collection was done using semi-structured questionnaires that were aimed at quantitative data. The results were presented in tables and charts. The study proved valuable in offering SME owners and entrepreneurs, insights into how various technological tools such as internet access, mobile money services, digital marketing strategies, and business management software could be leveraged to promote business growth. This information enabled them to make more informed decisions about technology investments, ultimately enhancing their operations and competitive positioning in the market. The study revealed a strong positive Pearson correlation between internet availability and SME development, indicating that improved internet access significantly supported the growth of small and medium enterprises. A statistically significant positive relationship was found between internet access and SME growth indicating that improved connectivity supports enterprise development. Mobile money services also showed a strong positive correlation with SME expansion, with regression analysis confirming a significant effect. Digital marketing strategies demonstrated a similarly strong positive correlation with SME growth, with regression results highlighting them as the most impactful factor. Additionally, the use of business management software was significantly associated with SME development, emphasizing its value in enhancing operational efficiency. Based on these findings, the study recommended several strategic actions. Government agencies and private internet providers should enhance internet infrastructure to improve connectivity. Financial institutions and mobile service providers were encouraged to strengthen mobile money platforms and promote inclusive adoption. Furthermore, marketing consultants and business development entities should offer training on effective digital marketing techniques. Lastly, SME support programs should integrate digital literacy initiatives and training on business management software to empower entrepreneurs with tools for informed decision-making and efficient planning. These measures are expected to drive sustainable growth and competitiveness among SMEs in the region.

Purpose Car-hailing services have reshaped urban mobility within the sharing economy, yet service reliability and safety concerns deter approximately 40% of consumers from engaging with these platforms. Despite the growing significance of digital platforms in mobility services, existing research lacks a robust framework for assessing service quality. This study develops and validates a comprehensive measurement instrument that captures three critical dimensions of car-hailing service quality: service delivery quality, service provider quality and service platform quality. By establishing a structured evaluation framework, this research enhances strategic decision-making for platform managers, strengthens consumer trust and supports data-driven improvements in service operations. Design/methodology/approach A multi-stage research design was adopted to develop and validate the measurement instrument. The study first conducted exploratory factor analysis through pilot testing to refine scale structure, followed by confirmatory factor analysis in a field study to assess reliability and validity. Additionally, six competing models were tested to determine the most appropriate structure. The final instrument comprises three second-order dimensions, 11 first-order dimensions and 41 measurement items, offering a robust framework for evaluating service quality in the car-hailing sector. Findings The study identifies three core dimensions crucial to car-hailing service quality: service delivery quality, service provider quality and service platform quality. Among the six competing models, Competing Models 4 and 6 demonstrated superior model fit, confirming their applicability in different operational contexts. The validated instrument offers strategic insights for platform managers, enabling them to enhance customer satisfaction, optimize service offerings and strengthen competitive positioning. The findings highlight the importance of service quality measurement in digital platform governance, reinforcing its role in consumer engagement and operational decision-making within SE-based transportation services. Research limitations/implications While the instrument is rigorously validated, this study focuses primarily on data from selected car-hailing platforms, which may limit generalizability across different SE-driven mobility services. Future research can extend the model to other on-demand service sectors and explore how platform-specific governance factors influence service quality. Practical implications The validated instrument serves as a decision-support tool for platform managers, allowing them to systematically assess and improve service quality. Insights from the study can help managers refine pricing models, driver allocation strategies and platform policies, ultimately enhancing service efficiency and customer loyalty. Originality/value This study is among the first to develop a validated service quality measurement instrument specifically tailored to SE-driven car-hailing services. It advances service quality management theory by integrating digital platform characteristics, algorithm-driven service allocation and human service interactions. The instrument provides practical applications for industry practitioners, offering a structured framework for optimizing service excellence, strengthening consumer trust and improving strategic decision-making in digital mobility platforms.

