This study conducts a comprehensive bibliometric analysis of 233 publications from 2016–2025 retrieved from the Web of Science Core Collection, aiming to map the global research landscape of intelligent detection of plant disease and pest. Using Bibliometrix and related tools, the study examines publication trends, leading countries and institutions, collaboration networks, and thematic structures. Results show a continuous growth in research output, with China, the United States, and India emerging as major contributors, and China leading in both productivity and citation impact. Keyword co-occurrence and thematic mapping reveal deep learning, convolutional neural networks, transfer learning, and object detection as central research themes, while remote sensing, drones, and smart farming represent rapidly developing fronts. Burst-term analysis further highlights lightweight models, vision transformers, and real-time detection as emerging technological directions. This study provides valuable insights into the knowledge evolution, research hotspots, and future pathways of AI-driven plant disease and pest detection.

With the rise of cloud computing, many users outsource their data to be stored in cloud servers, enjoying the convenience while facing many security issues. In the field of secure multiparty computing, traditional privacy set intersection protocol data users use cloud servers for their data outsourcing to operate for calculating the intersection, the data is susceptible to tampering by the cloud servers, and the data users do not formulate fine-grained access control policies. To solve the above problems, this paper combines blockchain with privacy set intersection for the first time, and proposes a blockchain-based privacy set intersection protocol with attribute access control. This scheme utilizes blockchain instead of a cloud server as a trusted third party, data users utilize smart contracts to compute intersection via OPRF, and attribute encryption is used to provide access control for privacy set intersection protocol. Thus, it solves the risk of data vulnerability to tampering. This paper analyzes the security of the scheme and conducts simulation experiments.

Modern health care systems are conducting continuous, automated surveillance of the electronic medical record (EMR) to identify adverse events with increasing frequency; however, many events such as sepsis do not have elucidated prodromes (i.e., event chains) that can be used to identify and intercept the adverse event early in its course. Clinically relevant and interpretable results require a framework that can (i) infer temporal interactions across multiple patient features found in EMR data (e.g., Labs, vital signs, etc.) and (ii) identify patterns that precede and are specific to an impending adverse event (e.g., sepsis). In this work, we propose a linear multivariate Hawkes process model, coupled with ReLU link function, to recover a Granger Causal (GC) graph with both exciting and inhibiting effects. We develop a scalable two-phase gradient-based method to obtain a maximum surrogate-likelihood estimator, which is shown to be effective via extensive numerical simulation. Our method is subsequently extended to a data set of patients admitted to Grady hospital system in Atlanta, GA, USA, where the estimated GC graph identifies several highly interpretable GC chains that precede sepsis. The code is available at https://github.com/SongWei-GT/two-phase-MHP.

In recent years, deep neural networks are increasingly popular in the field of radar high-resolution range profiles (HRRPs) target recognition. Unfortunately, recent researches have revealed that a deep-learning classifier can be easily fooled by adding small perturbations to the input, named adversarial attack. This provides us an inspiration for radar deceptive jamming signal generation in electronic countermeasures (ECMs). However, the perturbations generated by these adversarial attacks are usually of complex envelopes and quite low power, making it challenging for jammers to generate such actual jamming signals. To solve that issue, we propose a practical deceptive jamming generation method that learns the vulnerable range cells in an HRRP sample and injects several jamming pulses with specific amplitudes into these range cells. Such jamming signals are easy to generate and can deceive the radar automatic target recognition (RATR) model to output the wrong target category prediction with high confidence. To avoid the requirement of the recognition network structure information, we leverage the differential evolution optimization algorithm (non-gradientbased). Further, to provide the potential of real-time jamming signal generation during the test, an encoder is constructed not only to learn the separable features but also to find the vulnerable range cells and the specific amplitudes of the jamming pulses. In the experiments, we apply the proposed attack algorithms to fool the one-dimensional convolutional neural network-based HRRPRATR models. The extensive experimental results on measured aircraft HRRP dataset prove that the proposed algorithms achieve a promising attack performance and serve as a practical and fast deceptive jamming generation method.

