Search

In this paper we report epoxy molding compound lead frames (EMC-LFs) with encapsulated silicone as a simple and inexpensive packaging for AlGaN-based ultraviolet-B (UVB) light-emitting diodes (LEDs) displaying high light extracting efficiencies (LEE) and long operation lifetimes. The convex surfaces and beveled shapes obtained after curing the encapsulated silicone surrounding the UVB-LED chips significantly enhanced the light output power (LOP). With silicone present inside the EMC-LFs having bonding cavity diameters of 1.7 and 1.45 mm, the LOPs of the UVB-LEDs improved by 26 and 42%, respectively; reliability tests performed over a period of 1000 h revealed, however, that the LOPs decreased to 70 and 71%, respectively, of their initial values, but no cracks appeared in the silicone during such long-term operation. Thus, the stability of silicone-encapsulating EMC-LFs for UVB-LEDs was acceptable. When compared with AlN-based direct plating copper ceramic lead frames (AlN-DPC-LFs), our proposed packaging structure and method have the potential to lower the manufacturing cost of UVB-LEDs.

The emergence of blockchain technology has significantly changed the underlying infrastructure of existing information technology and will fundamentally affect the production modes of enterprises. However, because the application of blockchain is still in its infancy, it is difficult for an enterprise to develop a comprehensive assessment of various types of blockchain service providers in the market. Hence, enterprises need scientific decision tools to estimate which blockchain service provider is appropriate. However, few studies have focused on this phenomenon. Therefore, to address this challenge, this investigation proposes a novel integrated multi-attribute group decision-making (MAGDM) method to help enterprises estimate which blockchain vendor is more appropriate by considering more comprehensive influence factors. The proposed method is defined in an intuitionistic fuzzy environment and integrates entropy and the best-worst method (BWM) for comprehensive weighting of decision makers (DMs), subjective criteria and objective criteria in the decision-making process to make the decision results more reliable and reasonable. A numerical example and comparison are provided to illustrate the practicability and usefulness of the method. This study enriches the theory and methodology of blockchain technology and MAGDM analysis.

The noise of contra-rotating propellers contributes a major part to the underwater vehicle. The special noise properties often become an important basis for detecting and identifying targets. This paper establishes the numerical simulation and calculation approach on the radiated noise properties of contra-rotating propellers, which was set up based on the theory of acoustic analogy and the large eddy simulation approach, and then the numerical simulation results are verified. Taking the DTMB contra-rotating propellers which consist of DTMB3689 and DTMB3849 as an example, the numerical calculation of the hydrodynamic performance of the contra-rotating propellers is carried out based on the solving method of Reynolds stress turbulence model and the results agree well with the experimental results. The disk velocity distribution, blade pressure distribution and hydrodynamic wake distribution of the contra-rotating propellers are analyzed. Analyzing the acoustic signature of contra-rotating propellers shows that the low frequency line spectrum not only reflects the multiplicative frequency feature, but also the additive frequency feature, and the relationship between the radiated noise of the contra-rotating propellers and its inherent structure and its motion state is correlated.

Food safety and quality examination has received close attention from general public in recent years. One of examples is the freshness of pleurotus eryngii, which plays an important role in its economic values. The estimation of its freshness could not be based on the number of storage days because fungi could normally keep alive for a while after harvest depending on storage environment. With advances of hardware and software, hyperspectral technologies shed some light on prediction of its nonlinear decay trend. This paper proposed a spectral derivative analysis to improve the temporal accuracy of previous works [5] from weeks to days. Then, the long short-term memory neural network was utilized to predict the decay trend based on the data of beginning few days. The experimental studies demonstrated that the prediction trends were close to the real ones.

