Resource-constrained Environments Research Articles

Real-time field disease identification based on a lightweight model

In the field of agricultural technology, rapid and accurate diagnosis of crop diseases is crucial for ensuring crop health and yield. However, most methods for automatic diagnosis of plant diseases are primarily based on high-computational-performance server platforms, which limits their application in real-world environments. This paper establishes a crop disease dataset collected from real field scenarios, which is utilized for training, validating the proposed models, and enhancing model generalization in existing research. It provides an accurate and practical database for future research endeavors. The key innovation of this study lies in the development of a lightweight convolutional neural network architecture with high real-time capabilities, characterized by its high precision and efficiency. The network abandons traditional deep convolution, adopting partial convolution and point-wise convolution techniques instead. This approach significantly reduces computational complexity while maintaining high accuracy, making the model highly suitable for application in resource-constrained real-time environments. The proposed method achieved an accuracy of 99.04 % on the open-source PlantVillage dataset and 92.82 % accuracy on a dataset with complex backgrounds constructed. Additionally, this paper also investigates the deployment of the proposed method and other mature technologies on mobile platforms. The focus of this evaluation is to compare the real-time performance on devices with limited computational resources, thereby verifying the model’s applicability in the real world.

DEAC-IoT: Design of lightweight authenticated key agreement protocol for Intra and Inter-IoT device communication using ECC with FPGA implementation

The growing reliance on wireless communication in Internet-of-Things (IoT) devices highlights the critical need for secure and efficient communication protocols, especially in environments vulnerable to cyber threats. Existing IoT protocols often lack sufficient security, creating a need for robust authentication and key exchange mechanisms that can resist attacks while maintaining low computational overhead. In this paper, we propose a fog-enabled network architecture integrated with IoT devices (Intra and Inter IoT device) and develop the DEAC-IoT scheme using Elliptic Curve Cryptography (ECC) for secure authentication and key agreement. Our protocol is designed to protect device-to-device communication from security threats in resource-constrained IoT environments. We validate DEAC-IoT’s security through both informal analysis and formal verification using the Real-Or-Random (RoR) model, demonstrating its resistance to major attacks. Simulation via the Scyther tool confirms that private parameters remain secure throughout the protocol’s execution. For practical feasibility, we implement DEAC-IoT on a Field Programmable Gate Array (FPGA) and conduct performance evaluations. The results show that our protocol surpasses existing protocols in both computational and communication efficiency, making it highly suitable for real-world IoT applications.

Development of a Cost-Effective and High-Fidelity Gel Model for Peripheral Ultrasound-Guided Intravenous Access Training.

Introduction Simulation tools are crucial in medical educationbut current commercial models for ultrasound-guided intravenous (IV) access lack complexity and can be prohibitively expensive. This article proposes a cost-effective gel model system that replicates realistic vein and artery interactions, addressing the limitations of traditional models. An advanced gelatin model was constructed that incorporates intricate vein and artery configurations and enhances medical training by providing a more authentic experience. Patient testing will further validate its efficacy, promising improved accessibility for skill refinement in resource-constrained environments. Methods In a controlled study at theKirk Kerkorian School of Medicine at the University of Nevada, Las Vegas, 12 medical students with limited ultrasound experience participated in a workshop using novel and Blue Phantom™ models for ultrasound-guided IV catheter placement. The advanced gelatin model, created with Ziplock™ Tupperware®, ultrasonography gel-filled balloons, and gelatin, proved more effective, as assessed by participants' post-training comfort levels. The comparison of participants' pre- and post-training comfort levels with the models was the primary study objective. Participants were asked to complete a confidence survey based on a five-point Likert scale, and after using both models, this survey was re-administered to assess the participant's level of comfort after model use. The statistical analysis comparison of post-training survey data to the pre-training survey data was accomplished using SPSS version 29 (IBM Corp, Armonk, NY), where a paired t-test was set at a significance threshold of p <0.05. Results Analysis of data from both commercially made and advanced ultrasound-guided IV models using a paired t-test revealed a significant advantage for the advanced model. Participants, despite limited ultrasound experience, reported feeling over 4 points higher in skill confidence (p = 0.004) with the advanced model. Its popularity stems from diverse vasculature modeling, proving effective for both experienced practitioners and inexperienced individuals, maintaining value as user skill levels increase. Conclusion This study proposes an advanced model for ultrasound-guided peripheral IV access training, demonstrating a statistically significant increase in confidence levels. Despite limitations such as small sample size and single-site participation, the advanced model's adaptability and cost-effectiveness make it a strong contender for replacing current commercial models, potentially enhancing proficiency and confidence while reducing costs.

