Mobile Information Research Articles

Low-cost urban heat environment sensing device with Android platform for digital twin

The proper monitoring of heat and meteorological variables is essential for the well-being of residents of metropolitan areas. It is challenging to configure spatial heat variations in complex urban environments, even though the temporal variation of urban heat flux has been measured at several designated monitoring stations. Neither the budget nor existing techniques for efficient urban heat monitoring are sufficient for a digital twin of the urban heat environment. As a result, we have developed a low-cost monitoring system that can be easily integrated into a portable pedestrian device, kickboard, or electric bike. With this system, citizens can collect information about urban heat, such as air temperature, surface temperature, relative humidity, barometric pressure, light intensity, and micro-geophysical features including topological aspects and mobile information (e.g., three-dimensional accelerations). Citizens can participate in daily scientific activities using these devices, which facilitate data acquisition and information exchange in urban digital twin environments.

The Effectiveness of Tiktok in Increasing Brand Awareness Among Users

Technological advancements have revolutionized marketing strategies, particularly in the realm of social media. As businesses recognize the importance of brand awareness in consumer decision-making, platforms like TikTok have emerged as powerful tools for enhancing brand visibility. Despite its rapid rise in popularity, TikTok's effectiveness in increasing brand awareness remains underexplored. This study investigates "The Effectiveness of TikTok in Increasing Brand Awareness Among Users" with three primary objectives: (RO1) to identify the effect of Mobile Application Values, Information Quality, System Quality, and Influencer Trust on Brand Awareness; (RO2) to identify the effect between Brand Awareness and Word of Mouth; and (RO3) to analyze the effect between Brand Awareness on Purchase Intention. The research adopts a quantitative approach, utilizing a questionnaire distributed to B2C TikTok users. A sample size of 343 respondents was determined using stratified sampling. Descriptive and regression analyses were conducted to interpret the data. The results indicate that Mobile Application Value, System Quality, and Influencer Trust significantly influence Brand Awareness on TikTok, while Information Quality does not exhibit a significant effect. Moreover, Brand Awareness positively impacts both Word of Mouth and Purchase Intention, underscoring its pivotal role in consumer behavior. This study contributes to a deeper understanding of TikTok's potential as a branding tool and offers practical insights for marketers seeking to leverage the platform effectively. Despite limitations in sample size and survey biases, the findings provide a foundation for future research and the refinement of marketing strategies in the dynamic landscape of social media.

Intensity of Adoption of Improved Malt Barley Production Technologies in Ethiopia: A Case Study in Oromia Region

Improved malt barley production technology packages are not yet widely adopted in Ethiopia. Stakeholders, including brewers, malt factories, research institutes, and farmer-based organizations, have been collaborating and promoting new malt barley production technologies in order to boost the intensity of acceptance. The aim of this study was to find out the intensity of improved malt barley production technologies adoption in Arsi zones, Oromia region, Ethiopia. A stratified random sampling approach with multiple stages was employed to collect primary data from 384 malt barley household heads. The data was analyzed using descriptive statistics, and the intensity of adoption of improved malt barley production technologies was determined using an econometric Tobit regression model. The findings specified that the most adopted improved malt barley variety was Traveler (47.92%), which was followed in descending order by Iboni (14.58%), Sabini (9.38%), Grace (5.47%), Holker (4.43%), and 18.23% unnamed varieties. The Tobit model result also depicted that the intensity to which improved malt barley varieties adopted were affected by, taking into account factors including contract farming involvement, cooperative membership, off-farm income, size of livestock holdings, access to training, and mobile ownership. Enhancing farmers’ knowledge of the advantages of contract farming, income diversification, and mobile phone-based information delivery are among the many ways to support access to and accelerate the adoption of improved malt barley technology in the research area and beyond.

Assessing the Contribution of Mobile Management Information Systems to Work-Life Balance and Job Satisfaction Among University Teachers in China: A Focus on System Accessibility and Efficiency

