Search Time Research Articles

Improving A* algorithm for path planning of unmanned surface vessels in maritime rescue

ABSTRACT Path-planning is the key for marine rescue using unmanned surface vessel. Planning an efficient and safe path can significantly improve the efficiency of marine rescue, and existing path-planning algorithms are prone to collision and grounding with islands and shallows. To address this issue, this paper proposes a method for improving A* algorithm. First, global key nodes were extracted based on maritime map information using image processing techniques. Then, the global key nodes that can be directly reached in a straight line and meet safety threshold were screened as child nodes of current node to participate in the search. Finally, the path was planned by introducing the path danger value into the cost function of A* algorithm to consider the path cost and safety. Simulation results showed that the path planned by improved A* algorithm is safer and smoother than other paths, and the search time and path cost are optimized.

Autonomous Goal Detection and Cessation in Reinforcement Learning: A Case Study on Source Term Estimation

Reinforcement Learning has revolutionized decision-making processes in dynamic environments, yet it often struggles with autonomously detecting and achieving goals without clear feedback signals. For example, in a Source Term Estimation problem, the lack of precise environmental information makes it challenging to provide clear feedback signals and to define and evaluate how the source's location is determined. To address this challenge, the Autonomous Goal Detection and Cessation (AGDC) module was developed, enhancing various RL algorithms by incorporating a self-feedback mechanism for autonomous goal detection and cessation upon task completion. Our method effectively identifies and ceases undefined goals by approximating the agent's belief, significantly enhancing the capabilities of RL algorithms in environments with limited feedback. To validate effectiveness of our approach, we integrated AGDC with deep Q-Network, proximal policy optimization, and deep deterministic policy gradient algorithms, and evaluated its performance on the Source Term Estimation problem. The experimental results showed that AGDC-enhanced RL algorithms significantly outperformed traditional statistical methods such as infotaxis, entrotaxis, and dual control for exploitation and exploration, as well as a non-statistical random action selection method. These improvements were evident in terms of success rate, mean traveled distance, and search time, highlighting AGDC's effectiveness and efficiency in complex, real-world scenarios.

JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration

The co-design of neural network architectures, quantization precisions, and hardware accelerators offers a promising approach to achieving an optimal balance between performance and efficiency, particularly for model deployment on resource-constrained edge devices. In this work, we propose the JAQ Framework, which jointly optimizes the three critical dimensions. However, effectively automating the design process across the vast search space of those three dimensions poses significant challenges, especially when pursuing extremely low-bit quantization. Specifical, the primary challenges include: (1) Memory overhead in software-side: Low-precision quantization-aware training can lead to significant memory usage due to storing large intermediate features and latent weights for backpropagation, potentially causing memory exhaustion. (2) Search time-consuming in hardware-side: The discrete nature of hardware parameters and the complex interplay between compiler optimizations and individual operators make the accelerator search time-consuming. To address these issues, JAQ mitigates the memory overhead through a channel-wise sparse quantization (CSQ) scheme, selectively applying quantization to the most sensitive components of the model during optimization. Additionally, JAQ designs BatchTile, which employs a hardware generation network to encode all possible tiling modes, thereby speeding up the search for the optimal compiler mapping strategy. Extensive experiments demonstrate the effectiveness of JAQ, achieving approximately 7% higher Top-1 accuracy on ImageNet compared to previous methods and reducing the hardware search time per iteration to 0.15 seconds.

Resource Constrained Pathfinding with Enhanced Bidirectional A* Search

The classic Resource Constrained Shortest Path (RCSP) problem aims to find a cost optimal path between a pair of nodes in a network such that the resources used in the path are within a given limit. Having been studied for over a decade, RCSP has seen recent solutions that utilize heuristic-guided search to solve the constrained problem faster. Building upon the bidirectional A* search paradigm, this paper introduces a novel constrained search framework that uses efficient pruning strategies to allow for accelerated and effective RCSP search in large-scale networks. Results show that, compared to the state of the art, our enhanced framework can significantly reduce the constrained search time, achieving speed-ups of over to two orders of magnitude.

RBFleX-NAS: Training-Free Neural Architecture Search Using Radial Basis Function Kernel and Hyperparameter Detection.

