Search

The severe interface reaction, which has been a challenging problem in graphene nanoplatelets (GNPs) reinforced Ti6Al4V (TC4) matrix composites, results in poor mechanical and tribological properties. Herein, GNPs/TC4 composites exhibited excellent wear resistance by introducing the in-situ TiB whiskers (TiBw) on the interface between GNPs and matrix. This work highlights the mechanical and tribological properties of GNPs/TC4 composites by diminishing the interface reaction and strengthening the interface bonding through the in-situ formed TiBw.

Specific emitter identification (SEI) and automatic modulation classification (AMC) are generally two separate tasks in the field of radio monitoring. Both tasks have similarities in terms of their application scenarios, signal modeling, feature engineering, and classifier design. It is feasible and promising to integrate these two tasks, with the benefit of reducing the overall computational complexity and improving the classification accuracy of each task. In this paper, we propose a dual-task neural network named AMSCN that simultaneously classifies the modulation and the transmitter of the received signal. In the AMSCN, we first use a combination of DenseNet and Transformer as the backbone network to extract the distinguishable features; then, we design a mask-based dual-head classifier (MDHC) to reinforce the joint learning of the two tasks. To train the AMSCN, a multitask cross-entropy loss is proposed, which is the sum of the cross-entropy loss of the AMC and the cross-entropy loss of the SEI. Experimental results show that our method achieves performance gains for the SEI task with the aid of additional information from the AMC task. Compared with the traditional single-task model, our classification accuracy of the AMC is generally consistent with the state-of-the-art performance, while the classification accuracy of the SEI is improved from 52.2% to 54.7%, which demonstrates the effectiveness of the AMSCN.

With the strengths of quickness, low cost, and adaptability, unmanned aerial vehicle (UAV) communication is widely utilized in the next-generation wireless network. However, some risks and hidden dangers such as UAV “black flight” disturbances, attacks, and spying incidents lead to the necessity of the real-time supervision of UAVs. A compressed sensing-based genetic Markov localization method is proposed in this paper for two-dimensional trajectory tracking of the mobile transmitter in a finite domain, which consists of three modules: the multi-station sampling module, the reconstruction module, and the localization module. In the multi-station sampling module, multiple stations are deployed to receive the signal transmitted by the UAV using compressed sensing, and the motion model of the mobile transmitter is the constant turn rate and acceleration (CTRA) model. In the reconstruction module, we propose a direct reconstruction method to extract the joint cross-spatial spectrum. In the genetic Markov localization module, we propose a two-step localization method to genetically correct the inaccurate points in the preliminary results and generate the tracking result. Extensive simulations are conducted to verify the effectiveness of the proposed method. The results show that the proposed method is superior to the particle filter method and the Markov Monte Carlo method at all sampling moments. Specifically, when SNR = 15dB, the root-mean-square error (RMSE) of the proposed method is 39% and 60% lower than that of the other two methods, respectively. Moreover, under the premise that the RMSE of the localization result is less than 30 m, the reconstruction module can reduce the running time of the proposed method by 33.3%.

In order to tackle the issue of multi-scale object detection, recent detectors usually adopt hierarchical feature pyramids which are generated by naive combinations of top-down features and lateral features. Considering the limited effective receptive fields of the methods for top-down features augmentation, the generated regions are only associated with the fixed areas of the coarser features. Meanwhile, noisy features are introduced by irrelevant regions inevitably since the finer features in relation to rigid coarser regions. Thus, the pyramidal features with strong semantics are difficult to be obtained via simply enlarging the top-down features. In this paper, we present the Aggregated Residual Dilation based Feature Pyramid Network (ARDFPN) to exploit the inherent correlation of regions in feature pyramid. The network is designed by stacking a building block that aggregates a set of dilated convolutions with the same topology. We show that carefully adding additional transformation stages into feature pyramid enables a potential way for further multi-scale feature generation. As an intuitive extension of Feature Pyramid Network (FPN), we conduct an exhaustive study to evaluate the model performance by replacing FPN with the proposed ARDFPN in both object detection and instance segmentation tasks. With Residual network in Faster R-CNN and Mask R-CNN framework, ARDFPN outperforms the prevalent detection module - FPN on the challenging COCO dataset without bells and whistles. In particular, ARDFPN exhibits a superior performance, especially for the small and middle objects.

Unmanned aerial vehicles (UAVs), benefit by low cost, fast deployment, and large coverage, are widely applied as aerial relays in providing communication services for the areas with heavy traffic load or disasters. In this paper, the capacity of UAV relaying networks is studied, where the UAVs act as relays for the ground users. Two scenarios of UAVs distributed on an aerial 2-D plane and in a 3-D space are studied. The analysis reveals that in order to control the air-to-ground interference, the altitude of UAVs is at most in the same order to the distance between two adjacent UAVs. Besides, it is discovered that the pathloss exponent value α = 2.5 is a watershed for the capacity of UAV relaying networks, i.e., when α ≤ 2.5, the capacity of UAV relaying networks with the 2-D deployment of UAVs is greater than that with the 3-D deployment of UAVs. Otherwise, the capacity of UAV relaying networks with the 3-D deployment of UAVs is larger than that with the 2-D deployment of UAVs. Furthermore, the mobility of UAVs is studied, and it is verified that the mobility can orderly improve the capacity of UAV relaying networks. The theoretical analysis of this paper provides a guideline for the deployment of UAVs as aerial relays.

