Quantized neural networks (QNNs) have become a standard operation for efficiently deploying deep learning models on hardware platforms in real application scenarios. An empirical study on German traffic sign recognition benchmark (GTSRB) dataset shows that under the three white-box adversarial attacks of fast gradient sign method, random + fast gradient sign method and basic iterative method, the accuracy of the full quantization model was only 55%, much lower than that of the full precision model (73%). This indicates the adversarial robustness of the full quantization model is much worse than that of the full precision model. To improve the adversarial robustness of the full quantization model, we have designed an adversarial attack defense platform based on field-programmable gate array (FPGA) to jointly optimize the efficiency and robustness of QNNs. Various hardware-friendly techniques such as adversarial training and feature squeezing were studied and transferred to the FPGA platform based on the designed accelerator of QNN. Experiments on the GTSRB dataset show that the adversarial training embedded on FPGA can increase the model's average accuracy by 2.5% on clean data, 15% under white-box attacks, and 4% under black-box attacks, respectively, demonstrating our methodology can improve the robustness of the full quantization model under different adversarial attacks.

The use of EMG signals has been gaining prevalence in prosthetic control and gesture-control applications. This study aims to develop an EMG-based human machine interface system. A Myo Armband with eight electrode pairs is worn by a user to acquire and wirelessly transmit EMG data to a central controller. A pattern recognition algorithm is implemented on a central controller to recognize three different hand gesture commands. As a demonstration, a camera system equipped with servo motors is built. The recognized commands can remotely pan each camera and select one of multiple video feeds to display. The study demonstrates that the EMG-based pattern recognition could be a viable human machine interface option for a broad range of applications in industrial, medical, and consumer markets.

Hyperspectral remote sensing image (HSI) consists of hundreds of bands that contain rich space, radiation and spectral information. The high-dimensional data can also lead to the curse of dimensionality problem making it difficult to be used effectively. In this paper, we proposed a manifold learning algorithm to reduce the dimensionality for HSI data. For high dimensional datasets with continuous variables, it is often the case that the data points are arranged along with low dimensional structures, named manifolds, in the high dimensional space. Manifold learning aims to identifying those special low dimensional structures for subsequent usage such as classification or regression. However, many manifold learning algorithms perform an eigenvector analysis on a data similarity matrix whose size is N×N, where N is the number of data points. The memory complexity of the analysis is at least O(N2) that is not feasible for a regular computer to compute or storage for very large datasets. To solve this problem, we used statistical sampling methods to sample a subset of data points as landmarks. A skeleton of the manifold was then identified based on the landmarks. The remaining data points were then inserted into the skeleton by Locally Linear Embedding (LLE). We tested our algorithm on AVIRIS Salinas-A data set. The experimental results showed that the HSI dataset could be reduced to a lower-dimensional space for land use classification with good performance, and the main structure was preserved well.

High-dimensional data such as hyperspectral images contain abundant information of surface radiation. But the massive redundant information makes it complex to be utilized conveniently. To solve this problem, a manifold learning dimensionality reduction framework for hyperspectral image is proposed. Firstly, statistical sampling methods were used to sample a subset of data points as landmarks. A skeleton of the manifold was then identified basing on the landmarks. The remaining data points were then inserted into the skeleton by Locally Linear Embedding algorithm. At last, original data sets and data sets reduced with different manifold learning approaches were classified by KNN classifier to evaluate the performance of the proposed framework. The framework was tested on AVIRIS Salinas-A dataset. The experimental results showed that the tradeoff of accuracy with different landmarks is of great significant. Insufficient landmarks lead to low accuracy and excess landmarks may spend a considerable amount of time.

Under the indoor building environment, when the fires and other accidents occur, how to effectively organize the masses evacuation and fire rescue, is closely related to the safety of people's lives and property and has become a critical problem of public concern. This paper presents an improved ant colony algorithm (ACO) to solve the problem of how to optimize the evacuation route and rescue route when an accident occurs. According to the key factors affecting people emergency evacuation, such as indoor building environment, fire and its combustion products, problem of path's optimal selection, etc., we propose an emergency evacuation model, based on the model it can give an optimal evacuation route for the mass and an optimal rescue route for the firefighters. We also analyzes the search results, it shows that the search results is robust and reasonable.

In China, drought is one of the major environmental disasters, which bring great harm to the people. The middle reach of Yangtze River is the most important base to produce grains in China. Influenced by the summer monsoon, the drought occurs frequently. In our paper, the NDVI and LST from MODIS data were utilized to calculate the TVDI (Temperature Vegetation Dryness Index), which were used to monitor the drought of the study area. Meteorological drought indices were calculated from 10-day precipitation, temperature and evaporation data of 94 meteorological stations, including precipitation standardized variables, dryness and relative moisture index were used to analyze the degree of drought and the area of drought. The results showed that TVDI is significantly related to soil moisture.

In various signal processing applications, decomposition and analysis of non-stationary signals is a challenging problem. In this work, we present a computationally efficient method, fast chirplet signal decomposition (FCSD) algorithm, for decomposing highly convoluted signals into a linear expansion of chirplets, and successively estimates the chirplet parameters. These parameters are capable of representing a broad range of echo shapes, including the broad-band, narrow-band, symmetric, skewed, nondispersive or dispersive, and have significant physical interpretations for radar, sonar, and ultrasonic imaging applications. For the real-time implementation of chirplet signal decomposition algorithm, an FPGA-based hardware/software co-design is developed on Xilinx Virtex II Pro FPGA platform. In this study, based on the balance among the system constraints, cost, and the efficiency of estimations, the performance of different algorithm implementation schemes have been explored. The developed system successfully exhibits the robustness in the chirplet signal decomposition of experimental signals. This type of study addresses a broad range of applications including velocity measurement, target detection, deconvolution, object classification, data compression, and pattern recognition.

This letter presents a fast chirplet transform (FCT) algorithm, a computationally efficient method, for decomposing highly convoluted signals into a linear expansion of chirplets. The FCT algorithm successively estimates the chirplet parameters in order to represent a broad range of chirplet shapes, including the broadband, narrowband, symmetric, skewed, nondispersive, or dispersive. These parameters have significant physical interpretations for radar, sonar, seismic, and ultrasonic applications. For the real-time application and embedded implementation of the FCT algorithm, an FPGA-based hardware/software co-design is developed on Xilinx Virtex-II Pro FPGA development platform. Based on the balance among the system constraints, cost, and the efficiency of estimations, the performance of different algorithm implementation schemes have been explored. The developed system-on-chip successfully exhibits robustness in the chirplet transform of experimental signals. The FCT algorithm addresses a broad range of applications including velocity measurement, target detection, deconvolution, object classification, data compression, and pattern recognition.