JSJialong Shi

Jialong Shi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jialong Shi has a total of 28 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Vibroseis Vehicle Routing Problem with Spatio-Temporal Coupled Constraints

    by Kexin Zhu, Jialong Shi, Jianyong Sun, Mingen Kuang, Ye Fan

  • Open Access

    Breaking Validity-Induced Boundaries to Expand Algorithm Search Space: A Two-Stage AST-Based Operator for LLM-Driven Automated Heuristic Evolution

    by Shengming Sun, Jialong Shi

    Large Language Model (LLM) based automated heuristic design (AHD) has shown great potential in discovering efficient heuristics. Most existing LLM-AHD frameworks use semantic evolutionary operators that rely entirely on the LLM's pre-trained knowledge. These one-stage methods strictly require the generated code to be valid during the operation and often rely on a "thought-code" representation. We argue that this end-to-end generation fundamentally limits the exploration ability within the algorithm search space. In this paper, we propose a two-stage, structure-based evolutionary operator for LLM-AHD. In the first stage, our approach directly performs crossover and mutation on the Abstract Syntax Trees (ASTs) of the heuristic code, intentionally generating diverse but often invalid structural variants. In the second stage, the LLM is employed to repair these invalid heuristics into executable, high-quality code. Depending on the underlying framework, either the raw invalid variants or the repaired heuristics are integrated into the population to preserve potential structural patterns. We demonstrate that the proposed operator can significantly enhance the search ability of state-of-the-art LLM-AHD algorithms, such as EoH-S. Experimental results on the Traveling Salesman Problem (TSP) and the Online Bin Packing Problem (OBP) show that our method effectively improves both optimization performance and convergence speed.

  • Physical Layer Key Generation of LEO Satellite Communication Based on OTFS Technology

    by Ye Fan, Xiaotong Sun, Rugui Yao, Tong-Xing Zheng, Xiaoya Zuo, Jialong Shi

    Low earth orbit (LEO) satellite signals cover extensive areas with high intensity, rendering them vulnerable to interception. However, the rapid movement of LEO satellites leads to severe Doppler frequency shift, making it extremely challenging to generate a consistent key using traditional physical key generation techniques. In response to these issues, we have fully utilized Orthogonal Time Frequency Space (OTFS) in dynamic environments and propose a physical layer key generation (PLKG) scheme based on delay- Doppler (DD) domain signal processing. In the preprocessing stage, we propose a Linearly Weighted Moving Average Coding (LW-MAC) algorithm that dynamically adjusts weights with varying channel response intensities, significantly reducing the inconsistency in channel estimation. Subsequently, to address the reduction in key security caused by insufficient key length, we propose a Maximum of Real and Imaginary parts of channel response Assisted Amplitude Quantization (MRIAAQ) algorithm, which increases the key length and enhances the key entropy value. Simulation results demonstrate that our proposed PLKG scheme has substantial advantages over bidirectional difference quantization (BDQ) and equal probability quantization schemes in terms of key disagreement rate (KDR). Moreover, our PLKG scheme significantly reduces the bit error rate (BER) by approximately 71.37$\%$ on average compared to artificial noise-aided physical layer security scheme, thereby greatly enhancing the security of dynamic satellite-to-ground communication.

  • Neuro-PLS: A Generalizable Local Search Framework for Multi-objective Combinatorial Optimization

    by Haotian Zhang, Jialong Shi, Jianyong Sun, Qingfu Zhang, Zongben Xu

    In this paper, we present a novel neural multi-objective combinatorial optimization framework with generalization ability across problems. The main idea is to integrate the framework of Pareto Local Search (PLS), a well-known problem independent multi-objective heuristic, with the concept of learning-to-optimize (L2O). In the proposed framework, namely Neuro-PLS, the backbone of PLS is guided by two neural networks to utilize cross-problem knowledge. Specifically, in Neuro-PLS, the solution-selection component is guided by a Graph Neural Network (GNN) and the neighborhood-exploration component is guided by a multi-layer perception. In the experimental studies, the training set of Neuro-PLS contains only one 200-dimensional multi-objective unconstrained binary quadratic programming (mUBQP) instance. The trained Neuro-PLS shows remarkable efficiency on optimizing large-size mUBQP instances and middle-size multi-objective traveling salesman problem (mTSP) instances with different number of objectives. Extensive experiments on a variety of mUBQP and mTSP instances show that the trained Neuro-PLS significantly outperforms some recently proposed reinforcement learning-based methods.


