Search

Modern unmanned aerial vehicle (UAV) reconnaissance is widely used. UAV equipped with FPV camera can realize the reconnaissance of dense small objects with the help of object detection technology. However, it is difficult to detect people or vehicle objects in UAV overhead images because the pixels are small and densely distributed. In this paper, we propose an improved YOLOv7 UAV dense small object detection algorithm (DS-YOLOv7) to improve the UAV detection performance of dense small objects. SFN technology optimizes the fusion network to further improve the semantic information and location information of dense small objects. LDSPP is an optimized module for feature extraction of small objects. It pays more attention to edge information of small objects and reduces the rate of missing detection. Dimensionality reduction techniques focus on reducing model parameters to facilitate the deployment of algorithms on lightweight devices. The experimental verification on the public data set VisDrone2019 shows that mAP50 and mAP50-95 have increased by 4.3% and 3.3% respectively, F1 scores have increased by 3.81%, model volume has decreased by 23.3MB, parameters have decreased by 13 million, and the improved algorithm is more conducive to UAV deployment and dense small object detection.

In this paper, a fully tunable bandpass filter (BPF) with three states of filtering (single passband state, dual passband state and all-off state) is proposed, the proposed fully tunable BPF is cascaded by a tunable low pass filter section (LP) and a tunable high pass filter section(HP). By introducing a switchable dual-mode notch in the passband, the proposed BPF is capable of operating in single, dual passband and all-off state, demonstrating high flexibility in working mode. Tunable LP and HP filters with 7-order generalized Chebyshev response are designed to improve the roll-off rate and out-of-band rejection level of the BPF. The measured results show that the bandwidth of the BPF can be tuned from 0.25GHz to 2.69GHz (10.8:1), and the center frequency can be tuned from 2.9GHz to 4.6GHz with constant absolute bandwidth of 1GHz. Besides, high rejection level of out-of-band is realized in all working mode. The high flexibility in working mode makes the proposed fully tunable BPF very attractive in carrier aggregation scenarios.

In the process of rehabilitation treatment for stroke patients, rehabilitation evaluation is a significant part in rehabilitation medicine. Researchers intellectualized the evaluation of rehabilitation evaluation methods and proposed quantitative evaluation methods based on evaluation scales, without the clinical background of physiatrist. However, in clinical practice, the experience of physiatrist plays an important role in the rehabilitation evaluation of patients. Therefore, this paper designs a 5 degrees of freedom (DoFs) upper limb (UL) rehabilitation robot and proposes a rehabilitation evaluation model based on Belief Rule Base (BRB) which can add the expert knowledge of physiatrist to the rehabilitation evaluation. The motion data of stroke patients during active training are collected by the rehabilitation robot and signal collection system, and then the upper limb motor function of the patients is evaluated by the rehabilitation evaluation model. To verify the accuracy of the proposed method, Back Propagation Neural Network (BPNN) and Support Vector Machines (SVM) are used to evaluate. Comparative analysis shows that the BRB model has high accuracy and effectiveness among the three evaluation models. The results show that the rehabilitation evaluation model of stroke patients based on BRB could help physiatrists to evaluate the UL motor function of patients and master the rehabilitation status of stroke patients.

Cyber-physical-social systems (CPSS) have recently gained attention from researchers due to their combination of cyber, physical, and social spaces. Modeling and Analysis of Real-Time and Embedded systems (MARTE) is a Unified Modeling Language (UML) extension profile that supports the specification, design, and verification of Real-Time Embedded Systems (RTES). While MARTE Statecharts can assist in describing CPS, it does not model the uncertainty within a CPSS environment. To enhance the accuracy of CPSS analysis, we propose the stohMCharts (stochastic hybrid MARTE statecharts) modelling framework as an extension of MARTE statecharts for modelling and analyzing stochastic hybrid systems. stohMCharts can model CPSS in a unified manner. Additionally, based on the mapping rules and algorithms, we have developed a tool to convert models built in stohMChart language into Networks Stochastic Hybrid Automata (NSHA) which can be verified by statistical model checker UPPAAL-SMC. We demonstrate the efficiency and accuracy of the framework by applying it to one autonomous driving scenarios.

This paper presents a method for building a programming platform for ternary optical computer(TOC). Firstly, the reasons why the existing programming platform can not be directly applied to the ternary optical computer are analyzed. Then, the theoretical basis and core technologies for building the programming platform of the ternary optical computer are given, including: building a model—simple structured data type computer to express the application characteristics of the ternary optical computer, building an operation-data file containing data and computational requirements, expanding the operation-data file transfer instructions. According to our proposed theory, the implementation mechanism of the TOC programming platform is constructed. Finally, the effectiveness of the programming platform is verified by experiments. The programming platform simplifies the application of the TOC and bridges the gap between the user and the TOC.