Neural architecture search (NAS) is an automated technique to design optimal neural network architectures for a specific workload. Conventionally, evaluating candidate networks in NAS involves extensive training, which requires significant time and computational resources. To address this, training-free NAS has been proposed to expedite network evaluation with minimal search time. However, state-of-the-art training-free NAS algorithms struggle to precisely distinguish well-performing networks from poorly performing networks, resulting in inaccurate performance predictions and consequently suboptimal top-one network accuracy. Moreover, they are less effective in activation function exploration. To tackle the challenges, this article proposes RBFleX-NAS, a novel training-free NAS framework that accounts for both activation outputs and input features of the last layer with a radial basis function (RBF) kernel. We also present a detection algorithm to identify optimal hyperparameters using the obtained activation outputs and input feature maps. We verify the efficacy of RBFleX-NAS over a variety of NAS benchmarks. RBFleX-NAS significantly outperforms state-of-the-art training-free NAS methods in terms of top-one accuracy, achieving this with short search time in NAS-Bench-201 and NAS-Bench-SSS. In addition, it demonstrates a higher Kendall correlation compared to layer-based training-free NAS algorithms. Furthermore, we propose the neural network activation function benchmark (NAFBee), a new activation design space that extends the activation type to encompass various commonly used functions. In this extended design space, RBFleX-NAS demonstrates its superiority by accurately identifying the best-performing network during activation function search, providing a significant advantage over other NAS algorithms.

Optimal experimental plan for multi-level stress testing with log-location-scale regression under progressive Type-II censoring

ABSTRACT We examine the optimal allocation strategy based on a general Type-II progressively censored sample within the framework of a multi-level stress log-location-scale regression model. To identify the optimal censoring schemes, we propose employing a meta-heuristic algorithm rooted in the variable neighborhood search (VNS) approach. Our findings reveal that the VNS-based procedure not only significantly reduces the search time but also achieves the exact optimal allocation and progressive censoring schemes for small sample sizes as those derived from exhaustive search methods. Additionally, for larger sample sizes, the procedure attains optimal or near-optimal objective values within a reasonable computational time. The effectiveness of optimal unit allocation in multi-level stress experiments is illustrated through a real-world data set concerning hardened steel specimens in a rolling contact fatigue test.

The Scope Review of Kinesiophobia in Patients with Chronic Obstructive Pulmonary Disease

Objective: To review the current status of research on kinesiophobia, assessment tools, influencing factors, and intervention strategies in patients with chronic obstructive pulmonary disease, aiming to provide a reference for promoting pulmonary rehabilitation in these patients. Methods: A scoping review framework was employed to search databases including CNKI, Wanfang, VIP, China Biology Medicine (CBM), PubMed, Web of Science, and Wiley Online Library. The search time frame spanned from the database inception to May 20, 2024. Two researchers independently screened the literature, summarized, and analyzed the data. Results: A total of 18 articles were included. Commonly used assessment tools included the Tampa Scale for kinesiophobia and the dyspnea beliefs questionnaire. Influencing factors encompassed demographic, disease-related, psychosocial, and BMI-related factors. Intervention methods included inspiratory muscle training, narrative nursing, and cognitive interventions combined with active cycle of breathing techniques. Conclusion: The incidence of kinesiophobia in COPD patients is relatively high and varies among individuals, influenced by multiple factors. There is a need to develop localized assessment tools to identify kinesiophobia in a timely and accurate manner and to further refine intervention strategies.

Automatic path planning for pelvic fracture reduction with multi-degree-of-freedom.

Automatic path planning for pelvic fracture reduction with multi-degree-of-freedom.

Exponential Global Health Hazards of Pharmaceutical Pollution and Its Preventive Measures: A Comprehensive Review

Introduction: Antimicrobial agents from different categories like antibiotics, anti-parasitic agents, and other agents such as Xeno (estrogens) can exert some intimidating effects on the environment that can be ecotoxicological as well. Disposal of chemicals in the form of drugs in various water bodies such as lakes, ponds, rivers, and commonly used drinking water might cause potential health damage to human, animal, and aquatic life via environmental pollution. Thus, production of such waste requires proper disposal and supervision, which might be a hurdle for the medical personnel, city administrators, workers working in the industry involved in recycling, and planners of policies. Materials and Methods: The review is taken the help of resources for getting appropriate information are PubMed, Google Scholar, Scopus, Web of Science very carefully. The period of time for article search in databases varied from 2001-2023. The articles between this time range were included. Results: In the present study, an effort was made to pinnacle sources, categories, and information regarding various drugs and regulatory bodies across the globe to control these functions. To overcome the pharmaceutical pollution issues, functions, categories of wastes, and strategies to resolve were elaborated. Conclusion: The study highlighted the crucial function of pharmacists in reducing pharmaceutical waste and evaluated current water management policies, emphasizing the necessity for cohesive efforts to diminish pollution. Moreover, an examination of existing regulatory frameworks revealed inadequacies and provided suggestions for improved monitoring and enforcement. This comprehensive report aimed to offer practical recommendations for the advancement of sustainable pharmaceutical waste management techniques, aiding in the protection of world health and the environment.

