ALBERT

Description: Speech is easily interfered by external environment in reality, which results in the loss of important features. Deep learning has become a popular speech enhancement method because of its superior potential in solving nonlinear mapping problems for complex features. However, the deficiency of traditional deep learning methods is the weak learning capability of important information from previous time steps and long-term event dependencies between the time-series data. To overcome this problem, we propose a novel speech enhancement method based on the fused features of deep neural networks (DNNs) and gated recurrent unit (GRU). The proposed method uses GRU to reduce the number of parameters of DNNs and acquire the context information of the speech, which improves the enhanced speech quality and intelligibility. Firstly, DNN with multiple hidden layers is used to learn the mapping relationship between the logarithmic power spectrum (LPS) features of noisy speech and clean speech. Secondly, the LPS feature of the deep neural network is fused with the noisy speech as the input of GRU network to compensate the missing context information. Finally, GRU network is performed to learn the mapping relationship between LPS features and log power spectrum features of clean speech spectrum. The proposed model is experimentally compared with traditional speech enhancement models, including DNN, CNN, LSTM and GRU. Experimental results demonstrate that the PESQ, SSNR and STOI of the proposed algorithm are improved by 30.72%, 39.84% and 5.53%, respectively, compared with the noise signal under the condition of matched noise. Under the condition of unmatched noise, the PESQ and STOI of the algorithm are improved by 23.8% and 37.36%, respectively. The advantage of the proposed method is that it uses the key information of features to suppress noise in both matched and unmatched noise cases and the proposed method outperforms other common methods in speech enhancement.

Description: The cruising range of an electric vehicle is limited by its battery. Reducing the energy consumption of MES (main energy systems) or AES (auxiliary energy systems) of the vehicle battery is an effective means to increase the electric vehicle cruising range. Platoon driving can greatly reduce the wind resistance of the vehicle and then reduce the energy consumption of MES for electric vehicles. This paper proposes an adaptive communication energy optimization scheme based on road curvature radius to save the energy of AES for the electric vehicle platoon on curved roads. In this paper, the inter-vehicle distance error based on the car-like model in a two-dimensional space is established. Then, the inter-vehicle distance error is used to design a control law K to accomplish successful platooning. Next, three platooning control schemes based on different information flow topologies are discussed. Finally, the consensus of three platooning control schemes and the energy consumption of electric vehicle communication systems are analyzed by MATLAB’s Simulink. Simulation results show that the communication energy optimization scheme reduces the power consumption of AES as long as the platoon driving on curved roads.

Description: Global warming caused by excessive carbon dioxide emissions has seriously threatened the sustainable development of human society. How to reduce carbon dioxide emissions has become a common problem faced by the international community. This article aims to study the decomposition of carbon emission factors and the prediction of carbon peaks from the perspective of multi-objective decision-making and information fusion processing. The sample collection method and statistical analysis method are used to collect samples and simplify the algorithm. A collection experiment of carbon emission factors based on the industry of City A is designed. The experimental data collection takes into account the conversion of coal and oil products into standard coal and carbon dioxide the resulting emissions impact. The experimental results in this paper show that the simulated and real values of my country’s petroleum carbon emissions have both increased from 2000 to 2015, and the decline will be controlled in 2017. Both the simulated value and the real value of my country's coal carbon emissions have been on the rise from 2000 to 2015, and the decline will be controlled in 2017. The carbon emissions of coal are far greater than those of petroleum. The research on carbon emission factor decomposition and carbon peak prediction based on multi-objective decision-making and information fusion processing has been completed well. The research results can be used for industrial carbon emission factor decomposition and carbon peak prediction in other cities across the country.

Description: Respiration and heartbeats rates are important physiological assessment indicators that provide valid prior-knowledge for the diagnosis of numerous diseases. However, most of the current research focuses on the vital signs measurement of single target, and multi-target vital signs detection has not received much attention. In this paper, we use frequency-modulated continuous wave (FMCW) radar to measure the vital signs signals of multi-target. First, we apply the three-dimensional fast Fourier transform (3D-FFT) method to separate multiple targets and get their distance and azimuth information. Subsequently, the linear constrained minimum variance-based adaptive beamforming (LCMV-ADBF) technique is proposed to form a spatially distributed beams on the targets of interest directions. Finally, a compressive sensing based on orthogonal matching pursuit (CS-OMP) method and rigrsure adaptive soft threshold noise reduction based on discrete wavelet transform (RA-DWT) method are present to extract the respiratory and heartbeat signals. We perform tests in a real experimental environment and compare the proposed method with reference devices. The results show that the degrees of agreement for respiratory and heartbeat are 89% and 87%, respectively, for two human targets. The level of agreement for respiratory and heartbeat is 87% and 85%, respectively, for three human targets, proving the effectiveness of the proposed method.