The computer system of the traditional storage architecture has many bottlenecks in massive data transmission, analysis, processing, etc., especially the frequent data migration or copying problem between memory and external storage, which is the most prominent and restricts the full play of CPU performance. To address this, Professor Y. Jin proposed a new solution called dual-space storage architecture based on non-volatile random-access memory (NVRAM) and a data security technique called non-closable window. For the new storage architecture, a corresponding underlying software management model is proposed in this paper. The design scheme of the memory shifting system in this model is introduced in detail, and the feasibility of the scheme is verified through software simulation experiments.

For triple-level or quad-level 3D NAND flash memory, narrowing the Vth distribution of each state without influencing page program performance is one of the challenges. Considering this challenge, a novel adaptive pulse programming (APP) scheme was proposed. The proposed APP scheme adopted additional verify operations to separate the cells with different programming speed. It enhanced the program effect of slow cells by using increasing programming step voltage, and prevented the fast cells from over programming by using shorter programming pulse width through controlling the voltage of bitline. Compared with general incremental step pulse programming scheme, experimental results on TLC 3D NAND flash showed that, APP scheme could reduce the Vth distribution width of cells by around 15% and at the same time save the program time.

In this work, a cooperative optical Internet of Underwater Things (IoUT) system with hybrid decode-amplify-forward (HDAF) strategy is first proposed and investigated over the aggregated underwater wireless optical communication (UWOC) channel. The impacts of absorption, scattering and the misalignment caused by spatial spreading in the sea, which are modeled by the beam spread function (BSF), as well as the oceanic turbulence on the underwater optical links are all included to describe the practical channel characteristics. With the help of Gauss-Hermite and Gauss-Legendre quadrature numerical methods, the closed-form expressions of the average bit error ratio (ABER) and outage probability for this cooperative optical HDAF-IoUT system are derived and verified by the Monte Carlo (MC) simulations. Furthermore, numerical analyses are offered to explore the effects of water type, turbulence strength, relay location and power allocation scheme on this HDAF-IoUT system. The performance of this optical system over the mixture Exponential Generalized Gamma (EGG) channel is also given for comparison. The obtained results indicate that the optical HDAF-IoUT system is superior to the IoUT system with fixed amplify-and-forward (FAF) strategy, and has a better performance when the relay is close to the middle position for a fixed power allocation scheme. This work is beneficial for the cooperative system design in IoUT network.

Vehicle counting and traffic volume estimation on traffic videos has gained extensive attention from multimedia and computer vision communities. Recent vehicle counting and volume estimation methods, including detection based and time-spatial image (TSI) based methods have achieved significant improvements. However, how to balance the accuracy and speed is still a challenge to this task. In this paper, we design a fast and accurate vehicle counting and traffic volume estimation method. Firstly, traffic videos are converted to TSIs and we annotate the vehicle locations in TSIs manually. Then, we design a simple TSI density map estimation network which utilizes attention mechanism to strengthen the features in the traffic locations for vehicle counting. Finally, we use the parameters obtained from the vehicle counting network to further estimate the traffic volume. Experiments on UA-DETRAC dataset demonstrate that the vehicle counting network not only takes a balance between counting accuracy and speed, but also well estimates the traffic volume when the video data is insufficient.

Face alignment is a common technology in face recognition and face verification field. Previous works mostly pay attention to improving the accuracy of prediction and ignored the practicability of the method. In this paper, we aim at providing a two-stage face alignment network for mobile platform. Firstly, the network was trained with residual label which is the difference between ground truth and mean shape. Secondly, the input data in the second stage is composed of the original data and generated heatmap which enriched the data types. Finally, a new loss function is used to enhance the convergence of local region. Experimental results show that our method not only provides high precision but also improve the real-time processing performance on the mobile platforms.

The emission uniformity of an annular knife-edged cathode in a coaxial diode with a focusing electrode and operating in a low macro electric field has been investigated. It was found that the emission uniformity deteriorated as the cathode width increased from 0.5 mm to 2.0 mm. To improve the emission uniformity, a grooved graphite cathode was prepared by a laser micro-etching treatment. Experimental results demonstrated that the emission threshold for the grooved cathode may be reduced and thus the delay in explosive emission can be decreased. Visual inspection of photographs of the cathode plasmas operating under different guiding magnetic fields (GMFs) was used to confirm improvements in emission uniformity. Even under a low GMF of 0.21 T, good emission uniformity was realized.

