Search

Millimeter-wave (MMW) point clouds, characterized by their low resolution and high noise, limit the detection accuracy of point-based IA-SSD method due to the inadequate consideration of contextual information in MMW scenarios. Therefore, this paper proposes a three-dimensional (3D) MMW object detector, greatly augmenting the detection performance of the baseline model IA-SSD by the integration of the local-global context information. Central to our approach is the implementation of a multi-scale feature aggregation (MFA) module in the encoder stage of IA-SSD, which utilizes a self-attention mechanism to apprehend local contextual distinctions. This module is further applied to the centroid aggregation stage to enhance the capture of local context from foreground points. Complementarily, a global feature fusion module is devised to combine global contextual insights, drawing upon the localized information delineated by the MFA modules. This integrated framework significantly diminishes the false detection rate while concurrently elevating the detection precision for occluded objects. Relative to the IA-SSD baseline, the empirical evaluations validate the efficiency of our proposed model, demonstrating marked decreases in false positives and false negatives. Specifically, there is a 2.78% and 7.39% improvement in AP_R40_0.25 and AP_R40_0.5, respectively. When the intersection-over-union threshold is set as 0.25 and 0.5, the corresponding recall rate increases by 2.13% and 6.2%, respectively. Moreover, the inference speed reaches 32.3 frames per second(FPS), only a slight decrease of 2.9 FPS compared to the baseline model. These results demonstrate that the proposed detector significantly enhances detection performance without compromising on speed, marking a considerable advancement in the domain of 3D MMW object detection.

Remaining useful life (RUL) prediction is a key technology to ensure the reliability and safety of high-end equipment. Deep learning is widely used for RUL prediction due to the excellent feature extraction ability and nonlinear fitting ability. Traditional recurrent neural networks adopt recursive strategy, which easily lead to the problems of error accumulation and low stability. On the other hand, most deep learning methods are used for point prediction and cannot quantify uncertainty in the prediction results. Although some probability prediction methods based on deep learning can provide probability prediction results, it require the assumption that the prediction results follow a specific distribution in advance. However, the distribution of most prediction results does not match a suitable distribution function. To solve above problems, a novel RUL prediction approach based on eXtreme gradient boosting (XGBoost) and multi-quantile recursive neural network (MQ-RNN) is proposed in this article. Specifically, XGBoost is used to select features closely related to RUL, and the selected features are fed into MQ-RNN to train the RUL prediction model. The advantage of MQ-RNN is that it has non-parametric framework, prediction results can be obtained by multi-quantile regression, which does not require prior assumptions about the distribution of predicted results. Furthermore, the proposed framework is verified by C-MAPSS dataset. Finally, comparative experiments are conducted. The experimental results show that the proposed method maintains good predictive performance in both point estimation and interval estimation.

Video prediction is an essential vision task due to its wide applications in real-world scenarios. However, it is indeed challenging due to the inherent uncertainty and complex spatiotemporal dynamics of video content. Several state-of-the-art deep learning methods have achieved superior video prediction accuracy at the expense of huge computational cost. Hence, they are not suitable for devices with limitations in memory and computational resource. In the light of Green Artificial Intelligence (AI), more environment friendly deep learning solutions are desired to tackle the problem of large models and computational cost. In this work, we propose a novel video prediction network 3DTransLSTM, which adopts a hybrid transformer-long short-term memory (LSTM) structure to inherit the merits of both self-attention and recurrence. Three-dimensional (3D) depthwise separable convolutions are used in this hybrid structure to extract spatiotemporal features, meanwhile enhancing model efficiency. We conducted experimental studies on four popular video prediction datasets. Compared to existing methods, our proposed 3DTransLSTM achieved competitive frame prediction accuracy with significantly reduced model size, trainable parameters, and computational complexity. Moreover, we demonstrate the generalization ability of the proposed model by testing the model on dataset completely unseen in the training data.

Micro-expression recognition based on ima- ges has made some progress, yet limitations persist. For instance, image-based recognition of micro-expressions is affected by factors such as ambient light, changes in head posture, and facial occlusion. The high temporal resolution of electroencephalogram (EEG) technology can record brain activity associated with micro-expressions and identify them objectively from a neurophysiological standpoint. Accordingly, this study introduces a novel method for recognizing micro-expressions using node efficiency features of brain networks derived from EEG signals. We designed a real-time Supervision and Emotional Expression Suppression (SEES) experimental paradigm to collect video and EEG data reflecting micro- and macro-expression states from 70 participants experiencing positive emotions. By constructing functional brain networks based on graph theory, we analyzed the network efficiencies at both macro- and micro-levels. The participants exhibited lower connection density, global efficiency, and nodal efficiency in the alpha, beta, and gamma networks during micro-expressions compared to macro-expressions. We then selected the optimal subset of nodal efficiency features using a random forest algorithm and applied them to various classifiers, including Support Vector Machine (SVM), Gradient-Boosted Decision Tree (GBDT), Logistic Regression (LR), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost). These classifiers achieved promising accuracy in micro-expression recognition, with SVM exhibiting the highest accuracy of 92.6% when 15 channels were selected. This study provides a new neuroscientific indicator for recognizing micro-expressions based on EEG signals, thereby broadening the potential applications for micro-expression recognition.

To address the limitations of traditional burdensome and time-consuming manual diagnosis of Sjogren’s syndrome, this study proposes and implements an improved version of YOLOv5s algorithm, named YOLOv5s-MSS. Using YOLOv5s-MSS, we are able to detect lymphocytic infiltrative lesions in pathological images and provide assistance for pathological diagnosis. Given the small size of lymphocytes and the difficulty in distinguishing them, we made four improvements to the YOLOv5s model. Firstly, we replace the original CIOU loss function with the Focal-SIOU loss function to accelerate model convergence and improve the detection accuracy. Additionally, we introduce the multi-head self-attention module into the backbone to enhance the model’s ability to capture long range dependencies and overcome the challenges posed by complex background. Furthermore, we introduce the Shuffle Attention module into the neck, which enhances the model’s ability to fuse features from both spatial and channel dimensions. Finally, we remove the 1/32 downsampling section in the neck and the corresponding large object detection head. This not only enhances accuracy but also reduces parameters and model complexity. Experimental results show that YOLOv5s-MSS achieves a mAP, Precision, and Recall of 93.2%, 87.2%, and 89%, representing increases of 2.9%, 2.6%, and 2.8% compared to the original YOLOv5s model. Additionally, YOLOv5s-MSS reduces the parameters by 28.2%. These results demonstrate the effectiveness and value of YOLOv5s-MSS for lymphocyte detection.