Deep Learning: A Heuristic Three-Stage Mechanism for Grid Searches to Optimize the Future Risk Prediction of Breast Cancer Metastasis Using EHR-Based Clinical Data.

Background: A grid search, at the cost of training and testing a large number of models, is an effective way to optimize the prediction performance of deep learning models. A challenging task concerning grid search is time management. Without a good time management scheme, a grid search can easily be set off as a "mission" that will not finish in our lifetime. In this study, we introduce a heuristic three-stage mechanism for managing the running time of low-budget grid searches with deep learning, sweet-spot grid search (SSGS) and randomized grid search (RGS) strategies for improving model prediction performance, in an application of predicting the 5-year, 10-year, and 15-year risk of breast cancer metastasis. Methods: We develop deep feedforward neural network (DFNN) models and optimize the prediction performance of these models through grid searches. We conduct eight cycles of grid searches in three stages, focusing on learning a reasonable range of values for each of the adjustable hyperparameters in Stage 1, learning the sweet-spot values of the set of hyperparameters and estimating the unit grid search time in Stage 2, and conducting multiple cycles of timed grid searches to refine model prediction performance with SSGS and RGS in Stage 3. We conduct various SHAP analyses to explain the prediction, including a unique type of SHAP analyses to interpret the contributions of the DFNN-model hyperparameters. Results: The grid searches we conducted improved the risk prediction of 5-year, 10-year, and 15-year breast cancer metastasis by 18.6%, 16.3%, and 17.3%, respectively, over the average performance of all corresponding models we trained using the RGS strategy. Conclusions: Grid search can greatly improve model prediction. Our result analyses not only demonstrate best model performance but also characterize grid searches from various aspects such as their capabilities of discovering decent models and the unit grid search time. The three-stage mechanism worked effectively. It not only made our low-budget grid searches feasible and manageable but also helped improve the model prediction performance of the DFNN models. Our SHAP analyses not only identified clinical risk factors important for the prediction of future risk of breast cancer metastasis, but also DFNN-model hyperparameters important to the prediction of performance scores.

Risk of Recurrent Stroke, Mortality, and Intracerebral Hemorrhage in Patients With Atrial Fibrillation Detected Before or After a Stroke.

The risk of recurrent ischemic stroke, intracranial hemorrhage, and mortality in people with atrial fibrillation detected after stroke (AFDAS) is still unclear compared with people with known atrial fibrillation (KAF). We systematically reviewed the literature to provide updated estimates for the risk of recurrent stroke, intracerebral hemorrhage, and mortality in AFDAS compared with KAF. Our protocol was registered in PROSPERO (CRD42024583064). Presentation followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses and Meta-Analysis of Observational Studies in Epidemiology guidelines. We searched MEDLINE, EMBASE, Cochrane CENTRAL, and MedRxiv up to August 28, 2024, for studies comparing AFDAS and KAF for the following outcomes of interest: recurrent ischemic stroke (primary), intracerebral hemorrhage, mortality, and any stroke recurrence. We included cohort, observational studies (either prospective or retrospective) and randomized controlled trials and excluded studies with less than 15 patients per group. Eligible studies were assessed for bias using the Risk of Bias in Non-Randomized Studies tool. We pooled study-level results through random-effect meta-analysis of risk ratios (RRs). We also performed prespecified sensitivity analysis for study quality, timing of search for AF, propensity score matching, and study data source (administrative vs local data), and we planned meta-regression analysis to test for the interaction of sex, comorbid cardiovascular risk factors, and anticoagulation status on the difference between AFDAS and KAF. Seventeen studies were retrieved (n = 113,365; nKAF = 80,339; nAFDAS = 33,026; female in KAF, 49.0%; female in AFDAS, 45.1%), eight of which had low risk of bias. Ischemic stroke recurrence was significantly lower in AFDAS compared with the KAF group (RR = 0.79, 95% CI = 0.66-0.95, I2 = 70%; nstudies = 10). Meta-regression analysis revealed no interaction of anticoagulation, CHA2DS2-VASc score, or sex on the difference in risk of recurrent ischemic stroke between groups. Mortality was lower in the AFDAS group compared with KAF (RR = 0.84, 95% CI = 0.74-0.95, I2 = 74%; nstudies = 14). The rates of any intracerebral bleeding (RR = 0.97, 95% CI = 0.68-1.39, I2 = 58%; nstudies = 5) and any stroke recurrence (RR = 0.99, 95% CI = 0.75-1.30; I2 = 60; nstudies = 3) were similar in AFDAS and KAF. AFDAS may carry a lower risk of ischemic stroke recurrence and mortality compared with KAF, with similar risk of intracerebral hemorrhage. Stratification through implementation of AF burden measures may support more personalized management for people with AFDAS.