In this paper, we combined hyperspectral imaging techniques and deep neural networks (DNN) to detect Fusarium wilt on Phalaenopsis. Spectral angle mapper (SAM) and constrained energy minimization (CEM) were used to find abnormal areas. Band selection (BS) methods include Harsanyi-Farrand-Chang (HFC), band priority (BP) and band decorrelation (BD) were applied to get effective bands. The results showed that, on the fifth day of Phalaenopsis infection, the best accuracy rates for detecting Fusarium wilt using VNIR and SWIR hyperspectral imaging were 93.5% and 94.9%, respectively. In most cases, the accuracy of using DNN is better than using support vector machine (SVM).

Mechanical faults is one of the main faults that occur in the circuit breaker. The vibration signal generated during the opening and closing process of the circuit breaker can effectively reflect its operating state. In this paper, the vibration signal of the circuit breaker under normal and fault conditions is collected by the self made online monitor of the circuit breaker, and the vibration signal is analyzed and processed by using autoencoder neural network and support vector machine. The experimental results show that the autoencoder neural network can effectively extract the characteristics of the vibration signal of the circuit breaker; the support vector machine is used to diagnose the signal, and the high accuracy is obtained on the experimental samples.

This paper presents a novel aperture coupled patch array-fed dual-band transmitarray antenna with frequency ratio of 1.7 (10 GHz and 17 GHz). First, by introducing square loop slot and cross dipole slot, the element demonstrates over 75% phase coverage. Then, two aperture coupled patch array antennas are designed to illuminate the aperture, providing advantages of being low-profile and lightweight. Full-wave simulations show that realized gain of 22.3 dBi and 23.3 dBi, and 1-dB gain bandwidth of 3% and 5.3% are achieved in 10 GHz band and 17 GHz band, respectively.

To deliver video in a high quality across various network conditions, adaptive bitrate (ABR) algorithms dynamically select bitrate for each chunk according to perceived network rate and buffer occupancy. Unfortunately, though ameliorating the quality of chunks with dynamic scenes can obtain more QoE gain than the ones with static scenes, current ABR algorithms generally aim to maximize the average bitrate rather than perceptual quality, resulting in the QoE degradation. To address this issue, we propose a dynamic-chunk quality aware adaptive bitrate scheme via apprenticeship learning named DAVS, in which higher quality is chosen for the dynamic chunks without decreasing the quality of static chunks excessively. The experimental results show that DAVS enhances the quality of dynamic chunks and greatly improves the overall QoE compared with the state-of-the-art ABR algorithms.

This paper proposes Adaptive Batch Sizing (ABS) for online federated learning. ABS is an iteration process-efficient solution that adaptively adjusts batch size of the training process at edge nodes. Preliminary results show that ABS maintains training efficiency and accuracy, compared with existing iteration round-efficient solutions.

In this paper, we propose a method to inspect the quality of Phalaenopsis by using hyperspectral imaging techniques. Phalaenopsis is easy to get infected with Fusarium wilt. We use the k-means clustering method to find out that the reflection spectrum of Phalaenopsis stem changes. The methods of the Spectral Angle Mapper (SAM) and Constrained Energy Minimization (CEM) are then used to find the area of the infected area. The Harsanyi, Farrand and Chang (HFC) methods and virtual dimensions (VD) are used to estimate the amount of spectrum required for band selection (BS). Band priority (BP) is used to calculate the priority of each band, and band de-correlation (BD) will remove band data with high correlation with each other. Then use the support vector machine (SVM) to detect Phalaenopsis wilt. The detection accuracy of VNIR and SWIR is 0.81 and 0.86, respectively, with band selection.

In order to study the properties of radiation noise of single-propeller and contra-rotating propellers, the numerical simulation and computing was accomplished by using RNG turbulence model, LES turbulence model, FW-H acoustic analog equation and dynamic grid model. The open water performance of single propeller and contra-rotating propellers is calculated respectively, and the calculated results are in good agreement with the published results. Then the flow field properties of single propeller and contralateral propeller are compared and analyzed, on this basis, acoustic signature analysis and computing on properties of radiation noise from underwater single-propeller and contra-rotating propellers was accomplished, the properties of pulsating sound pressure at the monitoring point are solved. From the computing results, it can be seen that there are line spectral components related to front and rear blade frequency in the noise power spectrum, the low frequency line spectrum of contra-rotating propellers is more abundant than that of single propeller.