Lossy Image Compression with Stochastic Quantization

Introduction. Lossy image compression algorithms play a crucial role in various domains, including graphics, and image processing. As image information density increases, so do the resources required for processing and transmission. One of the most prominent approaches to address this challenge is color quantization, proposed by Orchard et al. (1991). This technique optimally maps each pixel of an image to a color from a limited palette, maintaining image resolution while significantly reducing information content. Color quantization can be interpreted as a clustering problem (Krishna et al. (1997), Wan (2019)), where image pixels are represented in a three-dimensional space, with each axis corresponding to the intensity of an RGB channel. The purpose of the paper. Scaling of traditional algorithms like K-Means can be challenging for large data, such as modern images with millions of colors. This paper reframes color quantization as a three-dimensional stochastic transportation problem between the set of image pixels and an optimal color palette, where the number of colors is a predefined hyperparameter. We employ Stochastic Quantization (SQ) with a seeding technique proposed by Arthur et al. (2007) to enhance the scalability of color quantization. This method introduces a probabilistic element to the quantization process, potentially improving efficiency and adaptability to diverse image characteristics. Results. To demonstrate the efficiency of our approach, we present experimental results using images from the ImageNet dataset. These experiments illustrate the performance of our Stochastic Quantization method in terms of compression quality, computational efficiency, and scalability compared to traditional color quantization techniques. Conclusions. This study introduces a scalable algorithm for solving the color quantization problem without memory constraints, demonstrating its efficiency on a subset of images from the ImageNet dataset. The convergence speed of the algorithm can be further enhanced by modifying the update rule with alternative methods to Stochastic Gradient Descent (SGD) that incorporate adaptive learning rates. Moreover, the stochastic nature of the proposed solution enables the utilization of parallelization techniques to simultaneously update the positions of multiple quants, potentially leading to significant performance improvements. This aspect of parallelization and its impact on algorithm efficiency presents a topic for future research. The proposed method not only addresses the limitations of existing color quantization techniques but also opens up new possibilities for optimizing image compression algorithms in resource-constrained environments. Keywords: non-convex optimization, stochastic optimization, stochastic quantization, color quantization, lossy compression.

The Predictors of Medication Adherence among TB Patients on the E-Refill Prescription System in Health Care Facilities in Lagos State

Background: Tuberculosis (TB) has continued to be a major health concern to man and has affected majority of the population around the world. In the World Health Organisation (WHO)’s estimate, Nigeria is second in Africa and seventh in the world with regard to cases. Since Lagos is the most populous state in Nigeria, it has made a high number of tuberculosis cases. Since there is no cure for TB without taking the prescription drugs, noncompliance has been as frequent as the disease, leading to treatment failure, drug resistant TB and increased cost of healthcare. The e-refill prescription system which is an electronic prescription refill system is targeted to increase medical compliance amongst TB patients consequently improving overall health.  Aim: The purpose of this study is therefore to evaluate the factors which determine medication compliance among TB patients on the e-refill prescription in health facilities in Lagos state.  Setting: Various healthcare facilities across Lagos.  Methodology: This study employed the cross-sectional method. For sampling, we opted for a purposive sampling approach to select the patients. The sample size, determined using the Kish formula, comprised approximately 338 TB patients. In order to collect data on critical factors such as patient’s satisfaction, factors influencing e-refill medication adherence, and the willingness to adopt the e-refill system, this study made use of in-depth interview and semi- structured question. Furthermore, the collected data was analysed with SPSS software, with two team members independently coding the interview transcripts to identify emerging themes and resolve discrepancies through consensus discussions.  Results: A large proportion of the participants fell between the ages of 28 to 38 years (45.9%), (53.0%) were married, and the Yoruba ethnic group dominated the population at (49.4%). Most patients received care from government- owned facilities (75.1%). 68.6% considered medical adherence important. Of factors influencing medical adherence, (47%) said that forgetfulness often affected their adherence, and (23.7%) cited the side effect. Of those surveyed, 54.4% expressed interest in using the e- Refill system, and 60.7% were knowledgeable about it. Ease of use (32.8%) and system trust (29.9%) are the main variables influencing readiness to utilise the e-Refill system.  Conclusion: The e-Refill system has shown potential for success in improving medication adherence among TB patients in Lagos state. However, it is important to address challenges such as limited access to healthcare and reluctance among certain patient groups need to be addressed. To get maximum result possible from the system, it is important to take steps to enhance patient engagement, address stigma associated with the illness, and ensure sustained support over the duration of the treatment.  Contribution: The study highlights the significance of niche interventions geared towards promoting medication adherence and improving TB treatment outcomes in resource-constrained environments.