Mobile management information systems, job satisfaction, and work-life balance affect Chinese university teachers, examined in the study. The quantitative study surveyed 516 university teachers on a 5-point Likert scale. The research included instructors with diverse mobile management information systems backgrounds due to this systematic approach. Work-life balance, system accessibility, and teaching experience increased university professors' job satisfaction and balance, the study found. Regression analyses showed that teaching experience, system accessibility, and technology proficiency significantly affect outcomes. Teaching experience and system accessibility improve university professors' job satisfaction and work-life balance. Mobile management information systems and teaching experience boost teacher job satisfaction and work-life balance. We must integrate advanced technology and make systems user-friendly and accessible to all educators, regardless of technology background. The study found that teachers need ongoing technological training to use these systems effectively, improving job satisfaction and work-life balance. Working-life balance, mobile management information system accessibility, and comprehensive teacher technological training are recommended by the study. These factors improve work-life balance and job satisfaction by integrating mobile management information systems into education. Policymakers and administrators should consider cultural and contextual factors and provide personalized support to educators. This study shows how mobile management information systems, work-life balance, and job satisfaction can help administrators, educators, and policymakers understand Chinese educators' technology use. Technology in instruction, culture and personality affect Chinese university professors' well-being.

Collecting population-representative bike-riding GPS data to understand bike-riding activity and patterns using smartphones and Bluetooth beacons

Bike-riding GPS data offers detailed insights and individual-level mobility information which are critical for understanding bike-riding travel behaviour, enhancing transportation safety and equity, and developing models to estimate bike route choice and volumes at high spatio-temporal resolution. Yet, large-scale bicycling-specific GPS data collection studies are infrequent, with many existing studies lacking robust spatial and/or temporal coverage, or have been influenced by sampling biases leading to these data lacking representativeness. Additionally, accurately detecting bike-riding trips from continuously collected raw GPS data without human intervention remains a challenge. This study presents a novel GPS data collection approach by leveraging the combination of a smartphone application with a Bluetooth beacon attached to a participant’s bike. Aided by minimal heuristic post-processing, our method limits data collection to trips taken by bike without the need for participant intervention, carefully optimising between survey participation, privacy challenges, participant workload, and robust bike-riding trip detection. Our method is applied to collect 19,782 bike trips from 673 adults spanning eight months and three seasons in Greater Melbourne, Australia. The collected dataset is shown to represent the underlying adult bike-riding population in terms of demographics (sex, occupation and employment type), temporal and spatial patterns. The average trip length (median = 4.8 km), duration (median = 20.9 min), and frequency of bicycling trips (median = 2.7 trips/week) were greater among men, middle-aged and older adults. The ‘Interested but Concerned’ riders (classified using Geller typology) rode more frequently, while the ‘Strong and Fearless’ and ‘Enthused and Confident’ groups rode greater distances and for longer. Participants rode on roads/streets without bike infrastructure for more than half of their trips by distance, while spending 24% and 17% on off-road paths and bike lanes respectively. This population-representative dataset will be key in the context of urban planning and policymaking.

A machine learning approach to forecast 5G metrics in a commercial and operational 5G platform: 5G and mobility

The demand for more secure, available, reliable, and fast networks emerges in a more interconnected society. In this context, 5G networks aim to transform how we communicate and interact. However, studies using 5G data are sparse since there are only a few number of publicly available 5G datasets (especially about commercial 5G network metrics with real users). ►In this work, we analyze the data of a commercial 5G deployment with real users, and propose forecasting techniques to help understand the trends and to manage 5G networks. We propose the creation of a metric to measure the traffic load. We forecast the metric using several machine learning models, and we choose LightGBM as the best approach. We observe that this approach obtains results with a good accuracy, and better than other machine learning approaches, but its performance decreases if the patterns contain unexpected events. Taking advantage of the lower accuracy in the performance, this is used to detect changes in the patterns and manage the network in real-time, supporting network resource elasticity by generating alarms and automating the scaling during these unpredictable fluctuations. ►Moreover, we introduce mobility data and integrate it with the previously traffic load metric, understanding its correlation and the prediction of 5G metrics through the use of the mobility data. We show again that LightGBM is the best model in predicting both types of 5G handovers, intra- and inter-gNB handovers, using the mobility information through Radars in the several roads, and lanes, near the 5G cells.

