Enhanced Deep Reinforcement Learning Strategy for Energy Management in Plug-in Hybrid Electric Vehicles with Entropy Regularization and Prioritized Experience Replay

Plug-in Hybrid Electric Vehicles(PHEVs)represent an innovative breed of transportation,harnessing diverse power sources for enhanced performance.Energy management strategies(EMSs)that coordinate and control different energy sources is a critical component of PHEV control technology,directly impacting overall vehicle performance.This study proposes an improved deep reinforcement learning(DRL)-based EMSthat optimizes realtime energy allocation and coordinates the operation of multiple power sources.Conventional DRL algorithms struggle to effectively explore all possible state-action combinations within high-dimensional state and action spaces.They often fail to strike an optimal balance between exploration and exploitation,and their assumption of a static environment limits their ability to adapt to changing conditions.Moreover,these algorithms suffer from low sample efficiency.Collectively,these factors contribute to convergence difficulties,low learning efficiency,and instability.To address these challenges,the Deep Deterministic Policy Gradient(DDPG)algorithm is enhanced using entropy regularization and a summation tree-based Prioritized Experience Replay(PER)method,aiming to improve exploration performance and learning efficiency from experience samples.Additionally,the correspondingMarkovDecision Process(MDP)is established.Finally,an EMSbased on the improvedDRLmodel is presented.Comparative simulation experiments are conducted against rule-based,optimization-based,andDRL-based EMSs.The proposed strategy exhibitsminimal deviation fromthe optimal solution obtained by the dynamic programming(DP)strategy that requires global information.In the typical driving scenarios based onWorld Light Vehicle Test Cycle(WLTC)and New European Driving Cycle(NEDC),the proposed method achieved a fuel consumption of 2698.65 g and an Equivalent Fuel Consumption(EFC)of 2696.77 g.Compared to the DP strategy baseline,the proposed method improved the fuel efficiency variances(FEV)by 18.13%,15.1%,and 8.37%over the Deep QNetwork(DQN),Double DRL(DDRL),and original DDPG methods,respectively.The observational outcomes demonstrate that the proposed EMS based on improved DRL framework possesses good real-time performance,stability,and reliability,effectively optimizing vehicle economy and fuel consumption.

Fermatean Hesitant Fuzzy Prioritized Heronian Mean Operator and Its Application in Multi-Attribute Decision Making

In real life,incomplete information,inaccurate data,and the preferences of decision-makers during qualitative judgment would impact the process of decision-making.As a technical instrument that can successfully handle uncertain information,Fermatean fuzzy sets have recently been used to solve the multi-attribute decision-making(MADM)problems.This paper proposes a Fermatean hesitant fuzzy information aggregation method to address the problem of fusion where the membership,non-membership,and priority are considered simultaneously.Combining the Fermatean hesitant fuzzy sets with Heronian Mean operators,this paper proposes the Fermatean hesitant fuzzy Heronian mean(FHFHM)operator and the Fermatean hesitant fuzzyweighted Heronian mean(FHFWHM)operator.Then,considering the priority relationship between attributes is often easier to obtain than the weight of attributes,this paper defines a new Fermatean hesitant fuzzy prioritized Heronian mean operator(FHFPHM),and discusses its elegant properties such as idempotency,boundedness and monotonicity in detail.Later,for problems with unknown weights and the Fermatean hesitant fuzzy information,aMADM approach based on prioritized attributes is proposed,which can effectively depict the correlation between attributes and avoid the influence of subjective factors on the results.Finally,a numerical example of multi-sensor electronic surveillance is applied to verify the feasibility and validity of the method proposed in this paper.

C-CORE:Clustering by Code Representation to Prioritize Test Cases in Compiler Testing

Edge devices,due to their limited computational and storage resources,often require the use of compilers for program optimization.Therefore,ensuring the security and reliability of these compilers is of paramount importance in the emerging field of edge AI.One widely used testing method for this purpose is fuzz testing,which detects bugs by inputting random test cases into the target program.However,this process consumes significant time and resources.To improve the efficiency of compiler fuzz testing,it is common practice to utilize test case prioritization techniques.Some researchers use machine learning to predict the code coverage of test cases,aiming to maximize the test capability for the target compiler by increasing the overall predicted coverage of the test cases.Nevertheless,these methods can only forecast the code coverage of the compiler at a specific optimization level,potentially missing many optimization-related bugs.In this paper,we introduce C-CORE(short for Clustering by Code Representation),the first framework to prioritize test cases according to their code representations,which are derived directly from the source codes.This approach avoids being limited to specific compiler states and extends to a broader range of compiler bugs.Specifically,we first train a scaled pre-trained programming language model to capture as many common features as possible from the test cases generated by a fuzzer.Using this pre-trained model,we then train two downstream models:one for predicting the likelihood of triggering a bug and another for identifying code representations associated with bugs.Subsequently,we cluster the test cases according to their code representations and select the highest-scoring test case from each cluster as the high-quality test case.This reduction in redundant testing cases leads to time savings.Comprehensive evaluation results reveal that code representations are better at distinguishing test capabilities,and C-CORE significantly enhances testing efficiency.Across four datasets,C-CORE increases the average of the percentage of faults detected(APFD)value by 0.16 to 0.31 and reduces test time by over 50% in 46% of cases.When compared to the best results from approaches using predicted code coverage,C-CORE improves the APFD value by 1.1% to 12.3% and achieves an overall time-saving of 159.1%.

