IoT-based intelligent emergency logistics management using DETR-driven visual perception and deep Q-learning

With the development of 6G to higher frequency bands and the awareness of the environmental pollution caused by carbon emissions, green and low carbon has become a key performance indicator (KPI) for mobile communications. To meet the demand, a deep reinforcement learning (DRL) framework for hybrid energy supply based on intelligent battery charge/discharge management is proposed. Firstly, hybrid renewable-grid-batteries energy is designed to power a new generation of green base stations (BSs). On this basis, the grid-connected depth (GCD) model and battery charging/discharging model of heterogeneous BSs under the hybrid energy supply mode are established. Then, a deep Q-learning (DQL) algorithm is employed to learn the time-varying energy harvesting (EH) information, local load information, and battery status information to optimize the GCD. In addition, an intelligent management strategy of GCD under hybrid energy power supply is proposed. Finally, simulation results showcase that better base station(BS) battery state detection without predicting causal information and real-time energy sharing can effectively minimize GCD. This confirms the feasibility of the proposed scheme and strategy.

Emergency logistics management—Review and propositions for future research

Reinforcement learning approaches for efficient and secure blockchain-powered smart health systems

This paper presents the results of intelligent traffic light management (TLM) which improves the traffic efficiency via optimally controlling the green lights’ time interval and selecting the traffic phases. As the control problem is stochastic and difficult to be modeled accurately, model-free reinforcement learning (RL) is applied in this work. To stabilize the training process and mitigate the overestimation issue of conventional deep Q-learning based RL methods, we developed an RL algorithm with double deep Q-network (DQN) and a clipping function for the TLM problem with a discrete action space. The advantage of this clipped version of double DQN over other Q-learning-based algorithms is demonstrated in this work. Furthermore, the performance of RL-based TLM is compared with both fixed-time and adaptive rule-based TLM by using PTV Vissim which is a multi-modal traffic simulation software as the testing platform in this work.

The present research considers the request for prompt response in the same-day delivery (SDD) problem with drone resupply. SDD has gained popularity since customer satisfaction is highly valued in the logistics industry. Customers, even those residing far from distribution centres, anticipate the opportunity to get prompt responses. The decision-maker (DM) promptly decides whether to accept the order or not as customers’ requests stochastically occur throughout the day. We assume that the truck promises to deliver packages within the promised time while a drone performs multiple trips from the warehouse to replenish the truck at any required time. A novel Deep Q-Learning (DQL) approach is proposed to maximise the acceptance rate of requests and simultaneously ensure prompt responses. Two nested agents are utilised to (a) determine order acceptance and (b) dynamically adjust drone deployment based upon its availability. Comprehensive testing and analysis demonstrate the superior effectiveness of our approach compared to benchmarks. Findings suggest that: (1) Drone resupply enables SDD to remote customers within designated distances; (2) Deep Q-learning optimises drone’s waiting times to dynamically adjust payload capacity; and (3) it is the increase in resupply frequency rather than payload size per resupply that more effectively improve the whole delivery volume.

Skill learning for robotic assembly based on visual perspectives and force sensing

In this research, the use of non-invasive electrode-based EEG (electroencephalogram) signal measurement as a means to detect emotional and stress-related factors in individuals, is explored. This research focuses on evaluating EEG signals, particularly those channels that provide insights into motor-related brain activity, cognitive processes, and visual perception and processing. These have attracted interest in the context of predicting diseases. By integrating stress and disease prediction into a single module, this approach aims to offer an early warning system for individuals, enabling them to mitigate or avoid future health risks. Chronic stress is known to have hazardous effects on health, potentially triggering inflammatory responses within the body. These responses are linked to an elevated risk of cardiovascular diseases, which, in turn, can heighten the risk of stroke. The proposed research aims to classify stress-induced emotions and predict stroke risk using advanced deep learning algorithms. The study utilizes EEG signals to categorize stress-related emotions, subsequently assessing stroke risk via an optimized deep learning model. The proposed model is distinguished by its optimized hybrid optimization technique for feature extraction, aimed at stress and stroke prediction. The classification of stress emotions is achieved through the application of a BiLSTM (Bidirectional Long Short-Term Memory) network, while the assessment of stroke risk is conducted using deep Q-learning. The effectiveness of the proposed model is validated through experiments conducted with the benched mark DEAP dataset, demonstrating its robust performance in both stress and stroke prediction.