Task Scheduling Algorithm for Power Minimization in Low-Cost Disaster Monitoring System: A Heuristic Approach

This study investigates the optimization of a low-cost IoT-based weather station designed for disaster monitoring, focusing on minimizing power consumption. The system architecture includes application, middleware, communication, and sensor layers, with solar power as the primary energy source. A novel task scheduling algorithm was developed to reduce power usage by efficiently managing the sensing and data transmission periods. Experiments compared the energy consumption of polling and deep sleep techniques, revealing that deep sleep is more energy-efficient (4.73% at 15 s time intervals and 16.45% at 150 s time intervals). Current consumption was analyzed across different test scenarios, confirming that efficient task scheduling significantly reduces power consumption. The energy consumption models were developed to quantify power usage during the sensing and transmission phases. This study concludes that the proposed system, utilizing affordable hardware and solar power, is an effective and sustainable solution for disaster monitoring. Despite using non-low-power devices, the results demonstrate the importance of adaptive task scheduling in extending the operational life of IoT devices. Future work will focus on implementing dynamic scheduling and low-power routing algorithms to enhance system functionality in resource-constrained environments.

A dictionary learning based unsupervised neural network for single image compressed sensing

In the field of Compressed Sensing (CS), the sparse representation of signals and the advancement of reconstruction algorithms are two critical challenges. However, conventional CS algorithms often fail to sufficiently exploit the structured sparsity present in images and suffer from poor reconstruction quality. Most deep learning-based CS methods are typically trained on large-scale datasets. Obtaining a sufficient number of training sets is challenging in many practical applications and there may be no training sets available at all in some cases. In this paper, a novel deep Dictionary Learning (DL) based unsupervised neural network for single image CS (dubbed DL-CSNet) is proposed. It is an effective trainless neural network that consists of three components and their corresponding loss functions: 1) a DL layer that consists of multi-layer perceptron (MLP) and convolution neural networks (CNN) for latent sparse features extraction with the L1-norm sparsity loss function; 2) an image smoothing layer with the Total Variation (TV) like image smoothing loss function; and 3) a CS acquisition layer for image compression, with the Mean Square Error (MSE) loss function between the original image compression and the reconstructed image compression. In particular, the proposed DL-CSNet is a lightweight and fast model that does not require datasets for training and exhibits a fast convergence speed, making it suitable for deployment in resource-constrained environments. Experiments have demonstrated that the proposed DL-CSNet achieves superior performance compared to traditional CS methods and other unsupervised state-of-the-art deep learning-based CS methods.

IoT Video Delivery Optimization through Machine Learning-Based Frame Resolution Adjustment

Providing acceptable video quality in the Internet of Things (IoT) implementation poses a significant challenge, mainly when the application is performed on low-cost and low-power devices. This research focuses on developing a frame resolution adjustment system that maintains the frame rate value of video delivery in wireless IoT environments with resource-constrained devices. Consistent frame rates prevent motion lag and data loss, improving user experience. The system works by predicting the upcoming throughput values using machine learning methods to adjust the sensing parameter, which is the resolution of the video frame to be captured by camera nodes. Hence, the proposed system is equipped with a file size estimator to estimate the size of the next video frame and then adjust the resolution in accordance with the throughput prediction. In this research, we conducted extensive experiments to evaluate the accuracy of the file size estimator and the throughput prediction. The experiment generated a dataset to evaluate throughput prediction and file size estimator model. The evaluation results for the file size estimator showed a mean absolute percentage error (MAPE) of 6.73% in the experiment using 317 frames with video resolutions between 72p and 720p. Experiments were also conducted to compare several machine learning methods for predicting throughput values. Compared to long short-term memory (LSTM) and autoregressive integrated moving average (ARIMA), simple exponential smoothing (SES) outperforms the others with the lowest root mean squared error (RMSE) and mean absolute error (MAE) values. Building upon these findings, we implemented the frame resolution adjustment system using SES as the method for predicting the upcoming throughput values. Finally, we demonstrated that the proposed system can maintain the frame rate according to the threshold set by the system while the resolution is being maximized, thereby addressing the challenges of maintaining video quality in resource-constrained IoT environments.