Laser beam transmission in atmospheric turbulence causes image distortion and affects the quality of information transmission in the field of optical communication. The strength of the atmospheric turbulence, which can be characterized by refractive index structure constant $C^{2}_{n}$, significantly influences the properties of a laser beam. The accurate estimation of $C^{2}_{n}$ is essential for understanding the strength of turbulence. Although multilayer perceptron (MLP) and deep neural network (DNN) has been applied to estimate the atmospheric turbulence strength, the estimation accuracy is sensitive to the strength of the turbulence. In this article, we propose a method based on the convolution neural network (CNN) approach to estimate $C^{2}_{n}$ ranging from $10^{-17}$ to $10^{-13}$ $\text{m}^{-2/3}$. We experimentally demonstrate that the correlation coefficient ($\rm R^{2}$) of the model is 99.39%. The mean relative error (MRE), root mean square error (RMSE), and mean absolute error (MAE) are 0.0047, 0.0916, and 0.0684, respectively. For the turbulence strength with the same order of refractive index structure constant $C^{2}_{n}$, the estimation accuracy of the weak turbulence is higher than that of medium and strong turbulence. Moreover, the mix training different levels of turbulence strength improves the estimation accuracy of $C^{2}_{n}$ compared to that with the same order of $C^{2}_{n}$. Based on the high estimation accuracy of the CNN in the scheme, the proposed method will be able to provide a way of estimating the strength of atmospheric turbulence without the need for additional optical devices.

Brain connectivity networks based on functional magnetic resonance imaging (fMRI) have expanded our understanding of brain functions in both healthy and diseased states. However, most current studies construct connectivity networks using averaged regional time courses with the strong assumption that the activities of voxels contained in each brain region are similar, ignoring their possible variations. Additionally, pairwise correlation analysis is often adopted with more attention to positive relationships, while joint interactions at the network level as well as anti-correlations are less investigated. In this paper, to provide a new strategy for regional activity representation and brain connectivity modeling, a novel homogeneous multiset canonical correlation analysis (HMCCA) model is proposed, which enforces sign constraints on the weights of voxels to guarantee homogeneity within each brain region. It is capable of obtaining regional representative signals and constructing covariation and contravariance networks simultaneously, at both group and subject levels. Validations on two sessions of fMRI data verified its reproducibility and reliability when dealing with brain connectivity networks. Further experiments on subjects with and without Parkinson’s disease (PD) revealed significant alterations in brain connectivity patterns, which were further associated with clinical scores and demonstrated superior prediction ability, indicating its potential in clinical practice.

As an important means of environmental reconnaissance and regional security protection, sound target detection (STD) has been widely studied in the field of machine learning for a long time. Considering the shortcomings of the robustness and generalization performance of existing methods based on machine learning, we proposed a target detection method by an auditory brain-computer interface (BCI). We designed the experimental paradigm according to the actual application scenarios of STD, recorded the changes in Electroencephalogram (EEG) signals during the process of detecting target sound, and further extracted the features used to decode EEG signals through the analysis of neural representations, including Event-Related Potential (ERP) and Event-Related Spectral Perturbation (ERSP). Experimental results showed that the proposed method achieved good detection performance under noisy environment. As the first study of BCI applied to STD, this study shows the feasibility of this scheme in BCI and can serve as the foundation for future related applications.

Signal source number detection is an essential issue for the direction of arrival (DOA) estimation in satellite communication systems. The performances of conventional and deep-learning-based signal source number detection methods will deteriorate when the signal-to-noise ratio is low or coherent signals exist. This paper proposes a DOA detection network (DTN) combined with the root weighted subspace fitting (root-WSF) method to tackle this challenge. The DTN uses the constructed deep neural networks (DNN) to denoise the received signals and captures the nonlinear mapping relationship between the received signals and the number of signal sources. The received signals in the complex-valued domain are directly treated as DTN’s input, and the label of DTN is the one-hot encoding of the source number. It solves the issue that the classifier cannot well-handle the coherent signals and extends the values of discrete features to Euclidean space. Accordingly, the trained DTN can detect the signal source numbers with an average detection accuracy of 96.6%, and the root-WSF algorithm is applied as the rear stage of DOA estimation. Compared with the traditional DOA methods, the proposed DTN incorporated with the root-WSF algorithm features superior robustness, high DOA estimation accuracy, and enhanced resolution.

Green plums are a characteristic fruit resource in China, with a long history of cultivation. Many surface defects will appear in the growth, transportation and preservation of green plums which seriously affect the processing quality of by-products. The existing manual sorting method of green plums is limited by the experience of workers. It is difficult to ensure the quality and speed of detection. Therefore, the formation of automatic detection of green plums surface defects is of great significance to the development of green plum industry. According to the surface defects of green plums, this paper divides green plums into five categories: rot, cracks, scars, rain spots and normal. A total of 1235 images of green plums were obtained by self-built image acquisition device. The WideResNet50-AdamW-Wce model based on WideResNet model was built to classify the surface defects of green plums. Accuracy, recall and F1-measure were selected as the indexes to evaluate the accuracy of classification. The accuracy of classification reached 98.95%, and the classification accuracy of rain spots, normal, scars, rot and crack reached 100%, 99.56%, 98.59%, 98.25% and 96.10% respectively. Comparing the performance of ResNet50-SGD, WideResNet50-SGD, WideResNet50-SGD-Wce, and WideResNet50-AdamW network models, the F1-Measure based on WideResNet50-AdamW-Wce is the highest in each defect, and more greengage defect features can be learned. The detection results can meet the production needs of plum deep processing enterprises – evaluating 1800 green plums per hour on the assembly line.

Most of the current indoor localization methods based on channel state information (CSI) utilize the amplitude and phase of each subcarrier individually as location fingerprints, but the correlation between adjacent subcarriers also contains essential location information. Therefore, this paper proposes a device-free indoor localization method based on CSI and limited penetrable horizontal visibility graph (LPHVG), which does not require the subject to carry a device and can be implemented with only a single access point (AP). Firstly, we model the frequency correlation between subcarriers by LPHVG algorithm and construct a CSI-based complex network. Secondly, the topology of the complex network is utilized to analyze the relationship between CSI adjacent subcarriers and extract network features, which are combined with statistical features as fingerprint information to characterize different locations. Finally, the method is combined with support vector regression (SVR) to realize indoor localization in different environments. The experimental results show that the proposed method can significantly improve the localization accuracy, and has an excellent performance in different indoor scenarios.

