Mobile Machines Research Articles

AI-Assisted Diagnosing, Monitoring and Treatment of Mental Disorders: A Survey

Globally, one in seven people has some kind of mental or substance use disorder that affects their thinking, feelings and behaviour in everyday life. People with mental health disorders can continue their normal lives with proper treatment and support. Mental well-being is vital for physical health. The use of AI in mental health areas has grown exponentially in the last decade. However, mental disorders are still complex to diagnose due to similar and common symptoms for numerous mental illnesses, with a minute difference. Intelligent systems can help us identify mental diseases precisely, which is a critical step in diagnosing. Using these systems efficiently can improve the treatment and rapid recovery of patients. We survey different artificial intelligence systems used in mental healthcare, such as mobile applications, machine learning and deep learning methods, and multi-modal systems and draw comparisons from recent developments and related challenges. Also, we discuss types of mental disorders and how these different techniques can support the therapist in diagnosing, monitoring, and treating patients with mental disorders.

Mobile Application and Machine Learning-Driven Scheme for Intelligent Diabetes Progression Analysis and Management Using Multiple Risk Factors

Diabetes mellitus is a chronic disease that affects over 500 million people worldwide, necessitating personalized health management programs for effective long-term control. Among the various biomarkers, glycated hemoglobin (HbA1c) is a crucial indicator for monitoring long-term blood glucose levels and assessing diabetes progression. This study introduces an innovative approach to diabetes management by integrating a mobile application and machine learning. We designed and implemented an intelligent application capable of collecting comprehensive data from diabetic patients, creating a novel diabetes dataset named DiabMini with 127 features of 88 instances, including medical information, personal information, and detailed nutrient intake and lifestyle. Leveraging the DiabMini, we focused the analysis on HbA1c dynamics due to their clinical significance in tracking diabetes progression. We developed a stacking model combining eXtreme Gradient Boosting (XGBoost), Support Vector Classifier (SVC), Extra Trees (ET), and K-Nearest Neighbors (KNN) to explore the impact of various influencing factors on HbA1c dynamics, which achieved a classification accuracy of 94.23%. Additionally, we applied SHapley Additive exPlanations (SHAP) to visualize the contributions of risk factors to HbA1c dynamics, thus clarifying the differential impacts of these factors on diabetes progression. In conclusion, this study demonstrates the potential of integrating mobile health applications with machine learning to enhance personalized diabetes management.

Smart whole-body vibration attenuation, cushion for heavy equipment seating: Model and simulation

Off-road mobile machine operators are exposed to whole-body vibration (WBV) which can result in adverse health effects. Seat suspensions are used to reduce WBV exposure, but typical passive seats cannot attenuate frequencies below 1.13 Hz. The proposed device is designed to minimize transmissibility from 0 to 20 Hz because this bandwidth contains the dominant frequency for most off-road vehicles. The semi-active smart device uses bang-bang control and is designed to be installed in place of the seat-pan cushion in OEM passive seats. Modelled as a two degree of freedom system, simulations were performed using a lumped mass model (ωn = 3 Hz; sinusoidal base excitation 0-20 Hz). Using a hexapod robot, a prototype reduced transmissibility compared to a passive OEM seat. The device was up to 5 times more effective than a passive seat in reducing vibration transmissibility. Simulations revealed that operator mass and seat stiffness variations have little effect on device WBV attenuation performance.

Energy Efficient and Redundant Steer-by-Wire for Articulated Non-road Mobile Machines

Energy Efficient and Redundant Steer-by-Wire for Articulated Non-road Mobile Machines

Optimization of a metal additively manufactured hydraulic silencer with array resonators

As mobile machines shift to electrification, hydraulic circuit noise, previously masked by combustion engine noise, has emerged as a significant concern. To address acoustic comfort issues, this paper investigates an innovative solution for high-performance noise reduction in hydraulic circuits. The proposed silencer design incorporates an optimized array of Helmholtz resonators, strategically arranged to broaden the narrow band characteristics of single resonators. The chosen configuration effectively reduces pressure pulsations across a broad mid-frequency spectrum. While this design is well-established in air medium, its application in a hydraulic oil medium is pioneering. Fabricated through metal additive manufacturing, the silencer undergoes testing on a dedicated bench. Transmission Loss measurements validate both the concept and the optimization methodology.