With the increase in the number of live TV channels, audiences must spend increasing amounts of time and energy deciding which shows to watch; this problem is called information overload, and recommender systems (RSs) are effective methods for addressing such problems. Due to the high update rates and low replay rates of TV programs, the item cold-start problem is prominent, and this problem seriously affects the effectiveness of the recommender and limits the application of recommendation algorithms for live TV. To solve this problem better, RSs must consider information in addition to the time slot strategy, which relies on experience. At present, no methods make good use of viewing behavior records. Therefore, in this paper, we proposed a viewing environment model called DeepTV that considers viewing behavior records and electronic program guides and includes a feature generation process and a model construction process. In the feature generation process, we defined seven key features by clustering viewing time, distinguishing positive and negative feedback, capturing continuous viewing preference and introducing the remaining time proportion of candidate programs. We normalize the continuous features and add powers of them. In the model construction process, we regard the live TV recommendation task as a classification problem and fuse the above features by using a neural network. Finally, experiments on industrial datasets show that the proposed model significantly outperforms baseline algorithms.

With the development of industrial Internet and artificial intelligence, data fusion in cross-domains and cross-layers have become an inevitable trend. Most of the data fusion involved in the production process of hot rolling are concentrated on the level of sensors, Internet of Things (IoT) and the Internet; but human data are not well integrated. In order to avoid the human factor from becoming the bottleneck of the entire production schedule, this paper proposes a ternary data fusion model based on reinforcement learning algorithm. The related data source from human-cyber-physical space includes: social network, Internet and IoT. By merging the ternary data, a variety of data (including humans') can be quickly calculated to obtain better and faster decisions. In order to achieve automated fusion from ternary data, this paper proposes a method based on reinforcement learning: firstly, the domain ontology used for associating ternary data is reduced and tessellated (dimension reduction), and then the reinforcement learning model is used to form “the new ontology”. Compared with resource-intensive global calculations (which may cost a few days), the new method can complete the calculations in minutes. This means that the new method optimizes the data source required for decision-making and improves the efficiency. Finally, the production scheduling of hot rolled steel is used as an example to verify the feasibility of the proposed method.

When there are too many people in large shopping malls, crowd congestion accidents are likely to occur. To ensure the rapid and safe evacuation of indoor crowds, this paper uses crowd density maps to determine the location of crowded areas and uses an improved ant colony algorithm to optimize the evacuation route from this location to the exit. First, a crowd density map is generated from the collected image data by the improved multiscale convolutional neural network algorithm, and the location of the high-density crowd is determined as the initial location. Then, the pheromone volatility coefficient $\rho $ is measured through adaptive adjustment by using the exponential decline method and the introduction of elite ants to optimize and update the ant colony pheromone to improve the ant colony algorithm, and the optimal evacuation route from the location of the crowded area to the exit is obtained. The research in this paper uses Beijing Xidan Joy City as an example. The results show that the method in this paper can optimize evacuation routes and reduce the turning points of the evacuation route by 25% and reduce the route length by 10%. Therefore, it can be seen that the proposed method can achieve the optimal evacuation path with the shortest distance and the least turning points, which has feasibility and practicability.

Spatiotemporal data fusion is an effective way of generating a dense time series with a high spatial resolution. Traditionally, the spatiotemporal fusion models, especially the popular ones such as the spatial and temporal adaptive reflectance fusion model, require at least three images as input, i.e., a coarse-resolution image on the target date and a pair of fine- and coarse-resolution images on the reference date. However, this cannot always be satisfied, as the high-quality coarse-resolution image on the reference date may be unavailable in some application scenarios. This led to efforts to achieve data fusion only using the other two images as input. In this article, we proposed an effective strategy that can be combined with any spatiotemporal fusion model to accomplish the fusion with simplified input. To confirm the validity of the method, we comprehensively compared the fusion performances under the two input modalities. In total, 38 tests were conducted with Moderate Resolution Imaging Spectroradiometer (MODIS), Landsat, and Sentinel-2 land surface reflectance products. Results suggest that by applying the proposed method, the fusion performance with only two input images is comparable or even superior to that with three input images. This article challenges the stereotype that spatiotemporal data fusion strictly needs at least three input images. The proposed method extends the application scenarios of spatiotemporal fusion, and creates opportunities to fuse sensors with barely overlapping temporal coverages, such as the Landsat 8 Operational Land Imager and the Sentinel-2 MultiSpectral Instrument.

In this paper, we investigate an energy harvesting wireless body area network (WBAN) with relay cooperation, where the destination nodes and the relay simultaneously harvest energy from the radio frequency (RF) source, then the destination nodes transmit data to the source by maximum ratio combining (MRC) transmission mode. We study the optimal design for relay power splitting ratio in each relaying sub-slot and the destination nodes power allocation to maximize the sum-throughput with the proposed protocol. The optimization problem is divided into two cases, destination node power limit (DPL) case and relay power limit (RPL) case. In essence, the problem is a joint-objective optimization and is solved by the Lagrangian multiplier method. Simulation results show that our proposed optimal method can greatly improve the sum-throughput compared with conventional mean power allocation (MPA) method and mean time allocation (MTA) method. Moreover, a significant sum-throughput promotion is achieved on the RPL case over the DPL case.