This paper proposes a robust digital signal recovery (DSR) technique to tackle the high signal-to-noise ratio (SNR) variation and transmitter memory effects for broadband power efficient down-link in next-generation low Earth orbit (LEO) satellite constellations. The robustness against low SNR is achieved by concurrently integrating magnitude normalization and noise feature filtering using a filtering block built with one batch normalization (BN) layer and two bidirectional long short-term memory (BiLSTM) layers. Moreover, unlike existing deep neural network-based DSR techniques (DNN-DSR), which failed to effectively take into account the memory effects of radio-frequency power amplifiers (RF-PAs) in the model design, the proposed BiLSTM-DSR technique can extracts the sequential characteristics of the adjacent in-phase (I) and quadrature (Q) samples, and hence can obtain superior memory effects compensation compared with the DNN-DSR technique. Experimental validation results of the proposed BiLSTM-DSR with a 100 MHz bandwidth OFDM signal demonstrate an excellent performance of 11.83 dB and 9.4% improvement for adjacent channel power ratio (ACPR) and error vector magnitude (EVM), respectively. BiLSTM-DSR also outperforms the existing DNN-DSR technique in terms of the ACPR and EVM by 2.4 dB and 0.9%, which provides a promising solution for developing deep learning-assisted receivers for high-throughput LEO satellite networks.

Since optimal portfolio strategy depends heavily on the distribution of uncertain returns, this article proposes a new method for the portfolio optimization problem with respect to distribution uncertainty. When the distributional information of the uncertain return rate is only observable through a finite sample dataset, we model the portfolio selection problem with a robust optimization method from the data-driven perspective. We first develop an ambiguous mean-CVaR portfolio optimization model, where the ambiguous distribution set employed in the distributionally robust model is a Wasserstein ball centered within the empirical distribution. In addition, the computationally tractable equivalent model of the worst-case expectation under the uncertainty set of a cone is derived, and some theoretical conclusions of the box, budget and ellipsoid uncertainty set are obtained. Finally, to demonstrate the effectiveness of our mean-CVaR portfolio optimization method, two practical examples concerning the Chinese stock market and United States stock market are considered. Furthermore, some numerical experiments are carried out under different uncertainty sets. The proposed data-driven distributionally robust portfolio optimization method offers some advantages over the ambiguity-free stochastic optimization method. The numerical experiments illustrate that the new method is effective.

In this paper, an efficient digital predistortion (DPD) architecture utilizing over-the-air (OTA) feedback is presented to linearize phased array transmitters. It places one additional observation antenna (OA) in the far field to capture the combined signal of the array outputs and uses the combined signal to build a nonlinear model that describes the joint nonlinear distortions of all the power amplifiers (PAs) in the phased array. Then, a corresponding DPD model is extracted by the typical indirect learning method to linearize the phased array. After introducing this DPD architecture, the relationship between the OA position and the performance of the extracted DPD model is specifically explored, and two significant results are found. First, when the OA is perfectly colocated in the main beam direction, the DPD coefficients extracted with an arbitrary steering angle for the phased array are also applicable to any other steering angle. Second, when the OA is not perfectly placed in the main beam direction, the linearization performance for the extracted DPD coefficients will degrade as the OA placement mismatch increases, and the phased array has an optimum steering angle at which the OA placement mismatch has a minimal influence on the DPD performance. Based on the above two results, a new DPD training strategy is proposed, which extracts only one set of DPD coefficients by making the phased array point at the optimum steering angle. The advantages of the proposed strategy are that the OA can be placed in a relatively wide range of positions and that the extracted coefficients will be applicable to any other steering angle. The two results and the proposed DPD training strategy are verified by simulations, which are conducted on a 1 × 4 uniform linear array (ULA) and a 4 × 4 uniform rectangular array (URA).

The spatial heterogeneity of the influences of various driving factors on the digital economy restricts the further development of regional coordination. This paper constructs an index system for measuring the development level of the digital economy from the three dimensions of infrastructure construction, digital application and digital industry development. Using the entropy method to measure the development level of the digital economy in each region in 2018 and based on the theory of economic growth and new economic geography, a theoretical model of the influences of input factors, technological progress and institutional changes on China’s digital economy is established. Combined with Exploratory Spatial Data Analysis (ESDA) and Geographically Weighted Regression (GWR) model analysis, the spatial distribution pattern of China’s digital economy and its influencing factors are discussed. The results show that there is a large gap in the development level of the digital economy in the eight comprehensive economic regions, and the development level of the digital economy presents a significant spatial correlation in space. The driving patterns of input factors, technological progress and institutional changes to the spatial distribution of the digital economy show obvious spatial differentiation. This study provides important referential value for promoting the coordinated development of the regional digital economy.

With the growing demand for information security, finger-vein recognition has become widespread. However, the robustness of the recognition process becomes a major problem. When identifying unseen categories with traditional finger-vein recognition systems, a few issues remain, such as recognition interference and low efficiency. This paper proposes a Deep Generalized Label Finger-Vein (DGLFV) model to extract feature maps and achieve high-accuracy recognition. The largest rectangular finger-vein region is extracted through image semantic segmentation and the advanced bidirectional traversing and center diffusion method for the known categories. Then we generalize all the unseen categories actively as Class $C+1$ to reduce interference from unregistered users. Furthermore, an adaptive threshold acquisition algorithm is proposed for Label Receiver Operating Characteristic (LROC), so that the procedures of classification, recognition, and verification are unified. Apart from Shandong University Homologous Multi-modal Traits (SDUMLA-HMT), we have conducted additional experiments on our self-built database, Finger Veins of Signal and Information Processing Laboratory (FV-SIPL). The recognition accuracy of the approach proposed in this paper has reached 99.25% and 99.08% testing on FV-SIPL and SDUMLA-HMT, with a low error rate at 1.481% and 2.228% and little time consumption of 0.157s for a single image, which is better than most state-of-the-art finger-vein recognition methods.

In this article, seven filter algorithms were compared. The Lee sigma method was more suitable for estimating soil moisture (SM) than the other filtering methods under different land cover types. First, we used a combination of roughness and the dual-polarized Sentinel-1A backscattering coefficients (VV and VH) to estimate SM in bare soil areas. Second, we employed water cloud model (WCM) to remove the influence of vegetation signals on the land surface backscattering and estimate SM in vegetation-covered areas. SM was also retrieved by modified soil moisture monitoring index (MSMMI) and modified perpendicular drought index (MPDI) of Sentinel-2A images. The results show that MSMMI can more accurately monitor SM in bare soil areas, which was slightly better than synthetic aperture radar (SAR) results. The SAR backscattering coefficients after the removal of vegetation influence by WCM can more precisely estimate SM in vegetation-covered areas, which is significantly better than MSMMI and MPDI, especially in high vegetation-covered areas. Optics and SAR differ in their abilities to estimate SM under different land cover, but the powerful fitting ability of machine learning can make full use of their advantages. We employed the generalized regression neural network (GRNN), support vector regression (SVR), random forest regression (RFR), and deep neural network (DNN) algorithms to estimate SM combining Sentinel-1A with Sentinel-2A images. The estimation accuracies of SM by regression algorithms were higher than those by the semiempirical SAR and optical models. The accuracy of estimated SM by DNN was higher than that of GRNN and RFR, which were better than SVR.