The effect of icon color gradient features on users’ visual search efficiency

This study explored the influence of different colour gradients and colour area icons on user visual efficiency through a visual search task experiment with 35 participants involved. The results showed that the colour gradient slope and colour area of the icon significantly affected the visual search efficiency. Icons with high colour gradient slope had the highest search accuracy and shortest search time, whereas icons with low- and medium-slope differed only in search time. Icons with different colour areas affected the participants’ search accuracy, and the accuracy rate of the graphic area was higher than that of the background area. In addition, the effect of the colour gradient slope on the search time was significant when the colour gradient was in the graphic area.Practitioner Summary: icons with a higher colour gradient slope and a coloured graphic area performed better in the visual search. These findings can provide clues for icon design.

Acute intestinal obstruction, difficulties in diagnosis in starged hernias of the opturate forana and surgical tactics

Relevance. Hernias of the obturator canal are extremely rare in surgical practice. This type occurs in 0.07% to 1% of all known hernias, in which the contents of the pelvic or abdominal organs penetrate through the obturator foramen. The hernias in question occur predominantly in elderly women of low nutrition with a large history of childbirth. This is explained by the peculiarities of the anatomical structure of the female pelvis: its pronounced slope, the larger size of the obturator foramen, the more vertical position of the obturator canal compared to the male, and the weakness of the pelvic floor muscles. Diagnosing an obturator hernia is very difficult. Being difficult to diagnose cases, strangulated hernias of the obturator canal are detected at the treatment stage and are accompanied by high mortality. Mortality for these manifestations ranges from 12% to 70%, with postoperative measurements in 11.6% of cases. These statistics provide the majority of observations provided by reputable Japanese colleagues [3]. Conclusions. Hernias of the obturator foramen, due to their rare occurrence and lack of clear clinical manifestations, are difficult diagnostic cases. Knowledge of the symptoms characteristic of this pathology, the use of computed tomography of the abdominal cavity and pelvis with contrast enhancement is extremely important, influencing the adoption of a reliably correct, quick decision for surgical intervention, largely determining the outcome of the disease. Specific diagnostics for determining obturator foramen hernia are not covered in clinical recommendations. Due to the fact that this clinical pathology is quite complex for a surgeon to quickly determine, it is detected at the stage of complications and is accompanied by high mortality. The leading clinical picture for a strangulated hernia of the obturator foramen is signs of intestinal obstruction. Correctly and timely preoperative diagnosis is crucial for the surgeon to decide on tactics. In the case of a clinical picture of intestinal obstruction, one should act on the basis of national clinical recommendations, not forgetting to manually check the location of the hernia, which will significantly reduce the time for diagnostic searches and reduce postoperative mortality in case of a strangulated hernia of the obturator foramen.

A Personalized Recommendation System for Housing Information Based on Deep Learning

In view of the problems of complex housing information in the real estate market and the difficulty for users in finding houses, the personalized recommendation system of housing information based on deep learning is studied. The system adopts a hierarchical architecture. The data layer collects multi-source data from the housing information platform and stores it in MySQL and MongoDB databases respectively according to the structural characteristics. The preprocessing layer improves the data quality by removing noise, processing stopped words and eliminating duplicate data. The recommendation layer uses the convolutional neural network to generate the recommendation results. The service layer realizes invalid housing filtering, grouping and sorting optimization, and recommendation reason adding functions. The experiment shows that the recommendation reliability of the system is high, and significantly improves the efficiency of user house hunting, greatly shortens the house search and transaction time, and has a good effect of house information recommendation.

