Search

Detecting and recognizing pests are paramount for ensuring the healthy growth of crops, maintaining ecological balance, and enhancing food production. With the advancement of artificial intelligence technologies, traditional pest detection and recognition algorithms based on manually selected pest features have gradually been substituted by deep learning-based algorithms. In this review paper, we first introduce the primary neural network architectures and evaluation metrics in the field of pest detection and pest recognition. Subsequently, we summarize widely used public datasets for pest detection and recognition. Following this, we present various pest detection and recognition algorithms proposed in recent years, providing detailed descriptions of each algorithm and their respective performance metrics. Finally, we outline the challenges that current deep learning-based pest detection and recognition algorithms encounter and propose future research directions for related algorithms. [ABSTRACT FROM AUTHOR]

Orthogonal frequency division multiplexing (OFDM) in 5G has many advantages; however, one of the disadvantages is that the superposition of a large number of subcarriers leads to a high peak-to-average power ratio (PAPR) of the transmit signal. A high PAPR results in high-power amplifier distortion and performance degradation. The partial transmit sequence (PTS) algorithm is commonly used for PAPR reduction. It enumerates all combinations of phase factors, weighs the signal using each phase factor combination, and finds the set of phase factors that minimizes the PAPR value of the OFDM signal. The advantage of the PTS is that it determines the optimal solution through enumeration; however, its major drawback is the higher complexity caused by the use of enumeration. Some studies have introduced the discrete particle swarm optimization (DPSO) algorithm instead of enumeration to determine the optimal solution of the PTS algorithm. As an excellent optimization method, the DPSO algorithm represents each individual as a solution during the optimization. Through iterative updates of the initial population, individuals in the population continuously move closer to the optimal solution. This approach significantly reduces complexity compared with the exhaustive enumeration used in the traditional PTS algorithm. However, the disadvantage of the general DPSO algorithm is that it can result in premature and early convergence, which leads to degradation of the PAPR reduction performance. In this study, we propose an improved method based on the general DPSO-based PTS algorithm, and the improved algorithm MDPSO-PTS adopts dynamic time-varying learning factors, which can find the optimal combination of phase factors more efficiently. The MDPSO-PTS algorithm expands the search space when seeking the optimal combination of phase factors. This avoids the drawback of premature convergence commonly observed in general DPSO-PTS algorithms, preventing early consideration of local optima as global optima. A comparative simulation of the improved MDPSO-PTS algorithm with the general DPSO-PTS algorithm shows that the improved algorithm has stronger PAPR reduction, whereas the complexity remains basically unchanged. A comparative simulation with the traditional PTS algorithm shows a significant reduction in complexity, with only a slight, acceptable loss of reduction performance. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) in deep learning have input pixel limitations, which leads to lost information regarding microcalcification when mammography images are compressed. Segmenting images into patches retains the original resolution when inputting them into the CNN and allows for identifying the location of calcification. This study aimed to develop a mammographic calcification detection method using deep learning by classifying the presence of calcification in the breast. Using publicly available data, 212 mammograms from 81 women were segmented into 224 × 224-pixel patches, producing 15,049 patches. These were visually classified for calcification and divided into five subsets for training and evaluation using fivefold cross-validation, ensuring image consistency. ResNet18, ResNet50, and ResNet101 were used for training, each of which created a two-class calcification classifier. The ResNet18 classifier achieved an overall accuracy of 96.0%, mammogram accuracy of 95.8%, an area under the curve (AUC) of 0.96, and a processing time of 0.07 s. The results of ResNet50 indicated 96.4% overall accuracy, 96.3% mammogram accuracy, an AUC of 0.96, and a processing time of 0.14 s. The results of ResNet101 indicated 96.3% overall accuracy, 96.1% mammogram accuracy, an AUC of 0.96, and a processing time of 0.20 s. This developed method offers quick, accurate calcification classification and efficient visualization of calcification locations. [ABSTRACT FROM AUTHOR]

