The Linux kernel has been applied in various security-sensitive fields, so ensuring its security is crucial. Vulnerabilities in the Linux kernel are usually caused by undefined behaviors of the C programming language, the most threatening of which are memory safety vulnerabilities. Both the software-based and hardware approaches to memory safety have disadvantages of poor performance, false positives, and poor compatibility. This paper explores the feasibility of using the safe programming language Rust to reconstruct a Linux kernel component and open-source the component's code. We leverage the Rust FFI mechanism to design a safe foreign interface layer to enable the reconstructed component to invoke other Linux functionalities, and then use Rust to reconstruct the component, during which we leverage Rust's type-safety and ownership mechanisms to improve its security, and finally export the C interface of the component to enable the invocation by the Linux kernel. The performance and memory overhead of the reconstructed component, referred to as “rOOM”, were evaluated, revealing a performance overhead of 8.9% in kernel mode, 5% in user mode, 3% in real time, and a memory overhead of 0.06%. These results suggest that it is possible to develop key components of the Linux kernel using Rust in terms of functionality, performance, and memory overhead.

Facial Beauty Prediction (FBP) is a significant pattern recognition task that aims to achieve consistent facial attractiveness assessment with human perception. Currently, Convolutional Neural Networks (CNNs) have become the mainstream method for FBP. The training objective of most conventional CNNs is usually to learn static convolution kernels, which, however, makes the network quite difficult to capture global attentive information, and thus usually ignores the key facial regions, e.g., eyes, and nose. To tackle this problem, we devise a new convolution manner, Dynamic Attentive Convolution (DyAttenConv), which integrates the dynamic and attention mechanism into convolution in kernel-level, with the aim of enforcing the convolution kernels adapted to each face dynamically. DyAttenConv is a plug-and-play module that can be flexibly combined with existing CNN architectures, making the acquisition of the beauty-related features more globally and attentively. Extensive ablation studies show that our method is superior to other fusion and attention mechanisms, and the comparison with other state-of-the-arts also demonstrates the effectiveness of DyAttenConv on facial beauty prediction task.

We introduce the Hexagonal Convolutional Neural Network (HCNN), a modified version of CNN that is robust against rotation. HCNN utilizes a hexagonal kernel and a multi-block structure that enjoys more degrees of rotation information sharing than standard convolution layers. Our structure is easy to use and does not affect the original tissue structure of the network. We achieve the complete rotational invariance on the recognition task of simple pattern images and demonstrate better performance on the recognition task of the rotated MNIST images, synthetic biomarker images and microscopic cell images than past methods, where the robustness to rotation matters.

We thank Kamata et al. (2023) [1] for their interest in our work [2], and for providing an explanation of the quasi-linear kernel from a viewpoint of multiple kernel learning. In this letter, we first give a summary of the quasi-linear SVM. Then we provide a discussion on the novelty of quasi-linear kernels against multiple kernel learning. Finally, we explain the contributions of our work [2].

Human motion prediction has always been an interesting research topic in computer vision and robotics. It means forecasting human movements in the future conditioning on historical 3-dimensional human skeleton sequences. Existing predicting algorithms usually rely on extensive annotated or non-annotated motion capture data and are non-adaptive. This paper addresses the problem of few-frame human motion prediction, in the spirit of the recent progress on manifold learning. More precisely, our approach is based on the insight that achieving an accurate prediction relies on a sufficiently linear expression in the latent space from a few training data in observation space. To accomplish this, we propose Regressive Gaussian Process Latent Variable Model (RGPLVM) that introduces a novel regressive kernel function for the model training. By doing so, our model produces a linear mapping from the training data space to the latent space, while effectively transforming the prediction of human motion in physical space to the linear regression analysis in the latent space equivalent. The comparison with two learning motion prediction approaches (the state-of-the-art meta learning and the classical LSTM-3LR) demonstrate that our GPLVM significantly improves the prediction performance on various of actions in the small-sample size regime.