This article aims to explore the applicability of SMMI (soil moisture monitoring index), MSMMI (modified soil moisture monitoring index), PDI (perpendicular drought index), and MPDI (modified perpendicular drought index) in estimating soil moisture (SM) in farmland. The random forest classifier was used to obtain two-stage land cover types maps. The sensitivity of Sentinel-2 spectral bands to the measured SM at a depth of 0–5 cm was optimized by random forest regression. According to the sensitive bands, SMMI and PDI from different feature spaces were constructed to explore their feasibility for monitoring SM under different land cover types. Second, fractional vegetation cover (FVC) in the study area was estimated by nine kinds of FVC estimation models and compared with the measured FVC. The effects of different FVC methods on estimating SM by MSMMI and MPDI were evaluated. The results show that red edge and short-wave infrared (SWIR) bands of Sentinel-2 had irreplaceable effects on the land cover classification. In terms of monitoring SM in bare soil areas, the SM indices with SWIR bands had high correlations with measured SM. For vegetation-covered areas, MSMMI from the FVCgr model (dimidiate pixel model with red edge bands) and the Short wave infrared1–Short wave infrared2 feature space had the highest correlation with the measured 0–5 cm depth SM. Whether vegetation-covered areas or bare soil areas, the combination of red edge and SWIR bands can effectively improve the estimation accuracy of SM. MSMMI can be used as the best SMMI in the study area. Sentinel-2 images, with great potential, can effectively estimate SM at a depth of 0–5 cm in farmland with complex environments.

The insulation of high-frequency transformers (HFTs) has a significant impact on the safety and reliability of high voltage power electronic transformers (PETs). The transient voltages from the rapid turn-off and turn-on of the high voltage power semiconducting device increase the insulation stress and loss, resulting in thermal stress distortion. However, few studies have presented an accurate evaluation of the dielectric loss, especially under high dV/dt square waves. This paper focuses on the dielectric loss calculation in HFT insulation by analyzing the loss from a high-frequency square wave with spike voltages. A step function that is equivalent to spike voltage superposition is proposed for the quantitative calculation of the dielectric loss of epoxy resin. A cutoff frequency ( $f_{\mathrm {c}}$ ) is defined to indicate high dV/dt characteristics. A similar narrow step function is used for simulating spike voltage at the rising/falling edge. The additional dielectric loss increases with the spike voltage and the duration. The electric field and temperature distributions are simulated in a 10 kW, 10 kHz HFT by considering the calculation of dielectric loss. The spike voltages enhance the electric field and temperature in the insulation. The increase in the external temperature (close to the glass transition temperature ( $T_{\mathrm {g}}$ ) of epoxy resin) causes a significant increase in the insulation temperature. This paper is of great importance to the design and application of HFT insulation.

Advances in moving object detection have been driven by the active application of deep learning methods. However, many existing models render superior detection accuracy at the cost of high computational complexity and slow inference speed. This fact has hindered the development of such models in mobile and embedded vision tasks, which need to be carried out in a timely fashion on a computationally limited platform. In this paper, we propose a super-fast (inference speed-154 fps) and lightweight (model size-1.45 MB) end-to-end 3D separable convolutional neural network with a multi-input multi-output (MIMO) strategy named “3DS_MM” for moving object detection. To improve detection accuracy, the proposed model adopts 3D convolution which is more suitable to extract both spatial and temporal information in video data than 2D convolution. To reduce model size and computational complexity, the standard 3D convolution is decomposed into depthwise and pointwise convolutions. Besides, we proposed a MIMO strategy to increase inference speed, which can take multiple frames as the network input and output multiple frames of detection results. Further, we conducted the scene dependent evaluation (SDE) and scene independent evaluation (SIE) on the benchmark CDnet2014 and DAVIS2016 datasets. Compared to state-of-the-art approaches, our proposed method significantly increases the inference speed, reduces the model size, meanwhile achieving the highest detection accuracy in the SDE setup and maintaining a competitive detection accuracy in the SIE setup.

Aiming at the problems of the face image super-resolution reconstruction method based on convolutional neural network, such as single feature extraction scale, low utilization rate of features and blurred face images texture, a model combining convolutional neural network with self-attention mechanism is proposed. Firstly, the shallow features of the image are extracted by the cascaded 3 × 3 convolutional kernels, and then self-attention mechanism is combined with the residual blocks in depth residual network to extract the deep detail features of faces. Finally, the extracted features are fused globally by skip connections, which provide more high-frequency details for face reconstruction. Experiments on Helen, CelebA face datasets and real-world images showed that the proposed method could make full use of facial feature information, and its peak signal to noise ratio (PSNR) and structural similarity (SSIM) were both higher than the comparison methods with better subjective visual effects.

The emergence of the 5G network has brought broad prospects for the massive terminal access and ubiquitous Internet of Things (IoTs). Potential attacking opportunities triggered by this progress are severely impacting the security fortress of current networks, especially in the edge access part. However, due to the unitary protection and inferior isolation, available security schemes are incapable of effectively eliminating these hidden perils. Motivated by these facts, we propose a Multi-dimensional Fine-grained Control (MFC) framework to strengthen safety and reliability in Radio Access Networks (RANs). First, we comprehensively survey and summarize the existing security schemes to grasp respective effects and limitations. Second, the MFC framework is established to describe the model structure and implementation processes. An identifier mapping mechanism is designed to achieve network isolation. We perform the security analysis of MFC by theoretically comparing diversified policies. Third, an integrated set of the authentication prototype system is created with wireless environment parameters settings. Specific verification scenarios are illustrated. Finally, we test the performances of the MFC framework. Validation results demonstrate that the proposed scheme can accomplish reliable security control at the access side. Comparing to multiple schemes, the performances, in terms of time and concurrency, are optimized. Therefore, the MFC framework is feasible for applications in 5G or IoT.

