Resource-constrained Environments Research Articles

Continual Learning and Adaptation In Resource-Constrained Environments (CLAIRE)

As climate-related extreme events continue to increase and impact the world, of particular importance are the threats posed to food, agriculture, and water (FAW) systems. Deep learning could benefit FAW systems for classification of threats and for forecasting potential future events given historical patterns. However, many FAW systems are faced with operational environments that are resource-constrained, which could present challenges in deploying deep learning models. Continual learning offers a way to overcome certain deployment challenges by enabling deep learning models that are more robust to data distribution changes, without the need for GPUs or off-line training. We describe a continual learning approach to forecasting extreme air quality events developed for the National Oceanic and Atmospheric Administration to provide operational air quality guidance to the Continental United States. We describe how this deep learning model is resilient to future data distribution changes by performing curriculum learning, and how it can be deployed as a continual learner, offering better predictive performance for resource-constrained environments.

Enhancing mosquito classification through self-supervised learning

Traditional mosquito identification methods, relied on microscopic observation and morphological characteristics, often require significant expertise and experience, which can limit their effectiveness. This study introduces a self-supervised learning-based image classification model using the Bootstrap Your Own Latent (BYOL) algorithm, designed to enhance mosquito species identification efficiently. The BYOL algorithm offers a key advantage by eliminating the need for labeled data during pretraining, as it autonomously learns important features. During fine-tuning, the model requires only a small fraction of labeled data to achieve accurate results. Our approach demonstrates impressive performance, achieving over 96.77% accuracy in mosquito image analysis, with minimized both false positives and false negatives. Additionally, the model’s overall accuracy, measured by the area under the ROC curve, surpasses 99.55%, highlighting its robustness and reliability. A notable finding is that fine-tuning with just 10% of labeled data produces results comparable to using the full dataset. This is particularly valuable for resource-limited settings with limited access to advanced equipment and expertise. Our model provides a practical solution for mosquito identification, overcoming the challenges of traditional microscopic methods, such as the time-consuming process and reliance on specialized knowledge in healthcare services. Overall, this model supports personnel in resource-constrained environments by facilitating mosquito vector density analysis and paving the way for future mosquito species identification methodologies.

Systematic Analysis of Low-Precision Training in Deep Neural Networks: Factors Influencing Matrix Computations

As Deep Neural Networks (DNNs) continue to increase in complexity, the computational demands of their training have become a significant bottleneck. Low-precision training has emerged as a crucial strategy, wherein full-precision values are quantized to lower precisions, reducing computational overhead while aiming to maintain model accuracy. While prior research has primarily focused on minimizing quantization noise and optimizing performance for specific models and tasks, a comprehensive understanding of the general principles governing low-precision computations across diverse DNN architectures has been lacking. In this paper, we address this gap by systematically analyzing the factors that influence low-precision matrix computations, which are fundamental to DNN training. We investigate three critical factors—accumulation in matrix calculations, the frequency of element usage, and the depth of matrices within the model—and their impact on low-precision training. Through controlled experiments on standard models, as well as customized experiments designed to isolate individual factors, we derive several key insights: layers with higher accumulation and matrices with lower usage frequencies demonstrate greater tolerance to low-precision noise, without significantly compromising the stability of model training. Additionally, while the depth of matrices influences the stability of matrix operations to some extent, it does not have a noticeable effect on the overall training outcomes. Our findings contribute to the development of generalizable principles for low-precision training, offering a systematic framework applicable across various DNN architectures. We provide empirical evidence supporting the strategic allocation of training bit-widths based on the analyzed factors, thereby enhancing the efficiency and effectiveness of DNN training in resource-constrained environments.

Effectiveness of EHR systems on decision support in primary healthcare: a technology acceptance model 3 perspective.