The article presents the design and initial implementation of a low-cost air quality monitoring system integrated with an unmanned mobile platform (UAV). The system is based on an open-source microcomputer (Raspberry Pi) to which a set of environmental sensors (PM, CO, CO₂, NO₂, CH₄, VOC, NH₃ and others) is connected. Each of the sensors can be dynamically mounted and configured thanks to a flexible software system. Data is saved locally on an SD card and sent in real time to a remote server using a GSM/LTE module. Thanks to the integration with the GPS module, it is possible to create spatial maps of air pollution, which opens up new possibilities of applications in urban and agricultural environments. The system can simultaneously support from several to a dozen or so sensors of different types, which makes it a universal tool for field studies of atmosphere quality.

Objectives: To develop and evaluate an AI-driven mobile platform that integrates deep learning-based exercise analysis with large language model (LLM) feedback for enhancing osteoarthritis (OA) rehabilitation accessibility and effectiveness. Methods: A deep learning framework was developed using Long Short-Term Memory (LSTM) architecture to classify exercise phases from video data of 10 rehabilitation exercises. The dataset consisted of approximately 800,000 frames collected from 20 healthy volunteers. A feedback system utilizing chain-of-thought reasoning in LLMs (GPT-4o and Claude 3.5 Sonnet) was implemented to generate targeted corrective feedback. Evaluation was conducted with OA patients (n=2) and physiotherapists (n=7) using the Intraclass Correlation Coefficient (ICC) and Likert scales. Results: The developed LSTM models achieved 97.8% accuracy in exercise phase classification. Strong agreement between system-generated scores and expert evaluations was demonstrated (ICC=0.85). Physiotherapists slightly preferred Claude's outputs (52.4% vs 47.6%) but rated GPT-4o higher on clinical relevance (4.57/5 vs 4.13/5), clarity (4.71/5 vs 4.38/5), and helpfulness (4.50/5 vs 4.29/5). Conclusions: DeepTherapy effectively addresses critical limitations in rehabilitation monitoring by providing qualitative movement assessment, identifying incorrect movements, and offering detailed guidance on technique improvement, potentially increasing rehabilitation accessibility while maintaining quality of care.

Advancements in robotics and computer vision are transforming how infrastructure is monitored and maintained. This paper presents a novel, fully automated pipeline for pavement condition assessment that integrates real-time image analysis with PCI (Pavement Condition Index) computation, which is specifically designed for deployment on mobile and robotic platforms. Unlike traditional methods that rely on costly equipment or manual input, the proposed system uses deep learning-based object detection and ensemble segmentation to identify and measure multiple types of road distress directly from 2D imagery, including surface weathering, a key precursor to pothole formation often overlooked in previous studies. Depth estimation is achieved using a monocular diffusion model, enabling volumetric assessment without specialized sensors. Validated on real-world footage captured by a smartphone, the pipeline demonstrated reliable performance across detection, measurement, and scoring stages. Its potential hardware-agnostic design and modular architecture position it as a practical solution for autonomous inspection by drones or ground robots in future smart infrastructure systems.

Natural disasters such as floods, earthquakes, and landslides frequently result in extensive damage, loss of life, and delayed relief due to inaccessible terrains and damaged infrastructure. To overcome these challenges, VisionRelief introduces an AI-powered drone-based disaster response system designed to deliver emergency medical supplies, communication devices, and aid packages to affected areas in real time. The system integrates computer vision, thermal imaging, and satellite mapping to detect survivors, classify disaster zones, and optimize drone navigation using intelligent pathfinding algorithms. With a payload capacity of up to 5 kilograms, the drone autonomously identifies and prioritizes red zones, ensuring immediate relief delivery where it is most needed. Additionally, the VisionRelief web and mobile platform enables government agencies, NGOs, and foundations to monitor missions, track survivors, and analyze real-time data through an interactive dashboard. This AI-driven solution significantly reduces response time, enhances operational efficiency, and improves situational awareness during critical emergencies. The implementation of VisionRelief aligns with the United Nations Sustainable Development Goals (SDGs) — particularly Goals 3 (Good Health and Well-being), 9 (Industry, Innovation and Infrastructure), 11 (Sustainable Cities and Communities), and 13 (Climate Action). The proposed system demonstrates a scalable, cost-effective, and socially impactful approach to modernizing disaster management using emerging technologies

