Search

The exploration of deep and subtle oil and gas reservoirs is currently an important means of increasing production in older oil fields. How to effectively identify weak signals with noise is a common problem faced in such reservoirs. Especially for deep seismic reflection data, the application of traditional denoising methods is limited due to the weak energy and small difference frequency band between the effective signals and the noise. A novel method of noise attenuation for weak seismic signals based on compressed sensing and CEEMD (complementary ensemble empirical mode decomposition) was proposed in this work. This method consists of three steps: First, the CEEMD algorithm, a time-frequency analysis method, was introduced into the classic CS (compressed sensing) denoising method to overcome the non-adaptability of CS. CEEMD decomposed the raw seismic signals into sets of IMFs (finite intrinsic mode functions). The IMFs with noise were reconstructed and denoised by CS. In the second step, an enhancement operator was introduced into the penalty term to ensure that the effective signals could be extracted. Finally, the OMP algorithm is adopted to reconstruct the seismic weak signal to prevent the iterative threshold method from damaging weak effective signals. It was demonstrated through the synthetic seismic record and the field seismic data that (a) the CS method can identify the weak signals submerged in the noise by selecting the basic function that is most similar to the effective signals, but it cannot adaptively suppress the high frequency and high wavenumber noise of the complex seismic records; (b) the proposed method overcome the non-adaptability of CS and enhance the edge information described by the curved wave rather than the noises, as a result, the high frequency noise is suppressed while the middle/low frequency noise and weak effective signals are also effectively separated.

Anomaly detectors are used to distinguish the difference between normal and abnormal data, which are usually implemented by evaluating and ranking anomaly scores of each instance. Static unsupervised anomaly detectors can be difficult to adjust anomaly score calculation for streaming data. In real scenarios, anomaly detection often needs to be regulated by human feedback, which benefits to adjust anomaly detectors. In this paper, we propose a human-machine interactive anomaly detection method, named ISPForest, which can be adaptively updated under the guidance of human feedback. In particular, the feedback will be used to adjust the anomaly score calculation and structure of the tree-based detector, ideally attaining more accurate anomaly scores in the future. Our main contribution is to improve the tree model that can be dynamically updated from perspectives of anomaly score calculation and the model’s structure. Our approach is instantiated for the powerful class of tree-based anomaly detectors, and we conduct experiments on a range of benchmark datasets. The results demonstrate that human expert feedback is helpful to improve the accuracy of anomaly detectors.

This paper aims to address the problem of oriented object detection under the complex background of remote sensing images. To this end, we propose a one-stage object detection method with feature fusion structure, and modify the loss function to enhance the detection of small objects. More specifically, on the basis of the end-to-end one-stage object detection model RetinaNet, the method of gliding the vertices of the horizontal bounding box is used to describe an oriented object. In order to obtain multi-scale context information, we design a feature fusion module. Besides, we propose a novel area-weighted loss function to pay more attention to small objects. Experimental results conducted on the DOTA dataset demonstrate that the proposed framework outperforms several state-of-the-art baselines.

With the rapid development of high-speed railway, the mobile communication system for railway need to optimize the allocation of wireless communication resources according to the train motion, thus improving the quality of communication services. In this paper, we construct a chain base station (BS) network model based on LTE-R. A Gauss-Markov (GM) motion prediction model is used to simulate a period of train motion in the orbit, and a cell zooming (CZ) algorithm based on orbital motion prediction and load balance is proposed. The performance of our algorithm is verified by simulation results. When the CZ strategy is implemented or not implemented, the load rate, load balancing factor, blocking rate and throughput of the network model at different moments of the orbital motion are obtained. By comparing these performance indexes, it can be concluded that the proposed CZ algorithm improves these performance indexes.

Although wide-area signals sent by remote phasor measurement units (PMUs) provide better solutions to damp inter-area low frequency oscillations, the random time delay of wide-area signal also brings new challenges for the design of wide-area damping controllers (WADCs). Most of existing wide-area damping controllers require either partial or complete knowledge of time delay. Without any knowledge of the random delays of remote PMU signals, this paper presents a reinforcement learning (RL) based model-free WADC to damp the inter-area low frequency oscillations. The RL agent takes the learning process to maximize the reward function by choosing an optimal action on each state. In terms of the RL algorithm, the absolute value of angular velocity difference between two generators is chosen as states while generators' active power set point is selected as actions. Comparison studies are performed on IEEE 10-Generator 39-Bus system with a fixed parameter WADC and a model-based Q-learning WADC. The results show the proposed model-free WADC can quickly damp inter-area low frequency oscillations with random delays of wide-area signals sent by PMUs, while the fixed parameter WADC fails to stable the system and the model-based Q-learning WADC has large steady-state errors.

