Application of artificial intelligence for resilient and sustainable healthcare system: systematic literature review and future research directions

International Journal of Production Research, Journal Year: 2023, Volume and Issue: unknown, P. 1 - 23

Published: March 13, 2023

Recent years have witnessed increased pressure across the global healthcare system during COVID-19 pandemic. The pandemic shattered existing operations and taught us importance of a resilient sustainable system. Digitisation, specifically adoption Artificial Intelligence (AI) has positively contributed to developing in recent past. To understand how AI contributes building system, this study based on systematic literature review 89 articles extracted from Scopus Web Science databases is conducted. organised around several key themes such as applications, benefits, challenges using technology sector. It observed that wide applications radiology, surgery, medical, research, development Based analysis, research framework proposed an extended Antecedents, Practices, Outcomes (APO) framework. This comprises applications' antecedents, practices, outcomes for Consequently, three propositions are drawn study. Furthermore, our adopted theory, context methodology (TCM) provide future directions, which can be used reference point studies.

Language: Английский

---

Topology-Based Routing Protocols and Mobility Models for Flying Ad Hoc Networks: A Contemporary Review and Future Research Directions

Drones, Journal Year: 2021, Volume and Issue: 6(1), P. 9 - 9

Published: Dec. 31, 2021

Telecommunications among unmanned aerial vehicles (UAVs) have emerged recently due to rapid improvements in wireless technology, low-cost equipment, advancement networking communication techniques, and demand from various industries that seek leverage data improve their business operations. As such, UAVs started become extremely prevalent for a variety of civilian, commercial, military uses over the past few years. form flying ad hoc network (FANET) as they communicate collaborate wirelessly. FANETs may be utilized quickly complete complex are frequently deployed three dimensions, with mobility model determined by work do, hence differ between vehicular networks (VANETs) mobile (MANETs) terms features attributes. Furthermore, different flight constraints high dynamic topology make design routing protocols difficult. This paper presents comprehensive review covering UAV network, several links, protocols, models, important research issues, simulation software dedicated FANETs. A topology-based protocol specialized is discussed in-depth, detailed categorization, descriptions, qualitatively compared analyses. In addition, demonstrates open topics future challenge issues need resolved researchers, before communications expected reality practical industry.

Language: Английский

---

Application of Unmanned Aerial Vehicles in Logistics: A Literature Review

Sustainability, Journal Year: 2022, Volume and Issue: 14(21), P. 14473 - 14473

Published: Nov. 4, 2022

The booming development of e-commerce has brought many challenges to the logistics industry. To ensure sustainability industry, impact environmental and social factors on needs be considered. Unmanned Aerial Vehicles (UAVs)/drones are used in field because their flexibility, low cost, protection energy-saving advantages, which can achieve both economic benefits benefits. This paper reviews 36 studies UAVs applications from Web Science database past two years (2021–2022). selected literature is classified into theoretical models (the traveling salesman problem other path planning problems), application scenarios (medical safety last-mile delivery problems) problems (UAV implementation obstacles, costs, pricing, etc.). Finally, future directions proposed, such as different that considered algorithms combined optimize paths for specific flight environments.

Language: Английский

---

Automatic Target Detection from Satellite Imagery Using Machine Learning

Sensors, Journal Year: 2022, Volume and Issue: 22(3), P. 1147 - 1147

Published: Feb. 2, 2022

Object detection is a vital step in satellite imagery-based computer vision applications such as precision agriculture, urban planning and defense applications. In imagery, object very complicated task due to various reasons including low pixel resolution of objects small the large scale (a single image taken by Digital Globe comprises over 240 million pixels) images. images has many challenges class variations, multiple pose, high variance size, illumination dense background. This study aims compare performance existing deep learning algorithms for imagery. We created dataset imagery perform using convolutional neural network-based frameworks faster RCNN (faster region-based network), YOLO (you only look once), SSD (single-shot detector) SIMRDWN (satellite multiscale rapid with windowed networks). addition that, we also performed an analysis these approaches terms accuracy speed developed The results showed that 97% on high-resolution images, while Faster 95.31% standard (1000 × 600). YOLOv3 94.20% (416 416) other hand 84.61% (300 300). When it comes efficiency, obvious leader. real-time surveillance, fails. takes 170 190 milliseconds task, 5 103 milliseconds.

Language: Английский

---

Using Adaptive Sensors for Optimised Target Coverage in Wireless Sensor Networks

Sensors, Journal Year: 2022, Volume and Issue: 22(3), P. 1083 - 1083

Published: Jan. 30, 2022

Innovation in wireless communications and microtechnology has progressed day by day, this resulted the creation of sensor networks. This technology is utilised a variety settings, including battlefield surveillance, home security, healthcare monitoring, among others. However, since tiny batteries with very little power are used, target monitoring issues. With development various architectures algorithms, considerable research been done to address these problems. The adaptive learning automata algorithm (ALAA) scheduling machine method that study. It offers time-saving method. As result, each node network outfitted automata, allowing them choose their appropriate state at any given moment. one two states: active or sleep. Several experiments were conducted get findings suggested Different parameters experiment verify consistency for so it can cover all targets while using less power. experimental indicate proposed an effective approach schedule nodes monitor electricity. Finally, we have benchmarked our technique against LADSC algorithm. All data collected thus far demonstrate justified problem description achieved project's aim. Thus, constructing actual network, may be as useful nodes.

