Search Results (74)

Synthetic aperture radar (SAR) automatic target recognition (ATR) plays a pivotal role in SAR image interpretation. While existing approaches predominantly rely on batch learning paradigms, their practical deployment is constrained by the sequential arrival of training data and high retraining costs. To overcome this challenge, this paper introduces a divergence-constrained incremental dictionary learning framework that enables progressive model updates without full data reprocessing. Specifically, firstly, this method learns class-specific dictionaries for each target category via sub-dictionary learning, where the learning process for a specific class does not involve data from other classes. Secondly, the intra-class divergence constraint is incorporated during sub-dictionary learning to address the challenges of significant intra-class variations and minor inter-class differences in SAR targets. Thirdly, the sparse representation coefficients of the target to be classified are solved across all sub-dictionaries, followed by the computation of corresponding reconstruction errors and intra-class divergence metrics to achieve classification. Finally, when the targets of new categories are obtained, the corresponding class-specific dictionaries are calculated and added to the learned dictionary set. In this way, the incremental update of the SAR ATR system is completed. Experimental results on the MSTAR dataset indicate that our method attains >96.62% accuracy across various incremental scenarios. Compared with other state-of-the-art methods, it demonstrates better recognition performance and robustness. Full article

Recently, electrocardiography (ECG) has attracted significant attention in the field of biometrics, presenting a compelling alternative for biometric recognition based on physical or biological traits. Impressive application results have been achieved by existing methods, the majority of which are designed in the batch processing mode. The batch mode inherently assumes that all data can be acquired prior to training the final model and that no new data will subsequently arrive. Clearly, this assumption is unrealistic, as real-world data often arrive in a streaming fashion, meaning that they are continuously generated and transmitted. When confronted with streaming data, traditional batch-based methods require re-training on all the data once again, including both the newly arrived data and the previously trained data. Consequently, these methods lead to redundant calculations and significant expenses. To overcome this limitation, we propose a new online method for ECG biometrics that incrementally learns from streaming data. Our method updates itself with only the new arriving data, eliminating the need to retrain with both old and new data. To enhance the discriminative power of to-be-learned sample representations, we introduce two novel modules: bidirectional regression and prototype learning. Since our method does not revisit old data when new data arrive, we incorporate a memory enhancement module to mitigate the catastrophic forgetting problem caused by a lack of exposure to old data. Furthermore, we design a novel and efficient online optimization algorithm to minimize the overall loss function. Extensive experiments conducted on two widely used datasets demonstrate the effectiveness of our proposed method. Full article

This research examines a multi-server retrial queueing system with a batch Markov arrival process and a phase-type service time distribution. The system’s distinguishing feature is its ability to control the admission of retrial customers. An attempt by a customer to retry is successful only if the number of busy servers does not exceed certain threshold values, which may depend on the state of the fundamental process of the primary customer’s arrival. Impatient retrying customers may abandon the system without obtaining service. A group of primary customers that arrives while the number of available servers is fewer than the group size is either entirely rejected or occupies all available servers, while the remainder of the group transitions to the orbit. The system’s behavior, under a defined set of thresholds, is characterized by a multidimensional Markov chain classified as asymptotically quasi-Toeplitz. This enables the acquisition of the ergodicity condition and the computation of the steady-state distribution of the Markov chain and the system’s performance measures. The presented numerical examples demonstrate the impact of threshold value variation. An example of solving an optimization problem is presented. The importance of the account of the batch arrivals is shown. Full article

In this study, we consider a multi-server priority queueing model with batch arrivals of two types of customers, a finite buffer, and two input finite buffers for storing customers that cannot be admitted for service immediately upon arrival. The transition of a customer from an input buffer to the main buffer can occur after an exponentially distributed time. Customers residing in the input and main buffers are impatient. The four-dimensional Markov chain is used to describe the dynamics of the system under consideration. It is analyzed via the derivation of its generator and providing an effective algorithm for computing its steady-state probabilities. Formulas for calculating the system’s major performance metrics are established. Numerical results demonstrating the suggested methods’ viability and the effect of variation of transition rates of customers from the input buffers are presented. Full article