3D Modeling Simulation and Innovative Design of a Saw Cutting Mechanism for a Movable Buckling Machine

In this research, a sawing mechanism of a mobile buckling machine was innovatively designed for the forest resources and environmental characteristics of the northeast region of China. The northeast region of China is rich in forest resources, but the climate is cold, which puts high demands on the performance and adaptability of mechanical equipment. In this study, the three-dimensional modeling of the saw-cutting mechanism was completed by Pro/Engineer 5.0 modeling software, and an in-depth dynamics simulation analysis was carried out using dynamics simulation software. The study aims to assess the applicability of this saw-cutting mechanism in the northeast region of China, analyze its design characteristics, and explore possible directions for performance optimization. Through this study, we expect to provide valuable references for future technological innovations, as well as to promote the practical application and development of mobile buckling machines in cold regions. This research not only has regional characteristics, but also reflects the innovative idea of combining mechanical equipment design with environmental adaptability.

Mobile Web Application for Durian Orchard Management and Geospatial Data Visualization Using Deep Learning

Durian, a globally popular fruit, is primarily exported by Thailand, making it the foremost contributor to the world market. Nevertheless, there remains a notable absence of a comprehensive platform or application catering to both consumer tourists and businesses seeking domestic purchases. Prior research has highlighted several shortcomings, notably the inability of existing applications to provide location-based search functionality or automatically identify durian plantation plots from digital photographs. Consequently, this study proposes the development of a mobile web application aimed at managing, processing, and visualizing geospatial data pertaining to orchards and durian plantations. Through the integration of mobile technology, geospatial technology, and machine learning, the research endeavours to address these deficiencies. The findings indicate promising results, particularly in the accurate classification of durian plantations using four machine learning algorithms: convolutional neural network (CNN), support vector machine (SVM), random forest, and k-nearest neighbor (KNN). Among these algorithms, CNN exhibited the highest accuracy, achieving a value of 95%, with precision, recall, and f-measure values of 95.55%, 94.44%, and 94.97%, respectively.

Polycystic Ovary Syndrome and the Internet of Things: A Scoping Review.

Polycystic ovary syndrome (PCOS) is a prevalent endocrine disorder impacting women's health and quality of life. This scoping review explores the use of the Internet of Things (IoT) in PCOS management. Results were grouped into six domains of the IoT: mobile apps, social media, wearables, machine learning, websites, and phone-based. A further domain was created to capture participants' perspectives on using the IoT in PCOS management. Mobile apps appear to be useful for menstrual cycle tracking, symptom recording, and education. Despite concerns regarding the quality and reliability of social media content, these platforms may play an important role in disseminating PCOS-related information. Wearables facilitate detailed symptom monitoring and improve communication with healthcare providers. Machine learning algorithms show promising results in PCOS diagnosis accuracy, risk prediction, and app development. Although abundant, PCOS-related content on websites may lack quality and cultural considerations. While patients express concerns about online misinformation, they consider online forums valuable for peer connection. Using text messages and phone calls to provide feedback and support to PCOS patients may help them improve lifestyle behaviors and self-management skills. Advancing evidence-based, culturally sensitive, and accessible IoT solutions can enhance their potential to transform PCOS care, address misinformation, and empower women to better manage their symptoms.