This study aims to evaluate healthcare practitioners' perceptions of electronic health record (EHR) systems and their effectiveness in supporting clinical decision-making in Tanzanian Primary Healthcare (PHC) facilities. A mixed-methods approach was employed, combining quantitative data from structured questionnaires and qualitative insights from open-ended responses. The study was conducted in the Dodoma region of Tanzania, focusing on a diverse representation of PHC facilities, including district hospitals, health centres and dispensaries. Data were analysed using multiple linear regression for quantitative data, and thematic analysis was applied to qualitative responses. The results revealed that while EHR systems are widely used in Tanzanian PHC facilities, their impact on clinical decision-making remains limited. Only a moderate portion of practitioners perceived EHR systems as effective in decision support, and frequent system use was negatively correlated with user satisfaction. Challenges such as inadequate training and support, system crashes, slow performance and poor usability and integration into clinical workflows were significant barriers to effectively utilising EHR systems. This study contributes to the limited literature on EHR system implementation in low-resource settings, specifically Tanzania, by focusing on decision-support features within EHR systems. The findings offer valuable insights for healthcare policymakers, system designers and practitioners to optimise EHR implementation and improve healthcare outcomes in resource-constrained environments.

FastPTM: Fast weights loading of pre-trained models for parallel inference service provisioning

Pre-trained models (PTMs) have demonstrated great success in a variety of NLP and CV tasks and have become a significant development in the field of deep learning. However, the large memory and high computational requirements associated with PTMs can increase the cost and time of inference, limiting their service provisioning in practical applications. To improve the Quality of Service (QoS) of PTM applications by reducing waiting and response times, we propose the FastPTM framework. This general framework aims to accelerate PTM inference services in a multi-tenant environment by reducing model loading time and switching overhead on GPUs. The framework utilizes a fast weights loading method based on weights and model separation of PTMs to efficiently accelerate parallel inference services in resource-constrained environments. Furthermore, an online scheduling algorithm is designed to reduce the inference service time. The results of the experiments indicate that FastPTM can improve the throughput of inference services by an average of 4x and up to 8.2x, while reducing the number of switches by 4.7x and the number of overtimes by 15.3x.

Message Authentication Scheme on Light Weight Parallel Encryption Model With Digit Artithmetic of Covertext using Secure Hash Algorithm

This research aims to enhance message security by developing a Light Weight Parallel Digit Arithmetic of Covertext (PDAC) encryption-based authentication scheme that adopts the Secure Hash Algorithm (SHA) algorithm to ensure message integrity and authentication aspects. Through experiments, tests are conducted on two main aspects: entropy and collision resistance. The experimental results show that the average entropy generated reaches 4.992, or 62.41% of the optimal entropy value. While this result shows a good randomness, there is room for further improvement to reach the optimal level. Collision resistance testing using Google's SHAttered tool showed very positive results. No collisions were found in any of the samples tested, indicating that the PDAC scheme combined with SHA can maintain message integrity well. This indicates that PDAC has strong resistance to hash-based attacks, ensuring that messages remain authentic and safe from manipulation. Thus, this study concludes that PDAC schemes offer a good balance between efficiency, security, and low power consumption, making it suitable for use in resource-constrained environments such as IoT devices and mobile applications

Organizational Commitment as a Mediator: Exploring the Relationship between Job Satisfaction and Job Performance in the Ghanaian Public Sector

Public sector organizations in developing countries face significant challenges related to workforce retention, job satisfaction, and performance, particularly in Ghana, where limited resources and economic constraints exacerbate these issues. Addressing these challenges is vital for improving organizational outcomes and ensuring effective delivery of public services. This study explores the relationship between job satisfaction and job performance in Ghana’s public sector, focusing on the mediating role of organizational commitment. Understanding these dynamics is becoming increasingly important as public sector organizations grapple with the complexities of workforce management in resource-constrained environments. A sample of 300 employees was selected through purposive and convenience sampling, with 200 valid responses (66.6% response rate). Data were analyzed using SMART PLS 3.0 and SPSS 22, applying partial least squares structural equation modeling (PLS-SEM) to assess the research model and hypotheses. The findings reveal that job satisfaction significantly impacts affective, continuance, and normative commitment. Additionally, continuance and normative commitment positively influence job performance, whereas affective commitment does not. This study underscores the importance of job satisfaction in enhancing job performance through its effect on organizational commitment. To improve workforce outcomes, the study recommends targeted training programs that address skill gaps and increase job satisfaction. Public sector organizations, particularly local governments, should prioritize the implementation of effective job satisfaction strategies to boost employee performance and commitment. This research provides valuable insights into how public sector entities in developing countries like Ghana can foster employee performance through improved organizational commitment.