Enhancing resilience of distribution systems: Integrating mobile energy storage systems and information gap decision theory for uncertainty management

Power Distribution Systems (PDSs) have seen considerable disruption owing to events and the intrinsic uncertainty associated with renewable energy sources (RES). The fundamental purpose of this project is to identify methods to enhance the resilience of Mobile Energy Storage Systems (MESSs) against unexpected cyber and natural disasters. Information Gap Decision Theory (IGDT) is used to effectively handle the uncertainties linked with RES's outputs. It also applies the Seasonal Autoregressive Integrated Moving Average (SARIMA) model to predict important aspects that affect the output of RES. The shift to microgrid mode prioritizes the delivery of critical loads through MESSs, which are crucial amid adverse situations. A risk-averse strategy mitigates risks associated with wind turbine and photovoltaic (PV) outputs, therefore enhancing the resilience of the PDS. An optimization model utilizing Mixed-Integer Linear Programming (MILP) was formulated. The approach's efficacy in reducing uncertainties in RES has been proved by simulations conducted on the IEEE 69 bus and Dakota transport system. Assuming the most severe situation, the Uncertainty Radius (UR) for wind turbines is 0.7385, but for PVs, it is 0.8753, thereby guaranteeing the robustness of the system against power failures and disturbances.

Modern Applications of Fiqh in Hajj: Analyzing Islamic Legal Responses to Contemporary Issues

This study analyzes the adaptation of Hajj Fiqh to technological developments and social changes in the modern context. By looking at recent developments, including the use of technologies such as mobile applications, information systems, and communication technologies, as well as updates in Hajj procedures and protocols, this study highlights the response of scholars and fatwa institutions to the demands of the times. Recent data shows that there has been an increase in the number of fatwas relevant to the use of technology, health, and the environment in the performance of Hajj. By analyzing the role of clerics, governments, and technologists in addressing the challenges of modern Hajj, this study offers suggestions for further encouraging technological innovation, increasing health and environmental awareness, fostering collaboration among stakeholders, and strengthening the role of religious authorities. It is hoped that the results of this study will help guide decision makers in improving the efficiency, safety, and sustainability of the Hajj in the future.

Investigating the relative accuracy of GPS, GSM and CDR data for inferring spatiotemporal travel trajectories

AbstractThe potential of passively generated big data sources in transport modelling is well‐recognised. However, assessing their accuracy and suitability for policymaking remains challenging due to the lack of ground‐truth (GT) data for validation. This study evaluates the accuracy of inferring human mobility patterns from global positioning system (GPS), call detail records (CDR), and global system for mobile communication (GSM) data. Using outputs from an agent‐based simulation platform (MATSim) as ‘synthetic GT’ (SGT), synthetic GPS, CDR, and GSM data were generated, considering their positional disturbances and conventional spatiotemporal resolutions. Mobility information, including activity location, departure time, and trajectory distance, derived from the synthetic data, was compared with SGT to evaluate the accuracy of passive trajectory data at both disaggregate and aggregate levels. The results indicated a higher accuracy of GPS data in identifying stay locations at high resolution. But, GSM data at a lower resolution effectively accounted for over 80% of the variability in stay locations. Comparisons of departure time distribution and travel distance revealed higher measurement errors in GSM and CDR data than in GPS data. The proposed simulation‐based accuracy assessment framework will aid transport planners select the most suitable data for specific analyses and understand the potential margin of error involved.

Towards development of a roadway flood severity index

Flooding is among the costliest and deadliest weather disasters. Moreover, different types of flooding have significant impacts on the transportation network and infrastructure including flash, riverine, urban, coastal, and storm surge. The variety of flooding scenarios makes it challenging to quantify the impacts of flooding on transportation across spatial scales; however, such metrics would be beneficial both prior to and after the event. Pre-flood metrics can promote enhanced impact-based decision-support guidance and hazard communication, while post-flood metrics may include larger regional disruptions located away from the most inundated areas and their associated secondary societal impacts. This study developed a retrospective Roadway Flood-Severity Index (RFSI) from 1982 to 2020 capable of integrating geo-located hydrometeorological data and transportation mobility information across localized and multi-state, sub-national regions to (1) categorize larger-scale, flood-related transportation disruptions, (2) understand the origins of those disruptions, and (3) identify severity risk levels of individual road segments and broader regions of transportation disruption during flood events. The fundamental question is, as flooding events unfold, can past hydrometeorological inundation information be coupled with transportation system network and mobility data to identify the most vulnerable roadway segments and regions? The overall mobility impacts of flooding on transportation were highly variable and relatively uncommon throughout the study period. Given this variability in other mobility data (e.g., vehicle speeds), hydrometeorological parameters were used exclusively as model inputs and crowdsourced Waze flood reports were used as the target response variable. A logistic regression based RFSI was found to best align with the dataset providing a “no flood” or “flood” classification. Eventually, this retrospective analysis will be extended to provide predictive capability as well. The RFSI is intended to provide transportation agencies with a quantitative metric to classify, categorize, and communicate the potential impacts of flood events throughout the transportation network.

