By integrating the generative capabilities of Large Language Models (LLMs) with external biomedical knowledge repositories, Retrieval-Augmented Generation (RAG) offers significant potential for addressing knowledge-intensive biomedical tasks, enhancing the precision and effectiveness of clinical decision-making. However, the standard RAG approach fails to fully leverage the information within the retrieved documents, which can lead to incorrect response generation. While advanced RAG approaches empower LLMs to understand the correlation between queries and documents, they require costly annotation. In this work, we propose a strategy to help LLMs better leverage the information within retrieved documents in RAG system while reducing data acquisition costs. We fine-tuned an LLM on a dataset comprising queries, retrieved documents, and their relevance scores generated by a pre-trained biomedical re-ranker to adapt the model for answering questions from reference documents. The fine-tuned model can independently score retrieved documents before answering the question, thereby more effectively utilizing the information contained within retrieved documents. Experimental results shows that we have improved the model’s accuracy on two biomedical benchmarks while reduced the costs of data acquisition.

Edge intelligence is a critical enabler of intelligent application services in the Internet of Things (IoT). However, due to complex environmental factors, edge devices are subject to constant dynamic changes, which can result in security threats and sensitive information leakage. Therefore, it is essential to investigate data stream online analysis and detection strategies and implement an online releasing mechanism to ensure sensitive information is not leaked. Existing work rarely addresses these issues simultaneously or has poor performance, which poses a challenge. To address this challenge, we propose an intelligent edge dual-structure ensemble method (IEDSEM), consisting of three key components: 1) data preprocessing; 2) drift detection data analytics (IEDSEM-DDDA); and 3) privacy-preserving data releasing (IEDSEM-PPDR). Data preprocessing is used primarily to enhance the quality of data streams to improve the performance of model learning. IEDSEM-DDDA involves three sequential operations: 1) dynamic feature selection; 2) model learning and selection and 3) online model ensemble deployment to achieve anomaly detection of online data streams. Meanwhile, IEDSEM-PPDR uses differential privacy and online optimization operations to achieve intelligent hierarchical protection of edge data. To validate the performance of our proposed IEDSEM method, we conducted two comprehensive simulation experiments on real data machines, verifying the accuracy of the concept drift component detection and the privacy optimization performance of the privacy-preserving component, respectively. Simulation results show that compared with several other advanced high-performance algorithms, our algorithm has over 99% accuracy in data stream analysis detection and more outstanding privacy-preserving ability.

Collaborative resource scheduling between edge terminals and cloud centers is regarded as a promising means of effectively completing computing tasks and enhancing quality of service. In this paper, to further improve the achievable performance, the edge cloud resource scheduling (ECRS) problem is transformed into a multi-objective Markov decision process based on task dependency and features extraction. A multi-objective ECRS model is proposed by considering the task completion time, cost, energy consumption and system reliability as the four objectives. Furthermore, a hybrid approach based on deep reinforcement learning (DRL) and multi-objective optimization are employed in our work. Specifically, DRL preprocesses the workflow, and a multi-objective optimization method strives to find the Pareto-optimal workflow scheduling decision. Various experiments are performed on three real data sets with different numbers of tasks. The results obtained demonstrate that the proposed hybrid DRL and multi-objective optimization design outperforms existing design approaches.

An edge cloud architecture plays a key role in improving the user task computing service system by combining the powerful data processing capability of cloud centres with the low latency of edge computing. Existing methods for maximizing the efficiency of an edge cloud architecture take into account time and task parameters but ignore other factors such as load balancing, cost, and user satisfaction when scheduling resources. In this work, we propose a many-objective resource scheduling model for optimizing the performance of an edge cloud architecture, which takes into account the time spent on task, cost, load balance, user satisfaction, and trust measurement. The resource scheduling model converges to the optimal solution using a novel many-objective ensemble optimization algorithm based on a dynamic selection mechanism. The study also explores the support set convergence of eight evolutionary operators using the ensemble algorithm. The model solutions are dynamically updated with the help of the dynamic integration probability, and then a selection criteria is used to pick the best solutions from the pool of generated solutions. Two simulations on a benchmark dataset are used to verify the usefulness and performance of the designed algorithm. Our approach was able to locate more than half of the best solutions on the benchmark functions, and it also showed to be a better model solution than the some of the popular many-objective algorithms for dealing with the edge cloud resource scheduling problem, according to the results obtained from the simulations.

Summary Data imbalance and parameter selection have always been two important factors affecting the accuracy of software defect prediction. However, the existing methods have been poor in balancing these two factors. To address this challenge, a multi‐objective software defect prediction model is employed to describe the under sampled software defect prediction problem. And in this model, defect detection rate and defect false alarm rate are deemed as two objectives which should be optimized. Simultaneously, we design a novel multi‐objective immune optimization algorithm based on the comprehensive fitness of evaluation mechanism to effectively address the employed model. In the algorithm, the original mechanism based on neighborhood individual selection is replaced based on comprehensive fitness evaluation,which have better selection ability to attaining the predicted effect of software to improving in the process of selection solution of population evolution and further effectively help decision makers choose better scheme that meets requirements. In addition, in order to verify the effectiveness of the designed algorithm, the proposed algorithm is compared on eight different public data sets. Simulation results show that the proposed algorithm has better performance in handling with the multi‐objective under sampling software defect prediction problem.