Summary of best evidence on self-management in adult patients with systemic lupus erythematosus.

ObjectiveTo evaluate and summarize the best evidence on self-management in adult patients with systemic lupus erythematosus (SLE) and provide evidence-based recommendations in clinical settings.MethodsLiteratures related to self-management of SLE patients were searched in the guideline websites, professional association websites and relevant databases, including clinical decisions, guidelines, expert consensus, best practice recommendations, evidence summaries, meta-analyses, systematic reviews and randomized controlled trials, etc. The search time was from January 2018 to September 2023.ResultsA total of 19 literatures were included, consisting of 9 guidelines, 4 expert consensus, 4 clinical decisions, and 2 systematic reviews, and 49 pieces of evidence were extracted. After sorting and discussing, the evidence were integrated into six aspects: skin management, diet management, exercise management, vaccination management, complication management, as well as follow-up and lifestyle management.ConclusionThe best evidence of self-management in SLE patients summarized in this study is of high quality, which can provide evidence-based recommendations for clinical medical staff and patients, so as to help self-management of SLE patients in a more scientific and effective way.

Off-label drug use in palliative medicine: Delphi study for the consensus of evidence-based treatment recommendations.

Off-label use of drugs is an integral part of everyday clinical practice in palliative medicine. However, it is associated with many uncertainties, that is, drug therapy safety or legal issues including cost coverage. Healthcare professionals often lack time and resources for comprehensive literature search and patient-specific risk-benefit analyses. The aim of this project is to develop, evaluate and rate agreement/disagreement on treatment recommendations for off-label use in adult palliative medicine. Online Delphi study with two rounds each to rate agreement/disagreement with treatment recommendations for off-label use in adult palliative medicine. An international expert panel consisting of physicians, pharmacists and nurses working in palliative care evaluated previously developed recommendations based on the best available evidence. /participants:Professionals (physicians, pharmacists, nursing staff) working in inpatient and home palliative care involved in the medication process were recruited as experts to participate. Between 64 and 75 experts participated in the first two Delphi studies. A total of 64/68 recommendations on 21 drugs and 14 applications were agreed upon. Topics related to routes of administration as well as indications for sialorrhea, bronchorrhea, xerostomia, pruritus, singultus, fistula, gastroparesis and hot flashes. Recommendations that reached consensus are available to health care professionals via a free of charge database. For many off-label use applications, it is likely that there will be no registration studies and therefore no drug approvals in the future. The consensus-based recommendations are intended to facilitate individual treatment planning for prescribers and to enable a more reflected handling of off-label use.

Application of preoperative ultrasound combined with indocyanine green lymphography in lymphaticovenular anastomosis of the lower limb-A retrospective study research.

BackgroundWe evaluated the application of preoperative ultrasound (US) combined with indocyanine green (ICG) lymphography in lymphaticovenular anastomosis (LVA) of the lower limb.Methods66 patients with lower limb lymphedema were selected as study subjects and divided into research (n = 35) and control groups (n = 31). The patients were treated with LVA using ICG lymphography combined with US and simple ICG lymphography as the positioning method. The number of lymphatic vessels anastomosed, diameter, depth, and searching time were compared.ResultsThe number of anastomotic lymphatic vessels in the research group was more than in the control group (p < .05). Compared with the lymphatic vessels under ICG lymphography, the lymphatic vessels under US locating had less search time, larger diameter, and deeper depth (p < .05).ConclusionUS combined with ICG lymphography in preoperative can increase the number of lymphatic vessels and shorten the time to find lymphatic vessels.

Dynamic path planning of UAV with least inflection point based on adaptive neighborhood A* algorithm and multi-strategy fusion