Strong adhesive, high conductive and environmentally stable eutectogel based on “Water in deep eutectic Solvent”: Ultrasensitive flexible temperature and strain sensors

Eutectogel is a promising candidate of conductive materials for flexible electronic sensors. However, the existing eutectogel sensors still have some problems such as poor mechanical properties and antifatigue ability, limited ionic conductivity, and strong hygroscopicity. Herein, an eutectogel is fabricated via one-stop photoinitiated copolymerization of acrylic acid, hydroxyethyl acrylate, and highly branched modified polyethyleneimine in “water in deep eutectic solvent”. The optimized eutectogel exhibits strong adhesive strength (132 ± 9 kPa, with porcine skin), ultra elongation (3500 %), high conductivity (2.7 ± 0.1 mS cm−1), long term antidrying and antifreezing (∼30 d) in a wide range of working temperatures (−40 − 60 °C), flame resistance, biocompatability, and excellent resistance ability to tear and crack propagation. The superb flame resistance and sensitive response to temperature offer a potential application in fire alarm. Besides, this gel-based wearable strain sensors can sensitively monitor and differentiate large body joint movements and subtle muscle motions. The highly distinguishable and reproducible signals can be recorded while further utilizes as sensors for detecting human healthcare accurately and continuously in medical mobile electrocardiogram machine for a long time. This work provides a new strategy for constructing eutectogel based wearable devices and electronic devices with excellent performance.

Buoyancy and Propulsion Mechanisms for Stable Movement in Snow Field

For small-sized mobile machines, moving on snow without sinking is challenging. Snowmobiles are often used to move on snow. However, in smaller-sized machines, the skis attached to the machine become small, so small snow bumps or soft powdered snow quickly cause the entire machine to be buried under the snow. Therefore, it is necessary for small robots moving on snow to give appropriate driving mechanisms for producing propulsive force and snow-floating force. To this end, we propose new driving mechanisms, a “passive wing wheel” and a “spiral screw,” for small mobility services that move on snow without sinking or getting stuck. The passive wing wheel has transformable wing-like paddles, which extend to behave like animal feet and shrink to form a wheel if necessary. The spiral screw is designed to produce propulsive force by pushing snow particles with the screw. Additionally, by combining two sets of screws having opposite threads, they gather snow underneath the body attached to them, which causes floating force. This report also proposes ways to prepare pseudo-snow, which resembles natural snow in hardness, viscosity, and property transformation due to deformation. We conducted experiments to measure the performance of the proposed design in both the pseudo-snow and natural snow. From experiments, we confirmed that the mechanism performs well in terms of propulsion and floating on snow.

Pemanfaatan Teknologi dan Intervensi Digital dalam Pencegahan Risiko Jatuh pada Lansia

The aim of this research is to evaluate digital interventions aimed at preventing falls among individuals aged 65 and older. The methodology employed involves a literature review assessing the effectiveness of various technologies in reducing fall risks, as well as identifying the strengths and weaknesses of each approach. The study includes elderly participants using digital technology or interventions compared to a control group receiving standard care or no intervention. Outcomes considered include reduced fall risk, fall incidents, or severity of fall-related injuries. Studies meeting inclusion criteria encompass experimental designs (randomized controlled trials, controlled trials) or observational studies with adequate controls, available in English. PubMed, Scopus, and IEEE Xplore databases were utilized up to June 19, 2024, with additional reference searches. Research findings indicate that out of 608 identified articles, 10 studies met inclusion criteria following screening processes. These studies utilized a variety of technologies such as mobile applications, virtual reality (VR), augmented reality (AR), machine learning, and robotics. Conducted in various countries, these studies demonstrate diverse applications; for instance, UK studies used mobile apps and 3D games for fall awareness, Chinese studies employed VR for rehabilitation, and German studies explored robotics for fall prevention. The research concludes by highlighting the potential of technologies like VR, AR, machine learning, and robotics in reducing fall risks among the elderly, thereby enhancing healthcare practices and quality of life. Keywords: Elderly, Falls Risk, Prevention, Technology

Assessing The Effect of Digital Banking Services on Retail Banking Customers’ Satisfaction Levels in Lusaka’s Central Business District

