ALBERT

Description: Microelectromechanical System (MEMS) Inertial Measurement Unit (IMU) is popular in the community for constructing a navigation system, due to its small size and low power consumption. However, limited by the manufacturing technology, MEMS IMU experiences more complicated noises and errors. Thus, noise modeling and suppression is important for improving accuracy of the navigation system based on MEMS IMU. Motivated by this problem, in this paper, a deep learning method was introduced to MEMS gyroscope de-noising. Specifically, a recently popular Recurrent Neural Networks (RNN) variant Simple Recurrent Unit (SRU-RNN) was employed in MEMS gyroscope raw signals de-noising. A MEMS IMU MSI3200 from MT Microsystem Company was employed in the experiments for evaluating the proposed method. Following two problems were furtherly discussed and investigated: (1) the employed SRU with different training data length were compared to explore whether there was trade-off between the training data length and prediction performance; (2) Allan Variance was the most popular MEMS gyroscope analyzing method, and five basic parameters were employed to describe the performance of different grade MEMS gyroscope; among them, quantization noise, angle random walk, and bias instability were the major factors influencing the MEMS gyroscope accuracy, the compensation results of the three parameters for gyroscope were presented and compared. The results supported the following conclusions: (1) considering the computation brought from training dataset, the values of 500, 3000, and 3000 were individually sufficient for the three-axis gyroscopes to obtain a reliable and stable prediction performance; (2) among the parameters, the quantization noise, angle random walk, and bias instability performed 0.6%, 6.8%, and 12.5% improvement for X-axis gyroscope, 60.5%, 17.3%, and 34.1% improvement for Y-axis gyroscope, 11.3%, 22.7%, and 35.7% improvement for Z-axis gyroscope, and the corresponding attitude errors decreased by 19.2%, 82.1%, and 69.4%. The results surely demonstrated the effectiveness of the employed SRU in this application.

Description: Based on the analysis of geochemical and mineralogical compositions, deep sea clay sediment characteristics and their material sources were examined in the eastern flank of the Gagua Ridge. The mineralogy mainly consists of detrital clay minerals, quartz, and authigenic phillipsite. There is scarce biogenic debris (siliceous or calcareous). The consolidated sediments are more enriched in Si, Al, K, Na, Li, Sc, Cr, Rb, and Cs than the associated crusts and nodules. The unmixed sediment samples were mainlycontributed by Asian eolian dust. The onset of the outer Fe-Mn crust growth nearly coincides with the Central Asia aridification event at ~3.5 Ma, which resulted in an abrupt increase in eolian flux of Asian dust. Intensified surface primary productivity is assumed to bring more metals to deep waters, and eventually facilitate the outer Fe-Mn crust formation. Authigenic phillipsite may come from the alteration of local basic volcanic glasses and cause excess Al, high Al/Ti, and low Si/Al ratios. However, phillipsites hardly affect the abundance of rare earth elements (REEs) and their patterns. In addition, the investigation of two kinds of burrows inside the consolidated sediments reveals that the inner nodules of the amalgamated crusts may remain on the oxic sediment surface, due to frequent benthic activities.

Description: In recent years, various types of terrorist attacks have occurred which have caused worldwide catastrophes. The ability to proactively detect and even predict a potential terrorist risk is critically important for government agencies to react in a timely manner. In this study, a method of geospatial statistics was used to analyse the spatio-temporal evolution of terrorist attacks on the Indochina Peninsula. The machine learning random forest (RF) method was adopted to predict the potential risk of terrorist attacks on the Indochina Peninsula on a spatial scale with 15 driving factors. The RF model performed well with AUC values of 0.839 [95% confidence interval of 0.833–0.844]. The map of the potential distribution of terrorist attack risk was obtained with a 0.05×0.05-degree (approximately 5×5 km) resolution. The results indicate that Thailand is the most dangerous area for terrorist attacks, especially southern Thailand, Bangkok and its surrounding cities. Middle Cambodia and the northern and southern parts of Myanmar are also high-risk areas. Other areas are relatively low risk. This study provides the hotspots for terrorist attacks on a more fine-grained geographical unit. Meanwhile, it shows that machine learning algorithms (e.g., RF) combined with GIS have great potential for simulating the risk of terrorist attacks.

Description: The environment-dependent feature of physical unclonable functions (PUFs) is capable of sensing environment changes. This paper presents an analysis and categorization of a variety of PUF sensors. Prior works have demonstrated that PUFs can be used as sensors while providing a security authentication assurance. However, most of the PUF sensors need a dedicated circuit. It can be difficult to implemented in commercial off-the-shelf devices. This paper focuses on the intrinsic Dynamic Random Access Memory (DRAM) PUF-based sensors, which requires no modifications for hardware. The preliminary experimental results on Raspberry Pi have demonstrated the feasibility of our design. Furthermore, we configured the DRAM PUF-based sensor in a DRAM PUF-based key generation scheme which improves the practicability of the design.