Diabetic retinopathy detection and categorizing using a lightweight deep learning approach

Diabetic retinopathy is an ocular disorder that has the potential to result in visual impairment and complete loss of vision in those diagnosed with diabetes. This illness affects the retinal blood vessels inside the light-sensitive tissue layer at the posterior of the eye, known as the retina. This paper presents a complete approach to diagnosing and categorizing diabetic retinopathy using deep learning models. A lightweight Convolutional Neural Network (CNN) is used to detect diabetic retinopathy in fundus images. This CNN has been developed to have fewer parameters and calculations, making it suited for resource-constrained environments while retaining decent performance. The categorization of diabetic retinopathy is carried out with the help of EfficientNet. This model uses an innovative compound scaling approach to strike a balance between the model's depth, width, and resolution. As a result, it maximizes computing efficiency while preserving high accuracy. The proposed detection model obtained an accuracy of 95%, and the classification model produced an accuracy of 84%.

Performance evaluation and analysis of public-key schemes in embedded IoT devices

The Internet of Things (IoT) is considered one of the emerging technologies that have attracted widespread attention from industry and academia as a result of their ability to use them in many applications, including military, healthcare, and industrial control. The inherent vulnerabilities in communications of IoT networks, which consist of resource-constrained devices, pose significant security challenges. To protect sensitive data exchanged within these networks, it is necessary to design and implement lightweight and efficient cryptographic schemes that consider resource-constrained IoT devices. This paper evaluates the performance of five well-known public-key schemes on three real-world IoT devices including IOTLAB-M3, Arduino-Zero, and Decawave DWM1001. The examined public-key schemes are categorized into two classes: integer factorization-based (RSA and Rabin schemes) and elliptic curve-based (ECIES, ECDH, and ECDSA schemes). By conducting comprehensive experiments, we compare these schemes in terms of computational time and energy consumption, providing valuable insights for selecting optimal public-key schemes in resource-constrained IoT environments.

LVD-YOLO: An efficient lightweight vehicle detection model for intelligent transportation systems

Vehicle detection is a fundamental component of intelligent transportation systems. However, current algorithms often encounter issues such as high computational complexity, long execution times, and significant resource demands, making them unsuitable for resource-limited environments. To overcome these challenges, we propose LVD-YOLO, a Lightweight Vehicle Detection Model based on YOLO. This model incorporates the EfficientNetv2 network structure as its backbone, which reduces parameters and enhances feature extraction capabilities. By utilizing a bidirectional feature pyramid structure along with a dual attention mechanism, we enable efficient information exchange across feature layers, thereby improving multiscale feature fusion. Additionally, we refine the model's loss function with SIoU loss to boost regression and prediction performance. Experimental results on the PASCAL VOC and MS COCO datasets show that LVD-YOLO outperforms YOLOv5s, achieving a 0.5% increase in accuracy while reducing FLOPs by 64.6% and parameters by 48.6%. These improvements highlight its effectiveness for use in resource-constrained environments.

A Shark Inspired Ensemble Deep Learning Stacks for Ensuring the Security in Internet of Things (IoT)-Based Smart City Infrastructure

Recent advancements in the Internet of Things (IoT) have paved the way for intelligent and sustainable solutions in smart city environments. However, despite these advantages, IoT-connected devices present significant privacy and security risks, as network attacks increasingly exploit user-centric information. To protect the network against the rapidly growing number of cyber-attacks, it is essential to employ a cognitive intrusion detection system (CIDS) capable of handling complex and voluminous network data. This research presents a novel ensemble deep learning framework designed to enhance cybersecurity in IoT-based smart city ecosystems. The proposed architecture integrates Self-Attention Convolutional Neural Networks, Bidirectional Gated Recurrent Units, and Shark Smell Optimized Feed Forward Networks to create a robust, adaptive system for detecting and mitigating cyber threats. By leveraging fog computing, the model significantly reduces latency and computational overhead, making it highly suitable for large-scale IoT deployments. Extensive experimentation using the ToN-IoT dataset demonstrates the framework's exceptional performance, achieving a 99.78% detection rate across various attack types and an AUC of 0.989. The proposed model outperforms existing state-of-the-art approaches, achieving a mean fitness function value of 0.85640 and a standard deviation of 0.037630 in binary classification outcomes. In multi-class classification, the model maintains a mean fitness function value of 0.8230 and a variance of 2.28930 × 104, significantly outperforming other meta-heuristic algorithms such as Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). The model exhibits superior accuracy and efficiency compared to existing state-of-the-art approaches, particularly in identifying complex and emerging threats. This research makes significant contributions by introducing innovative feature extraction techniques, optimizing model performance for resource-constrained environments, and providing a scalable solution for securing smart city infrastructure. The findings highlight the potential of ensemble deep learning approaches to fortify IoT networks against cyberattacks, paving the way for more resilient and secure smart cities.