With the rapid increase in the number of Earth Observation Satellites (EOSs), research on autonomous mission scheduling has become increasingly critical for optimizing satellite sensor operations. While most existing studies focus on static environments or initial planning states, few address the challenge of dynamic request replanning for real-time sensor management. In this paper, we tackle the problem of multi-satellite rapid mission replanning under dynamic batch-arrival observation requests. The objective is to maximize overall observation revenue while minimizing disruptions to the original scheme. We propose a framework that integrates stochastic master-satellite mission allocation with single-satellite replanning, supported by reactive scheduling policies trained via deep reinforcement learning. Our approach leverages mission sequence modeling with attention mechanisms and time-attitude-aware rotary positional encoding to guide replanning. Additionally, scalable embeddings are employed to handle varying volumes of dynamic requests. The mission allocation phase efficiently generates assignment solutions using a pointer network, while the replanning phase introduces a hybrid action space for direct task insertion. Both phases are formulated as Markov Decision Processes (MDPs) and optimized using the PPO algorithm. Extensive simulations demonstrate that our method significantly outperforms state-of-the-art approaches, achieving a 15.27% higher request insertion revenue rate and a 3.05% improvement in overall mission revenue rate, while maintaining a 1.17% lower modification rate and achieving faster computational speeds. This demonstrates the effectiveness of our approach in real-world satellite sensor applications. Full article

Nowadays, Internet of Things (IoT) is one of the most dynamically evolving services in the 5G ecosystem. In industrial IoT (IIoT), this service can be utilized to deliver state updates of various equipment to the remote control center for further coordination and maintenance. As a result, one of the critical metrics of interest for such a service is the Age of Information (AoI) and its upper bound—peak AoI (AoI)—characterizing the freshness of information about the state of the systems. In spite of significant attention, these metrics received over the last decade, only little is known regarding the PAoI performance of a single source (e.g., sensor) in the presence of competing traffic from other sources in queuing systems. On top of this, models with batch arrivals and batch services that can be effectively used to represent service performance in modern cellular systems such as 5G New Radio are lacking. In our study, we consider a cellular air interface representing it as a queuing system (QS) in discrete-time with batch arrivals and service and investigate performance of a single (tagged) source in presence of competing traffic from other sources having the same priority, where all the sources are modeled using the switched Poisson process (SPP) characterized by sophisticated correlational properties. We also investigated the impact of several service disciplines on the performance of the tagged source including first-come–first-served (FCFS), last-come–first-served (LCFS), random, and priority-based service. Our results illustrate that, although the qualitative behavior of the mean PAoI is different for different service disciplines, the optimal value of PAoI is insensitive to the choice of the service order. On top of this, we observed that introducing a priority in service to one of the flows may drastically affect the performance of other flows even when the overall load contribution of a single flow is rather limited. Our observations can be utilized to design packet scheduling strategies for 4G/5G cellular systems carrying traffic of state update applications. Full article

With the rapid development of e-commerce, the scattered storage mode has been widely applied in B2C distribution centers in which there is a large assortment and quantity of small-sized, time-sensitive orders. Under the scattered storage mode, obtaining high-quality batching results and quickly completing order picking are key to improving the operation efficiency of a distribution center when a large number of orders arrive in a short period. Against this background, a new order batching problem under the scattered storage mode is studied. The feature is to improve the batching quality by considering the correlation between products. The problem is formulated as a 0–1 integer programming model to maximize the sum of pair-to-pair order correlations in all batches. To solve large-scale problems, we first propose two new seed batching algorithms based on the correlation between products. The first one selects the order with the largest number of products as the seed order, and the second one selects the order with the highest correlation as the seed order. Then tabu search (TS) is used to improve these two algorithms. In addition, a new seed batching algorithm for a special situation is proposed, which needs to use the location information of each product to obtain more accurate batching results. Finally, an improved two-stage order picking algorithm is proposed to verify the actual picking effect of the batching results obtained from the different algorithms. The experimental results show that the two seed batching algorithms improved by TS are superior to the existing batching algorithms in batch quality for the general situation, and the second seed batching algorithm improved by TS performs better for large-scale problems. Moreover, the new seed batching algorithm is more efficient and effective. Full article