Planning a safe and efficient global path in a complex three-dimensional environment is a complex and challenging optimization task. Existing planning algorithms are faced with problems such as lengthy path, too many inflection points and insufficient dynamic obstacle avoidance performance. In order to solve these challenges, this paper proposes a dynamic obstacle avoidance algorithm (MSF-MTPO) with multi-strategy fusion to achieve the least inflection point path optimization. Initially, an adaptive extended neighborhood A* algorithm is designed, which dynamically adjusts the neighborhood extension range according to the distribution of obstacles around the current location, selecting the optimal travel direction and step size each time to reduce redundant paths and unnecessary extended nodes. Then, combined with the two-way search mechanism, starting from the original starting point and the end point, the opposite current node is searched as the target point, respectively, so as to reduce the number of search nodes and reduce the search time. In order to further improve the path efficiency, an inflection point trajectory correction method is designed to eliminate redundant inflection points on the premise of ensuring path safety. Fourthly, in order to solve the problem of path deviation or excessive softening caused by the limited path control points in existing smoothing methods, a local tangent circle smoothing method is proposed, which effectively improves the smoothness of the trajectory on the basis of retaining the superiority of the original path. Finally, the global optimization path is used as the guiding trajectory of artificial potential field method to avoid falling into local optimum and realize dynamic obstacle avoidance. In addition, the performance is compared with several advanced algorithms in different environments, and the MSF-MTPO algorithm has the lowest path cost in different complex scenarios, which proves the effectiveness and stability of MSF-MTPO in UAV 3D path planning.

Hardware Acceleration-Based Privacy-Aware Authentication Scheme for Internet of Vehicles Using Physical Unclonable Function.

Due to technological advancement, the advent of smart cities has facilitated the deployment of advanced urban management systems. This integration has been made possible through the Internet of Vehicles (IoV), a foundational technology. By connecting smart cities with vehicles, the IoV enhances the safety and efficiency of transportation. This interconnected system facilitates wireless communication among vehicles, enabling the exchange of crucial traffic information. However, this significant technological advancement also raises concerns regarding privacy for individual users. This paper presents an innovative privacy-preserving authentication scheme focusing on IoV using physical unclonable functions (PUFs). This scheme employs the k-nearest neighbor (KNN) encryption technique, which possesses a multi-multi searching property. The main objective of this scheme is to authenticate autonomous vehicles (AVs) within the IoV framework. An innovative PUF design is applied to generate random keys for our authentication scheme to enhance security. This two-layer security approach protects against various cyber-attacks, including fraudulent identities, man-in-the-middle attacks, and unauthorized access to individual user information. Due to the substantial amount of information that needs to be processed for authentication purposes, our scheme is implemented using hardware acceleration on an Nexys A7-100T FPGA board. Our analysis of privacy and security illustrates the effective accomplishment of specified design goals. Furthermore, the performance analysis reveals that our approach imposes a minimal communication and computational burden and optimally utilizes hardware resources to accomplish design objectives. The results show that the proposed authentication scheme exhibits a non-linear increase in encryption time with a growing AV ID size, starting at 5μs for 100 bits and rising to 39 μs for 800 bits. Also, the result demonstrates a more gradual, linear increase in the search time with a growing AV ID size, starting at less than 1 μs for 100 bits and rising to less than 8 μs for 800 bits. Additionally, for hardware utilization, our scheme uses only 25% from DSP slides and IO pins, 22.2% from BRAM, 5.6% from flip-flops, and 24.3% from LUTs.

A multi objective optimization framework for smart parking using digital twin pareto front MDP and PSO for smart cities

Smart cities are designed to improve the quality of life by efficiently using resources and smart parking is an important part of this puzzle to help alleviate traffic congestion and efficiently address energy consumption and search time for parking spaces. However, existing parking management systems have issues with resource management, system scalability, and real-time dynamic changes. In response to these challenges, this paper proposes a Multi-Objective Optimization Framework for Smart Parking incorporating Digital Twin Technology, Pareto Front Optimization, Markov Decision Process (MDP), and Particle Swarm Optimization (PSO). Hence, the proposed framework utilizes Digital Twin whereby there is a generation of a virtual model of the existing parking infrastructure that can give a real-time prospective estimation of the entire system. The Pareto Front is then used for multi-objective optimization of the search domain, where the goal is to minimize the search time, use of energy, and traffic disruption, and maximize the availability of parking spaces. The MDP splits the resource allocation problem into a value function which can then model the real-time parking requests. Further, PSO refines the solutions found from the Pareto front for a globally superior distribution. The framework is evaluated using extensive simulations across multiple metrics: search time, energy, congestion level, scalability, and utilization. Evaluation outcomes also show that the proposed algorithm is better than Round Robin, Random Allocation, and Threshold Based algorithms in terms of 25% improvement in the search time, 18% better energy usage, and 30% less traffic congestion. This work has shown the prospects of combining hybrid optimization and real-time decision-making in the enhancement of parking management in smart cities for better efficiency in urban mobility.