Description: Collaborative target tracking is one of the most important applications of wireless sensor networks (WSNs), in which the network must rely on sensor scheduling to balance the tracking accuracy and energy consumption, due to the limited network resources for sensing, communication, and computation. With the recent development of energy acquisition technologies, the building of WSNs based on energy harvesting has become possible to overcome the limitation of battery energy in WSNs, where theoretically the lifetime of the network could be extended to infinite. However, energy-harvesting WSNs pose new technical challenges for collaborative target tracking on how to schedule sensors over the infinite horizon under the restriction on limited sensor energy harvesting capabilities. In this paper, we propose a novel adaptive dynamic programming (ADP)-based multi-sensor scheduling algorithm (ADP-MSS) for collaborative target tracking for energy-harvesting WSNs. ADP-MSS can schedule multiple sensors for each time step over an infinite horizon to achieve high tracking accuracy, based on the extended Kalman filter (EKF) for target state prediction and estimation. Theoretical analysis shows the optimality of ADP-MSS, and simulation results demonstrate its superior tracking accuracy compared with an ADP-based single-sensor scheduling scheme and a simulated-annealing based multi-sensor scheduling scheme.

Description: Microelectromechanical Systems (MEMS) Inertial Measurement Unit (IMU) containing a three-orthogonal gyroscope and three-orthogonal accelerometer has been widely utilized in position and navigation, due to gradually improved accuracy and its small size and low cost. However, the errors of a MEMS IMU based standalone Inertial Navigation System (INS) will diverge over time dramatically, since there are various and nonlinear errors contained in the MEMS IMU measurements. Therefore, MEMS INS is usually integrated with a Global Positioning System (GPS) for providing reliable navigation solutions. The GPS receiver is able to generate stable and precise position and time information in open sky environment. However, under signal challenging conditions, for instance dense forests, city canyons, or mountain valleys, if the GPS signal is weak and even is blocked, the GPS receiver will fail to output reliable positioning information, and the integration system will fade to an INS standalone system. A number of effects have been devoted to improving the accuracy of INS, and de-nosing or modelling the random errors contained in the MEMS IMU have been demonstrated to be an effective way of improving MEMS INS performance. In this paper, an Artificial Intelligence (AI) method was proposed to de-noise the MEMS IMU output signals, specifically, a popular variant of Recurrent Neural Network (RNN) Long Short Term Memory (LSTM) RNN was employed to filter the MEMS gyroscope outputs, in which the signals were treated as time series. A MEMS IMU (MSI3200, manufactured by MT Microsystems Company, Shijiazhuang, China) was employed to test the proposed method, a 2 min raw gyroscope data with 400 Hz sampling rate was collected and employed in this testing. The results show that the standard deviation (STD) of the gyroscope data decreased by 60.3%, 37%, and 44.6% respectively compared with raw signals, and on the other way, the three-axis attitude errors decreased by 15.8%, 18.3% and 51.3% individually. Further, compared with an Auto Regressive and Moving Average (ARMA) model with fixed parameters, the STD of the three-axis gyroscope outputs decreased by 42.4%, 21.4% and 21.4%, and the attitude errors decreased by 47.6%, 42.3% and 52.0%. The results indicated that the de-noising scheme was effective for improving MEMS INS accuracy, and the proposed LSTM-RNN method was more preferable in this application.

Description: A modified Green-Ampt model was developed to simulate water infiltration in fine-textured soil with a coarse interlayer. Because under such a soil structure, the two soils may not be fully saturated during infiltration, the model introduced two parameters—that is, the saturation coefficients a and b, to reflect the incomplete saturation condition and their influence on infiltration processes. In order to analyze the variation pattern of the two parameters in the above proposed model, scenarios were set for soil column infiltration in fine-textured soil with a coarse interlayer under different buried depths. A Richards equation-based model (RE-Model) was built for simulating the above scenarios and to obtain the evolution of soil water content along the soil profiles. Simulation results show that the infiltration rate decreased to a constant value when the wetting front crossed the upper interface between the fine and coarse soil layer. The soil matrix suction (ψ2) at the upper interface remained unchanged after the wetting front advanced into the coarse layer, and the steady value of ψ2 showed a linear relationship with the buried depth of the coarse layer. Based on the simulation results of the RE-Model, a method was proposed to determine the saturation coefficients related to the relative hydraulic conductivity and water content at ψ2 in the modified Green-Ampt model. Then, the modified model was tested under various infiltration conditions with different soil layered structures, and the results showed good agreement with the experimental data.

Description: Sorghum bicolor (L.) Moench, called sweet sorghum, is a drought-resistant and heat-tolerant plant used for ethanol bioenergy production, and is able to reduce the competition between growing crops for energy vs. growing crops for food. Quantitatively mapping the marginal lands of sweet sorghum is essential for the development of sorghum-based fuel ethanol production. However, knowledge of the contemporary marginal lands of sweet sorghum remains incomplete, and usually relies on sample data or is evaluated at a national or regional scale based on established rules. In this study, a novel method was demonstrated for mapping the global marginal lands of sweet sorghum based on a machine learning model. The total amount of global marginal lands suitable for sweet sorghum is 4802.21 million hectares. The model was applied to training and validation samples, and achieved high predictive performance, with the area under the receiver operating characteristic (ROC) curve (AUC) values of 0.984 and 0.978, respectively. In addition, the results illustrate that maximum annual temperature contributes more than do other variables to the predicted distribution of sweet sorghum and has a contribution rate of 40.2%.