Quantum key distribution (QKD) is an encrypted communication technique based on the principles of quantum mechanics that ensures communication security by exploiting the properties of quantum states. Currently, the transmission efficiency of the QKD system is low. Trusted relay technology is used to solve this problem and achieve long-distance transmission. However, trusted relaying alone cannot decrypt the issues of poor link stability and the low utilization of key resources. To further optimize the system performance, we propose a dynamic routing algorithm. One of the improvement schemes includes the following: firstly, an adjustable-size quantum key pool (QKP) is designed, which can dynamically adjust the size of the refreshing pool according to the actual demand. Secondly, the utilization of key resources is improved by using the residual quantum key model to dynamically obtain the remaining key amount in the QKP and set the key amount threshold. We calculate the link-blocking probability and track the blocking intensity and blocking entry by combining the Poisson process, thus realizing the evaluation of the link stability. Finally, the number of remaining keys in the QKP and the link-blocking probability combine with the random wandering model as the basis of the route selection for the QKD dynamic routing algorithm to achieve efficient key path selection. We validated the algorithm by comparing it with other algorithms on the Mininet simulation platform, and the algorithm proved to have a better performance in terms of congestion avoidance, delay reduction, and improved QKD efficiency. This scheme provides a novel and efficient way to solve the problems in existing QKD systems. It effectively improves the transmission efficiency and strengthens the system's security by dynamically obtaining the critical volume, accurately evaluating the link state, and selecting the optimal critical path. [ABSTRACT FROM AUTHOR]

To accurately estimate the state of charge (SOC) of lithium-ion power batteries in the event of errors in the battery model or unknown external noise, an SOC estimation method based on the H-infinity filter (HIF) algorithm is proposed in this paper. Firstly, a fractional-order battery model based on a dual polarization equivalent circuit model is established. Then, the parameters of the fractional-order battery model are identified by the hybrid particle swarm optimization (HPSO) algorithm, based on a genetic crossover factor. Finally, the accuracy of the SOC estimation results of the lithium-ion batteries, using the HIF algorithm and extended Kalman filter (EKF) algorithm, are verified and compared under three conditions: uncertain measurement accuracy, uncertain SOC initial value, and uncertain application conditions. The simulation results show that the SOC estimation method based on HIF can ensure that the SOC estimation error value fluctuates within ±0.02 in any case, and is slightly affected by environmental and other factors. It provides a way to improve the accuracy of SOC estimation in a battery management system. [ABSTRACT FROM AUTHOR]

A new proportional integral derivative (PID) control method is proposed for the 3D laser scanning system converted from 2D Lidar with a pitching motion device. It combines the advantages of a fuzzy algorithm, a radial basis function (RBF) neural network and a predictive algorithm to control the pitching motion of 2D Lidar quickly and accurately. The proposed method adopts the RBF neural network and feedback compensation to eliminate the unknown nonlinear part in the Lidar pitching motion, adaptively adjusting the PID parameter by a fuzzy algorithm. Then, the predictive control algorithm is adopted to optimize the overall controller output in real time. Finally, the simulation results show that the step response time of the Lidar pitching motion system using the control method is reduced from 15.298 s to 1.957 s with a steady-state error of 0.07°. Meanwhile, the system still has favorable response performance for the sinusoidal and step inputs under model mismatch and large disturbance. Therefore, the control method proposed above can improve the system performance and control the pitching motion of the 2D Lidar effectively. [ABSTRACT FROM AUTHOR]