The potentiostat utilizing the ESP32 has a 12-bit analog-to-digital converter (ADC), meaning the maximum value for ADC voltage readings on the ESP32 is 4095. These ADC readings are then converted into actual voltage units, ensuring more accurate measurements on the potentiostat. To facilitate the use of the ESP32 potentiostat, a mobile application must be designed as a user interface for data communication. The application will be developed on a mobile platform using a Bluetooth low energy (BLE) communication channel for easier access. The development process will utilize visual studio code as the code editor and programming languages like Dart and Flutter. The resulting application will feature a user-friendly dashboard, display data in a cyclic voltammetry graph, and store data in comma-separated values (CSV) files or images in the phone’s memory. This stored data will simplify observing results obtained from the ESP32 potentiostat.

Real-time high-resolution hardware–software co-design neural architecture search for unmanned mobile platforms

Optical sensing technologies are revolutionizing global food safety surveillance through exceptional sensitivity, rapid response, and high portability. This review systematically evaluates five major platforms, revealing unprecedented detection capabilities from sub-picomolar to single-cell resolution. Surface plasmon resonance achieves 0.021 ng/mL detection limits for veterinary drugs with superior molecular recognition. Quantum dot fluorescence sensors reach 0.17 nM sensitivity for pesticides, enabling rapid on-site screening. Surface-enhanced Raman scattering attains 0.2 pM sensitivity for heavy metals, ideal for trace contaminants. Laser-induced breakdown spectroscopy delivers multi-elemental analysis within seconds at 0.0011 mg/L detection limits. Colorimetric assays provide cost-effective preliminary screening in resource-limited settings. We propose a stratified detection framework that strategically allocates differentiated sensing technologies across food supply chain nodes, addressing heterogeneous demands while eliminating resource inefficiencies from deploying high-precision instruments for routine screening. Integration of microfluidics, artificial intelligence, and mobile platforms accelerates evolution toward multimodal fusion and decentralized deployment. Despite advances, critical challenges persist: matrix interference, environmental robustness, and standardized protocols. Future breakthroughs require interdisciplinary innovation in materials science, intelligent data processing, and system integration, transforming laboratory prototypes into intelligent early warning networks spanning the entire food supply chain.

Maternal health care during labor requires the continuous and reliable monitoring of analgesic procedures, yet conventional systems are often subjective, indirect, and operator-dependent. Infrared thermography (IRT) offers a promising non-invasive approach for labor epidural analgesia (LEA) monitoring, but its practical implementation is hindered by clinical and hardware limitations. This work presents a novel artificial intelligence-driven mobile platform to overcome these hurdles. The proposed solution integrates a lightweight deep learning model for semantic segmentation, a B-spline-based free-form deformation (FFD) approach for non-rigid dermatome registration, and efficient on-device inference. Our analysis identified a U-Net with a MobileNetV3 backbone as the optimal architecture, achieving a high Dice score of 0.97 and a 4.5% intersection over union (IoU) gain over heavier backbones while being 73% more parameter-efficient. The entire AI pipeline is deployed on a commercial smartphone via TensorFlow Lite, achieving an on-device inference time of approximately two seconds per image. Deployed within a user-friendly interface, our approach provides straightforward feedback to support decision making in labor management. By integrating thermal imaging with deep learning and mobile deployment, the proposed system provides a practical solution to enhance maternal care. By offering a quantitative, automated tool, this work demonstrates a viable pathway to augment or replace subjective clinical assessments with objective, data-driven monitoring, bridging the gap between advanced AI research and point-of-care practice in obstetric anesthesia.