Motion blur is one of the most common degradation artifacts in dynamic scene photography. This paper reviews the NTIRE 2020 Challenge on Image and Video Deblurring. In this challenge, we present the evaluation results from 3 competition tracks as well as the proposed solutions. Track 1 aims to develop single-image deblurring methods focusing on restoration quality. On Track 2, the image deblurring methods are executed on a mobile platform to find the balance of the running speed and the restoration accuracy. Track 3 targets developing video deblurring methods that exploit the temporal relation between input frames. In each competition, there were 163, 135, and 102 registered participants and in the final testing phase, 9, 4, and 7 teams competed. The winning methods demonstrate the state-of-the-art performance on image and video deblurring tasks.

Reducing the power consumption and maintaining the Flow Completion Time (FCT) for the Quality of Service (QoS) of applications in Data Center Networks (DCNs) are two major concerns for data center operators. However, existing works either fail in guaranteeing the QoS due to the neglect of the FCT constraints or achieve a less satisfying power efficiency. In this paper, we propose SmartFCT, which employs Software-Defined Networking (SDN) coupled with the Deep Reinforcement Learning (DRL) to improve the power efficiency of DCNs and guarantee the FCT. The DRL agent can generate a dynamic policy to consolidate traffic flows into fewer active switches in the DCN for power efficiency, and the policy also leaves different margins in different active links and switches to avoid FCT violation of unexpected short bursts of flows. Simulation results show that with similar FCT guarantee, SmartFCT can save 8% more of the power consumption compared to the state-of-the-art solutions.

There is plenty of human-machine joint decision-making scenarios in the real world applications, such as driving assistant, suspect identification, medical diagnosis, etc. Existing algorithms propose that machine should give a rejection option when having a high risk or uncertainty score so that the input can be passed to human to make the decision. This is an interesting algorithmic model of human-machine collaboration, but implicitly assumes that humans are more trustworthy than machines. Such an assumption ignores the bias and inconsistency of human, especially in scenarios where machines have superior recognition ability than humans. In this work, we investigate the human-machine joint decision-making problem in distorted surveillance videos, where machines experimentally prove to be comparable to human beings in tolerance to distortion, sometimes even stronger. We propose a new human-machine joint decision-making framework by considering both the confidences of machine and human. To obtain the confidence of human, we build a real-life human decision-making database and propose a deep neural network to estimate human's confidence. Then, confidence alignment method and decision rule are proposed to further output the final decision. Experiments demonstrate that the proposed framework can make less human intervention and more accurate decisions in several human-machine joint decision-making scenarios.

To solve large scale optimization problem, a new evolutionary algorithm using variable grouping and allocating computational resource based on contribution is proposed in this paper. First, we propose a new grouping scheme in which we adopt an existing and effective one called FBG for separable problems and design a new grouping scheme called a self-adaptive grouping (SAG) method for non-separable problems. By using these two schemes, any large scale problem can be effectively divided into small scale sub-problems. Second, in order to solve the sub-problems efficiently by making full use of limited computational resource, we design an efficient resource allocation method (ERA) which can reasonably allocate the resource to each sub-problem according to its contribution. The more contribution a sub-problem gives to whole problem, the more resource the sub-problem will get. Based on these, a new evolutionary algorithm is proposed. Finally, the experiments are conducted on widely used benchmark suite CEC'2010, and the proposed algorithm is compared with some state-of-the-art algorithms. The experimental results show the competitive performance of the proposed algorithm to solve these problems.