AI-Driven Prioritization and Filtering of Windows Artifacts for Enhanced Digital Forensics

Digital forensics aims to uncover evidence of cybercrimes within compromised systems.These cybercrimes are often perpetrated through the deployment of malware,which inevitably leaves discernible traces within the compromised systems.Forensic analysts are tasked with extracting and subsequently analyzing data,termed as artifacts,from these systems to gather evidence.Therefore,forensic analysts must sift through extensive datasets to isolate pertinent evidence.However,manually identifying suspicious traces among numerous artifacts is time-consuming and labor-intensive.Previous studies addressed such inefficiencies by integrating artificial intelligence(AI)technologies into digital forensics.Despite the efforts in previous studies,artifacts were analyzed without considering the nature of the data within them and failed to prove their efficiency through specific evaluations.In this study,we propose a system to prioritize suspicious artifacts from compromised systems infected with malware to facilitate efficient digital forensics.Our system introduces a double-checking method that recognizes the nature of data within target artifacts and employs algorithms ideal for anomaly detection.The key ideas of this method are:(1)prioritize suspicious artifacts and filter remaining artifacts using autoencoder and(2)further prioritize suspicious artifacts and filter remaining artifacts using logarithmic entropy.Our evaluation demonstrates that our system can identify malicious artifacts with high accuracy and that its double-checking method is more efficient than alternative approaches.Our system can significantly reduce the time required for forensic analysis and serve as a reference for future studies.

A Novel Green Supplier Selection Method Based on the Interval Type-2 Fuzzy Prioritized Choquet Bonferroni Means

In view of the environment competencies,selecting the optimal green supplier is one of the crucial issues for enterprises,and multi-criteria decision-making(MCDM)methodologies can more easily solve this green supplier selection(GSS)problem.In addition,prioritized aggregation(PA)operator can focus on the prioritization relationship over the criteria,Choquet integral(CI)operator can fully take account of the importance of criteria and the interactions among them,and Bonferroni mean(BM)operator can capture the interrelationships of criteria.However,most existing researches cannot simultaneously consider the interactions,interrelationships and prioritizations over the criteria,which are involved in the GSS process.Moreover,the interval type-2 fuzzy set(IT2FS)is a more effective tool to represent the fuzziness.Therefore,based on the advantages of PA,CI,BM and IT2FS,in this paper,the interval type-2 fuzzy prioritized Choquet normalized weighted BM operators with fuzzy measure and generalized prioritized measure are proposed,and some properties are discussed.Then,a novel MCDM approach for GSS based upon the presented operators is developed,and detailed decision steps are given.Finally,the applicability and practicability of the proposed methodology are demonstrated by its application in the shared-bike GSS and by comparisons with other methods.The advantages of the proposed method are that it can consider interactions,interrelationships and prioritizations over the criteria simultaneously.

Emergency Prioritized and Congestion Handling Protocol for Medical Internet of Things

Medical Internet of Things(MIoTs)is a collection of small and energyefficient wireless sensor devices that monitor the patient’s body.The healthcare networks transmit continuous data monitoring for the patients to survive them independently.There are many improvements in MIoTs,but still,there are critical issues that might affect the Quality of Service(QoS)of a network.Congestion handling is one of the critical factors that directly affect the QoS of the network.The congestion in MIoT can cause more energy consumption,delay,and important data loss.If a patient has an emergency,then the life-critical signals must transmit with minimum latency.During emergencies,the MIoTs have to monitor the patients continuously and transmit data(e.g.,ECG,BP,heart rate,etc.)with minimum delay.Therefore,there is an efficient technique required that can transmit emergency data of high-risk patients to the medical staff on time with maximum reliability.The main objective of this research is to monitor and transmit the patient’s real-time data efficiently and to prioritize the emergency data.In this paper,Emergency Prioritized and Congestion Handling Protocol for Medical IoTs(EPCP_MIoT)is proposed that efficiently monitors the patients and overcome the congestion by enabling different monitoring modes.Whereas the emergency data transmissions are prioritized and transmit at SIFS time.The proposed technique is implemented and compared with the previous technique,the comparison results show that the proposed technique outperforms the previous techniques in terms of network throughput,end to end delay,energy consumption,and packet loss ratio.