Digital banking platforms have improved the way banks deliver their services to clients which has resulted in the gradual movement from brick and mortar to the use of digital applications such as mobile phones, iPads, laptops and ATM machines. The purpose of this study was to assess the effect of digital banking on retail banking customer service satisfaction levels in Lusaka Town. The study was guided by three objectives which were; to determine customers’ perception of the reliability of digital banking services in Lusaka Central Business District; to assess customers’ perception of the responsiveness of digital banking services in Lusaka Central Business District and, to examine customers’ perceptions of the security of digital banking services in Lusaka Central Business District. This study investigated customers' perceptions of digital banking services, focusing on reliability, responsiveness, and security, using a quantitative approach. Simple random sampling was used to collect data using a structured questionnaire with 5-point Likert scale. The researcher ensured that the respondents remained anonymous to avoid bias and that whatever information they provided would be treated with confidentiality. The researcher did not influence the responses provided by the respondents in anyway. The sample size was 150 and 140 respondents who are bank customers in Lusaka Central Business District responded. The response rate was 93.33%. The data was analysed using descriptive statistics, ANOVA, hierarchical regression, and correlation analysis. The findings reveal that customers generally perceive digital banking services positively in terms of reliability and responsiveness, with significant associations found between these factors and overall customer satisfaction. However, concerns remain regarding security, despite moderate confidence in digital banking security measures. The study underscores the importance of trust, transparency, and technological advancement in shaping customer perceptions. Recommendations for further research include exploring the impact of AI technologies, regulatory frameworks, and demographic differences on digital banking adoption and satisfaction. These findings contribute to understanding customer behaviour in digital banking and inform strategies for enhancing service delivery and customer experience in the financial sector.

Automatic recognition of excavator working cycles using supervised learning and motion data obtained from inertial measurement units (IMUs)

This paper proposes an automatic method for excavator working cycle recognition using supervised classification methods and motion information obtained from four inertial measurement units (IMUs) attached to moving parts of an excavator. Monitoring and analyzing tasks that have been performed by heavy-duty mobile machines (HDMMs) are significantly required to assist management teams in productivity and progress monitoring, efficient resource allocation, and scheduling. Nevertheless, traditional methods depend on human observations, which are costly, time-consuming, and error-prone. There is a lack of a method to automatically detect excavator major activities. In this paper, a data-driven method is presented to identify excavator activities, including loading, trenching, grading, and idling, using motion information, such as angular velocities and joint angles, obtained from moving parts, including swing body, boom, arm, and bucket. Firstly, a dataset lasting 3 h is collected using a medium-rated excavator. One experienced and one inexperienced operator performed tasks under different working conditions, such as different types of material, swing angle, digging depth, and weather conditions. Four classification methods, including support vector machine (SVM), k-nearest neighbor (KNN), decision tree (DT), and naive Bayes, are off-line trained. The results show that the proposed method can effectively identify excavator working cycles with a high accuracy of 99%. Finally, the impacts of parameters, such as time window, overlapping configuration, and feature selection methods, on the classification accuracy are comprehensively analyzed.

Повышение ресурсного потенциала древесного сырья

According to the strategy for the development of the forestry complex of the Russian Federation until 2030, approved by Order of the Prime Minister of Russia no. 312r dated February 11, 2021, the contribution of the forestry industry to the country’s economy should increase by 2 times, including through deep wood processing. To this end, enterprises for deep processing of wood raw materials will be actively developed. Consequently, there will be a shortage of wood raw materials, which will lead to an urgent need to expand the raw material base of these industries. Despite this, as the analysis of the practical experience of modern logging enterprises has shown, today, during logging operations, only the stem part of the tree is removed from the cutting area, and the rest of the biomass in the form of stumpwood, branches, twigs and tops is burned or buried, although these parts of the tree are valuable raw materials for the production of many types of products of wood processing enterprises. This state of affairs is due to the lack of effective technology for processing potential raw materials in the places of their formation and a complex of mobile machines for its implementation. As a result, a technology for the production of wood and coniferous flour, technological chips and semi-finished wood-fiber products, as well as mobile equipment for its implementation, has been proposed for the processing of logging waste in the form of tops, branches and twigs. The article presents technological solutions and equipment models built in the SolidWorks computer-aided design system. The introduction of the proposed technologies, machines and mechanisms will increase the share of harvested raw materials per unit area, reduce the environmental load from the logging process, and increase the efficiency of the industry.

Site-Independent Mapping of Clay Content in Vineyard Soils via Mobile Proximal Gamma-Ray Spectrometry and Machine Learning Calibrations.