Abstract— In today’s digital era, users frequently upload high-resolution images, which often lead to system performance issues, slower load times, and excessive cloud storage usage. Manual image optimization remains inefficient and prone to human error for both developers and end-users. This paper introduces an automated, serverless image optimization pipeline utilizing AWS Lambda in combination with the Sharp.js library. When an image is uploaded to Amazon S3, it activates a Lambda function that automatically compresses and optimizes the image into a web-friendly format without noticeable quality degradation. This approach enables real-time image compression without the need for backend server management, thereby minimizing storage requirements, improving application speed, and enhancing user experiences across various platforms. In the modern internet-driven landscape, images represent a significant portion of the data transmitted across both web and mobile applications. Studies indicate that over 65% of webpage data weight is attributed to images, underlining the necessity of efficient image management. While high-resolution visuals are crucial for superior user engagement, they increase bandwidth consumption, load time, and cloud storage expenses. Traditional optimization approaches demand manual pre-processing or rely on specialized backend servers, which introduces inefficiency, cost, and maintenance challenges. This study proposes a completely automated, serverless pipeline for image compression and optimization using AWS Lambda and Sharp.js. Leveraging AWS Lambda’s eventdriven framework, the system triggers compression operations whenever new images are uploaded to S3. Sharp.js, built upon the efficient libvips engine, performs resizing and compression operations while maintaining visual quality. The integration of serverless computing with this high-performance library ensures real-time automation, scalability, and cost efficiency. Furthermore, this research introduces two innovative enhancements: 1. A Deep Reinforcement Learning (DRL)-based predictive resource provisioning mechanism that mitigates cold start latency. 2. A Semantic-Aware Adaptive Compression (S-ADC) algorithm that intelligently modifies compression settings based on image content and semantic complexity. Experimental evaluations conducted across formats such as JPEG, PNG, WebP, and AVIF reveal considerable reductions in file size while preserving visual fidelity. The proposed system not only enhances accessibility for users with limited bandwidth but also reduces cloud expenses and supports sustainable computing practices. By merging serverless infrastructure with adaptive intelligence, this work delivers a scalable, cost-effective, and eco- friendly solution for image optimization applicable to real-world web and mobile platforms. Keywords—Cloud Computing, Serverless Architecture, AWS Lambda, Sharp.js, Image Compression, Reinforcement Learning, Adaptive Compression, Media Optimization, Cloud Efficiency.

Nowadays, knowledge has become a commodity in the form of digital information in mobile consumption scenarios, and consumers are willing to pay through knowledge product APPs on mobile platforms. In reality, mobile knowledge payment not only serves as an internal means to promote national spiritual consumption but has also become one of the hotspots in academic research. Current literature on knowledge payment mainly focuses on three areas: pricing research, business model research, and user behavior research. Among these, user behavior research primarily examines participation behavior and consumer choices, but there are still some shortcomings in exploring the factors influencing knowledge payment. This paper focuses on the concept of "knowledge payment" and uses the SOR (stimulus-organism-response) model as the basis to analyze the internal and external factors influencing knowledge payment. The dual purpose is to provide suggestions for the real industry and to supplement new academic theoretical perspectives. The study concludes that knowledge product quality, knowledge anxiety, knowledge opinion leaders, and APP marketing influence knowledge payment behavior through consumer perceived value and satisfaction.

Localkart Hyperload E-Commerce presents a novel mobile platform aimed at revolutionizing agricultural business processes through advanced information and communication technologies. The platform enables farmers to manage product listings, integrate real-time market rate data, and receive customer feedback, while offering customers a seamless interface for product discovery, peer reviews, and secure payment processing. Modern mobile development techniques utilizing Flutter and Dart combine with robust backend services provided by Firebase, including Authentication, Firestore. Integration of chatbot for providing help to Customers and the recommendations ensures a highly interactive and responsive user experience. By addressing technical and operational challenges inherent in digital agriculture, Android Farmer App empowers rural stakeholders and enhances overall market efficiency.