  • Multi-Objective Regular Mapping QoS Path Planning for Mega LEO Constellation Networks

    by Ye Fan, Zhi Liu, Rugui Yao, Hao Jiang, Jialong Shi, Xu Yang, Xiaoya Zuo, Victor C. M. Leung

    To guarantee the low-congestion performance and quality of service (QoS) requirements of multi-services in Mega Low Earth Orbit Constellation Networks (MLEOCN), this paper focuses on the comprehensive communication link model in MLEOCN, commencing from users to access satellites, relayed by relay satellites, and finally delivered to the gateway by feeder satellites. Aiming at the problems of high congestion and low throughput in traditional path planning algorithms, we innovatively propose a multi-objective optimization service-correlated path optimization algorithm based on stochastic hill climbing strategy (MSCPO-SHCS). The algorithm initially achieves the joint optimization of three metrics through regular mapping and judicious weighting. Subsequently, it assesses the interplane hop via geometric parameter theory analysis (GPTA), then decouples the large-scale mixed integer optimization problem into the integer optimization problem superimposed linear programming problem, and ultimately employs the stochastic hill climbing strategy (SHCS) for path intelligent optimization. Based on the path Gaussianity assumption, we theoretically prove and numerically verify the convergence of the proposed algorithm. The simulation results indicate that the proposed algorithm boosts the throughput and load balancing coefficient compared with the greedy strategy, service-uncorrelated, minimum hop count, and resource allocation optimization. Additionally, it decreases the hop count compared with the maximum throughput and maximum balancing coefficient and maintains the optimal overall performance.


  • Open Access

    A Gradient-based Method for Differential Evolution Parameter Control by Smoothing

    by Haotian Zhang, Jialong Shi, Jianyong Sun, Ali Wagdy Mohamed, Zongben Xu

    Differential evolution (DE) is one of the most studied algorithms in evolutionary computation. However, the parameters in DE need to be tuned carefully, which costs much computational resources. The reason is that the basic paradigm of DE (mutation, crossover, bound constraint and selection) contains non-differentiable operators. In this paper, we propose a DE paradigm called "smoDE" for the first time by smoothing the crossover operator and the bound constraint operator to make them differentiable with respect to the parameters. The experiments show that we can tune the parameters of smoDE by gradient descent with much fewer computational resources than commonly used tools such as the Bayesian optimization algorithm (BOA). Then we analyze the population diversity of smoDE theoretically and prove that smoDE can converge faster than DE. A simple experiment also validates that. We further propose the "ada-smoDE" by embedding a neural network in smoDE to output parameters of smoDE adaptively and test ada-smoDE on the CEC 2018 test suite. The results show that ada-smoDE can perform competitively on the whole test suite and significantly better than DE on some problems.


  • Open Access

    Improving Neighborhood Exploration Mechanism to Speed up PLS

    by Yuhao Kang, Jialong Shi, Jianyong Sun, Ye Fan

    As an extension of local search for multiobjective case, the basic version of Pareto Local Search (PLS) suffers from a poor anytime behavior. Researches have been carried out to overcome this drawback from different aspects. In this paper, we focus on the mechanism of neighborhood exploration in bi-objective Travelling Salesman Problems (bTSPs). Inspired by existing fast local search strategies for single objective TSP, we propose two speed-up strategies to help PLS quickly find promising neighboring solutions in bTSPs. In the experimental studies, we investigate the sensitivity of parameters and test the performance of several PLS variants with different combinations of the two strategies. The experimental results verify the effectiveness of the two strategies and their combination.