Prioritized MPEG-4 Audio-Visual Objects Streaming over the DiffServ

The object-based scalable coding in MPEG-4 is investigated, and a prioritized transmission scheme of MPEG-4 audio-visual objects （AVOs） over the DiffServ network with the QoS guarantee is proposed. MPEG-4 AVOs are extracted and classified into different groups according to their priority values and scalable layers （visual importance）. These priority values are mapped to the 1P DiffServ per hop behaviors （PHB）. This scheme can selectively discard packets with low importance, in order to avoid the network congestion. Simulation results show that the quality of received video can gracefully adapt to network state, as compared with the ‘best-effort＇ manner. Also, by allowing the content provider to define prioritization of each audio-visual object, the adaptive transmission of object-based scalable video can be customized based on the content.

Value-Based Test Case Prioritization for Regression Testing Using Genetic Algorithms

Test Case Prioritization(TCP)techniques perform better than other regression test optimization techniques including Test Suite Reduction(TSR)and Test Case Selection(TCS).Many TCP techniques are available,and their performance is usually measured through a metric Average Percentage of Fault Detection(APFD).This metric is value-neutral because it only works well when all test cases have the same cost,and all faults have the same severity.Using APFD for performance evaluation of test case orders where test cases cost or faults severity varies is prone to produce false results.Therefore,using the right metric for performance evaluation of TCP techniques is very important to get reliable and correct results.In this paper,two value-based TCP techniques have been introduced using Genetic Algorithm(GA)including Value-Cognizant Fault Detection-Based TCP(VCFDB-TCP)and Value-Cognizant Requirements Coverage-Based TCP(VCRCB-TCP).Two novel value-based performance evaluation metrics are also introduced for value-based TCP including Average Percentage of Fault Detection per value(APFDv)and Average Percentage of Requirements Coverage per value(APRCv).Two case studies are performed to validate proposed techniques and performance evaluation metrics.The proposed GA-based techniques outperformed the existing state-of-the-art TCP techniques including Original Order(OO),Reverse Order(REV-O),Random Order(RO),and Greedy algorithm.

Fault Coverage-Based Test Case Prioritization and Selection Using African Buffalo Optimization

Software needs modifications and requires revisions regularly.Owing to these revisions,retesting software becomes essential to ensure that the enhancements made,have not affected its bug-free functioning.The time and cost incurred in this process,need to be reduced by the method of test case selection and prioritization.It is observed that many nature-inspired techniques are applied in this area.African Buffalo Optimization is one such approach,applied to regression test selection and prioritization.In this paper,the proposed work explains and proves the applicability of the African Buffalo Optimization approach to test case selection and prioritization.The proposed algorithm converges in polynomial time(O(n^(2))).In this paper,the empirical evaluation of applying African Buffalo Optimization for test case prioritization is done on sample data set with multiple iterations.An astounding 62.5%drop in size and a 48.57%drop in the runtime of the original test suite were recorded.The obtained results are compared with Ant Colony Optimization.The comparative analysis indicates that African Buffalo Optimization and Ant Colony Optimization exhibit similar fault detection capabilities(80%),and a reduction in the overall execution time and size of the resultant test suite.The results and analysis,hence,advocate and encourages the use of African Buffalo Optimization in the area of test case selection and prioritization.

Bug Prioritization Using Average One Dependence Estimator

Automation software need to be continuously updated by addressing software bugs contained in their repositories.However,bugs have different levels of importance;hence,it is essential to prioritize bug reports based on their sever-ity and importance.Manually managing the deluge of incoming bug reports faces time and resource constraints from the development team and delays the resolu-tion of critical bugs.Therefore,bug report prioritization is vital.This study pro-poses a new model for bug prioritization based on average one dependence estimator;it prioritizes bug reports based on severity,which is determined by the number of attributes.The more the number of attributes,the more the severity.The proposed model is evaluated using precision,recall,F1-Score,accuracy,G-Measure,and Matthew’s correlation coefficient.Results of the proposed model are compared with those of the support vector machine(SVM)and Naive Bayes(NB)models.Eclipse and Mozilla datasetswere used as the sources of bug reports.The proposed model improved the bug repository management and out-performed the SVM and NB models.Additionally,the proposed model used a weaker attribute independence supposition than the former models,thereby improving prediction accuracy with minimal computational cost.