Description: Unmanned aerial vehicle (UAV) detection has the advantages of flexible deployment and no casualties. It has become a force that cannot be ignored in the battlefield. Scientific and efficient mission planning can help improving the survival rate and mission completion rate of the UAV search in dynamic environments. Towards the mission planning problem of UAV collaborative search for multi-types of time-sensitive moving targets, a search algorithm based on hybrid layered artificial potential fields algorithm (HL-APF) was proposed. This method consists of two parts, a distributed artificial field algorithm and a centralized layered algorithm. In the improved artificial potential field (IAPF), this paper utilized a new target attraction field function which was segmented by the search distance to quickly search for dynamic targets. Moreover, in order to solve the problem of repeated search by the UAV in a short time interval, a search repulsion field generated by the UAV search path was proposed. Besides, in order to solve the unknown target search and improve the area coverage, a centralized layered scheduling algorithm controlled by the cloud server (CS) was added. CS divides the mission area into several sub-areas, and allocates UAV according to the priority function based on the search map. The CS activation mechanism can make full use of prior information, and the UAV assignment cool-down mechanism can avoid the repeated assignment of the same UAV. The simulation results show that compared with the hybrid artificial potential field and ant colony optimization and IAPF, HL-APF can significantly improve the number of targets and mission area coverage. Moreover, comparative experiment results of CS mechanism proved the necessity of setting CS activation and cool-down for improving the search performance. Finally, it also verified the robustness of the method under the failure of some UAVs.

Description: With the in-depth development of the market economy and the acceleration of the process of urbanization, a large number of people have poured into the city, and a large number of residential communities have been developed and constructed. Design quality in the development process is often replaced by output. Some companies attach importance to quality but do not know how to control quality. Based on this, this paper uses the method of multi-sensor information fusion to study the planning and layout design methods of residential areas, and provides a design basis for solving the problems of people’s living environment deterioration and increasingly scarce land resources. Based on the Rhinoceros and Grasshopper parametric platform, this paper integrates residential information model, performance prediction technology, and multi-sensor information fusion technology, taking residential planning and layout parameters as design variables. A set of intelligent optimization system for residential planning and layout based on multi-performance objective simulation was compiled. The “internal factors” and “external factors” that affect the results of RLIOS are studied, and then the residential planning and layout design methods are studied. Experiments have proved that no matter what algorithm is used, the performance of each target can be improved, the floor area ratio performance can be improved by 35.3–3.3%, and the open space performance can be improved by 12.6–31.36%. It shows that the residential planning and layout design method based on multi-sensor information fusion proposed in this paper improves the accuracy and efficiency of the work.

Description: Text detection is a key technique and plays an important role in computer vision applications, but efficient and precise text detection is still challenging. In this paper, an efficient scene text detection scheme is proposed based on the Progressive Scale Expansion Network (PSENet). A Mixed Pooling Module (MPM) is designed to effectively capture the dependence of text information at different distances, where different pooling operations are employed to better extract information of text shape. The backbone network is optimized by combining two extensions of the Residual Network (ResNet), i.e., ResNeXt and Res2Net, to enhance feature extraction effectiveness. Experimental results show that the precision of our scheme is improved more than by 5% compared with the original PSENet.

Description: Unmanned aerial vehicles (UAVs) are considered a promising example of an automatic emergency task in a dynamic marine environment. However, the maritime communication performance between UAVs and offshore platforms has become a severe challenge. Due to the complex marine environment, the task allocation and route planning efficiency of multiple UAVs in an intelligent ocean are not satisfactory. To address these challenges, this paper proposes an intelligent marine task allocation and route planning scheme for multiple UAVs based on improved particle swarm optimization combined with a genetic algorithm (GA-PSO). Based on the simulation of an intelligent marine control system, the traditional particle swarm optimization (PSO) algorithm is improved by introducing partial matching crossover and secondary transposition mutation. The improved GA-PSO is used to solve the random task allocation problem of multiple UAVs and the two-dimensional route planning of a single UAV. The simulation results show that compared with the traditional scheme, the proposed scheme can significantly improve the task allocation efficiency, and the navigation path planned by the proposed scheme is also optimal.

Description: Taking human movements has very good prospects of application in sports, animated projects, medicine and health and other areas. This article aims to study the human motion capture system in sports performances based on the Internet of Things technology and wireless inertial sensors. This article first introduces the theory and characteristics of the Internet of Things and motion capture; next, according to the different characteristics of the sensors in the inertial motion capture system, a two-step Kalman filter is proposed to process the accelerometer and the magnetometer separately and, finally, the structure of this article. The human body motion model is used to analyze the acceleration dynamic error that occurs during the motion. In addition, an inertial motion capture system is constructed to obtain and visualize the structure of each motion node. The experimental results in this paper show that the Kalman filtering algorithm can ensure the accuracy of angle estimation under different motion states and has good fault tolerance to external interference. Among them, the error of the static state is reduced by 23.1%.

Description: Pixel-value differencing (PVD) steganography is a popular spatial domain technology. Several PVD-based studies have proposed extended PVD steganography methods. The majority of these studies have verified their security against the regular-singular (RS) analysis. However, RS analysis is aimed at the feature of the least significant bit substitution method, which is relatively less significant for PVD steganography. The pixel difference histogram (PDH) is generally utilized to attack PVD steganography. If the embedding capacity is high, then the features on the PDH are evident; otherwise, the features are less obvious. In this paper, we propose a statistical feature-based steganalysis technique for the original PVD steganography. Experimental results demonstrate that, compared with existing steganalysis technique with weighted stego-image (WS) method, the proposed method effectively detects PVD steganography at low embedding ratios, such that there is no need of using the original embedding parameters. Furthermore, the accuracy and precision of the method are better than those of existing PVD steganalysis techniques. Therefore, the proposed method contributes to the security analysis of the original PVD steganography as an alternative to the commonly used RS, PDH and WS attack techniques.