Leak location in water-supply pipelines is of great significance in order to preserve water resources and reduce economic losses. Cross-correlation (CC) based leak location is a popular and effective method in water-supply pipelines (WSP). However, with a decrease of signal to noise ratio (SNR), the errors of time-delay estimation (TDE) based on CC will become larger making it almost impossible to determine a leakage position. Hence, this work proposes leak location based on a combination of phase difference spectrum and variational mode decomposition (PDS-VMD) of leakage-induced vibration signal under low SNR for WSP. Firstly, the leakage-induced vibration signal is decomposed into several intrinsic mode functions (IMFs) by VMD, where the characteristic frequency band is determined by PDS of cross spectrum of two leakage signals. Then, the energy ratio of leakage signal in characteristic frequency band serves as a guideline to select effective IMF components from the decomposed IMFs. Finally, the selective IMFs are reconstituted into a new signal which can be used to determine a leak position using CC based TDE. In order to verify the effectiveness of the proposed leak location algorithm, the method based on PDS-VMD is compared with that using CC, combination of CC coefficient and VMD (CCC-VMD) using both simulation and experiment. The simulation and experimental results demonstrate that the proposed PDS-VMD method is more suitable for leak location in WSP, which provides immunity to both broadband and narrow band noise under low SNR.

In China, recent ablation failures of water-blocking buffer layer occurred in high voltage (HV) cross-linked polyethylene (XLPE) cables with corrugated aluminum sheath have stimulated the product development of cables with smooth aluminum bonded sheath. Despite the many advantages, bending performance is one of the few weaknesses of smooth aluminum bonded sheath. In this paper, a three-dimensional model of a cable with smooth aluminum bonded sheath in a four-point bending test was set up, where the cohesive zone model was applied to simulate the mechanical behavior of the adhesive layer (bonding interface). The influence on the bending performance of the bonded sheath by the thickness of aluminum layer, the parameters of hot melt adhesive, the thickness and material parameters of outer jacket, as well as the cable specification was investigated, together with the stress distribution and damage analysis of the adhesive layer. Based on the research, the material selection and structural design of smooth aluminum bonded sheath were recommended for HV XLPE cables, including an additional requirement for the shear strength of hot melt adhesive besides those already in IEC and IEEE standards. Finally, a 110 kV XLPE cable with smooth aluminum bonded sheath was manufactured and type tested.

In the era of big data, the impact of the massive public opinion information generated by the Internet on the securities market has become a factor that can't be ignored in investment decision-making and supervision. Under the influence of these factors, investors are influenced and restricted by psychology, self-cognition and limited attention, which will make them pay different attention to stocks, which spread to the securities market, and then have an impact on the market performance of individual stocks. This paper selects big data's public opinion information from securities websites, authoritative media data and mainstream social networking sites designated by China Shenzhen Stock Exchange to quantify the Internet attention index. According to different subjects and angles, it is divided into: media attention, netizens' attention, public opinion attention. Based on these three kinds of attention index data, this paper establishes the panel regression model and the GARCH (1, 1) model of the influence of different subject attention on individual stocks, and introduces abnormal media attention, abnormal netizens' attention, abnormal public opinion attention, lag attention and change of attention into the model to empirically test the three main market manifestations of individual stocks, namely, earnings, liquidity and volatility. Through comprehensive analysis and research, this paper discusses in detail and comprehensively the internal mechanism of the influence of Internet attention on the performance of individual stocks in China's securities market under the environment of big data. The conclusion of the study provides a reference for investor decision-making, market capitalization maintenance of listed companies and supervision of financial institutions.

The analysis of the target's broadband electromagnetic scattering characteristics plays an important role in radar stealth and recognition areas. The traditional method of moments (MoM) needs to calculate the currents at each frequency point when analyzing the target. With the increase of the target electrical size and complexity, the radar cross section (RCS) of the target changes drastically with frequency, it is necessary to calculate the accurate frequency response with a small frequency interval, which is very time-consuming in calculation and not feasible. This paper proposes to combine the subdomain method of moments (SMoM) with the Chebyshev approximation technique (CAT) to efficiently analyze the electromagnetic scattering of arbitrary shaped objects over a broad frequency band. In the SMoM technique, the whole object can be divided into several regions, each of which can be independently solved by the method of moments (MoM). The CAT technique is employed to expand the unknown current coefficients into a Chebyshev series for achieving fast frequency sweeping. Instead of direct point-by-point simulations, it is only necessary to calculate the currents by SMoM at several Chebyshev-Gauss frequency sample points. Furthermore, the Chebyshev series are matched via the Maehly approximation to a rational function to improve the accuracy. Numerical examples show that the hybrid technique can greatly reduce the computation time without loss of accuracy.

In this paper, a miniaturized dual-band bandpass filter (BPF) with good selectivity based on ring-loaded resonator (RLR) and 0° feed structure is proposed. First, the RLR is investigated theoretically and numerically, and a miniaturized Filter I is designed based on the RLR and filter synthesis approach. Secondly, based on the coupling structure of the previous BPF and theory of 0° feed structure, the sub Filter II is formed. By appropriately adjusting the location of the I/O ports, the dual-band filter can be achieved simply. The proposed dual-band BPF provides compact size and satisfactory out-of-band rejection between each band with multiple transmission zeros (TZs) introduced by source/load coupling and a special coupling scheme.

Because of networking flexibility, strong robustness and expansibility, and low cost of operation and maintenance, distributed wireless ad hoc networks are widely used in ultra-density 5th-Generation (5G) networks, Device to Device (D2D) communications and industrial wireless sensor networks. However, compared with the centralized ones, the Time Division Multiple Access(TDMA)-based distributed network lacks centralized coordination by a control center, while its resource scheduling only depends on partial information, and the high receiving failure probability caused by neighbors' cumulative interference outside the scope of maintenance may reduce the resource efficiency and restrict its usability according to the existing protocols severely. The simulation results show that the transmission failure probability can be up to 20% when maintaining two-hops neighbors in TDMA-based coordinated distributed scheduling. But the research on the cumulative interference outside the scope of maintenance and the optimal neighbor maintenance scope is still unclear at present. In this paper, we establish a resource efficiency model and an interference model of control messages and data messages under different neighbor maintenance by hardcore point process (HCPP) considering cumulative interference, cost of Media Access Control (MAC) layer and channel multiplex. Furtherly, we build an optimization model to maximize the resource efficiency under scheduling delay and receiving success probability constraints, thus we can obtain the optimal scope of maintenance in different network conditions. We conduct extensive theoretical analysis and simulations to evaluate the correctness of models. Simulation results show that the resource efficiency optimization model can provide guidance for optimal protocol parameters design.

Variable selection has been highly successful in big data analyses, and regularization approaches are commonly used methods, which can automatically select important variables while constructing machine learning models. Due to the real datasets have complex relationships between relevant variable groups, many group-sparsity regularization approaches are proposed recently. However, these approaches usually are non-convex and sensitive to hyper-parameters. Therefore, optimization of the regularizations is a challenging task. In this paper, we present a novel memetic algorithm with the complex harmonic regularization (MA-CHR), which combines EC algorithm for hyper-parameters (global search) and complex harmonic regularization with path seeking strategy for the group-sparsity variable selection (local search). We further introduced a novel genetic individual representation (intron+exon) to efficient obtain the global optimal solution of this group-sparsity regularization. Simulation and five real data experiments demonstrate that the proposed MA-CHR method performs better than the state-of-the-art regularization methods in selecting groups of relevant variables and classification.