In this paper, a fault analysis and prediction of aircraft equipment is proposed via the construction of association rules and the analysis of Weibull Distribution. Firstly, for the recorded data in the airborne detection system, the prefix path graph is introduced to improve the Apriori algorithm to further mine the association rules between the fault equipments with low and high supports. Then, the first failure time of the equipment with high support is recorded, and the reliability analysis model of the equipment is established according to the Weibull distribution. Finally, the results of reliability analysis model obtained from the association rules provide the theoretical basis for the maintenance program of aircraft. The experiments in aircraft airborne detection system verifies the effectiveness and practicability of the proposed method.

The major challenge of Real Time Protocol is to balance efficiency and fairness over limited bandwidth. MPTCP has proved to be effective for multimedia and real time networks. Ideally, an MPTCP sender should couple the subflows sharing the bottleneck link to provide TCP friendliness. However, existing shared bottleneck detection scheme either utilize end-to-end delay without consideration of multiple bottleneck scenario, or identify subflows on switch at the expense of operation overhead. In this paper, we propose a lightweight yet accurate approach, EMPTCP, to detect shared bottleneck. EMPTCP uses the widely deployed ECN scheme to capture the real congestion state of shared bottleneck, while at the same time can be transparently utilized by various enhanced MPTCP protocols. Through theory analysis, simulation test and real network experiment, we show that EMPTCP achieves higher than 90% accuracy in shared bottleneck detection, thus improving the network efficiency and fairness.

Recently, deep learning-based techniques have shown great potential for image inpainting tasks thanks to the powerful representation ability of convolutional neural networks. However, current approaches failed to inpaint satisfactorily in both global structures and local textures, because they only use simple dilated convolution which hard to encode comprehensive deep features. In this paper, we propose Interleaved Zooming Network to tackle this issue. The network contains two branches in encode stage, major branch maintains the size of input features, zoom-out branch convolve and downsample the features by 4 times to perceive larger visual field of input signals. These two branches communicate in an interleaved manner, that is, each branch receive signals from previous layers in both branches. We empirically demonstrate that this interleaved zooming structure can help to generate better global structures and local details of missing regions of images. Compared with state-of-the-art deep learning-based inpainting methods, our approach provides more than 2dB gain on Places2 dataset with irregular mask.

In the data center network, a packet-level load balancer such as random packet spraying (RPS) achieves high throughput by spraying data packets to all transmission paths, which easily suffers from the packet out-of-order problem under network asymmetry. While state-of-the-art network coding schemes can mitigate the issue, too many encoded redundant packets introduced by the network coding will cause extra traffic overhead, larger queueing delay and even TCP time out. In this paper, we propose OPportunistic Encoded Redundant (OPER), a middle-layer design upon existing coding schemes to mitigate the curse of redundant packets. Specifically, OPER uses opportunistic redundant packets which are replaceable by the data packets in the switches under heavy congestion. OPER is implemented as a shim layer between TCP and IP layers at end-hosts and a loadable plugin at switches, leaving existing TCP/IP protocols unmodified. The testbed and NS2 experiments show that, OPER reduces the average flow completion time by up to 71% compared with the state-of-the-art multipath coding schemes.

Fusarium wilt on Phalaenopsis is a disease that makes farmers suffer seriously. Although Phalaenopsis does not die immediately with Fusarium wilt, it seriously decreases the quality that buyers cannot accept. In this paper, we introduce an emerging method to detect Fusarium wilt at the base of Phalaenopsis stems. The detection model divides Phalaenopsis samples into two categories, healthy and infection. The band selection (BS) processing technique based on band prioritization (BP) is applied to extract significant bands and eliminate redundant bands. Subsequently, some algorithms which are constrained energy minimization (CEM), spectral information divergence(SID) and SeQuential N-FINDER to detect the Fusarium wilt, and we hope the research would help farmers decrease their losses.