The growing demand for intelligent, real-time systems pushes artificial intelligence beyond the confines of centralized data centers toward distributed, edge-based applications such as autonomous robotics, mobile platforms, and IoT sensors. However, the energy and space requirements of conventional artificial intelligence (AI) hardware such as graphic processing units and AI-specific application-specific integrated circuits, pose fundamental limitations for deployment at the edge. Bioinspired computing offers a compelling alternative, emulating the efficiency and adaptability of biological systems to achieve low-power, real-time intelligence. Among these approaches, spiking neural networks stand out for their sparse, event-driven computation and have demonstrated orders-of-magnitude energy efficiency gains on neuromorphic platforms such as SpiNNaker and Intel's Loihi. Yet, to realize the full potential of bioinspired intelligence in edge environments, a new class of customized hardware is imperative. Emerging innovations in material science, particularly the integration of 2D materials, can enable the design of compact, reconfigurable neuromorphic devices that mimic complex neuronal dynamics with minimal power consumption. These advances promise a new generation of scalable, multifunctional edge AI systems that are capable of perception, adaptation, and autonomous decision-making, heralding a transformative leap in energy-efficient computing for pervasive intelligent technologies.

Background Chronic kidney disease (CKD) imposes a growing global burden, with hemodialysis (HD) patients facing high malnutrition rates (28% ~ 54%). Nutritional management is critical but challenging due to strict dietary restrictions and limited healthcare monitoring. Digital health technologies (DHTs) offer dynamic, personalized interventions, yet their efficacy remains inconsistent. This systematic review and meta-analysis aims to assess the effects of DHT-based nutritional interventions on the nutritional status of hemodialysis patients. Methods We systematically searched PubMed, Embase, Cochrane Library, Web of Science, CINAHL, Scopus, CNKI, CBM, WanFang, and VIP databases from their inception to 21 March 2025, to investigate the impact of DHTs-based nutritional interventions on the nutritional status of hemodialysis patients. Outcomes included biochemical parameters, anthropometric measures, and Modified Quantitative Subjective Global Assessment (MQSGA). Risk-of-bias assessment used Cochrane criteria, and meta-analyses employed RevMan 5.4 with random/fixed-effects models. Results A total of 23 literatures were included, involving 6 countries and 2,762 hemodialysis patients. DHT interventions improved the following 13 outcome measures: MQSGA, hemoglobin, albumin, prealbumin, phosphorus, potassium, BMI, mid-arm muscle circumference, triceps skinfold thickness, relative increase in body weight (%), weight gain, blood urea nitrogen, and serum creatinine. However, it had no significant effect on transferrin and calcium. The intervention forms are mainly applications and mobile platforms. Conclusion Overall, DHT-based nutritional interventions effectively enhance multiple nutritional indicators in HD patients. However, variability in study quality, intervention formats, and regional disparities limits generalizability. Future research should prioritize high-quality, multicenter RCTs to optimize intervention protocols and explore emerging technologies. Systematic review registration Identifier PROSPERO: CRD420251023133.

Livestock production plays a pivotal role in global agriculture, contributing significantly to food security, rural livelihoods, and economic development. With increasing demand for animal-based products and rising challenges such as disease outbreaks, climate variability, and resource inefficiency, the integration of Information and Communication Technology (ICT) has emerged as a transformative solution. The primary objective of this review is to explore the integration and impact of ICT across various facets of livestock production and management. ICT applications, ranging from artificial intelligence (AI), Internet of Things (IoT), mobile platforms, cloud computing, blockchain, and big data analytics, are revolutionising livestock systems across breeding, feeding, health management, housing, marketing, and environmental monitoring. A study found that RFID-based systems reduced animal identification errors by 97% and increased efficiency in herd management. Tools such as precision feeding systems, sensor-based health monitors, genomic selection platforms, and automated milking robots have led to measurable improvements in productivity, animal welfare, and cost efficiency. E-learning platforms offer scalable, cost-effective solutions for skill development in animal husbandry. Impact assessments show that livestock farmers who engage in structured online learning report a 20–30% improvement in practices such as record-keeping, health monitoring, and hygiene. Predictive analytics and decision support systems are enabling data-driven farm management, reducing losses and improving resilience to climatic shocks. Despite these advancements, several challenges persist, including high investment costs, limited digital literacy, poor rural connectivity, and concerns related to data privacy and ownership. Addressing these barriers through inclusive policy frameworks, financial incentives, and targeted training is essential for ensuring broad-based adoption and sustainability. Global case studies and regional initiatives underscore the potential of ICT in reshaping livestock production into a more responsive, transparent, and environmentally adaptive system. Analysis of current ICT applications, benefits, limitations, and emerging trends in the livestock sector, offering critical insights for policymakers, researchers, and practitioners seeking to harness digital technologies for resilient and sustainable livestock development. The convergence of technology and animal agriculture marks a new era of smart and inclusive livestock systems.