As the Internet of Things (IoT) has connected large number of devices to the Internet, it is urgently needed to guarantee the low latency, security, scalable content distribution of the IoT network. The benefits of Information-Centric Networking (ICN) in terms of fast and efficient data delivery and improved reliability have raised ICN as a highly promising networking model for IoT environments. However, with the widely spread of the viruses and the explosion of kinds of network devices, the attackers can easily control the devices to form a botnet such as the Mirai. Once the devices are under control, the attackers can launch a consumer-provider collusive attack in the Information-Centric IoT context. In this attack, the malicious clients issue Interest packets that can only be satisfied by the malicious content provider, and the malicious provider replies to the clients just before exceeding the Pending Interest Table entry's expiration time, to occupy the limited resources. In this paper, we expound the model of the consumer-provider collusive attack and analyze the negative effect of the attack. Then we propose a Reputation Value based Early Detection (RVED) mechanism to relieve the impact of the collusive attack. The method aims to adjust the packet dropping rates of different interfaces based on their reputation value, thus to protect the legitimate packets from being dropped as possible. We implement the consumer-provider collusive model and evaluate our defend mechanism in the simulator, and simulation results verify the feasibility and effectiveness against the collusive attack of the RVED mechanism.

The purpose of this article is to identify football and related environmental variables through its VR images under the current situation where the vision system has become the only way for football robots to obtain the external environment, so as to improve the chances of winning the game. First, this article uses color filters to enhance the VR football data to distinguish between shadow games and aliens. The best environment for enhancing the image is automatically determined by the Ostu method, so that the image is not affected by shadows as much as possible, and the outline of the image can be sealed. At the same time, using the humanoid medium-sized football game machine system as the platform, the relevant processing algorithms of the humanoid football robot front-view system are studied to realize the work of color image segmentation, edge extraction, straight line extraction, cross-line recognition and target post-recognition. PA-SIFT algorithm is used to quickly identify the graphics. Data verification results show that the recognition rate of the PA-SIFT algorithm can reach 96%, ensuring the real-time and feasibility of the algorithm. In addition, the divide-and-conquer algorithm and the related processing algorithm of the vision system are combined to determine the central area of the image, so that the algorithm is not affected by the external environment, and the algorithm is robust and can improve actual competition.

Bearing failure often occurs in rotating machinery. Fault diagnosis method based on vibration signals has been studied for many years. Considering complementary information of the vibration signals from different directions, this article proposed an applied model of a correlation probability box based on G-Copula function for diagnosing bearing faults. First, to avoid constructing binary Copula function directly from the definition of binary Copula function, a new function is defined, and a construction method of binary G-Copula function is proposed based on the new function. Then, the correlation probability box model is established based on a joint cumulative distribution of the G-Copula function to increase the independent of the input data in the support vector machine (SVM) model, and the aggregated widths of the correlation probability box model can be used to monitor a development of the bearing failure. Finally, the experimental results showed that the proposed method obtain the better classification accuracy than other data processing study.

Multi-class classification is one of the most important supervised learning problems and can be solved by either designing direct multi-class classifiers (direct strategy) or decomposing it into a set of binary classification problems (indirect strategy). Direct strategy only needs training one unified classifier while indirect strategy, especially the one-vs-one decomposition method, has shown its superiority and been utilized by some popular software packages. In this article, a first attempt towards bridging the gap between direct strategy and one-vs-one decomposition for multi-class classification is conducted, and accordingly a novel approach named CODIL is proposed. Specifically, CODIL firstly transforms the class vector into a ternary label matrix (only with {-1, 0, +1}) via one-vs-one rule, where each column of the label matrix corresponds to a pair of classes. Then, CODIL determines the binary label vector (only with {-1, +1}) for unseen instance by exploiting the manifold structure information residing in its k nearest neighbors, where each element of the label vector denotes the unseen instance's prediction for its corresponding class pair. Finally, the class for unseen instance is returned via majority voting based on the binary label vector. Extensive comparative studies are conducted between CODIL and six well-established multi-class approaches over seventeen benchmark multi-class data sets. The experimental results show the superiority of the proposed CODIL approach against the compared approaches.

Selection of the kernel function by the support vector regression (SVR), for the purposes of load forecasting, is affected by the power load characteristics. The non-ideal SVR with a kernel function has low forecasting accuracy and poor generalization ability. A novel load forecasting method combining SVR and stacking is proposed in this paper. Base models are constructed based on SVRs with different kernel functions, then multiple base models are merged to obtain a base model layer via stacking algorithm. Finally, an SVR is connected as the meta-model layer. The stacking fusion model is composed of base model layer and meta-model layer. This model is trained with k-fold cross validation to enhance its generalization ability. An improved artificial fish swarm algorithm is employed to optimize the parameters to improve the forecasting accuracy of the stacking fusion model; speed variables are introduced to replace step lengths and improve the convergence speed and search ability. The forecasting accuracy and generalization ability of the proposed method are verified by comparative analysis.

This paper proposes a novel deep neural network (DNN)-based receiver for next-generation low Earth orbit (LEO) satellite communications. The DNN receiver can concurrently compensate for multiple imperfections of the satellite communication system to improve the quality of satellite-to-ground transmission. A special focus has been placed on handling the nonlinear distortion in the transmitted signal caused by space-borne high-efficiency radio frequency power amplifiers (RF-PAs), which is crucial in high-throughput satellite communications, but has been overlooked by existing relevant research. In this receiver, a DNN is designed and trained to learn the channel effects, nonlinearities of the RF-PAs, and digital modulation schemes in the received signal for demodulation and nonlinearity/channel effect compensation at the same time. The proposed receiver has been evaluated using five popular filtered orthogonal frequency division modulations with the nonlinear distortions experimentally extracted from a real gallium nitride (GaN) RF-PA and the additive white Gaussian noise channel generated by simulations. The validation results demonstrate that the DNN receiver can accommodate different modulation schemes and two typical groups of RF-PA classes with a satisfactory bit error rate performance. It has the potential to boost the performance of existing on-orbit LEO satellite communication systems with minimal system modifications and serves as a promising solution for future satellite communication services.