In-vehicle network security plays a vital role in ensuring the secure information transfer between vehicle and Internet. The existing research is still facing great difficulties in balancing the conflicting factors for the in-vehicle network security and hence to improve intrusion detection performance. To challenge this issue, we construct a many-objective intrusion detection model by including information entropy, accuracy, false positive rate and response time of anomaly detection as the four objectives, which represent the key factors influencing intrusion detection performance. We then design an improved intrusion detection algorithm based on many-objective optimization to optimize the detection model parameters. The designed algorithm has double evolutionary selections. Specifically, an improved differential evolutionary operator produces new offspring of the internal population, and a spherical pruning mechanism selects the excellent internal solutions to form the selected pool of the external archive. The second evolutionary selection then produces new offspring of the archive, and an archive selection mechanism of the external archive selects and stores the optimal solutions in the whole detection process. An experiment is performed using a real-world in-vehicle network data set to verify the performance of our proposed model and algorithm. Experimental results obtained demonstrate that our algorithm can respond quickly to attacks and achieve high entropy and detection accuracy as well as very low false positive rate with a good trade-off in the conflicting objective landscape.

Mobile edge computing (MEC) is an effective computing tool to cope with the explosive growth of data traffic. It plays a vital role in improving the quality of service for user task computing. However, the existing solutions rarely address all the significant factors that impact the quality of service. To challenge this problem, a trusted many-objective model is built by comprehensively considering the task time delay, server energy consumption, trust metrics between task and server, and user experience utility factors in multi-server MEC networks. We decompose the original problem into task offloading (TO) and resource allocation (RA) to address the model. Then a novel hybrid many-objective optimization algorithm based on cascading clustering and incremental learning is designed to optimize the TO decision solutions. A low-complexity heuristic method is adopted based on the optimal TO decision solutions to optimize the RA problem continuously. To verify the model's validity and the optimisation algorithm's superiority, five other advanced many-objective algorithms are used for comparison. The results show that our algorithm has more than half the number of the superior values for the benchmark problem. And the obtained model solution shows good performance on different indicators metrics for the decomposition problem.

Abstract Blockchain has decentralization characteristics and requires more targeted security schemes to protect user privacy. In contrast, existing signature schemes have many high‐complexity operations and impose an enormous computational burden on wireless nodes. This article proposes a light‐weighted identity privacy scheme for blockchain‐based on edge computing. We construct linkable identity privacy and non‐linkable identity privacy, which can resist collusion attacks while virtually guaranteeing blockchain nodes' identity privacy. Since edge computing offloads heavily, the proposed scheme has lower computational complexity than the existing techniques.

Summary The problem of convergence and diversity in the course of population evolution is difficult to be balanced for solving the many‐objective optimization problem (MaOP). To track with the problem, a many‐objective optimization algorithm is designed. In the algorithm, a hybrid selection mechanism under the concurrent integration strategy is built to improve algorithm performance by employing the different selection operators. The concurrent integration strategy can select the suitable operator to balance the convergence and diversity of the solution in the course of the population evolutionary. To verify the effectiveness of the algorithm, the designed algorithm is compared with other five excellent many‐objective algorithms on DTLZ and WFG test problem. What is more, the designed algorithm is applied to solve the coal green production optimization problem. The simulation results show that the performance of designed algorithm is superior to whether the DTLZ and WFG test problem or the application problem.

The traditional coal energy system cannot meet the requirements of modern industrial production for sustainable development because extensive economic growth has caused significant coal consumption. Therefore, it is particularly important to formulate an effective coal production decision-making scheme to support complex coal production systems for sustainable development. To address this challenge, an improved many-objective fuzzy decision-making model with human participation for coal production prediction is established in this article. The model includes five objective functions: economic, energetic, environmental, coal gangue, and safety profits. Moreover, a novel multistage many-objective optimization algorithm is designed to adjust relevant model parameters and make the obtained model solution more accurate when compared with involved algorithms. In the algorithm, there are three stages of optimization. In stage one, the model with the relatively good convergence solution is chosen. In stage two, the diversity of the model solution needs to be retained by employing a diversity maintenance mechanism. In stage three, a comprehensive measurement approach is designed to ensure the balance of convergence and diversity during population evolution. To verify the validity of the model and the superiority of the optimization algorithm, five other advanced many-objective algorithms are used for comparison. The results from simulations on a benchmark function show that the proposed optimization algorithm has better performance than involved algorithms. Model solutions obtained on different metrics have better convergence and diversity for the coal fuzzy decision-making problem.

Summary Both the problem of class imbalance in datasets and parameter selection of Support Vector Machine (SVM) are crucial to predict software defects. However, there is no one working to solve these problems synchronously at present. To tackle this problem, a hybrid multi‐objective cuckoo search under‐sampled software defect prediction model based on SVM (HMOCS‐US‐SVM) is proposed to solve synchronously above two problems. Firstly, a hybrid multi‐objective cuckoo search with dynamical local search (HMOCS) is utilized to select synchronously the non‐defective sampling and optimize the parameters of SVM. Then, three under‐sampled methods for decision region range are proposed to select the non‐defective modules. In the simulation, the three indicators, including the false positive rate (pf), the probability of detection (pd), and G‐mean, are employed to measure the performance of the proposed algorithm. In addition, eight datasets from Promise database are selected to verify the proposed software defect predication model. Comparing with the result of eight prediction models, the proposed method comes into effect on solving software defect prediction problem.

Summary It is difficult to protect users' privacy and to process private information due to the complexity and uncertainty of such information. To protect private information quickly and accurately, a many‐objective optimization algorithm framework based on the hybrid elite selection strategy is proposed in this paper. First, a mating selection mechanism combined with the achievement scale function and angle information index is used to generate elite offspring of the internal population. Then, the balanceable fitness estimation method is employed to select and update the external archive. To test performance, the proposed algorithm is tested on many‐objective optimization problems (MaOPs) and compared with five state‐of‐the‐art algorithms. Experimental simulation results show that the proposed algorithm is more effective in solving MaOPs and can inspire development of a better privacy protection strategy.