Numerous empirical evidences have corroborated the importance of noise in nonconvex optimization problems. The theory behind such empirical observations, however, is still largely unknown. This paper studies this fundamental problem through investigating the nonconvex rectangular matrix factorization problem, which has infinitely many global minima due to rotation and scaling invariance. Hence, gradient descent (GD) can converge to any optimum, depending on the initialization. In contrast, we show that a perturbed form of GD with an arbitrary initialization converges to a global optimum that is uniquely determined by the injected noise. Our result implies that the noise imposes implicit bias towards certain optima. Numerical experiments are provided to support our theory.

Recently there have been many research efforts in developing generative models for self-exciting point processes, partly due to their broad applicability for real-world applications. However, rarely can we quantify how well the generative model captures the nature or ground-truth since it is usually unknown. The challenge typically lies in the fact that the generative models typically provide, at most, good approximations to the ground-truth (e.g., through the rich representative power of neural networks), but they cannot be precisely the ground-truth. We thus cannot use the classic goodness-of-fit (GOF) test framework to evaluate their performance. In this paper, we develop a GOF test for generative models of self-exciting processes by making a new connection to this problem with the classical statistical theory of Quasi-maximum-likelihood estimator (QMLE). We present a non-parametric self-normalizing statistic for the GOF test: the Generalized Score (GS) statistics, and explicitly capture the model misspecification when establishing the asymptotic distribution of the GS statistic. Numerical simulation and real-data experiments validate our theory and demonstrate the proposed GS test’s good performance.

Sequential data with serial correlation and an unknown, unstructured, and dynamic background is ubiquitous in neuroscience, psychology, and econometrics. Inferring serial correlation for such data is a fundamental challenge in statistics. We propose a Total Variation (TV) constrained least square estimator coupled with hypothesis tests to infer the serial correlation in the presence of unknown and unstructured dynamic background. The TV constraint on the dynamic background encourages a piecewise constant structure, which can approximate a wide range of dynamic backgrounds. The tuning parameter is selected via the Ljung-Box test to control the bias-variance trade-off. We establish a non-asymptotic upper bound for the estimation error through variational inequalities. We also derive a lower error bound via Fano’s method and show the proposed method is near-optimal. Numerical simulation and a real study in psychology demonstrate the excellent performance of our proposed method compared with the state-of-the-art.

Sports video summarization and classification is becoming a very important topic due to the pressing need to automatically classify sports scenes to enable better sport analysis, refereeing, training and advertisement. The vast majority of the techniques applied to sports video classifications involved black box techniques such as support vector machines (SVMs) and neural networks, which do not provide models that could be easily analysed and understood by human users. Fuzzy logic classification systems provide white box techniques encompassing linguistic rules and labels that can easily be understood and analysed by humans. However, the traditional fuzzy classification systems can result in huge rule bases due to the curse of the dimensionality problem. This paper presents a fuzzy logic based system for sports video scene classification using the Big Bang-Big Crunch technique to optimize the rules, thus producing high classification accuracy with a small number of rules, increasing system interpretability. Various experiments conducted on football videos demonstrated that the system produces a fuzzy classification system with only eight rules with average classification accuracy of 83%, outperforming other black box classification models which employ neural networks.

In this paper, we investigate the problem of link-level resource provision in multi-radio multi-channel (MR-MC) wireless networks. To quantify robustness of resource provision schemes, we propose the novel concept of interference margin. Using the notion of interference margin, a robust radio and channel assignment problem is formulated that explicitly takes into consideration link-level traffic demands. The key advantage of the proposed formulation is its robustness to channel variability and co-existence of external interference sources. We utilize the generalized Benders decomposition techniques to decouple the radio and channel assignment (combinatorial constraints) and network resource allocation (continuous constraints) so that the problem can be solved efficiently. The proposed algorithm is guaranteed to converge to the optimal solution within a finite number of iterations. We have evaluated our scheme using traces collected from a wireless mesh testbed and simulation studies in Qualnet. Experiments show that the proposed algorithm is superior to existing schemes in providing larger interference margin, and reducing outage and packet loss probabilities.