Acceleration and compression on Deep Neural Networks (DNNs) have become a critical problem to develop intelligence on resource-constrained hardware, especially on Internet of Things (IoT) devices. Previous works based on channel pruning can be easily deployed and accelerated without specialized hardware and software. However, weight-level sparsity is not well explored in channel pruning, which results in relatively low compression rate. In this work, we propose a framework that combines channel pruning with low-rank decomposition to tackle this problem. First, the low-rank decomposition is utilized to eliminate redundancy within filter, and achieves acceleration in shallow layers. Then, we apply channel pruning on the decomposed network in a global way, and obtains further acceleration in deep layers. In addition, a spectral norm-based indicator is proposed to balance low-rank approximation and channel pruning. We conduct a series of ablation experiments and prove that low-rank decomposition can effectively improve channel pruning by generating small and compact filters. To further demonstrate the hardware compatibility, we deploy the pruned networks on the FPGA, and the networks produced by our method have obviously low latency.

Artificial intelligence (AI) is enabling the automated analysis of large amounts of image/video data, boosting the speed of multimedia data processing remarkably. Meanwhile, Image Quality Assessment (IQA) plays an important role in developing automatic analysis methods. To ensure the effectiveness of AI, images in multimedia applications should be considered for visual examination by both human and machine. Therefore, it is significant to understand the differences between human's and AI's perception of semantic distortion. However, little work has been done due to the lack of data from human on the semantic level. In this paper, we first propose a semantic database (SID) based on the surveillance scenarios, by collecting subjective average recognition rates of 3 semantic targets (face, pedestrian, license plate) with 3 types of distortion (JPEG Compression, BPG Compression, Motion Blur). Then, we present a detailed analysis of how human and AI perceive semantic distortion differently. Experimental results show that AI is stronger in tolerance to distortion than human beings on average, while weaker at generalization and stability. It is also implied in the experiments that existing IQA methods are not effective enough at judging the semantic distortion.

Hyperspectral image feature extraction and classification is an important part in remote sensing field, and convolutional neural networks (CNNs) show their advantages in it. However, it is still affected by the lack of training samples, which may lead to the occurrence of overfitting. This issue gets more serious when dealing with high-dimensional data such as HSI. And the single scale of the input data ignores the abundance of multi-scale spatial information. In response to the above problems, we propose a multi-scale convolutional neural network method. And the method can extract multiple scale areas centered on the pixel to be classified. Then it adjusts the areas to the same size and inputs the adjusted data into the standard convolutional neural network for training and testing. Experimental results indicate that proposed method boost the performances in terms of classification accuracies.

Deep Neural Networks (DNNs) have shown superior performance on a variety of artificial intelligence problems. Reducing the resource usage of DNN is critical to adding intelligence on Internet of Things (IoT) devices. Channel pruning based network compression shows effective reduction simultaneously on storage, memory and computation without specialized software on general platforms. But limited by pruning flexibility, channel pruning methods have relatively low compression rate for a given target performance. In this paper, we demonstrate that channel pruning becomes more robust to decision errors by reducing the granularity of filters. Then we propose a Decouple and Stretch (DS) scheme to enhance channel pruning. Under this scheme, each filter in a specific layer is decoupled into two small spatial-wise filters, and the spatial-wise filters are stretched into two successive convolutional layers. Our scheme obtains up to 49% improvement on compression and 35% improvement on acceleration. To further demonstrate hardware compatibility, we deploy pruned networks on the FPGA, and the network produced by Decouple and Stretch scheme is more hardware-friendly with latency reduced by 42%.

In this paper, the problem of routing and spectrum assignment for static connection requests in elastic optical networks (EONs) is studied. Two different ratios of blocking formations are adopted, and a global constraint optimization model is established to minimize the ratio of blocking in the network. First, we propose an availability index of the frequency slots in the path. Second, a strategy of routing is designed by considering the two indexes of path length and availability index to judge the quality of the path. Then, a greedy strategy, which can obtain the largest availability index in the path after the frequency slot allocated, is proposed for the sake of assigning the spectra effectively. Simulation experiments were carried out in two network topologies. The two different ratios of blocking are obtained for different sorting strategy for connection requests and the number of connection requests. The experimental results show that the routing and spectrum assignment scheme designed in this paper can get a small ratio of blocking.