In this study, we propose an accurate range-Doppler analysis algorithm for moving multiple objects in a short range using microwave (including millimeter wave) radars. As a promising Doppler analysis for the above model, we previously proposed a weighted kernel density (WKD) estimator algorithm, which overcomes several disadvantages in coherent integration based methods, such as a trade-off between temporal and frequency resolutions. However, in handling multiple objects like human body, it is difficult to maintain the accuracy of the Doppler velocity estimation, because there are multiple responses from multiple parts of object, like human body, incurring inaccuracies in range or Doppler velocity estimation. To address this issue, we propose an iterative algorithm by exploiting an output of the WKD algorithm. Three-dimensional numerical analysis, assuming a human body model in motion, and experimental tests demonstrate that the proposed algorithm provides more accurate, high-resolution range-Doppler velocity profiles than the original WKD algorithm, without increasing computational complexity. Particularly, the simulation results show that the cumulative probabilities of range errors within 10mm, and Doppler velocity error within 0.1m/s are enhanced from 34% (by the former method) to 63% (by the proposed method).

Real-time applications are becoming more and more popular, and due to the demand for more compact and portable user devices, offloading terminal processes to edge servers is being considered. Moreover, it is necessary to process packets with low latency on edge servers, which are often virtualized for operability. When trying to achieve low-latency networking, the increase in server power consumption due to performance tuning and busy polling for fast packet receiving becomes a problem. Thus, we design and implement a low-latency and energy-efficient networking system, energy-efficient kernel busy poll (EE-KBP), which meets four requirements: (A) low latency in the order of microseconds for packet forwarding in a virtual server, (B) lower power consumption than existing solutions, (C) no need for application modification, and (D) no need for software redevelopment with each kernel security update. EE-KBP sets a polling thread in a Linux kernel that receives packets with low latency in polling mode while packets are arriving, and when no packets are arriving, it sleeps and lowers the CPU operating frequency. Evaluations indicate that EE-KBP achieves microsecond-order low-latency networking under most traffic conditions, and 1.4× to 3.1× higher throughput with lower power consumption than NAPI used in a Linux kernel.

Packet processing on commodity hardware is a cost-efficient and flexible alternative to specialized networking hardware. However, virtualizing dedicated networking hardware as a virtual machine (VM) or a container on a commodity server results in performance problems, such as longer latency and lower throughput. This paper focuses on obtaining a low-latency networking system in a VM and a container. We reveal mechanisms that cause millisecond-scale networking delays in a VM through a series of experiments. To eliminate such delays, we design and implement a low-latency networking system, kernel busy poll (KBP), which achieves three goals: (1) microsecond-scale tail delays and higher throughput than conventional solutions are achieved in a VM and a container; (2) application customization is not required, so applications can use the POSIX sockets application program interface; and (3) KBP software does not need to be developed for every Linux kernel security update. KBP can be applied to both a VM configuration and a container configuration. Evaluation results indicate that KBP achieves microsecond-scale tail delays in both a VM and a container. In the VM configuration, KBP reduces maximum round-trip latency by more than 98% and increases the throughput by up to three times compared with existing NAPI and Open vSwitch with the Data Plane Development Kit (OvS-DPDK). In the container configuration, KBP reduces maximum round-trip latency by 21% to 96% and increases the throughput by up to 1.28 times compared with NAPI.

Recently, control theory using machine learning, which is useful for the control of unknown systems, has attracted significant attention. This study focuses on such a topic with optimal control problems for unknown nonlinear systems. Because optimal controllers are designed based on mathematical models of the systems, it is challenging to obtain models with insufficient knowledge of the systems. Kernel functions are promising for developing data-driven models with limited knowledge. However, the complex forms of such kernel-based models make it difficult to design the optimal controllers. The design corresponds to solving Hamilton-Jacobi (HJ) equations because their solutions provide optimal controllers. Therefore, the aim of this study is to derive certain kernel-based models for which the HJ equations are solved in an exact sense, which is an extended version of the authors' former work. The HJ equations are decomposed into tractable algebraic matrix equations and nonlinear functions. Solving the matrix equations enables us to obtain the optimal controllers of the model. A numerical simulation demonstrates that kernel-based models and controllers are successfully developed.