Penerapan Model Design Thinking Pada Perancangan Aplikasi Informasi Desa Wisata Kabupaten Bantul

Tourism actors in the current technological era have implemented information systems. With the rapid growth of tourist villages in Bantul Regency, there is a need for promotion and digital information delivery media. However, in developing digital media it is also necessary to pay attention to aspects of the users who are the target market. The design of the application called sidewi mobile (mobile tourist village information system) is based on user experience and needs, using the Design Thinking methodology which has five stages as follows: Empathize, Define, Ideate, Prototype, and Test. The design of the Sidewi mobile application was created using FIGMA software. This research has direct benefits, namely that it can be used as a benchmark for design needs before the development process. The results of the design are then tested using the usability testing method. Using a user friendly design approach and conducting testing using usability testing with the results of five users being able to complete the testing proves that when it was created using user experience there were no significant difficulties when used and it covered all needs.

Rolling optimal scheduling for urban parcel crowdsourced delivery with new order insertion

The rapid development of mobile information technology has introduced numerous new solutions for delivery companies to enhance profits. One such solution employed by some companies is crowdsourced delivery. In this paper, we focus on rolling optimal scheduling for urban parcel crowdsourced delivery by utilizing private cars that will be in passing with the incorporation of new order insertion. The bonus incentive strategy is introduced to enhance the delivery probability of private car drivers. A static model and a rolling optimization model to maximize profits and the number of parcels delivered by private cars are established. To address the NP-hard problem, a hybrid genetic algorithm and insertion algorithm are designed. Numerical experiments are carried out to verify the proposed method in different scenarios, including the scattered network, clustered network, Dalian network, and Foursquare network. The computational results demonstrate that the method enhances the matching ratio and increases profits. Utilizing private cars that will be in passing for urban parcel delivery reduces the need for dedicated vehicles, mitigating traffic growth and alleviating traffic congestion. Increasing the private car-parcel ratio improves profits and the matching ratio while reducing traffic growth. Raising the incentive coefficient for bonuses increases the matching ratio and detour distance, but profits first increase and then decrease, and delivery distance by dedicated vehicles decreases. Our research findings offer a more rational basis for green urban parcel delivery decision-making by companies.

Research on Library Resource Management Based on Modern Information Technology and Reconfigurable Mobile Information System

Library resource library management based on modern information technology and reconfigurable mobile information systems have attracted much attention from researchers of academia. This paper introduces the LSTM model into the field of Chinese library resource management, and tries to propose a classification system with practical application value. The main research work:The Chinese library resource is designed LSTM model, and three experiments are designed on this basis: the coarse-grained book single classification experiment, different measures on the classification results; the fine-grained book single classification experiment, to compare The advantages and disadvantages of direct classification and layer-by-layer classification; coarse-grained book multi-classification experiments to explore the feasibility of multi-classification. After analyzing the experimental results, the model has achieved a good classification effect, and overcomes some deficiencies in the library resource library predecessors, and has a strong practical application value.

The Effect of Informative Mobile App Use on Anxiety, Distress, and Quality of Life of Women With Breast Cancer.

To evaluate the effect of mobile app-based educational information on anxiety, distress, and quality of life in patients with breast cancer (BC). This mobile app was designed to assist patients before and after BC surgery. This randomized controlled study was conducted between April and August 2021. The intervention group (n = 42) received routine care and access to the mobile app for one month, while the control group (n = 40) received only routine care. Data were collected using questionnaires one week before and three weeks after surgery. The patients in the intervention group, after using the mobile app, had significantly lower anxiety and distress levels than those in the control group (p<0.05). However, there was no difference between the two groups regarding overall quality of life and subscale mean scores (p>0.05). These findings suggest that using informative mobile apps starting before surgery can effectively reduce anxiety and distress in the early periods after surgery. Although the impact on overall quality of life was insignificant, such interventions may have long-term positive effects on quality of life.

Dispersal history of SARS-CoV-2 in Galicia, Spain.