A Review of Physical and Logical Design in IoT: Comparative Analysis of Devices, Protocols, Communication Models, and APIs

The Internet of Things (IoT) has emerged as a transformative technology, enabling connectivity and data exchange among a vast network of devices. This paper presents a comprehensive comparative analysis of the physical and logical design elements of IoT systems, focusing on IoT devices, communication protocols, models, and APIs (REST and WebSocket). The research highlights the critical role that both physical and logical components play in ensuring efficient, secure, and scalable IoT deployments. By examining the integration of these aspects, the paper aims to provide insights for optimizing IoT architectures for various use cases, particularly in resource-constrained environments.

Early-stage entrepreneurs’ communicative strategies in managing knowledge ambiguity

ABSTRACT Prior research demonstrates the importance of knowledge seeking on startup performance, but the process of accessing knowledge is less studied. Knowledge ambiguity in entrepreneurship is embedded in the complexities and interconnectedness of knowledge sources, knowledge components, knowledge transfer mechanisms, and knowledge adaptation processes. This study explores the communicative strategies entrepreneurs use to cope with knowledge ambiguity, specifically with the use of online and offline channels. Interview data were collected from 20 early-stage entrepreneurs in the knowledge-intensive industries in the New York metropolitan area. Five strategies emerged from the data: manage public visibility, optimize knowledge relevance, enhance communication efficiency, expand knowledge awareness, and access indirect knowledge. This research contributes to the knowledge of how communication and media use unfold in resource-constrained environments and to the growing literature of entrepreneurial bricolage (make do with what is at hand) in knowledge management.

ESG ratings and corporate competitive strategy: evidence from China

ABSTRACT This paper investigates the impact of ESG ratings on the competitive strategies of Chinese listed companies. Machine learning and text analysis methods are used to develop indicators for cost leadership and differentiation strategies. A time-varying difference-in-differences (DID) model is employed to quantitatively assess the impact of ESG ratings on these strategies. The findings show that ESG ratings positively affect both strategies. The heterogeneity analysis indicates that companies with lower bank concentration or insufficient financial asset allocation benefit more significantly from ESG ratings in enhancing their competitive strategies. This research provides theoretical insights and practical recommendations for the integration of ESG factors into corporate strategy, particularly in resource-constrained environments.

Adapting the ‘study and research path’ methodology in strength of materials to online teaching and resource-constrained scenarios

The Study and Research Path (SRP) methodology, emphasizing exploration of answers to open questions, has recently gained recognition as an effective active and inquiry-based learning approach, notably in the realm of Mechanical Engineering education. This study investigates the adaptation of SRPs to online and resource-constrained environments. We present and compare eight SRP-based Strength of Material courses conducted before, during, and after the COVID-19 pandemic. Our analysis focuses on the transformations observed in SRPs, encompassing shifts in course organization, question-answer maps, media-milieu dialectics, resource utilization, and inquiry procedures. Our findings demonstrate the successful adaptation of the SRP course to online teaching during the unprecedented remote conditions brought about by the pandemic. This adaptation resulted in a more guided Q-A map, innovative practical experiences with homemade setups, increased use of simulations, and parallelized inquiry by different groups. Importantly, materials and strategies developed during this transformation proved invaluable in subsequent post-pandemic courses, particularly in hybrid or constrained space and cohort settings. Our study highlights the adaptability and efficacy of SRPs in diverse teaching environments, providing valuable insights for educators seeking to implement SRPs and other active-learning, inquiry-based methodologies to challenging ecological conditions.