Portable ultrasound devices for obstetric care in resource-constrained environments: mapping the landscape

Background The WHO’s recommendations on antenatal care underscore the need for ultrasound assessment during pregnancy. Given that maternal and perinatal mortality remains unacceptably high in underserved regions, these guidelines are imperative for achieving better outcomes. In recent years, portable ultrasound devices have become increasingly popular in resource-constrained environments due to their cost-effectiveness, useability, and adoptability in resource-constrained settings. This desk review presents the capabilities and costs of currently available portable ultrasound devices, and is meant to serve as a resource for clinicians and researchers in the imaging community. Methods A list of ideal technical features for portable ultrasound devices was developed in consultation with subject matter experts (SMEs). Features included image acquisition modes, cost, portability, compatibility, connectivity, data storage and security, and regulatory certification status. Information on each of the devices was collected from publicly available information, input from SMEs and/or discussions with company representatives. Results 14 devices were identified and included in this review. The output is meant to provide objective information on ideal technical features for available ultrasound systems to researchers and clinicians working in obstetric ultrasound in low-resource settings. No product endorsements are provided. Conclusions This desk review provides an overview of the landscape of low-cost portable ultrasound probes for use in obstetrics in resource-constrained environments, and provides a description of key capabilities and costs for each. Methods could be applied to mapping the landscape of portable ultrasound devices for other clinical applications, or may be extended to reviewing other types of healthcare technologies. Further studies are recommended to evaluate portable ultrasound devices for usability and durability in global field settings.

Cooperation and Fairness in Multi-Agent Reinforcement Learning

Multi-agent systems are trained to maximize shared cost objectives, which typically reflect system-level efficiency. However, in the resource-constrained environments of mobility and transportation systems, efficiency may be achieved at the expense of fairness — certain agents may incur significantly greater costs or lower rewards compared to others. Tasks could be distributed inequitably, leading to some agents receiving an unfair advantage while others incur disproportionately high costs. It is, therefore, important to consider the tradeoffs between efficiency and fairness in such settings. We consider the problem of fair multi-agent navigation for a group of decentralized agents using multi-agent reinforcement learning (MARL). We consider the reciprocal of the coefficient of variation of the distances traveled by different agents as a measure of fairness and investigate whether agents can learn to be fair without significantly sacrificing efficiency (i.e., increasing the total distance traveled). We find that by training agents using min-max fair distance goal assignments along with a reward term that incentivizes fairness as they move towards their goals, the agents (1) learn a fair assignment of goals and (2) achieve almost perfect goal coverage in navigation scenarios using only local observations. For goal coverage scenarios, we find that, on average, the proposed model yields a 14% improvement in efficiency and a 5% improvement in fairness over a baseline model that is trained using random assignments. Furthermore, an average of 21% improvement in fairness can be achieved by the proposed model as compared to a model trained on optimally efficient assignments; this increase in fairness comes at the expense of only a 7% decrease in efficiency. Finally, we extend our method to environments in which agents must complete coverage tasks in prescribed formations and show that it is possible to do so without tailoring the models to specific formation shapes. [Code]

Multiple Function Merging for Code Size Reduction

Resource-constrained environments, such as embedded devices, have limited amounts of memory and storage. Practical programming languages such as C++ and Rust tend to output multiple similar functions by monomorphizing polymorphic functions. An optimization technique called Function Merging, which merges similar functions into a single function, has been studied. However, in the state-of-the-art approach, the number of functions that can be merged at once is limited to two; thus, efficiently merging three or more functions, which are often generated from polymorphic functions, has been impossible. In this study, we propose Multiple Function Merging optimization, which targets merging three or more similar functions into a single function using a multiple sequence alignment algorithm. With multiple aligned information, Multiple Function Merging can increase merge opportunities and reduce extra branching overheads at the code generation stage. We evaluated it using the SPEC CPU benchmark suite and some large-scale C/C++ programs, and the results show that it reduces code size by as much as 7.61% compared with the state-of-the-art approach.