The inference of a general Bayesian network has been shown to be an NP-hard problem, even for approximate solutions. Although k-dependence Bayesian (KDB) classifier can construct at arbitrary points (values of k) along the attribute dependence spectrum, it cannot identify the changes of interdependencies when attributes take different values. Local KDB, which learns in the framework of KDB, is proposed in this study to describe the local dependencies implicated in each test instance. Based on the analysis of functional dependencies, substitution-elimination resolution, a new type of semi-naive Bayesian operation, is proposed to substitute or eliminate generalization to achieve accurate estimation of conditional probability distribution while reducing computational complexity. The final classifier, averaged k-dependence Bayesian (AKDB) classifiers, will average the output of KDB and local KDB. Experimental results on the repository of machine learning databases from the University of California Irvine (UCI) showed that AKDB has significant advantages in zero-one loss and bias relative to naive Bayes (NB), tree augmented naive Bayes (TAN), Averaged one-dependence estimators (AODE), and KDB. Moreover, KDB and local KDB show mutually complementary characteristics with respect to variance. [ABSTRACT FROM AUTHOR]

Navigation technology is one of the most important challenges in the applications of autonomous underwater vehicles (AUVs) which navigate in the complex undersea environment. The ability of localizing a robot and accurately mapping its surroundings simultaneously, namely the simultaneous localization and mapping (SLAM) problem, is a key prerequisite of truly autonomous robots. In this paper, a modified-FastSLAM algorithm is proposed and used in the navigation for our C-Ranger research platform, an open-frame AUV. A mechanical scanning imaging sonar is chosen as the active sensor for the AUV. The modified-FastSLAM implements the update relying on the on-board sensors of C-Ranger. On the other hand, the algorithm employs the data association which combinesthe single particle maximum likelihood method with modified negative evidence method, and uses the rank-based resampling to overcome the particle depletion problem. In order to verify the feasibility of the proposed methods, both simulation experiments and sea trials for C-Ranger are conducted. The experimental results show the modified-FastSLAM employed for the navigation of the C-Ranger AUV is much more effective and accurate compared with the traditional methods. [ABSTRACT FROM AUTHOR]

With the rapid development of the Internet of Things (IoT), wearable devices have become ubiquitous and interconnected in daily lives. Because wearable devices collect, transmit, and monitor humans' physiological signals, data privacy should be a concern, as well as fully protected, throughout the whole process. However, the existing privacy protection methods are insufficient. In this paper, we propose a practical privacy-preserving mechanism for physiological signals collected by intelligent wearable devices. In the data acquisition and transmission stage, we employed existing asymmetry encryption-based methods. In the data publishing stage, we proposed a new model based on the combination and optimization of k-anonymity and differential privacy. An entropy-based personalized k-anonymity algorithm is proposed to improve the performance on processing the static and long-term data. Moreover, we use the symmetry of differential privacy and propose the temporal differential privacy mechanism for real-time data to suppress the privacy leakage while updating data. It is proved theoretically that the combination of the two algorithms is reasonable. Finally, we use smart bracelets as an example to verify the performance of our mechanism. The experiment results show that personalized k-anonymity improves up to 6.25% in terms of security index compared with traditional k-anonymity, and the grouping results are more centralized. Moreover, temporal differential privacy effectively reduces the amount of information exposed, which protects the privacy of IoT-based users. [ABSTRACT FROM AUTHOR]

With users being exposed to the growing volume of online information, the recommendation system aiming at mining the important or interesting information is becoming a modern research topic. One approach of recommendation is to integrate the graph neural network with deep learning algorithms. However, some of them are not tailored for bipartite graphs, which is a unique type of heterogeneous graph having two entity types. Others, though customized, neglect the importance of implicit relation and content information. In this paper, we propose the attentive implicit relation recommendation incorporating content information (AIRC) framework that is designed for bipartite graphs based on the GC–MC algorithm. First, through reconstructing the bipartite graphs, we obtain the implicit relation graphs. Then we analyze the content information of users and items with a CNN process, so that each user and item has its feature-tailored embeddings. Besides, we expand the GC–MC algorithms by adding a graph attention mechanism layer, which handles the implicit relation graph by highlighting important features and neighbors. Therefore, our framework takes into consideration both the implicit relation and content information. Finally, we test our framework on Movielens dataset and the results show that our framework performs better than other state-of-art recommendation algorithms. [ABSTRACT FROM AUTHOR]