Reverse logistics for electric vehicles under uncertainty: An intelligent emergency management approach

With the strong drive for economic and cultural development, China’s higher education has flourished and formed a higher education system and scale with typical Chinese characteristics, and the healthy development of higher education cannot be separated from the strong support and guarantee of university logistics. Based on FPGA technology, this paper explains in detail the design method and computing steps of FPGA technology to build a university intelligent logistics management data analysis system. The performance evaluation is carried out for the system designed in this paper, and the data analysis of the indicator examples is carried out by using five examples of logistics management service indicators of the University of W, namely campus environment, property service, commercial service, residence management service, and utility maintenance. From the performance evaluation data of the FPGA university intelligent logistics management system, the average accuracy, precision, recall, and AUC values of the FPGA-based university logistics management system are 91.90%, 95.78%, 97.28%, and 97.41%, respectively. From the index instance analysis, the average evaluation values of the five services of very satisfied, satisfied, generally satisfied, and dissatisfied are 24.89%, 25.16%, 40.97%, and 8.98%, compared with the previous average values of very satisfied and satisfied evaluations increased by 18.36% and 4.61%, respectively, and the average values of generally satisfied and unsatisfied evaluations decreased by 7.65% and 15.31%, respectively. The FPGA-based intelligent management system of colleges and universities has higher stability and stronger data analysis ability, which can more effectively propose corresponding reform directions for the problems and provide technical support to promote more intelligent logistics management of colleges and universities. At the same time, it enables university teachers and students to carry out relevant academic research and study life without any worries, contributes technical power to promote the overall healthy development of universities, and provides new research directions to broaden the development field of FPGA technology.

In recent years various disasters with enormous consequences occurred frequently around the world. Emergency Logistics, a new field of logistics which plays a key role in disaster relief and aftermath recovery, has got much attention and become a new efficient methodology in dealing with disastrous consequences. This paper illustrates the theory, practice development, specific characteristics and concept of Emergency Logistics. For emergency logistics management, the most important part is the establishment of emergency logistics system. Enlightened by the present theory and results, an Operations Reference Model for Emergency Logistics System is proposed, in which the support mechanism, compositional elements and functionalities of Emergency Logistics System are discussed in this essay. It is necessary that it has potential value for further study or practical use of Emergency Logistics Management.

The effective prevention and response of public emergencies such as natural disasters is not only a difficult problem for China, but also a problem that governments all over the world hope to be solved effectively. Emergency supply chain management is very important to disaster relief. It determines whether the emergency work can be carried out efficiently and orderly, which is a major event affecting the national economy and people’s livelihood. The theory of intelligent supply chain provides a new research perspective for emergency logistics management. This paper combines the theory of intelligent supply chain with emergency theory, analyzes the necessity of intelligent supply chain in emergency management, and puts forward the construction principles. Finally, the paper puts forward some suggestions based on the intelligent supply chain emergency logistics management.

Value Realization of Intelligent Emergency Management: Research Framework from Technology Enabling to Value Creation

This paper aims to analyze the characteristics and metrics of emergency logistics to public sector organizations, in order to manage emergency logistics more efficiently and effectively. Based on analyzing the characteristics of emergency logistics management for incidents and reviewing past practices, it applies integrated supply chain management theories to the performance assessment, and sets up a three tiers’ index system with 39 indicators, involving reliability, agility, flexibility, and cost-effectiveness in the first tier as goals, to assess the all-round performance of emergency logistics management. Then it combines hierarchy analysis process (HAP) and fuzzy comprehensive evaluation into the performance metrics. Also, it explains the results of the reliability evaluation of emergency logistics supply chain management, taking the Wenchuan earthquake incident as an example. By this performance assessment index system, some specific problems in emergency logistics management, such as operation coordination, supply chain links, and information communication, could be found and measured.

With the development of the logistics industry, the ability requirements for logistics talents are gradually improving, especially the demand for intelligent logistics management talents. However, the training system for advanced intelligent logistics management talents is not yet mature. Based on the theory of educational objectives and achievement-oriented educational theory, this research establishes the ability evaluation system for intelligent logistics management talents. The questionnaire survey method is used to analyze the quality of intelligent logistics management personnel and its influencing factors. It is found that the training quality of intelligent logistics management talents is generally low; uneven teachers, unreasonable teaching curriculum, and unclear educational objectives are the main factors affecting the ability of intelligent logistics management talents. Accordingly, this study proposes to improve the ability of intelligent logistics management talents in the aspects of curriculum arrangement, teachers, training programme design, and curriculum system design.

An emergency logistics distribution approach for quick response to urgent relief demand in disasters