The dynamics of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) transmission are influenced by a variety of factors, including social restrictions and the emergence of distinct variants. In this study, we delve into the origins and dissemination of the Alpha, Delta, and Omicron-BA.1 variants of concern in Galicia, northwest Spain. For this, we leveraged genomic data collected by the EPICOVIGAL Consortium and from the GISAID database, along with mobility information from other Spanish regions and foreign countries. Our analysis indicates that initial introductions during the Alpha phase were predominantly from other Spanish regions and France. However, as the pandemic progressed, introductions from Portugal and the United States became increasingly significant. The number of detected introductions varied from 96 and 101 for Alpha and Delta to 39 for Omicron-BA.1. Most of these introductions left a low number of descendants (<10), suggesting a limited impact on the evolution of the pandemic in Galicia. Notably, Galicia's major coastal cities emerged as critical hubs for viral transmission, highlighting their role in sustaining and spreading the virus. This research emphasizes the critical role of regional connectivity in the spread of SARS-CoV-2 and offers essential insights for enhancing public health strategies and surveillance measures.

CMAF: Context and Mobility-Aware Forwarding Model for V-NDN

Content dissemination in Vehicular Ad hoc Networks (VANET) is a challenging topic due to the high mobility of nodes, resulting in the difficulty of keeping routing tables updated. State-of-the-art proposals overcome this problem by avoiding the management of routing tables but resort to the so-called table of neighbors (NT) from which a next-hop is selected. However, NTs also require updating. For this purpose, some solutions resort to broadcasting beacons. We propose a Context- and Mobility-Aware Forwarding (CMAF) strategy that resorts to a Short-Term Mobility Prediction—STMP—algorithm, for keeping the NT updated. CMAF is based in Named Data Networking (NDN) and works in two modes, Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I). V2V CMAF leverages the overheard packets to extract mobility information used to manage NT and feed the STMP algorithm. V2I CMAF also uses a controlled and less frequent beaconing, initially from the Road-Side Units (RSUs), for a further refinement of the predictions from STMP. Results from extensive simulations show that CMAF presents superior performance when compared to the state of the art. In both modes, V2V and V2I (with one beacon broadcast every 10 s) present 5–10% higher Interest Satisfaction Ratio (ISR) than those of CCLF for the same overhead, at a cost of 1 s of increased Interest Satisfaction Delay (ISD). Moreover, the number of retransmissions of CMAF is also comparatively low for relatively the same number of hops. Compared to VNDN and Multicast, CMAF presents fewer retransmissions and 10% to 45% higher ISR with an increased overhead of about 20%.

Predicting changes in task difficulty perception based on visual behavior in mobile health information search

With the proliferation of online health resources, mobile health information search has become the new norm, in which the task difficulty perception in search affects the user's search experience. This study aimed to investigate the relationship between visual behavior that reflects users' cognitive processing and changes in perceived task difficulty, thereby predicting such changes.This study was conducted through a controlled experiment. 46 participants were recruited to complete four tasks. Visual behavior data were collected through eye-tracking technology, and changes in task difficulty perception were measured through pre-task and post-task questionnaires. The mobile health information search process is divided into three search activities: querying, browsing, and viewing activities. Predictors were inspected from the overall session and individual search activity levels using the Mann-Whitney U test, and then K-Nearest Neighbor, Extreme-Trees, Naive Bayesian, Support Vector Machine, Logistic Regression algorithms were used to predict and evaluate prediction effects.The results showed significant differences in participants' fixation and saccade behaviors between increases and decreases in task difficulty, both at the overall session and individual search activity level. The logistic regression algorithm demonstrated the highest predictive performance, Furthermore, visual behavioral indicators for the browsing activity proved to perform better relative to the other search activities.This study highlights the importance of visual behavioral indicators as reliable predictors of changes in users' perceived task difficulty in mobile health information search. It can help health information providers and administrators to provide timely and targeted assistance and implement effective guidance strategies.

Implementasi Pendataan Kawin Belum Tercatat : Solusi Melalui Aplikasi Kalimasada untuk Peningkatan Kualitas Data Penduduk di Kelurahan Kedungdoro