Digital predistortion (DPD) is known as an efficient solution to suppress nonlinear distortion of power amplifiers (PAs) in wireless transmitters to achieve both high linearity and power efficiency. In multiple input and multiple output (MIMO) applications, the power gains of multiple transmitting channels are usually different. Meanwhile, the channel crosstalk cannot be ignored, given the isolations between the physical channels are limited. Accordingly, the linearization performances of the conventional DPD methods are usually degraded. In this article, we propose a novel DPD method for MIMO transmitters, where both the crosstalk and different power gains of multiple channels are considered. In this method, the expected predistorted signals, which would be used to train the DPD model, are firstly obtained by an iterative algorithm derived from the contraction mapping theorem. Then, the coefficients of a MIMO-DPD model are extracted by fitting the DPD model to the obtained predistorted signal. Experimental results verify that the extracted coefficients can achieve an improved linearization performance for the MIMO transmitter with crosstalk between the channels, especially in the case where the channel gains are different. Specifically, for a $2 \times 2$ MIMO transmitter with -20 dB crosstalk and 1.2 dB difference between the two channel gains, the proposed DPD improves the adjacent channel power ratio (ACPR) from -31.4 dBc to -47.1 dBc, which outperforms the conventional DPD by 6.8 dB.

Secret Image Sharing (SIS) plays an important role in the field of information security. At present, from the perspective of image restoration, SIS schemes are roughly divided into two categories: traditional threshold SIS schemes and Progressive SIS (PSIS) schemes. The former provides an all-or-nothing recovery mode in image reconstruction phase. If one of these shadows is damaged or lost, the reconstruction will fail. In contrast, the latter can present the original image progressively during the reconstruction phase. In this paper, a PSIS scheme based on semantic segmentation is proposed, where only specific objects or sensitive areas in the image are shared. After simple processing, the remaining background images can be publicly transmitted on insecure channels of the network. The background image will be regarded as a normal picture by people without shares. Owners who have reached the share of trapdoor numbers can recover a key target in an image. As the share increases, more key targets can be recovered. This paper is the first to propose secure secret sharing of images based on semantic targets. Through this method, it is possible to perform permission control on the target that needs to be divided and shared. Since the shared object is not the entire image, it can save storage space to a certain extent. Finally, through the analysis of the experimental results and comparison with other works, it can be concluded that the proposed scheme has a higher level of security and the amount of data that needs to be transmitted is small.

Syslog parsing is of vital importance for the detection, diagnosis and prediction of network device failures in a datacenter. A common approach to syslog parsing is to extract templates from historical syslogs, after which syslogs are matched to these templates. To address the problems in the existing syslog parsing techniques, we propose a novel framework, Craftsman, which identifies frequent combinations of (syslog) words and then applies them as templates. Craftsman empirically extracts templates accurately, is extremely efficient in template matching, and naturally supports incremental learning. To compare the performance of Craftsman and three other template learning techniques designed for network devices, we experiment them on two-years' worth of syslogs collected from network devices deployed across 10+ datacenters of a tier-one service provider. The experiments demonstrate that Craftsman achieves a close-to-one accuracy (as measured by rand index), and improves the computational efficiency by 6.88 to 10.25 times in template matching, and by 730 to 6847 times in syslog parsing. It also improves the accuracy (as measured by F1 measure) of failure prediction by 13.07% to 188%. In addition, we demonstrate Craftsman's superior generality by comparing it with three widely-applied log parsing methods over five large log datasets collected from servers, distributed systems and applications.

The traditional edge detection-based shoreline extraction method is severely disturbed by noise, and it is difficult to obtain a continuous coastline. In response to the above problems, we propose a coastline extraction method based on convolutional neural networks. Firstly, we replace the standard convolution with the Mini-Inception structure in the backbone network to extract multi-scale features of the object, and all the multi-scale features are concatenated. Then, we use the leaky-ReLU activation function instead of the ReLU activation function to avoid the problem that “dead” neurons cannot learn the effective features of remote sensing images. Finally, the network fully exploits multi-level information of objects to perform the image-to-image prediction. We carried out experiments on the remote sensing images of Jiaozhou Bay in Qingdao. The experimental results showed that our method could effectively extract the coastline automatically, and the producer's accuracy and the user's accuracy were higher than the comparison methods.

In this paper, we investigate the great potential of the combination of machine learning technology and wireless communications. Currently, many researchers have proposed various optimization algorithms on resource allocation for distributed antenna systems (DASs). However, the existing methods are mostly hard to implement because of their high computational complexity. In this paper, a new system model for machine learning is considered for the scenario of DAS, which is more practical with its low computational complexity. We utilize the k-nearest neighbor (k-NN) algorithm based on the database of a traditional sub-gradient iterative method to get a power allocation scheme for DAS. The simulation results show that our k-NN algorithm can also obtain the power distribution scheme which is very similar to the results of the traditional algorithm.

The design of two high-gain Fabry–Perot antennas with wideband low monostatic radar cross section (RCS) is presented in this paper. First, a phase gradient metasurface (PGM) without lossy layer is used to realize in-band RCS reduction and high aperture efficiency, simultaneously. The simulated results show that its peak gain is 19.2 dBi, and a high aperture efficiency of 58.6% is achieved. By utilizing the PGM structure, the monostatic RCS is reduced from 7 to 11 GHz, and the in-band co-polarization RCS is reduced by 13.1 dB. After that, a PGM with metamaterial absorber is designed to broaden the bandwidth of RCS reduction. A prototype antenna is fabricated and measured. The peak gain of 17.9 dBi is obtained, and the monostatic RCS is reduced in a wider frequency band of 7–15 GHz.

Knowledge representation learning, which embeds entities and relations of knowledge graph into low-dimensional vectors, is efficient for predicting missing facts. Knowledge graph datasets only store positive triplets. Nevertheless, negative cases are similarly crucial in knowledge representation learning. Conventionally, corrupted triplets are uniformly generated as negative cases, but actually, these corrupted triplets are heterogeneous. The majority of corrupted triplets are trivial, and they have limited influence on learning. Regarding the large number of corrupted triplet candidates, it is not efficient to train the model by uniformly generated corrupted triplets. Generative adversarial network (GAN)-inspired approaches are proposed to remit easily discriminated negative training examples, enabling faster and better convergence of the embedding models. Pre-trained external sampling models are required in these approaches. In this paper, we introduce a simple but strong negative sampling approach for adversarial knowledge representation learning, named loss adaptive sampling mechanism, which is efficient without an external sampling model. Furthermore, false negative cases are always over-trained in the training stage with efficient negative sampling approaches. We propose a push-up mechanism and verify whether it is feasible to alleviate these over-trained false negative cases. The experimental results show that our adversarial knowledge representation learning approach outperforms the GAN-based sampling method—KBGAN.