This study reviews Citizen-Based Monitoring (CBM) as a participatory accountability mechanism through which communities monitor, evaluate, and influence government performance in Africa. It examines how CBM enhances public service delivery across key sectors. Guided by the PRISMA-ScR framework and a Population–Concept–Context approach, the scoping review systematically searched eight academic databases (Scopus, Web of Science, PubMed, Embase, Africa-Wide, CINAHL, PsycINFO, AJOL) and grey literature sources covering 2000–2025. Eligible studies reported empirical CBM initiatives directly involving citizens in monitoring public services or policies. CBM is most advanced in the health sector, particularly HIV, tuberculosis, and malaria programs, while applications in education, water, sanitation, and local governance are emerging. Common mechanisms include community scorecards, social audits, citizen report cards, and digital tools such as SMS and mobile platforms. CBM enhances accountability, responsiveness, and citizen trust when supported by strong institutional ownership and civil society–government collaboration. To sustain impact, CBM must be institutionalized within formal governance systems, supported by stable financing, inclusive design, and mechanisms that close feedback loops to ensure citizen evidence informs policy and service delivery decisions.

As a pioneering solution for precision agriculture, unmanned, robotics-centred greenhouse farms have become a key technological pathway for intelligent upgrades. The robotic arm is the core unit responsible for achieving full automation, and the level of technological development of this unit directly affects the productivity and intelligence of these farms. This review aims to systematically analyze the current applications, challenges, and future trends of robotic arms and their key technologies within unmanned greenhouse. The paper systematically classifies and compares the common types of robotic arms and their mobile platforms used in greenhouses. It provides an in-depth exploration of the core technologies that support efficient manipulator operation, focusing on the design evolution of end-effectors and the perception algorithms for plants and fruit. Furthermore, it elaborates on the framework for integrating individual robots into collaborative systems analyzing typical application cases in areas such as plant protection and fruit and vegetable harvesting. The review concludes that greenhouse robotic arm technology is undergoing a profound transformation evolving from single-function automation towards system-level intelligent integration. Finally, it discusses the future development directions highlighting the importance of multi-robot systems, swarm intelligence, and air-ground collaborative frameworks incorporating unmanned aerial vehicles (UAVs) in overcoming current limitations and achieving fully autonomous greenhouses.

This work focuses on the derivation and validation of inverse kinematics equations for a planar ball-plate robot, a critical step for its precise control. The robot's kinematic model was developed considering a simplified equilateral triangular base and mobile platform. We detail the mathematical procedures for determining the z-coordinates of the platform's points and establishing the unit vector normal to the platform, which are fundamental for the inverse kinematics solution. The derived equations allow for the calculation of the joint angles necessary to achieve a desired ball position on the plate. For modeling and simulation, Matlab and Simulink were utilized. The robot's SolidWorks design was exported to Simulink using the Simscape Multibody Link tool, and a PID controller was integrated to achieve realistic simulated behavior. Simulation results demonstrate that the derived inverse kinematics equations accurately guide the robot, with the simulated ball trajectory closely matching the desired circular path. Furthermore, computer vision techniques, implemented with OpenCV in Python, were employed for real-time detection and tracking of both the platform and the ball. This visual feedback system provides crucial positional data, allowing for the potential closure of the control loop for adaptive visual control. This project successfully combines precise inverse kinematics with visual feedback, laying a robust foundation for advanced control systems in planar ball-plate robots.