Community Service in English means community service, which is an activity of helping the community in the form of several activities without expecting any form of reward. Community service is one of the pillars of the Tri Dharma of Higher Education, namely: education, research and community service. Universities not only carry out education for their students, but also carry out research and develop innovation, as well as preserve and develop superior knowledge that is beneficial to society. Data collection on marriages that have not been registered is a problem that is often faced in managing population data in many sub-districts. This article discusses the proposed solution through the development of the Kalimasada application to improve the quality of population data in Kedungdoro Village. The service method used involves the process of data collection, needs analysis, application development, and user training. The approach used is the use of mobile application-based information technology to facilitate the process of collecting data on unregistered marriages. The Kalimasada application is designed with an intuitive and easy-to-use interface, allowing sub-district officials to quickly record data on unregistered marriages. In addition, this application is equipped with an automatic data validation feature to reduce input errors and increase data accuracy. During the service process, training was conducted for the community about the importance of reporting unregistered marriages to subdistrict officers via the Kalimasada application. The results of implementing the Kalimasada application show a significant increase in data collection on unregistered marriages in Kedungdoro Village. With this application, the data collection process becomes more efficient and accurate, producing more valid and reliable data. Apart from that, public participation in reporting unregistered marriages has also increased, so that the data collected becomes more complete. In conclusion, developing the Kalimasada application is an effective solution for improving the quality of population data in Kedungdoro Village. The use of information technology in public administration can help speed up the data collection process and increase data accuracy. The next step is to expand the implementation of this application to other sub-districts and continue to carry out monitoring and evaluation to ensure its sustainability and effectiveness in the long term.

Unveiling realistic mobility patterns with home–origin–destination data aggregation

The availability of increasingly abundant mobility data in recent years has opened up new avenues for researchers to unravel human mobility patterns. Data aggregation methods have been introduced to gain a quantitative understanding of collective individual movements using these data. Nevertheless, the widely adopted origin–destination (OD) aggregation method for human mobility data lacks an essential piece of information: home location, which plays a vital role in characterizing individual movement patterns. In this study, we propose a novel data aggregation approach called home–origin–destination (HOD) with the aim of improving the accuracy of human mobility estimation. We compare the performance of various data aggregation methods for estimating population distribution. Our experimental results reveal more realistic mobility patterns when incorporating estimated home information, where individuals move out in the morning and return home before midnight. To further evaluate the effectiveness of the HOD approach, we conduct an entropy analysis to measure the unpredictability of human mobility. The HOD results exhibit lower entropy values than those in the other two cases, OD and home–destination (HD). These findings underscore the importance of incorporating home information in understanding and modeling human mobility. By leveraging the HOD data aggregation method, we can achieve more accurate population distribution estimates and capture the inherent dynamics of human movement

Wearable sensors in patient acuity assessment in critical care.

Acuity assessments are vital for timely interventions and fair resource allocation in critical care settings. Conventional acuity scoring systems heavily depend on subjective patient assessments, leaving room for implicit bias and errors. These assessments are often manual, time-consuming, intermittent, and challenging to interpret accurately, especially for healthcare providers. This risk of bias and error is likely most pronounced in time-constrained and high-stakes environments, such as critical care settings. Furthermore, such scores do not incorporate other information, such as patients' mobility level, which can indicate recovery or deterioration in the intensive care unit (ICU), especially at a granular level. We hypothesized that wearable sensor data could assist in assessing patient acuity granularly, especially in conjunction with clinical data from electronic health records (EHR). In this prospective study, we evaluated the impact of integrating mobility data collected from wrist-worn accelerometers with clinical data obtained from EHR for estimating acuity. Accelerometry data were collected from 87 patients wearing accelerometers on their wrists in an academic hospital setting. The data was evaluated using five deep neural network models: VGG, ResNet, MobileNet, SqueezeNet, and a custom Transformer network. These models outperformed a rule-based clinical score (Sequential Organ Failure Assessment, SOFA) used as a baseline when predicting acuity state (for ground truth we labeled as unstable patients if they needed life-supporting therapies, and as stable otherwise), particularly regarding the precision, sensitivity, and F1 score. The results demonstrate that integrating accelerometer data with demographics and clinical variables improves predictive performance compared to traditional scoring systems in healthcare. Deep learning models consistently outperformed the SOFA score baseline across various scenarios, showing notable enhancements in metrics such as the area under the receiver operating characteristic (ROC) Curve (AUC), precision, sensitivity, specificity, and F1 score. The most comprehensive scenario, leveraging accelerometer, demographics, and clinical data, achieved the highest AUC of 0.73, compared to 0.53 when using SOFA score as the baseline, with significant improvements in precision (0.80 vs. 0.23), specificity (0.79 vs. 0.73), and F1 score (0.77 vs. 0.66). This study demonstrates a novel approach beyond the simplistic differentiation between stable and unstable conditions. By incorporating mobility and comprehensive patient information, we distinguish between these states in critically ill patients and capture essential nuances in physiology and functional status. Unlike rudimentary definitions, such as equating low blood pressure with instability, our methodology delves deeper, offering a more holistic understanding and potentially valuable insights for acuity assessment.