Abstract Under the carbon tax policy, vehicle remanufacturing has become popular, which threatens new market. Facing complicated competitive environment, automobile manufacturer always adjusts product modular design to deal with challenges from internal and external remanufacturing. Currently, considering impacts of market competitions on enterprise's operation management, how policy affects is still uncertain. Thus, we construct a duopoly competition model consisting an remanufacturer aim...

To address the challenges of infrared dim small target detection under sky cloud backgrounds on edge devices, this study proposes a lightweight sequential-differential-frame-based network (LSDF-Net) with optimization and deployment heterogeneous FPGA JFMQL100TAI. The enhances performance through sequential-differential inputs, false-alarm-object learning, multi-anchor assignment while reducing computational overhead acceleration convolutional pooling. Deployment efficiency is improved via...

Routing protocols based on topology control are significantly important for improving network longevity in wireless sensor networks (WSNs). Traditionally, some WSN routing distribute uneven traffic load to nodes, which is not optimal longevity. Differently conventional protocols, we propose a dynamic hierarchical protocol combinatorial optimization (DHCO) balance energy consumption of nodes and improve For each node, the DHCO algorithm obtains route by establishing feasible set instead...

Fruit freshness detection by computer vision is essential for many agricultural applications, e.g., automatic harvesting and supply chain monitoring. This paper proposes to use the multi-task learning (MTL) paradigm build a deep convolutional neural work fruit detection.

In this letter, we consider a cognitive wireless powered communication network (CWPCN), with secondary (WPCN) that has ability to coexist primary network. To tackle the unfairness resource allocation issue in CWPCN, extend proportional fair scheduler category of By utilizing time division-based “harvest-then-transmit” protocol, establish an optimization problem for optimal slot allocation, which maximizes bandwidth utility function fairness, under constraints and interference. solve problem,...

Along with the developments of deep learning, many recent architectures have been proposed for face recognition and even get close to human performance. However, accurately recognizing an identity from seriously noisy images still remains a challenge. In this paper, we propose carefully designed neural network coined noise-resistant (NR-Network) under noise. We present multi-input structure in final fully connected layer NR-Network extract multi-scale more discriminative feature input image....

Improving tracking quality and extending network lifespan are two main objects for target tracking, which usually contradictory due to limited energy of sensor nodes in wireless networks. This article incorporates this contradiction into a problem multi-objective optimization networks where multiple scheduled collaborative by adopting the unscented Kalman filter algorithm. We propose an effective scheme extend while guaranteeing preset quality. More specifically, with regard practical...

Target detection is an important issue in the unattended ground sensors. In this paper, inspired by idea of subspace-based direction arrival estimation algorithms, a new target algorithm called (SBTD) proposed to detect moving targets. The SBTD employs SNR acoustic signals decide whether targets are exiting or not. Although has good performance, its cost maybe little high for sensors with low-cost hardware and long-term monitoring. To relieve cost, we propose hierarchical scheme develop...

We consider a full-duplex wireless powered communication network (WPCN) with one hybrid access point (H-AP) and set of distributed users, where downlink energy broadcasting is employed at H-AP the same time, uplink information transmission takes place users in time-division multiple manner. extend proportional fair scheduler to this category when dealing "doubly near-far problem," far away from achieve low throughput but suffer both harvested high data power consumption. jointly optimize...

Reliability analysis for structural systems relies on an accurate surrogate model. Currently, several multiple Kriging methods are utilized to calculate the failure probability. However, existing reliability have generally not incorporated model form selection into modeling process, resulting in inaccurate probability of estimates. To overcome shortcomings methods, this article presents adaptive Bayesian averaging-based method. The proposed method utilizes averaging incorporate ensemble...

In this paper, we propose an effective and robust decentralized tracking scheme based on the square root cubature information filter (SRCIF) to balance energy consumption accuracy in wireless camera sensor networks (WCNs). More specifically, regarding characteristics constraints of nodes WCNs, some special mechanisms are put forward integrated scheme. First, a approach is adopted so that can be implemented energy-efficiently steadily. Subsequently, task cluster dynamically selected by...