Traffic signs recognition (TSR) is an important part of some advanced driver-assistance systems (ADASs) and auto driving systems (ADSs). As the first key step of TSR, traffic sign detection (TSD) is a challenging problem because of different types, small sizes, complex driving scenes, and occlusions. In recent years, there have been a large number of TSD algorithms based on machine vision and pattern recognition. In this paper, a comprehensive review of the literature on TSD is presented. We divide the reviewed detection methods into five main categories: color-based methods, shape-based methods, color- and shape-based methods, machine-learning-based methods, and LIDAR-based methods. The methods in each category are also classified into different subcategories for understanding and summarizing the mechanisms of different methods. For some reviewed methods that lack comparisons on public datasets, we reimplemented part of these methods for comparison. The experimental comparisons and analyses are presented on the reported performance and the performance of our reimplemented methods. Furthermore, future directions and recommendations of the TSD research are given to promote the development of the TSD.

This paper investigates the dependence of the properties of the spatial harmonics on the overmoded ratio of the corrugated waveguide operating in TM01 at 30 GHz with the consideration of the effects of the ripple shape. It is found that as the overmoded ratio grows, the electric fields concentrate towards the ripple surface, which weakens the enhancement of the power handling capacity caused by augmentation of the overmoded ratio. As the overmoded ratio grows, the ratio between the field amplitudes of the -1st spatial harmonic and the fundamental harmonic increases monotonically. Therefore, the total electric fields composed of the spatial harmonics become the spatial beating-wave with the single frequency, whose amplitudes vary along z-axis with the spatial period determined mainly by the -1st spatial harmonic and the fundamental harmonic. Researches on coupling impedances show that with the same overmoded ratio, the corrugated waveguide consisting of the improved rectangular ripples provides better synchronous coupling for the wave-beam interaction than that of the sinusoidal ripples does. Moreover, it is better to choose the fundamental harmonic close to the light line as the synchronous wave for the wave-beam interaction in the low magnetic field. In that case, even if the electron beam keeps far away from the ripple surface, the synchronous wave still provides strong enough coupling for the electron beam.

In general, reverse logistics network design has been driven by a need to reduce costs and to improve customer service without considering its environmental impact. In this paper, we address a reverse logistics network design problem regarding carbon emission. The problem is formulated as a bi-objective, mixed-integer, and nonlinear programming model under various operation technologies and transport modes in the truck tire remanufacturing industry. An improved non-dominated sorting genetic algorithm II (NSGA-II) solves this NP-hard problem with bi-objectives. The numerical cases demonstrate the validation of the proposed model and the advantage of improved NSGA-II over the basic NSGA-II. Furthermore, we conducted extensive sensitivity analysis, and several managerial insights are derived.

This paper optimizes the energy efficiency performance by joint time and beamforming weights allocation in a wireless body area network (WBAN), which consists of a multi-antenna access point (AP), in particular, the AP intends to broadcast radio frequency (RF) power to several single-antenna on-body sensors and receives physiological information from them synchronously. Different path loss and shadowing values are considered in each sensor's channel model to be more practical. In this paper, maximal ratio transmission (MRT) technique and zero-forcing (ZF) technique are applied in RF energy transmission and information decoding, respectively. Considering the signal-to-inference-plus-noise ratio (SINR) threshold of each sensor, the total rate-energy ratio is formulated as a nonconvex optimization problem in each time block, we transform the nonconvex optimization problem into a convex optimization problem and solved it by convex optimization tools. We investigate the energy efficiency performance and reliability performance of the optimal solutions, and numerical results demonstrate the effectiveness of the optimal solutions.

Data privacy protection is crucial to cloud computing since privacy leakage may prevent users from using cloud services. To ensure data privacy, we propose PriGuarder, a novel privacy-aware access control method. This method spans the three stages of a cloud service, i.e., user registration, data creation, and data access. At each stage, users can choose two modes to interact with the cloud service provider, i.e., direct or indirect. With the indirect mode, an attribute fuzzy grouping scheme is introduced to ensure user identity privacy and attribute privacy in all the three stages. Furthermore, exploiting data encryption and timestamp techniques, new access control protocols are proposed to regulate interactions between users and the cloud service provider. We illustrate the use of our method in the context of Amazon S3. Theoretical analysis and comprehensive simulation experiments have been conducted, which demonstrate the efficacy of PriGuarder.