The solution of the ordinary kernel ridge regression, based on the squared loss function and the squared norm-based regularizer, can be easily interpreted as a stochastic linear estimator by considering the autocorrelation prior for an unknown true function. As is well known, a stochastic affine estimator is one of the simplest extensions of the stochastic linear estimator. However, its corresponding kernel regression problem is not revealed so far. In this paper, we give a formulation of the kernel regression problem, whose solution is reduced to a stochastic affine estimator, and also give interpretations of the formulation.

Multikernel adaptive filtering is an attractive nonlinear approach to online estimation/tracking tasks. Despite its potential advantages over its single-kernel counterpart, a use of inappropriately weighted kernels may result in a negligible performance gain. In this paper, we propose an efficient recursive kernel weighting technique for multikernel adaptive filtering to activate all the kernels. The proposed weights equalize the convergence rates of all the corresponding partial coefficient errors. The proposed weights are implemented via a certain metric design based on the weighting matrix. Numerical examples show, for synthetic and multiple real datasets, that the proposed technique exhibits a better performance than the manually-tuned kernel weights, and that it significantly outperforms the online multiple kernel regression algorithm.

In this article, we propose a method called “continuous noise masking (cNM)” that allows eliminating residual buzziness in a continuous vocoder, i.e. of which all parameters are continuous and offers a simple and flexible speech analysis and synthesis system. Traditional parametric vocoders generally show a perceptible deterioration in the quality of the synthesized speech due to different processing algorithms. Furthermore, an inaccurate noise resynthesis (e.g. in breathiness or hoarseness) is also considered to be one of the main underlying causes of performance degradation, leading to noisy transients and temporal discontinuity in the synthesized speech. To overcome these issues, a new cNM is developed based on the phase distortion deviation in order to reduce the perceptual effect of the residual noise, allowing a proper reconstruction of noise characteristics, and model better the creaky voice segments that may happen in natural speech. To this end, the cNM is designed to keep only voice components under a condition of the cNM threshold while discarding others. We evaluate the proposed approach and compare with state-of-the-art vocoders using objective and subjective listening tests. Experimental results show that the proposed method can reduce the effect of residual noise and can reach the quality of other sophisticated approaches like STRAIGHT and log domain pulse model (PML).

Convolutional neural networks (CNNS) have a strong ability to understand and judge images. However, the enormous parameters and computation of CNNS have limited its application in resource-limited devices. In this letter, we used the idea of parameter sharing and dense connection to compress the parameters in the convolution kernel channel direction, thus greatly reducing the number of model parameters. On this basis, we designed Shared and Dense Channel-wise Convolutional Networks (SDChannelNets), mainly composed of Depth-wise Separable SD-Channel-wise Convolution layer. The advantage of SDChannelNets is that the number of model parameters is greatly reduced without or with little loss of accuracy. We also introduced a hyperparameter that can effectively balance the number of parameters and the accuracy of a model. We evaluated the model proposed by us through two popular image recognition tasks (CIFAR-10 and CIFAR-100). The results showed that SDChannelNets had similar accuracy to other CNNs, but the number of parameters was greatly reduced.

Stance detection in twitter aims at mining user stances expressed in a tweet towards a single or multiple target entities. Detecting and analyzing user stances from massive opinion-oriented twitter posts provide enormous opportunities to journalists, governments, companies, and other organizations. Most of the prior studies have explored the traditional deep learning models, e.g., long short-term memory (LSTM) and gated recurrent unit (GRU) for detecting stance in tweets. However, compared to these traditional approaches, recently proposed densely connected bidirectional LSTM and nested LSTMs architectures effectively address the vanishing-gradient and overfitting problems as well as dealing with long-term dependencies. In this paper, we propose a neural network model that adopts the strengths of these two LSTM variants to learn better long-term dependencies, where each module coupled with an attention mechanism that amplifies the contribution of important elements in the final representation. We also employ a multi-kernel convolution on top of them to extract the higher-level tweet representations. Results of extensive experiments on single and multi-target benchmark stance detection datasets show that our proposed method achieves substantial improvement over the current state-of-the-art deep learning based methods.

A fast cross-validation algorithm for model selection in kernel ridge regression problems is proposed, which is aiming to further reduce the computational cost of the algorithm proposed by An et al. by eigenvalue decomposition of a Gram matrix.