Effects of Recognition on Motivation of Volunteers in Non-Governmental Organizations in Tanzania: A Case of World Vision in Tanzania

This study investigates the impact of various recognition practices on volunteer motivation in non-governmental organizations (NGOs) in Tanzania, with a focus on World Vision Tanzania. The research addresses the challenge of maintaining volunteer engagement and retention in resource-constrained environments. This study used descriptive research design. Simple random sampling method was used to select 81 respondents. Quantitative data was collected by use of questionnaires. Data was analysed using multiple regression method by the aid of Statistical Package of Social Scientists Program (SPSS). The findings reveal that recognition significantly influences volunteer motivation. Recognition from superiors (Beta coefficient= 0.987, Sig. value = .000) and Member recognition being treated as an integral part of the organization (Beta coefficient= 0. 832, Sig. value = .000) emerged as the most potent motivators. Personal forms of recognition, such as verbal acknowledgment, were found to be more impactful than public or formal recognitions. Based on these results, the study recommends a multi-faceted approach to volunteer recognition, emphasizing personal acknowledgment, organizational inclusion, and strategic use of formal recognition methods. The research suggests that NGOs should prioritize training for supervisors on effective recognition practices, create an inclusive organizational culture, and regularly assess and adapt their recognition strategies to maintain long-term volunteer motivation and engagement.

Decentralized Machine Learning Framework for the Internet of Things: Enhancing Security, Privacy, and Efficiency in Cloud-Integrated Environments

The Internet of things (IoT) presents unique challenges for the deployment of machine learning (ML) models, particularly due to constraints on computational resources, the necessity for decentralized processing, and concerns regarding security and privacy in interconnected environments such as the Internet of cloud. In this paper, a novel decentralized ML framework is proposed for IoT environments characterized by wireless communication, dynamic data streams, and integration with cloud services. The framework integrates incremental learning algorithms with a robust decentralized model exchange protocol, ensuring that data privacy is preserved, while enabling IoT devices to participate in collaborative learning from distributed data across cloud networks. By incorporating a gossip-based communication protocol, the framework ensures energy-efficient, scalable, and secure model exchange, fostering effective knowledge sharing among devices, while addressing the potential security threats inherent in cloud-based IoT ecosystems. The framework’s performance was evaluated through simulations, demonstrating its ability to handle the complexities of real-time data processing in resource-constrained IoT environments, while also mitigating security and privacy risks within the Internet of cloud.

Beyond Empathy: Examining the Complexities of Outpatient Satisfaction in a Resource-Constrained Setting

Patient satisfaction is a critical indicator of healthcare quality, particularly in resource-constrained settings where efficient and effective care is paramount. This study aimed to explore the multifaceted nature of outpatient satisfaction at a private Indonesian hospital, moving beyond the traditional focus on empathy to understand the interplay of various service quality dimensions. A mixed-methods sequential explanatory design was employed. The quantitative phase involved a survey of 400 outpatients, measuring their satisfaction with five service quality dimensions: tangibles, reliability, responsiveness, empathy, and assurance. Data were analyzed using descriptive statistics, Importance-Performance Analysis (IPA), and gap analysis (suitability index). The qualitative phase utilized in-depth interviews and focus group discussions with patients, staff, and management to provide context and depth to the quantitative findings. While overall patient satisfaction was 82.9%, a gap analysis revealed substantial discrepancies between patient expectations and perceptions across several service quality dimensions. Tangibles, reliability, and responsiveness emerged as key areas requiring improvement. Qualitative findings highlighted extended wait times, inconsistent staff communication, and concerns about the physical environment as significant contributors to patient dissatisfaction. Achieving high levels of patient satisfaction in resource-constrained environments necessitates a comprehensive approach that addresses systemic inefficiencies and communication gaps alongside interpersonal factors like empathy. These findings underscore the need for targeted interventions to optimize resource allocation, streamline processes, and enhance staff communication skills to improve the patient experience.