Vineyards hold considerable soil variability between regions and plots, and there is frequently large soil heterogeneity within plots. Clay content in vineyard soils is of interest with respect to soil management, environmental monitoring, and wine quality. However, spatially resolved clay mapping is laborious and expensive. Gamma-ray spectrometry (GS) is a suitable tool for predicting clay content in precision agriculture when locally calibrated, but it has scarcely been tested site-independently and in vineyards. This study evaluated GS to predict clay content with a site-independent calibration and four machine learning algorithms (Support Vector Machines, Random Forest, k-Nearest Neighbors, and Bayesian regulated neuronal networks) in eight vineyards from four German vine-growing regions. Clay content in the studied soils ranged from 62 to 647 g kg-1. The Random Forest calibration was most suitable. Test set evaluation revealed good model performance for the entire dataset with RPIQ = 4.64, RMSEP = 56.7 g kg-1, and R2 = 0.87; however, prediction quality varied between the sites. Overall, GS with the Random Forest model calibration was appropriate to predict the clay content and its spatial distribution, even for heterogeneous geopedological settings and in individual plots. Therefore, GS is considered a valuable tool for soil mapping in vineyards, where clay content and product quality are closely linked.

Обґрунтування вибору типу приводу стрічкового конвеєра

The designs and dynamic properties of electromechanical and hydraulic drives for a belt conveyor have been analyzed to justify their selection. The main advantages and disadvantages of their operation have been formulated. It has been established that the hydraulic drive has advantages compared to the electromechanical one for installation in a built-in drive for a belt conveyor. The design features and principles of operation of these drives have been described. Calculation schemes have been developed for the electromechanical and hydraulic drives of the belt conveyor. A mathematical model of the electromechanical drive has been constructed, taking into account the Voigt viscoelastic model for the conveyor belt, Hooke's laws for the deformation of stretching elements, equations of motion of the mechanical system, and electromagnetic phenomena in the asynchronous motor. Additionally, a mathematical model for the hydraulic drive of the belt conveyor has been constructed, which, besides the equations of motion of the mechanical system and the Voigt viscoelastic model for the conveyor belt, also includes the continuity equations of the working fluid flows in the hydraulic drive. The parameters of the belt conveyor for studying the dynamic properties of the electromechanical and hydraulic drives, which are considered in the mathematical models, have been described. The mathematical models for the electromechanical and hydraulic drives have been solved using the Mathcad software package. Theoretical curves for cases of transient processes in the mechanical system of the belt conveyor without load and with load have been constructed. Transient processes of acting torques and angular velocities have been compared by the dynamic coefficient, and it has been established that the hydraulic drive has a better indicator by 1.78 times. It has also been established that the duration of the transient process in the drive with the electric motor exceeds this parameter in the drive with the hydraulic motor by 3.5 times. It is recommended to use the built-in hydraulic drive for belt conveyors of mobile working machines because it has more advantages over the electromechanical one, and the dynamic indicators of the hydraulic drive provide better performance during operation.

Electric field induced mechanical flapping motors enabling soft robotic and wearable applications

Here we present a new type of soft motors, termed Electric Field Induced Mechanical Flapping (EFIMF) motors, which are robust and present versatile potential applications. The EFIMF motors harness an actuation mechanism that combines two processes: 1) using the electric field to induce charges, and 2) coupling the electromechanical forces to achieve fast and robust actuation. Our EFIMF motor can remain functional even with its electrode punctured by a metal needle. The EFIMF motors also present the fault-tolerant capability, which helps them to survive the dielectric breakdown. We demonstrate a robust crawling soft robot, which is powered by one EFIMF motor and capable of surviving continuous hammering. We also show a wearable haptic glove powered by five EFIMF motors, generating rich notification signals with a wide frequency range and different mechanical feedback intensities. The robustness of the soft EFIMF motors enhances their lifetime and performances, and represents an important step towards realistic soft mobile machines and wearable human machine interfaces.