In this work, we focus on the autonomous navigation of snake robots in densely-cluttered environments, where collisions between the robot and obstacles are frequent, which could happen often in disaster scenarios, underground caves, or grassland/forest environments. This work takes the view that obstacles are not to be avoided, but rather exploited to support and direct the motion of the snake robot. We build upon a decentralized state-of-the-art compliant controller for serpenoid locomotion, and develop a bi-stable dynamical system that relies on inertial feedback to continuously steer the robot toward a desired direction. We experimentally show that this controller allows the robot to autonomously navigate dense environments by consistently locomoting along a given, global direction of travel in the world, which could be selected by a human operator or a higher level planner. We further equip the robot with an onboard vision system, allowing the robot to autonomously select its own direction of travel, based on the obstacle distribution ahead of its position (i.e., enacting feedforward control). In those additional experiments on hardware, we show how such an exteroceptive sensor can allow the robot to steer before hitting obstacles and to preemptively avoid challenging regions where proprioception-only (i.e., torque and inertial) feedback control would not suffice.

An adaptive dynamic surface controller (ADSC), which comprises an online parameter estimator and a robust control law, is developed for the pneumatic servo systems driven by the proportional directional control valves. Departing from the use of time-consuming offline fitting of the orifice area to accommodate the effect of valve dead zone, this paper employs the least-square-type indirect parameter estimation algorithm with online condition monitoring to estimate the dead-zone parameters and some other important model parameters. These accurate estimates of model parameters are utilized in the development of a precise position tracking controller for the single-rod pneumatic actuator. By using the dynamic surface control technique to synthesize the robust control law, the problem of “explosion of complexity” in traditional backstepping design method is avoided. The stability of the closed-loop system is proved by the means of the Lyapunov theory. The obtained extensive comparative experimental results verify the effectiveness of the proposed valve dead-zone compensation strategy and the high-performance nature of the ADSC in practical implementation.

This paper presents a new method to design the shortest smooth 3D path for multiple Autonomous Underwater Vehicles (AUVs) to visit multiple targets. This path planning method can be separated into the target assignment problem and path designing problem. For the target assignment problem, we compare the genetic algorithm and ant colony optimization algorithm to get target sequence for each AUV with less distance cost. For the given target sequence for each AUVs, the path designing problem is to design shortest smooth path for visiting each target with constraint of G1 continuity. This paper designs 3D Bezier curves by selecting the control points along the incoming and out-going heading direction. Each two-target segment has a set of discrete in-coming and out-going heading direction. For multi-target path planning, the in-coming heading direction and the out-going heading direction at each target have to be the same and the shortest path is selected via back propagation algorithm. It is proved that the combined 3D cubic Bezier curves ensure G1 continuity along the entire multi-target path. Back propagation algorithm is applied to find the shortest curve sequence for multiple targets.

In this paper, An adaptive dynamic surface controller (ADSC) is developed for the pneumatic servo systems with the single-rod pneumatic actuator. The ADSC scheme contains a nonlinear feedback part, a parametric adaption part, and a disturbance observer part in the parallel structure. The nonlinear feedback part is synthesized by the backstepping method, while the explosion of complexity in traditional backstepping design is avoided by utilizing dynamic surface control technique. Since precision motion control of pneumatic servo system is always disturbed by unknown model parameters and disturbance, the gradient adaption laws are employed to further estimate and compensate those factors. Experimental results obtained verify the effectiveness of the proposed ADSC controller and its performance robustness to parameter variations and external disturbance in practical implementation.

