Deep Texture Manifold for Ground Terrain Recognition

Multi-objective optimization sampling based on Pareto optimality for soil mapping

We formulate face localization as a maximum a posteriori probability (MAP) problem of finding the best estimation of human face configuration in a given image. The a prior distribution for intrinsic face configuration is defined by active shape model (ASM). The likelihood model for local facial features is parameterized as mixture of Gaussians in feature space. A hierarchical CONDENSATION framework is then proposed to estimate the face configuration parameter. In order to improve the discriminative power of likelihood distribution in feature space, a new feature subspace, Fisher boosting feature space, is proposed and compared against PCA subspace and biased PCA subspace. Experiments show that, Fisher boosting algorithm can generate strong classifier with less number of weaker classifiers comparing to conventional Adaboosting algorithm as illustrated in a toy problem, that the face localization with Fisher boosting feature subspace outperforms that with PCA feature subspaces in localization accuracy and convergence rate, and that the design of hierarchical CONDENSATION framework alleviates the local minima problem which is frequently encountered by previous ASM optimization algorithms.

PulseID: Multi-scale photoplethysmographic identification using a deep convolutional neural network

Although rare in the sound recognition literature, previous work using features derived from a sparse temporal representation has led to some success [8, 2, 9]. A great advantage of deriving features from a temporal representation is that such an approach does not face the trade-off problem between time and frequency resolution. Here, we present a biologically inspired two-step process for audio classification: In the first step, efficient basis functions are learned in an unsupervised manner [12] on mixtures of percussion sounds (drum phrases). In the second step, features are extracted by using the learned basis functions to decompose percussion sounds (base drum, snare drum, hi-hat) with matching pursuit [7]. The classification accuracy in a 3-class database transfer task is 91.5% as opposed to 70.7% when using MFCC features. Further, we show that a MP-feature representation preserves sound similarity to a greater extent than MFCC-features, i.e. an artificial mixture of two sounds of equal energy normally lies in the middle between the two single sound distributions in feature space. An MP-representation thus inherently contains a similarity measure between different sounds.

A hierarchical naive Bayesian network classifier embedded GMM for textural image

The widely deployment of infrastructure and wireless interfaces increases industrial IoT (IIoT) vulnerability to network intrusions, highlighting the requirements for robust network intrusion detection systems (NIDSs). Although deep learning (DL) provides a promising solution for NIDSs, it remains susceptible to adversarial attacks as minor input perturbations can lead to major misclassifications. In this paper, we propose a packet-level adversarial traffic generation (PATG) approach for attacking NIDSs in IIoT, which not only aligns with domain constraints but also evades various DL-based NIDSs. Particularly, we introduce a reversible abstract traffic representation to ensure that the original traffic can be effectively modified while preserving its functionality. We propose a packet-level generative adversarial networks to craft adversarial traffic by learning benign data distribution in feature space and simulating evasion behaviors, which escapes the DL-based NIDSs. We further design two defense schemes to enhance system resilience against proposed adversarial attacks. We evaluate PATG on nine state-of-the-art DL-based NIDSs in the Kitsune and CICIoT23 datasets. Experimental results demonstrate that PATG can achieve a maximum evasion increase rate of 99% with cost-effective execution, while the defense methods significantly mitigate the impact of the adversarial attacks.

We study the use of Support Vector Machines (SVM) for detecting the occurrence of articulatory features in speech audio data and using the information contained in the detector outputs to improve phone and speech recognition. Our expectation is that an SVM should be able to appropriately model the separation of the classes which may have complex distributions in feature space. We show that performance improves markedly when using discriminatively trained speaker dependent parameters for the SVM inputs, and compares quite well to results in the literature using other classifiers, namely Artificial Neural Networks (ANN). Further, we show that the resulting detector outputs can be successfully integrated into a state of the art speech recognition system, with consequent performance gains. Notably, we test our system on English broadcast news data from dev04f.

Gaussian Mixture Density Modelling and Decomposition (GMDD) is a hierarchical clustering method based on robust statistical theory. Firstly, GMDD is assumed with a mixture group of Gaussian distribution in feature space, then by optimization algorithm the feature which mostly accord with the assumed distribution is hierarchically extracted from space until all of the features in the space are decomposed to a group of featuring pattern. Compared with conventional statistical clustering methods, GMDD's main outstanding superorities are:(1)Initial number of features does not need to be specified a priori; (2)The proportion of noisy data in the mixture can be large; (3)The parameters estimation of each feature is virtually initial independent; and (4)The variability in the shape and size of the feature densities in the mixture is taken into account. The article presented the model named the GMDD based remote sensing image feature estimation model (GIFEM) , and the model of GA space searching optimization is also presented out.

Many of the near-duplicate (ND) image detection methods involve a greater number of interest points (IPs) and large dimensions of the feature descriptors requiring huge computations and are unsuitable for large image databases. They may fail to detect NDs if the query and images in the database contain sparse IPs due to low entropy. Besides, the k-means algorithm used for the quantization of visual words may land at a sub-optimal minimum for descriptors because of their distance distribution in feature space. This article presents a new ND image detection method, which uniformly distributes the IPs over low and high entropy regions, reduces the dimension of feature descriptors using discrete wavelet transform (DWT) and employs Seagull Optimization algorithm (SOA) for optimally forming the visual words. It examines proposed method performs on image databases of various sizes and shows that the developed method is more reliable and computationally efficient than the alternatives.