This paper presents an analysis of random number generators based on continuous-time chaotic oscillators. Two different methods for random number generation have been studied: 1) Regular sampling of a chaotic waveform, and 2) Chaotic sampling of a regular waveform. Kernel density estimation is used to analytically describe the distribution of chaotic state variables and the probability density function corresponding to the output bit stream. Random bit sequences are generated using analytical equations and results from numerical simulations. Applying the concepts of autocorrelation and approximate entropy, randomness quality of the generated bit sequences are assessed to analyze relationships between the frequencies of the regular and chaotic waveforms used in both random number generation methods. It is demonstrated that in both methods, there exists certain ratios between the frequencies of regular and chaotic signal at which the randomness of the output bit stream changes abruptly. Furthermore, both random number generation methods have been compared against their immunity to interference from external signals. Analysis shows that chaotic sampling of regular waveform method provides more robustness against interference compared to regular sampling of chaotic waveform method.

An automorphism of a graph G=(V, E) is such a one-to-one correspondence from vertex set V to itself that all the adjacencies of the vertices are maintained. Given a subset S of V whose one-to-one correspondence is decided, if the vertices of V-S possess unique correspondence in all the automorphisms that satisfy the decided correspondence for S, S is called determiner set of G. Further, S is called minimal determiner set if no proper subset of S is a determiner set and called kernel set if determiner set S with the smallest number of elements. Moreover, a problem to judge whether or not S is a determiner set is called determiner set decision problem. The purpose of this research is to deal with determiner set decision problem. In this paper, we firstly give the definitions and properties related to determiner sets and then propose an algorithm JDS that judges whether a given S is a determiner set of G in polynomial computation time. Finally, we evaluate the proposed algorithm JDS by applying it to possibly find minimal determiner sets for 100 randomly generated graphs. As the result, all the obtained determiner sets are minimal, which implies JDS is a reasonably effective algorithm for the judgement of determiner sets.

Software defect prediction (SDP) plays a significant part in allocating testing resources reasonably, reducing testing costs, and ensuring software quality. One of the most widely used algorithms of SDP models is Naive Bayes (NB) because of its simplicity, effectiveness and robustness. In NB, when a data set has continuous or numeric attributes, they are generally assumed to follow normal distributions and incorporate the probability density function of normal distribution into their conditional probabilities estimates. However, after conducting a Kolmogorov-Smirnov test, we find that the 21 main software metrics follow non-normal distribution at the 5% significance level. Therefore, this paper proposes an improved NB approach, which estimates the conditional probabilities of NB with kernel density estimation of training data sets, to help improve the prediction accuracy of NB for SDP. To evaluate the proposed method, we carry out experiments on 34 software releases obtained from 10 open source projects provided by PROMISE repository. Four well-known classification algorithms are included for comparison, namely Naive Bayes, Support Vector Machine, Logistic Regression and Random Tree. The obtained results show that this new method is more successful than the four well-known classification algorithms in the most software releases.

It is a hot issue that speeding up the network layers and decreasing the network parameters in convolutional neural networks (CNNs). In this paper, we propose a novel method, namely, symmetric decomposition of convolution kernels (SDKs). It symmetrically separates k×k convolution kernels into (k×1 and 1×k) or (1×k and k×1) kernels. We conduct the comparison experiments of the network models designed by SDKs on MNIST and CIFAR-10 datasets. Compared with the corresponding CNNs, we obtain good recognition performance, with 1.1×-1.5× speedup and more than 30% reduction of network parameters. The experimental results indicate our method is useful and effective for CNNs in practice, in terms of speedup performance and reduction of parameters.

Recent studies utilize multiple kernel learning to deal with incomplete-data problem. In this study, we introduce new methods that do not only complete multiple incomplete kernel matrices simultaneously, but also allow control of the flexibility of the model by parameterizing the model matrix. By imposing restrictions on the model covariance, overfitting of the data is avoided. A limitation of kernel matrix estimations done via optimization of an objective function is that the positive definiteness of the result is not guaranteed. In view of this limitation, our proposed methods employ the LogDet divergence, which ensures the positive definiteness of the resulting inferred kernel matrix. We empirically show that our proposed restricted covariance models, employed with LogDet divergence, yield significant improvements in the generalization performance of previous completion methods.