Test Case Prioritization in Unit and Integration Testing:A Shuffled-Frog-Leaping Approach

Both unit and integration testing are incredibly crucial for almost any software application because each of them operates a distinct process to examine the product.Due to resource constraints,when software is subjected to modifications,the drastic increase in the count of test cases forces the testers to opt for a test optimization strategy.One such strategy is test case prioritization(TCP).Existing works have propounded various methodologies that re-order the system-level test cases intending to boost either the fault detection capabilities or the coverage efficacy at the earliest.Nonetheless,singularity in objective functions and the lack of dissimilitude among the re-ordered test sequences have degraded the cogency of their approaches.Considering such gaps and scenarios when the meteoric and continuous updations in the software make the intensive unit and integration testing process more fragile,this study has introduced a memetics-inspired methodology for TCP.The proposed structure is first embedded with diverse parameters,and then traditional steps of the shuffled-frog-leaping approach(SFLA)are followed to prioritize the test cases at unit and integration levels.On 5 standard test functions,a comparative analysis is conducted between the established algorithms and the proposed approach,where the latter enhances the coverage rate and fault detection of re-ordered test sets.Investigation results related to the mean average percentage of fault detection(APFD)confirmed that the proposed approach exceeds the memetic,basic multi-walk,PSO,and optimized multi-walk by 21.7%,13.99%,12.24%,and 11.51%,respectively.

基于TD3-PER的氢燃料电池混合动力汽车能量管理策略研究

为优化氢燃料电池混合动力汽车的燃料经济性及辅助动力电池性能,提出了一种基于优先经验采样的双延迟深度确定性策略梯度(TD3-PER)能量管理策略。采用双延迟深度确定性策略梯度(TD3)算法,在防止训练过优估计的同时实现了更精准的连续控制;同时结合优先经验采样(PER)算法,在获得更好优化性能的基础上加速了策略的训练。仿真结果表明:相较于深度确定性策略梯度(DDPG)算法,所提出的TD3-PER能量管理策略的百公里氢耗量降低了7.56%,平均功率波动降低了6.49%。

KANO模型在VR家具购物中的应用——洞察设计决策

本文以用户为中心的视角,深入探讨VR(虚拟现实)如何改善在线家具的购物体验。这项研究通过比较线上和线下用户的家具购买过程,分析物理和虚拟环境中家具购物体验的研究现状,采用KJ法获取用户需求的考量维度:VR家具购物体验、VR系统与环境和VR特征,通过用户行为定义16项功能需求。以kano模型收集有效样本,进行用户需求和功能优先级分析,聚焦VR系统的具体优化功能,构建产品的信息架构及产品与用户的互动方式。运用可用性测试和专家访谈法对VR系统原型进行测试,测试结果表明,此种设计策略可提升VR在线家具系统的用户购物体验。这项研究对于开发符合用户需求,以及用户期望的VR在线家具购物系统具有参考意义。

一种任务驱动的车联网边缘卸载策略

边缘计算为解决未来车联网中移动流量的爆炸式增长提供了可行范式,然而位置的动态变化以及计算任务的多样性和差异性,使得资源有限的边缘服务器很难在规定时间内完成区域内多车辆任务的并行处理需求。基于此,以最小化时延为目标,提出一种结合深度确定性策略梯度算法的任务驱动卸载策略。首先,结合差异性任务类型和紧迫程度进行预处理,构建了一种基于最大延迟容忍度的任务动态优先级调整模型;然后,利用道路区域内的车辆拓扑和通信半径,提出了基于网络密度和负载均衡的动态协作簇划分方法,解决了多样性任务的动态协作卸载优化问题。实验结果表明,所提算法在收敛性、卸载时延及卸载命中率等方面具有性能优势。

煤矸分拣多机械臂任务分配问题研究

针对煤矸分拣过程中分拣率低、大粒度矸石分拣效果差等问题,通过考虑矸石粒度、分拣时间、矸石与分拣区边界距离等因素,构建矸石优先级模型;采取分拣机械臂放置矸石后不复位的方式,提出了一种煤矸分拣多机械臂任务分配策略,并以分拣率为标准进行评判,最后,采用本研究分配策略和传统的分配策略进行仿真。结果表明:本研究分配策略比传统的分配策略分拣效果更好,提高了7%~10%的分拣率,减少了大粒度矸石的漏拣数量;当矸石的间距不变时,矸石数量变化对分拣率影响较小,分拣率波动在3%左右,验证了本研究分配策略的有效性;矸石间距对分拣率和分拣机械臂数量的影响较大,当矸石的间距增大时,分拣率得到提高;矸石间距在250 mm以上时,3个分拣机械臂能保证较高的分拣率。