Parcel delivery networks have grown rapidly during the last few years due to the intensive evolution of online marketplaces. We address the issue of managing the operation of a network’s pick-up point, including the selection of the warehouse’s capacity and the policy for accepting orders for delivery. The existence of the time lag between order placing and delivery to the pick-up point is accounted for via modeling the order’s processing as the service in the dual tandem queueing system. Distinguishing features of this tandem queue are the account of possible irregularity in order generation via consideration of the versatile Markov arrival process and the possibilities of batch transfer of the orders to the pick-up point, group withdrawal of orders there, and client no-show. To reduce the probability of an order rejection at the pick-up point due to the overflow of the warehouse, a threshold strategy of order admission at the first stage on a tandem is proposed. Under the fixed value of the threshold, tandem operation is described by the continuous-time multidimensional Markov chain with a block lower Hessenberg structure for the generator. Stationary performance measures of the tandem system are calculated. Numerical results highlight the dependence of these measures on the capacity of the warehouse and the admission threshold. The possibility of the use of the results for managerial goals is demonstrated. In particular, the results can be used for the optimal selection of the capacity of a warehouse and the policy of suspending order admission. Full article

Data center architecture plays an important role in effective server management network systems. Load balancing is one such data architecture used to efficiently distribute network traffic to the server. In this paper, we incorporated the load-balancing technique used in cloud computing with power business intelligence (BI) and cloud load based on the queueing theoretic approach. This model examines a bulk arrival and batch service queueing system, incorporating server overloading and underloading based on the queue length. In a batch service system, customers are served in groups following a general bulk service rule with the server operating between the minimum value $\mathit{‘}\mathit{a}\mathit{’}$ and the maximum value $\mathit{‘}b\mathit{’}$. But in certain situations, maintaining the same extreme values of the server is difficult, and it needs to be changed according to the service request. In this paper, server load balancing is introduced for a batch service queueing model, which is the capacity of the server that can be adjusted, either increased or decreased, based upon the service request by the customer. On service completion, if the service request is not enough to start any of the services, the server will be assigned to perform a secondary job (vacation). After vacation completion based upon the service request, the server will start regular service, overload or underload. Cloud computing using power BI can be analyzed based on server load balancing. The function that determines the probability of the queue size at any given time is derived for the specified queueing model using the supplementary variable technique with the remaining time as the supplementary variable. Additionally, various system characteristics are calculated and illustrated with suitable numerical examples. Full article

This research investigated a single bulk server queuing model where service modes and server vacations are dependent on the number of clients. The server operates in three different service modes: single service, fixed batch service, and variable batch service. Modes will be determined by queue length. The service starts only when the minimum number of customers, say ‘a’, has accumulated in the queue. At this point, the server selects one of three service modes. Transitions between duty modes are permitted only at the beginning of a duty period. At the end of the service, the server can go on vacation if the queue length drops below ‘a’. When returning from vacation, if threshold ‘a’ is not reached, the server will remain inactive until it is reached. A special technique called the Supplementary Variables Technique (SVT) was used to determine the probability-generating function when estimating the queue size at a given time. Appropriate numerical examples exemplify the method developed in the paper. An optimal cost analysis was performed to set the threshold values for different server modes with the intention of minimizing the aggregate average cost. Full article

Nowadays, efficient spectrum usage is one of the most important design principles to take into account in wireless communications due to the exponential growth of mobile devices. In that sense, solutions such as Non-Orthogonal Multiple Access (NOMA) and cognitive radio (CR) have been proposed. In essence, NOMA allows some interference level by using non-orthogonal resource allocation with a tolerable increase in receiver complexity employing successive interference cancellation (SIC). In this work, a novel mathematical model of teletraffic for users performing accessment, simultaneously, by means of Orthogonal Multiple Access (OMA) and NOMA, is developed using a Markovian process that considers bursts of arrivals to model the access schemes. This novel procedure implies a closed-form solution of the proposed system compared to other works where these parameters are estimated assuming the moment generating function obtained with approximation models. The model is validated with a discrete event simulator, considering different scenarios and simulation conditions. The simulation results are in agreement with the mathematical solution proposed. Full article