An 8-port multiple-input multiple-output (MIMO) array operating in the long-term evolution (LTE) band 42 (3400-3600 MHz) based on the characteristic mode theory (CMT) is described. As designing a multi-antenna system with multiple significant modes is difficult for the CMT, a new method is, therefore, proposed to effectively provide useful physical insights and improve the envelope correlation coefficient (ECC). Although many of the same modes are excited by two antennas, the proposed method is still effective to improve the ECC of the two antennas. A detailed and reasonable framework adopting the CMT to analyze geometries with multi-significant modes is presented. The consideration of the mode number can be avoided by using this method. For an arbitrary structure, it is verified that the modal weighting coefficient (MWC) phases of the same modes excited by two ports are in phase or out of phase. Therefore, for the design of a multi-port MIMO array, the same modes excited by different ports can be divided into two types: equiphase modes and antiphase modes in the proposed method, and the tradeoff of the equiphase modes and the antiphase modes is first proposed and analyzed as an efficient way to improve the ECC. Furthermore, the proposed method can also be applied to asymmetric structures. In order to prove the effectiveness of the proposed method in the design of MIMO antennas with desirable ECC, an 8-port MIMO array for 5G mobile applications is implemented and measured.

Super-resolution ultrasound (SR-US) imaging technique overcomes the acoustic diffraction limit and greatly improves the spatial resolution. Furthermore, by exploiting temporal fluctuations in microbubbles, a super-resolution fluctuation imaging (SOFI) method has also been used to improve the temporal resolution of SR-US. However, this is at the expense of the reduction of spatial resolution. To address this problem, in this paper, a temporally correlated multiple sparse Bayesian learning (TMSBL) method is introduced to SR-US. Since TMSBL takes advantage of both the temporal correlation between successive frames and sparsity priors of microbubbles, it provides the possibility to obtain an enhancement in spatial resolution compared to SOFI (only considering the temporal fluctuations). To evaluate the performance of the proposed method, two types of numerical simulation and one physical phantom experiment were performed. Especially, we also investigate the effect of US imaging modes on the performance of SR-US implemented by TMSBL, where US data were acquired from the plane wave (the high imaging speed and the low spatial resolution) and synthetic transmit aperture (the low imaging speed and the high spatial resolution) scan, respectively. The experimental results show that compared to SOFI method when using the proposed TMSBL method, the imaging spatial resolution of SR-US can be improved. In addition, the imaging performance obtained by TMSBL can be hardly affected by US imaging modes. As a result, by combining with plane wave scan, TMSBL provides the potential in enhancing the spatial resolution of SR-US while maintaining a desired temporal resolution.

The ecological conditions in urban area are greatly changed during the process of industrialization and urbanization of China. The pressure-state-response (PSR) framework is the most popular method to evaluate the ecological quality by integrating a set of remote sensing and statistical indicators into one index through a weighting method. However, a completely remote-sensed ecological index (RSEI), integrating normalized difference vegetation index (NDVI), Wet, land surface temperature (LST), and the normalized differential build-up and bare soil index (NDBSI) through principal components analysis (PCA) method, has been proposed to assess the regional ecological quality. The publications about urban ecological evaluation by RSEI often focus on only one city or a certain area and there are few types of research on the ecological quality assessment by RSEI of 35 major cities in China. In this paper, we employed RSEI to monitor the changes in the ecological quality in China' 35 major cities. The results of RSEI were compared to that of PSR and stepwise regression method was applied to establish the quantitative relationship among RSEI, NDVI, Wet, NDBSI, and LST. The results show that there are 18 cities with ecological quality deteriorated, mainly located in the east and southwest of China (Shanghai, Guangzhou, Hongkong, Macao, Nanjing, Haikou, Shijiazhuang, and Xi'an), and 17 cities with better ecological quality, mainly located in the north and central area of China (Beijing, Tianjin, Shenzhen, Taipei, Fuzhou, Chongqing, and Jinan), from 1990 to 2015. The 3D-scatter plots of RSEI, NDVI, Wet, NDBSI, and LST demonstrate that the levels of very bad and bad mainly situate in where with a high density of built-up and low vegetation cover and soil water content. The PSR map, acquired from integrating 17 indicators, is quite similar to that of RSEI generated by merging only four remote-sensed indicators. This indicates that RSEI can be adopted to characterize regional ecological quality. Take the quantitative equation of Shanghai in 2015 as an example, every 1.46 decrement in NDBSI or each 3.72 increments in NDVI value can result in one increment in RSEI value and the ecological quality can be improved. Specifically, the expansion of the built-up area can lead to ecological degradation, and vegetation construction can promote eco-environmental quality.

With the development of technologies, such as big data, cloud computing, and the Internet of Things (IoT), digital twin is being applied in industry as a precision simulation technology from concept to practice. Further, simulation plays a very important role in the healthcare field, especially in research on medical pathway planning, medical resource allocation, medical activity prediction, etc. By combining digital twin and healthcare, there will be a new and efficient way to provide more accurate and fast services for elderly healthcare. However, how to achieve personal health management throughout the entire lifecycle of elderly patients, and how to converge the medical physical world and the virtual world to realize real smart healthcare, are still two key challenges in the era of precision medicine. In this paper, a framework of the cloud healthcare system is proposed based on digital twin healthcare (CloudDTH). This is a novel, generalized, and extensible framework in the cloud environment for monitoring, diagnosing and predicting aspects of the health of individuals using, for example, wearable medical devices, toward the goal of personal health management, especially for the elderly. CloudDTH aims to achieve interaction and convergence between medical physical and virtual spaces. Accordingly, a novel concept of digital twin healthcare (DTH) is proposed and discussed, and a DTH model is implemented. Next, a reference framework of CloudDTH based on DTH is constructed, and its key enabling technologies are explored. Finally, the feasibility of some application scenarios and a case study for real-time supervision are demonstrated.

As information-centric networking (ICN) cache can effectively reduce the requests from customers to producers and improve the efficiency of content acquisition, there are many studies propose to improve system performance of the Internet of Things (IoT) by using the concept of the ICN. In the context of information-centric IoT, the addressing location based on content names and routing transport mechanisms, which presents a high demand for the statistics and prediction of the content popularity. To improve the accuracy of the content popularity prediction, in this paper, we demonstrate a particular analysis of the content popularity and propose a content popularity prediction algorithm based on auto-regressive (AR) model. The algorithm derives regression parameters based on least-squares estimates and predicts future trends of the content popularity through combining various known values in a certain period. The evaluation results show that the proposed algorithm can accurately predict the content popularity of the next time period in information-centric IoT. As a result, the algorithm can increase the cache hit rate in routers, and reduce the network traffic and service access delay effectively to improve the experience of users in various scenarios such as real-time streaming media services.