The application and challenges of different face recognition technologies in the three major fields of security, social media, and medical care

Abstract. Face recognition technology is a very important part of modern technology, which can not only be used to ensure security, but also can be used in the field of information organization and content division. However, with the popularization and application of face recognition technology, many problems that need to be solved urgently have emerged: excessive computing resources are consumed in order to pursue high-precision recognition, which brings computing pressure; The basis for improving recall is the need for a lot of power and memory; If security is not guaranteed, it can cause problems such as data breaches. The demand for face recognition technology is different in different use fields, so the purpose of this study is to combine the scene requirements and technical advantages more reasonably. The research results are as follows: the high accuracy and recall rate of 3D convolutional neural networks (3DCNNs) ensure that it can be used safely in high-precision and high-security scenarios. Lightweight Convolutional Neural Network (MobileNetV2) is suitable for resource-constrained environments due to its low memory consumption and low communication cost. Edge computing real-time face recognition (EC-RFERNet) is the most suitable for large-scale popularization and application among the three because of its lowest power consumption and latency. This study deeply explores the advantages and disadvantages of different facial recognition technologies and finds solutions to their shortcomings. According to their unique advantages combined with the requirements of commonly used scenarios, it provides a scientific basis for the deployment of face recognition technology in different fields. However, due to limited information, this paper cannot cover all application scenarios and the latest technologies, so it is hoped that in the future, we can combine the advantages of different technologies to develop more comprehensive face recognition technology and make more reasonable technical planning.

A Feature-Fusion Technique-Based Alzheimer’s Disease Classification Using Magnetic Resonance Imaging

Background: Early identification of Alzheimer’s disease (AD) is essential for optimal treatment and management. Deep learning (DL) technologies, including convolutional neural networks (CNNs) and vision transformers (ViTs) can provide promising outcomes in AD diagnosis. However, these technologies lack model interpretability and demand substantial computational resources, causing challenges in the resource-constrained environment. Hybrid ViTs can outperform individual ViTs by visualizing key features with limited computational power. This synergy enhances feature extraction and promotes model interpretability. Objectives: Thus, the authors present an innovative model for classifying AD using MRI images with limited computational resources. Methods: The authors improved the AD feature-extraction process by modifying the existing ViTs. A CatBoost-based classifier was used to classify the extracted features into multiple classes. Results: The proposed model was generalized using the OASIS dataset. The model obtained an exceptional classification accuracy of 98.8% with a minimal loss of 0.12. Conclusions: The findings highlight the potential of the proposed AD classification model in providing an interpretable and resource-efficient solution for healthcare centers. To improve model robustness and applicability, subsequent research can include genetic and clinical data.

Implementation of a genotyped African population cohort, with virtual follow-up: A feasibility study in the Western Cape Province, South Africa

Background There is limited knowledge regarding African genetic drivers of disease due to prohibitive costs of large-scale genomic research in Africa. Methods We piloted a cost-effective, scalable virtual genotyped cohort in South Africa, with participant recruitment using a tiered informed consent model and DNA collection by buccal swab. Genotype data was generated using the H3Africa Illumina micro-array, and phenotype data was derived from routine health data of participants. We demonstrated feasibility of nested case control genome wide association studies using these data for phenotypes type 2 diabetes mellitus (T2DM) and severe COVID-19. Results 2267346 variants were analysed in 459 participant samples. 78.6% of SNPs and 74% of samples passed quality control (QC). Principal component analysis showed extensive ancestry admixture in study participants. For 1780 published COVID-19-associated variants, 3 SNPs in the pre-imputation data and 23 SNPS in the imputed data were significantly associated with severe COVID-19 cases compared to controls. For 2755 published T2DM associated variants, 69 SNPs in the pre-imputation data and 419 SNPs in the imputed data were significantly associated with T2DM cases when compared to controls. Conclusions The results shown here are illustrative of what will be possible as the cohort expands in the future. Here we demonstrate the feasibility of this approach, recognising that the findings presented here are preliminary and require further validation once we have a sufficient sample size to improve statistical significance of findings. We implemented a genotyped population cohort with virtual follow up data in a resource-constrained African environment, demonstrating feasibility for scale up and novel health discoveries through nested case-control studies.