This paper investigates the problem of processing jobs on unrelated parallel batch machines, taking into account job arrival times, machine deterioration effects, and variable preventive maintenance (VPM). To address this complex scheduling problem, this paper proposes a Self-Adaptive Artificial Bee Colony (SABC) algorithm, incorporating an adaptive variable neighborhood search mechanism into the algorithm. To verify the effectiveness of the proposed algorithm, we designed comparative experiments, comparing the SABC algorithm with the NSGA-III algorithm on problem instances of different scales. The results indicate that the SABC algorithm outperforms the NSGA-III algorithm in terms of solution quality and diversity, and this advantage becomes more pronounced as the problem scale increases. Full article

With the continuous development of the information industry, semiconductor manufacturing has become a key basic industry in the information age. Due to the demands of the process, there are more batch processes in the semiconductor manufacturing process, such as the aging test session of chips. In this paper, in the context of semiconductor manufacturing, we consider the unrelated parallel batch processing machine (UPBPM) scheduling problem in which jobs have different processing times, arrival times, sizes, and processing eligibility constraints, where the machines have different capacity constraints and the objective of minimizing the makespan. We propose the actor–critic algorithm, incorporating the Rolling Time Window (R-AC algorithm) to solve the UPBPM scheduling problem. Through simulation experiments, the R-AC algorithm outperforms the separate heuristic scheduling rules. Full article

There are various types of sharing economy services, such as ride-sharing and shared-taxi rides. Motivated by these services, we consider a single-server queue in which customers probabilistically select the type of service, that is, the single service or batch service, or other services (e.g., train). In the proposed model, which is denoted by the M+M(K)/M/1 queue, we assume that the arrival process of all the customers follows a Poisson distribution, the batch size is constant, and the common service time (for the single- and batch-service customers) follows an exponential distribution. In this model, the derivation of the sojourn time distribution is challenging because the sojourn time of a batch-service customer is not determined upon arrival but depends on single customers who arrive later. This results in a two-dimensional recursion, which is not generally solvable, but we made it possible by utilizing a special structure of our model. We present an analysis using a quasi-birth-and-death process, deriving the exact and approximated sojourn time distributions (for the single-service customers, batch-service customers, and all the customers). Through numerical experiments, we demonstrate that the approximated sojourn time distribution is sufficiently accurate compared to the exact sojourn time distributions. We also present a reasonable approximation for the distribution of the total number of customers in the system, which would be challenging with a direct-conventional method. Furthermore, we presented an accurate approximation method for a more general model where the service time of single-service customers and that of batch-service customers follow two distinct distributions, based on our original model. Full article

The objective of this study was to assess the health and welfare of 70 commercial broiler flocks (transport batches) in three distinct slaughterhouses based on various indicators including emaciation, dirty feathers (DFs), footpad dermatitis (FPD), hock burn (HB), breast burn (BB), breast blister, breast ulcer, ascites, septicemia/abnormal color, cellulitis, extensive traumatisms, dead on arrival (DoA) and condemnation rate. Assessment scales ranging from 0 (absence) to 2 (severe) were used for DFs, FPD, and HB, while a 0 (absence) to 1 (present) scale was applied to BB, breast blisters, and breast ulcers. The prevalence of total condemnation causes (emaciation, ascites, septicemia/abnormal color, cellulitis, and extensive traumatism) and DoA were recorded and presented in percentages. Three flocks presented condemnation rates higher than 4% and 11 flocks presented DoA rates higher than 0.5%. Twenty-one flocks achieved grade 1 (warning) for FPD and 14 achieved grade 2 for FPD (alarm). Extensive trauma was observed in 0.01% of the slaughtered animals, and no flock reached the threshold of 2%. Breast blisters and breast ulcers lesions were not observed in the studied flocks. The significant positive associations observed for the presence of severe footpad dermatitis (FPD2), severe hock burns (HB2), and breast burns (BB1) indicate simultaneous occurrences. Absences of hock burns (HB0) and breast burns (BB0) were also associated. Eleven houses that obtained the worst results for welfare indicators at slaughterhouses were audited. FPD, HB, DoA, and the condemnation rate were the most crucial indicators for identifying farms with inadequate welfare conditions. These indicators should be systematically integrated into the welfare monitoring of broilers in slaughterhouses. Audits conducted on farms detected some noncompliance with regulatory welfare standards and suggested improvements in environmental and structural conditions, as well as the reduction in stocking densities and improvements in the water systems. Full article