We develop a conceptually simple, flexible, and effective framework (named T-Net) for two-view correspondence learning. Given a set of putative correspondences, we reject outliers and regress the relative pose encoded by the essential matrix, by an end-to-end framework, which is consisted of two novel structures: "−" structure and "|" structure. " − " structure adopts an iterative strategy to learn correspondence features. "|" structure integrates all the features of the iterations and outputs the correspondence weight. In addition, we introduce Permutation-Equivariant Context Squeeze-and-Excitation module, an adapted version of SE module, to process sparse correspondences in a permutation-equivariant way and capture both global and channel-wise contextual information. Extensive experiments on outdoor and indoor scenes show that the proposed T-Net achieves state-of-the-art performance. On outdoor scenes (YFCC100M dataset), T-Net achieves an mAP of 52.28%, a 34.22% precision increase from the best-published result (38.95%). On indoor scenes (SUN3D dataset), T-Net (19.71%) obtains a 21.82% precision increase from the best-published result (16.18%). Source code: https://github.com/x-gb/T-Net.

Legged robots have potential advantages in mobility compared with wheeled robots in outdoor environments. The knowledge of various ground properties and adaptive locomotion based on different surface materials plays an important role in improving the stability of legged robots. A terrain classification and adaptive locomotion method for a hexapod robot named Qingzhui is proposed in this paper. First, a force-based terrain classification method is suggested. Ground contact force is calculated by collecting joint torques and inertial measurement unit information. Ground substrates are classified with the feature vector extracted from the collected data using the support vector machine algorithm. Then, an adaptive locomotion on different ground properties is proposed. The dynamic alternating tripod trotting gait is developed to control the robot, and the parameters of active compliance control change with the terrain. Finally, the method is integrated on a hexapod robot and tested by real experiments. Our method is shown effective for the hexapod robot to walk on concrete, wood, grass, and foam. The strategies and experimental results can be a valuable reference for other legged robots applied in outdoor environments.

Achieving seamless integration between virtual objects and real scenes has always been an important issue in augmented reality (AR) research. To achieve this, it is necessary to provide virtual objects with real-time and accurate lighting conditions from a real scene. Therefore, the purpose of this study is to realize lighting consistency rendering for real-time AR systems in outdoor environments, aiming to enhance the user’s sense of immersion. In this paper, we propose a lighting consistency technique for real-time AR systems in outdoor environments based on multi-source geographical information (MGI). Specifically, we introduce MGI into the study of lighting consistency and construct a comprehensive database to store and manage the acquired MGI data. Based on this, we proposed a sky radiance model driven using the MGI. Finally, we utilized the sky radiance model along with light sensor data to render the virtual objects in outdoor scenes. The experimental results show that the shadow angular error is reduced to 5.2°, and the system frame rate is increased to 94.26. This means that our method achieves a high level of realism in the fusion of virtual objects and real scenes while ensuring a high frame rate in the system. With this technology, users can conveniently and extensively realize the lighting consistency rendering of real-time AR systems in outdoor scenes using mobile devices.

Aiming at the problems of easy loss of GPS positioning signals in outdoor environments and inaccurate map construction and position drift of traditional SLAM algorithms in outdoor scenes, this paper proposes a 3D LiDAR and inertial guidance tightly coupled SLAM algorithm. Firstly, inertial measurement unit (IMU) forward propagation is used to predict the current position, then backward propagation is used to compensate the motion distortion in the LiDAR data, and the point cloud alignment residuals are constructed based on the GICP algorithm, and then the iterative error state Kalman filter (IESKF) algorithm is utilized to complete the fusion of the point cloud residuals and the a priori position obtained from the forward propagation of the IMU to complete the state updating, and then the front-end fusion odometer is constructed. Next, a sparse voxel near-neighbor structure, iVox-based method, is employed to select key frames and construct local maps, leveraging spatial information during frame-map matching. This approach reduces the computational time required for point cloud alignment. Finally, the proposed algorithm is validated in real-world scenarios and on the outdoor open-source dataset KITTI. It is compared against mainstream algorithms, including FAST-LIO2 and LIO-SAM. The results demonstrate that the proposed approach achieves lower cumulative error, higher localization accuracy, and improved visualization with greater robustness in outdoor environments.

Does protein pretrained language model facilitate the prediction of protein-ligand interaction?

Atrial fibrillation (AF) is a common cardiac disease that potentially leads to fatal conditions. Machine Learning (ML) classification methods are widely used to distinguish between sinus rhythm and AF for post-ablation rhythms in ECG. However, intracardiac electrograms (iEGMs) recorded in the left atrium (LA) and right atrium (RA) might have different sinus rhythms characteristics. In this work, we demonstrate a method to evaluate the iEGMs in the high-dimensional parameter space and effectively discriminate between the sinus rhythms recorded from LA and RA by extracting the features from the time series and using Support Vector Machine (SVM) and K-means clustering. We also demonstrate that the rhythms in LA post ablations exhibit a similar distribution in feature space to that of the sinus RA. The classification has achieved an accuracy of 90.15% for the non-supervised K-Means cluster. It marks the difference between LA and RA baseline and provides insights into signal identification using iEGMs.