Open Data-Driven 3D Building Models for Micro-Population Mapping in a Data-Limited Setting

Urban planning and management increasingly depend on accurate building and population data. However, many regions lack sufficient resources to acquire and maintain these data, creating challenges in data availability. Our methodology integrates multiple data sources, including aerial imagery, Points of Interest (POIs), and digital elevation models, employing Light Gradient Boosting Machine (LightGBM) and Gradient Boosting Decision Tree (GBDT) to classify building uses and morphological filtration to estimate heights. This research contributes to bridging the gap between data needs and availability in resource-constrained urban environments, offering a scalable solution for global application in urban planning and population mapping.

A Multilayer Nonlinear Permutation Framework and Its Demonstration in Lightweight Image Encryption

As information systems become more widespread, data security becomes increasingly important. While traditional encryption methods provide effective protection against unauthorized access, they often struggle with multimedia data like images and videos. This necessitates specialized image encryption approaches. With the rise of mobile and Internet of Things (IoT) devices, lightweight image encryption algorithms are crucial for resource-constrained environments. These algorithms have applications in various domains, including medical imaging and surveillance systems. However, the biggest challenge of lightweight algorithms is balancing strong security with limited hardware resources. This work introduces a novel nonlinear matrix permutation approach applicable to both confusion and diffusion phases in lightweight image encryption. The proposed method utilizes three different chaotic maps in harmony, namely a 2D Zaslavsky map, 1D Chebyshev map, and 1D logistic map, to generate number sequences for permutation and diffusion. Evaluation using various metrics confirms the method’s efficiency and its potential as a robust encryption framework. The proposed scheme was tested with 14 color images in the SIPI dataset. This approach achieves high performance by processing each image in just one iteration. The developed scheme offers a significant advantage over its alternatives, with an average NPCR of 99.6122, UACI of 33.4690, and information entropy of 7.9993 for 14 test images, with an average correlation value as low as 0.0006 and a vast key space of 2800. The evaluation results demonstrated that the proposed approach is a viable and effective alternative for lightweight image encryption.

The role of innovation strategies in balancing growth and profit: evidence from Colombian firms

ABSTRACT Research highlights the significant impact of exploratory, exploitative, and ambidextrous innovation strategies on firm performance. Ambidextrous innovation is particularly effective, enhancing performance in both emerging and developed markets. However, the differential effects on growth and profitability in resource-constrained emerging markets are still not fully understood. This study employs panel data regression to analyze the influence of these innovation strategies on 1047 Colombian manufacturing firms from 2007 to 2018, with a specific focus on the moderating role of diverse knowledge sources. Findings indicate that ambidextrous innovation positively correlates with both growth and profitability. In contrast, firms focusing solely on either exploratory or exploitative strategies experience negative impacts on domestic growth. The integration of a broad range of knowledge sources further amplifies the positive effects of ambidextrous innovation. This research provides valuable insights for effectively leveraging innovation strategies in emerging markets, offering a strategic framework for firms and policymakers in resource-constrained environments.

Ponte: Represent Totally Binary Neural Network Toward Efficiency

In the quest for computational efficiency, binary neural networks (BNNs) have emerged as a promising paradigm, offering significant reductions in memory footprint and computational latency. In traditional BNN implementation, the first and last layers are typically full-precision, which causes higher logic usage in field-programmable gate array (FPGA) implementation. To solve these issues, we introduce a novel approach named Ponte (Represent Totally Binary Neural Network Toward Efficiency) that extends the binarization process to the first and last layers of BNNs. We challenge the convention by proposing a fully binary layer replacement that mitigates the computational overhead without compromising accuracy. Our method leverages a unique encoding technique, Ponte::encoding, and a channel duplication strategy, Ponte::dispatch, and Ponte::sharing, to address the non-linearity and capacity constraints posed by binary layers. Surprisingly, all of them are back-propagation-supported, which allows our work to be implemented in the last layer through extensive experimentation on benchmark datasets, including CIFAR-10 and ImageNet. We demonstrate that Ponte not only preserves the integrity of input data but also enhances the representational capacity of BNNs. The proposed architecture achieves comparable, if not superior, performance metrics while significantly reducing the computational demands, thereby marking a step forward in the practical deployment of BNNs in resource-constrained environments.