Language: Английский

---

A survey on the role of UAVs in the communication process: A technological perspective

Computer Communications, Journal Year: 2022, Volume and Issue: 194, P. 86 - 123

Published: July 14, 2022

Language: Английский

---

A Comprehensive Review of Research Hotspots on Battery Management Systems for UAVs

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 84636 - 84650

Published: Jan. 1, 2023

Battery-powered unmanned aerial vehicles (UAVs), also known as drones, have emerged the primary choice in UAV market. The Battery Management System (BMS) performs critical functions such charging and discharging control, state detection, fault diagnosis warning, data recording analysis, etc., making it an essential component of UAVs. However, with rapid advancements battery-related materials electrochemistry, new types batteries are constantly emerging. Furthermore, rise big has expanded possibilities for information processing. This necessitates development BMS to keep pace ongoing research efforts, adjusting enhancing design, calculation methods existing systems meet increasingly diverse requirements power battery performance. Despite growing importance BMS, this area primarily focused on electric vehicles, leaving UAVs relatively understudied. To address gap, paper offers a comprehensive background overview investigates recent hotspots field BMS. A total nine been identified classified into three main categories. first category focuses discharging, involving studies control strategies, equalization hybrid energy management strategies. second revolves around estimation, emphasis estimating crucial parameters State Charge (SOC), Health (SOH), Remaining Useful Life (RUL), other parameters. third addresses system components safety-related issues, including storage transmission within security considerations, techniques, safety topics. proposes potential future trends areas further exploration.

Language: Английский

---

UAV Detection Using Reinforcement Learning

Sensors, Journal Year: 2024, Volume and Issue: 24(6), P. 1870 - 1870

Published: March 14, 2024

Unmanned Aerial Vehicles (UAVs) have gained significant popularity in both military and civilian applications due to their cost-effectiveness flexibility. However, the increased utilization of UAVs raises concerns about risk illegal data gathering potential criminal use. As a result, accurate detection identification intruding has emerged as critical research concern. Many algorithms shown effectiveness detecting different objects through approaches, including radio frequency (RF), computer vision (visual), sound-based detection. This article proposes novel approach for identifying based on RF signals by using hierarchical reinforcement learning technique. We train UAV agent hierarchically with multiple policies REINFORCE algorithm entropy regularization term improve overall accuracy. The focuses utilizing extracted features from detect UAVs, which contributes field investigating less-explored approach. Through extensive evaluation, our findings show remarkable results proposed achieving RF-based identification, an outstanding accuracy 99.7%. Additionally, demonstrates improved cumulative return performance reduced loss. obtained highlight solution enhancing security surveillance while advancing

Language: Английский

---

Investigating drone technology in health-care products delivery in rural communities in Ghana: benefits, barriers and perceptions

Journal of Humanitarian Logistics and Supply Chain Management, Journal Year: 2025, Volume and Issue: unknown

Published: April 14, 2025

Purpose Access to health care in rural communities is a challenge many developing countries. One major factor contributing this the unavailability of health-care products these areas during emergencies. Most governments seek leverage use technology improve delivery. This research, therefore, aims bridge gap by identifying benefits, barriers and perceptions associated with Zipline’s operations communities. Design/methodology/approach research adopts quantitative approach through closed-ended questionnaires evaluate drones deliver under study. The questionnaire designed using general factors derived from literature. responses received are then analysed principal component analysis determine specific relevant area. Findings results indicate that efficiency cost-effectiveness, inventory management accessibility significant benefits accompanying drone technology. However, study also identified limited payload capacity hampers range medical can be transported. quantities which they delivered lack trained personnel as for product In addition, workers have perception industry influenced attitude towards Research limitations/implications Health favourable inclination utilisation They perceive offer substantial enhancements services. Practical implications Zipline flourishing Ghana issues on limitations, investing education training, well involving decision-making process should addressed. Social established its expansion other eminent expand access Originality/value set tone seeking delivery Ghana.

Language: Английский

---

Cloud- and Fog-Integrated Smart Grid Model for Efficient Resource Utilisation

Sensors, Journal Year: 2021, Volume and Issue: 21(23), P. 7846 - 7846

Published: Nov. 25, 2021

The smart grid (SG) is a contemporary electrical network that enhances the network’s performance, reliability, stability, and energy efficiency. integration of cloud fog computing with SG can increase its combination resource allocation. To minimise burden on Cloud optimise allocation, concept presented. Fog has three essential functionalities: location awareness, low latency, mobility. We offer fog-based architecture for information management in this study. By allocating virtual machines using load-balancing mechanism, makes system more efficient (VMs). proposed novel approach based binary particle swarm optimisation inertia weight adjusted simulated annealing. technique named BPSOSA. Inertia an important factor BPSOSA which adjusts size search space finding optimal solution. compared against round robin, odds algorithm, ant colony optimisation. In terms response time, outperforms by 53.99 ms, 82.08 81.58 respectively. processing 52.94 81.20 80.56 Compared to BPSOSA, slightly better cost efficiency, however, difference insignificant.

Language: Английский

---