Estimation of housing requirement is beneficial for many applications such as guidance of house trading and real estate market regulation. Although there have been studies focusing on the demand analysis of urban resources, estimation of housing requirement is still under explored. To this end, in this paper we propose a systematic housing demand inference method, named Housing Demand Inference Model (HDIM), to estimate housing demand by exploiting the residential mobility of communities based on express delivery data. In this work, we first aggregate the express delivery records at community scale with clustering methods. Then, we propose a useful method to infer residential mobility by extracting express delivery related features and community related features. Since the features extracted are sparse for some residents, we utilize Regularized Singular Value Decomposition Model (RSVD) to construct missing values of features. After that, we infer residential mobility probability of each community by taking advantage of the less sparse features. We also consider community attractiveness as one of the factors influencing housing demand with the help of community profiles and geographical data. With the residential mobility probability and community attractiveness being obtained, we estimate housing demand with a regression model. Finally, experimental results on real-world data show that our model is effective to infer housing demand for communities in urban areas.

In this paper, a disturbance observer based backstepping controller is developed for the electro-pneumatic servo systems with single-rod cylinder. A disturbance observer that does not require the state derivatives is firstly constructed, and based on which a nonlinear control law is then synthesized by adopting the backstepping method. By utilizing the Barrier Lyapunov Function in the controller design, a prescribed tolerance of position tracking error can be guaranteed theoretically. The stability of the closed-loop system is proven by the means of Lyapunov theory. Experimental results are presented to demonstrate the effectiveness of the proposed controller.

Cortical thickness estimation performed in-vivo via magnetic resonance imaging (MRI) is an effective measure of brain atrophy in preclinical individuals at high risk for Alzheimer’s disease (AD). However, the high dimensionality of individual cortical thickness data coupled with small population samples make it challenging to perform cortical thickness feature selection for AD diagnosis and prognosis. Thus far, there are very few methods that can accurately predict future clinical scores using longitudinal cortical thickness measures. In this paper, we propose an unsupervised dictionary learning algorithm, termed Multi-task Sparse Screening (MSS) that produces improved results over previous methods within this problem domain. Specifically, we formulate and solve a multi-task problem using extracted top-p significant features from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) longitudinal data. Empirical studies on publicly available longitudinal data from ADNI dataset (N = 2797) demonstrate improved correlation coefficients and root mean square errors, when compared to other algorithms.

SaaS (Software-as-a-Service) often uses multi-tenancy architecture (MTA) where tenant developers compose their applications online using the components stored in the SaaS database. Tenant applications need to be tested, and combinatorial testing can be used. While numerous combinatorial testing techniques are available, most of them produce static sequences of test configurations and their goal is often to provide sufficient coverage such as 2-way interaction coverage. But the goal of SaaS testing is to identify those compositions that are faulty for tenant applications. This paper proposes an adaptive test configuration generation algorithm AR (Adaptive Reasoning) that can rapidly identify those faulty combinations so that those faulty combinations cannot be selected by tenant developers for composition. The AR algorithm has been evaluated by both simulation and real experimentation using a MTA SaaS sample running on GAE (Google App Engine). Both the simulation and experiment showed show that the AR algorithm can identify those faulty combinations rapidly. Whenever a new component is submitted to the SaaS database, the AR algorithm can be applied so that any faulty interactions with new components can be identified to continue to support future tenant applications.

As a typical multi-hop clustering routing algorithm for wireless sensor networks (WSNs), RBMC (ring-based multi-hop clustering routing algorithm) needs to select cluster heads in every round and the nodes with little energy still have chance to become cluster heads. This leads to extra and uneven consumption of nodes' energy. to address the problem, we propose in this paper an energy-efficient ring-based multi-hop clustering routing algorithm based on RBMC. Our proposed algorithm considers remaining energy when selecting cluster heads and uses multi-round clustering instead of clustering in every round. Simulation results show that our algorithm performs better in reducing the energy consumption of nodes and effectively improves the lifetime of WSNs as compared to RBMC.

In this paper, we proposed an energy-efficient clustering routing algorithm based on directional antennas (EECDA) for wireless sensor networks. In a large scene, a cluster-head is responsible for data acquisition within its cluster and data forwarding among different clusters. As the sensor nodes are too simple and the energy providing is limited, the energy will be quickly run out with the increase of the amount of round. The joining of directional antennas can reduce the interference in network, minimize the unnecessary sending energy consumption, and extend the lifetime of the network. Modeling and simulating of EECDA on the OPNET simulator platform, we get the quantitative results that reflect the performance and effectiveness of our proposed algorithm.