Assessing Impact of AI on Resource Efficiency in Manufacturing in West Africa

This study investigates the impact of Artificial Intelligence (AI) on resource efficiency in the manufacturing sector within West Africa, a region characterized by infrastructural challenges and resource constraints. Through integrating Transaction Cost Economics (TCE) and the Resource-Based View (RBV) theories, the research explores how AI-driven technologies, including predictive maintenance, production optimization, real-time data analytics, and smart manufacturing systems, enhance resource efficiency. A quantitative research design with a correlational approach was employed, surveying 381 professionals across various manufacturing sectors. The study also examined the moderating role of the regulatory environment and the mediating effect of employee training and adaptation on these relationships. Findings indicate that AI-driven technologies significantly improve resource efficiency by reducing downtime, optimizing production processes, and enhancing decision-making. The regulatory environment positively moderates the relationship between AI technologies and resource efficiency, particularly when coupled with employee training. This study contributes to the existing body of knowledge by providing empirical evidence on the strategic role of AI in resource-constrained environments, emphasizing the importance of supportive regulations and workforce adaptation. The results offer practical implications for policymakers and industry leaders in West Africa, highlighting the need for targeted investments in AI infrastructure, regulatory development, and capacity building to fully leverage AI's potential in manufacturing.

Robust Mixed-Rate Region-of-Interest-Aware Video Compressive Sensing for Transmission Line Surveillance Video

Classic video compression methods usually suffer from long encode time and requires large memories, making it hard to deploy on edge devices; thus, video compressive sensing, which requires less resources during encoding, is receiving more attention. We propose a robust mixed-rate ROI-aware video compressive sensing algorithm for transmission line surveillance video compression. The proposed method compresses foreground targets and background frames separately and uses reversible neural network to reconstruct original frames. The result on transmission line surveillance video data shows that the proposed compressive sensing method can achieve 26.47, 34.71 PSNR and 0.6839, 0.9320 SSIM higher than existing methods on 1.5% and 15% measurement rates, and the proposed ROI extraction net can precisely retrieve regions under high noise levels. This research not only demonstrates the potential for a more efficient video compression technique in resource-constrained environments, but also lays a foundation for future advancements in video compressive sensing techniques and their applications in various real-time surveillance systems.

Enhancing Transmission Efficiency in Non-IID Federated Learning by Integrating Quantization into an Existing Trustworthiness Model

Federated Learning (FL) is a distributed machine learning paradigm that enables multiple clients to collaboratively train a model without sharing their data, thus preserving privacy. In this approach, data is not transmitted between the client and the base station. Instead, a model is sent to each device, where it is trained locally, and then retransmitted back to the base station. Each iteration of this process is known as a communication round. However, FL faces challenges, especially when data is not independently and identically distributed (Non-IID). Non-IID data means that the data across clients can vary significantly in distribution, leading to situations where certain classes or features are overrepresented in some clients and underrepresented in others. This lack of uniformity quickly leads to biased model updates and reduced performance. To address this, previous studies have introduced trustworthiness metrics to ensure more reliable model aggregation, minimizing accuracy losses associated with Non-IID data. Another significant challenge is the high transmission load, as model updates between clients and the base station are resource-intensive. Model parameters are transmitted between clients and base stations, which can strain communication channels and slow down the entire process, especially when dealing with larger models and datasets. This communication overhead is a bottleneck that limits the scalability of FL, particularly in resource-constrained environments. Our research addresses these challenges by integrating quantization into the trustworthiness model specifically in a Non-IID scenario. Quantization reduces the precision of model parameters to minimize data transmission, resulting in more efficient communication. We applied different levels of quantization intensity to a model trained on the CIFAR-10 dataset and found that certain methods can significantly reduce transmission overhead without substantial accuracy loss. Our findings suggest that combining quantization with trustworthiness metrics can significantly enhance the efficiency and potentially improve the adoption of Federated Learning in resource-constrained environments.

Optimization of Patient and Nurse Management in Health Care: A Case Study

Effective patient selection and nurse allocation are crucial for optimizing hospital care, especially in resource-constrained environments. This study introduces a two-stage mixed integer linear programming (MILP) model designed to prioritize patients based on care urgency and match them with appropriately skilled nurses. Following consultations with healthcare professionals, patients were categorized into three priority levels: high (critical care), normal (basic care), and low (expert consultations). Applying the model to the surgery department of Pabna Medical College Hospital, Bangladesh, 196 out of 950 patients were selected for care: 117 requiring critical care, 59 needing basic care, and 20 for consultative care, necessitating the allocation of 41 nurses. The model demonstrated significant improvements in patient selection and nurse workload management, ensuring maximum patient service within capacity constraints and achieving a balanced distribution of nurse workloads. This approach enhances hospital efficiency and patient care quality, allowing non-chosen patients to seek alternative care options. The model’s adaptability across different departments underscores its potential for widespread application in healthcare management. Journal of Engineering Science 15(1), 2024, 83-94