With autonomous driving developing in a booming stage, accurate object detection in complex scenarios attract wide attention to ensure the safety of autonomous driving. Millimeter wave (mmWave) radar and vision fusion is a mainstream solution for accurate obstacle detection. This article presents a detailed survey on mmWave radar and vision fusion based obstacle detection methods. First, we introduce the tasks, evaluation criteria, and datasets of object detection for autonomous driving. The process of mmWave radar and vision fusion is then divided into three parts: sensor deployment, sensor calibration, and sensor fusion, which are reviewed comprehensively. Specifically, we classify the fusion methods into data level, decision level, and feature level fusion methods. In addition, we introduce three-dimensional(3D) object detection, the fusion of lidar and vision in autonomous driving and multimodal information fusion, which are promising for the future. Finally, we summarize this article.

Pedestrian surveillance is one of the most important aspects in the surveillance system.Traditional surveillance equipment can only cover the limit area.Namely,once the surveillance equipment is implemented,it can only monitor a specific region.Besides,the surveillance system can't detect if there is a person in the surveillance picture or not.The professional staffs are needed to determine whether there is a person in the surveillance picture.To solve this problem,a computer vision based on mobile pedestrian surveillance system was designed.By implementing a surveillance camera on a mobile small vehicle and remotely control it,the system could switch the monitoring area.Besides,the system could classify and locate the pedestrian in the picture with the deep convolutional neural network and correlation filters.Finally,the system was tested on the spot,which verified the feasibility of the system.

Software defect prediction (SDP) is an effective technique to lower software module testing costs. However, the imbalanced distribution almost exists in all SDP datasets and restricts the accuracy of defect prediction. In order to balance the data distribution reasonably, we propose a novel resampling method LIMCR on the basis of Naïve Bayes to optimize and improve the SDP performance. The main idea of LIMCR is to remove less-informative majorities for rebalancing the data distribution after evaluating the degree of being informative for every sample from the majority class. We employ 29 SDP datasets from the PROMISE and NASA dataset and divide them into two parts, the small sample size (the amount of data is smaller than 1100) and the large sample size (larger than 1100). Then we conduct experiments by comparing the matching of classifiers and imbalance learning methods on small datasets and large datasets, respectively. The results show the effectiveness of LIMCR, and LIMCR+GNB performs better than other methods on small datasets while not brilliant on large datasets.

For autonomous driving, it is important to detect obstacles in all scales accurately for safety consideration. In this paper, we propose a new spatial attention fusion (SAF) method for obstacle detection using mmWave radar and vision sensor, where the sparsity of radar points are considered in the proposed SAF. The proposed fusion method can be embedded in the feature-extraction stage, which leverages the features of mmWave radar and vision sensor effectively. Based on the SAF, an attention weight matrix is generated to fuse the vision features, which is different from the concatenation fusion and element-wise add fusion. Moreover, the proposed SAF can be trained by an end-to-end manner incorporated with the recent deep learning object detection framework. In addition, we build a generation model, which converts radar points to radar images for neural network training. Numerical results suggest that the newly developed fusion method achieves superior performance in public benchmarking. In addition, the source code will be released in the GitHub.

Offline-trained Siamese networks are not robust to the environmental complication in visual object tracking. Without online learning, the Siamese network cannot learn from instance domain knowledge and adapt to appearance changes of targets. In this paper, a new lightweight Siamese network is proposed for feature extraction. To cope with the dynamics of targets and backgrounds, the weight in the proposed Siamese network is updated in an online manner during the tracking process. In order to enhance the discrimination capability, the cross-entropy loss is integrated into the contrastive loss. Inspired by the face verification algorithm DeepID2, the Bayesian verification model is applied for candidate selection. In general, visual object tracking can benefit from face verification algorithms. Numerical results suggest that the newly developed algorithm achieves comparable performance in public benchmarks.

This study focuses on developing an effective online teaching strategy to improve students' cognition engagement and application ability by applying design thinking and case readings on current economic issues for private university students in Taiwan during the COVID-19 pandemic. The teaching method combines design thinking and the reading comprehension process by the two principles of divergence and convergence. The design thinking method provides stepwise guidance for building understanding and analyzing competence on current economic issues. The reading comprehension process strengthens students' reading skills and learning capability. This combination increases student engagement and concentration in economic case readings during online learning. The research participants comprised 189 first-year students studying economics courses. After implementing the innovative teaching strategies, the results show that the more students are involved in frequent readings, the better are their economics semester grade. The findings revealed that their post-quiz scores improved significantly, and the semester grade increased by 3.44 points. Increasing the reading engagement on current economic issues cases also affected the learning outcomes for absentees. Using design thinking to introduce case reading comprehension, empathy has been suggested as an essential factor affecting the effectiveness of reading learning. This theoretical model can offer directional insights and guidance on developing an effective strategy in online economics education.

Cube-like Cu2MoS4 nanoparticles with low-index facets and high crystallinity were fabricated via a hydrothermal method. The as-obtained nanocubes with an average size of 40-60 nm are composed of stacking-Cu2MoS4 layers separated by a weak Van der Waals gap of 0.5 nm. A strong absorption at visible light region is observed in the nanocube aqueous solution, indicating its optical-band gap of 1.78 eV. The photocatalytic measurements reveal that the nanocubes can thoroughly induce the degradation of methyl orange under visible light irradiation with good structural stability. Our finding may provide a way in design and fabrication of transition metal dichalcogenide nanostructures for practical applications.