基于测试树模型的软件测试能力值优先级排序

为了有效提升软件测试用例排序的执行效率,保障软件运行安全,提出基于UML顺序图的软件测试用例优先级排序方法。根据UML顺序图场景概念,通过遍历顺序图中的时间序列获取全部场景,得到与之对应的场景测试树模型。设置约束条件,根据场景环境条件形成软件测试用例。计算各个软件测试用例的迁移重要度,通过反馈机制动态调整软件测试用例的总测试能力值,根据测试能力值展开优先级排序。实验结果表明,采用所提方法可以全面提升软件测试用例缺陷检测率,确保在最短的时间内获取最优的排序结果。

应对过滤气泡:算法策展对用户信息消费行为选择性和态度极端化的影响

[目的/意义]“过滤气泡”是个性化推荐算法仅向用户推荐他们所认同、感兴趣的信息而造成的不利结果,体现为信息消费行为的选择性及个体态度的极端化。本研究旨在探索不同信息排序方式对于过滤气泡的干预效果。[方法/过程]共招募38位参与者访问模拟新闻推荐系统,并将其划分到不同信息排序方式的组别中,通过服务器日志观测参与者的新闻点击与阅读行为,使用量表测量其态度极端性变化情况。[结果/结论]信息排序方式不会影响用户的新闻标题点击行为的选择性,但会影响其新闻文章阅读行为的选择性及态度极端性变化:相较于基于偏好的排序方式,基于时间与基于质量的排序方式均会显著降低用户阅读行为的选择性,同时基于质量的排序方式还显著降低了用户的态度极端性。本研究不仅为过滤气泡研究提供了新的研究视角与有效的方法论,还为个性化推荐算法设计提供了实践启示。

基于动态优先级的机坪车辆避冲突运行规划方法

【目的】针对机坪车机混行环境,提出了一种考虑动态优先级的避冲突运行规划方法。【方法】首先,从作业效率和运行风险两个层面,提出动态优先级计算方法,完善了多类型保障车辆时变冲突风险划分的规则。其次,考虑保障车辆运行规则和物理特性,建立了考虑行驶和等待时间最小化的混合整数规划模型。最后,设计全局路径优化的两阶段算法进行求解,并通过低时间复杂度的改进冲突探测方法,弥补了传统方法求解大规模复杂问题在时效性方面的不足。【结果】实验表明,设计的算法在大、小规模场景均有较好的适用性,相比对照算法,冲突优化幅度提升7.6%,车辆与航空器冲突占比降低7.5%。【结论】所提方法满足了保障车辆差异化运行要求,实现了车辆和航空器混合运行环境下避冲突路径规划的功能。

全面理解中国式社会治理现代化的四重维度

中国式社会治理现代化是中国式现代化事业的重要组成部分,是价值立场、思想方法、话语原则和实践旨归的有机统一。中国式社会治理现代化坚持人民至上的价值立场,在马克思主义对资本主义批判的理论基础上超越了西方纯粹工具理性导致单向度物质文明和维护资本利益的社会治理价值偏差,实现了“人”的价值理性的回归;秉持守正创新的思想方法,走出一条不同于西方社会治理模式和传统社会治理范式的中国特色社会主义社会治理现代化之路,拓展了社会治理现代化发展空间;坚持自信自立,不断推进社会治理话语创新,消除对西式话语的依赖,强化对社会治理现代化的体系化、学理化研究,做到既不封闭僵化,也不食洋不化;坚持共建共治共享,建设社会治理共同体,凝聚社会治理价值共识,健全社会治理体制机制,共享社会治理发展成果,筑牢社会治理道路根基。

基于模糊综合评价方法对枳椇果柄可食性的选优

于2019年起,在走访调查的基础上,对福建省闽西北3市13县的35株适口性较好的枳椇的成熟果柄,通过检测色泽、甜味、单果重和感官评价质感、涩味、风味等共6个指标,建立模糊综合评价体系,对35株枳椇果柄的可食性进行综合评价。研究结果表明,所建立的模糊综合评价方法评价枳椇果柄的选优技术确实可行;通过综合评价优选出:SW2、JO9、JN17、JL25、JL26、WY30为优株,SW1、SW3、SC7、JL27为较优良株,可作为优树母树加以保护,并通过无性繁殖方法加以扩繁,为进一步研究提供基础。