Development of a Mobile Hydraulic Lifting Machine

This paper develops a mobile hydraulic lifting machine for lifting heavy automobile engines in the central workshop of Olusegun Agagu University of Science and Technology, Okitipupa. It was fabricated using locally sourced materials for economic viability and affordability. Full welding was applied to all parts to avoid failure during lifting operation and avert accidents or injuries. The maximum designed load of the machine is 500 kg, and the minimum force produced by the hydraulic cylinder is 22.22 KN. The pressure generated by the Ram force with a piston area of 8.495 x 10-3 m2 was 2.616 MPa and the effort required to overcome the force produced by the cylinder was 2103 N. The maximum circumferential stress and the allowable bending stress of the cylinder were 54.413 x 106 N/m2 and 108.8 MPa which are far below the AISC recommended, this shows the beam is safe to lift without failure. The maximum shear force and the bending moment of the cantilever were found to be 17222 N and 6200 Nm respectively, and the maximum shear stress developed at the pivots were 17.54 MPa and 22.63 MPa respectively, which are far below the allowable stress. This shows that the developed machine is safe to use without failure.

METHODOLOGY AND EXAMPLE OF CALCULATING THE RATIONAL RESOURCE OF AXIAL-PISTON HYDRAULIC MACHINES OF MOBILE EQUIPMENT

The article analyzes approaches for creating models for optimizing the durability of mobile machine units. On the basis of the selected model, in which the target function is the total specific costs of purchasing the machine and the costs of maintaining its working condition, a method of calculating the rational resource of axial-plunger hydraulic machines has been developed for the condition when the resource of the hydraulic machine is limited by the resource of only its plunger pairs. The methodology, built on the basis of the chosen model for optimizing the durability of simple technical systems, takes into account the patterns of wear of plunger pairs under certain operating conditions, and also takes into account the proposed dependencies for calculating their total wear limit. The methodology consists of five consecutive operations, namely: determining the total marginal wear; obtaining experimental patterns of wear of plunger pairs over time in the form of regression equations; calculation of the number and periodicity of technical maintenance of the hydraulic machine for the inter-repair cycle; calculation of the rational resource of the hydraulic machine.The results of the comparative calculation of the rational resource of the adjustable axial-plunger pump 321.224 of the hydraulic system of the single-bucket excavator EO-3323 according to the developed method are also given.The total marginal wear of the pump was determined according to the criterion of reducing its efficiency, namely from the condition of a drop due to the wear of its volume coefficient of useful action by 30 %.To obtain the patterns of wear of the pump's plunger pairs, the results of previous operational tests of the pump were used for two variants of its lubrication: lubrication with ordinary hydraulic oil and lubrication with oil whose anti-wear properties are activated by an external electric field. Specific costs for the purchase of the pump, which are included in the durability optimization model in the form of depreciation deductions, were calculated for the inter-repair cycle. The specific costs of maintaining the working condition of the pump were equal to the costs of its maintenance, during which hydraulic oil and filters are replaced, that is, the pattern of wear of plunger pairs is returned to the starting point.

Real-Time Tracking Data and Machine Learning Approaches for Mapping Pedestrian Walking Behavior: A Case Study at the University of Moratuwa.

The growing urban population and traffic congestion underline the importance of building pedestrian-friendly environments to encourage walking as a preferred mode of transportation. However, a major challenge remains, which is the absence of such pedestrian-friendly walking environments. Identifying locations and routes with high pedestrian concentration is critical for improving pedestrian-friendly walking environments. This paper presents a quantitative method to map pedestrian walking behavior by utilizing real-time data from mobile phone sensors, focusing on the University of Moratuwa, Sri Lanka, as a case study. This holistic method integrates new urban data, such as location-based service (LBS) positioning data, and data clustering with unsupervised machine learning techniques. This study focused on the following three criteria for quantifying walking behavior: walking speed, walking time, and walking direction inside the experimental research context. A novel signal processing method has been used to evaluate speed signals, resulting in the identification of 622 speed clusters using K-means clustering techniques during specific morning and evening hours. This project uses mobile GPS signals and machine learning algorithms to track and classify pedestrian walking activity in crucial sites and routes, potentially improving urban walking through mapping.