Zoning search strategies have been utilized to solve multimodal multi-objective optimization problems (MMOPs). However, effectively transferring knowledge among subspaces and mitigating the negative transfer remain significant challenges. To this end, we propose an adaptive transfer learning-assisted zoning search (ZSATL) method to assist other multimodal multi-objective evolutionary algorithms (MMOEAs) in obtaining more equivalent Pareto optimal solutions and a high-quality Pareto front approximation. In the ZSATL, the zoning search is employed to segment the search space into many subspaces. Moreover, an adaptive transfer learning method is proposed to alleviate the negative transfer issue. If the distribution of solution sets in two subspaces is similar, the transfer learning method is employed to exchange knowledge. Otherwise, the brain storm optimization algorithm is employed to find promising regions for mining useful knowledge. The performance of the proposed algorithm is compared with that of seven advanced MMOEAs on balanced and imbalanced MMOPs. Based on the experimental results, the ZSATL can locate more equivalent Pareto optimal solutions in the decision space and find a better PF approximation when compared with other competitors.

Hand function impairment induced by factors like stroke exerts a serious impact on human life. Hand function training systems, as key technologies for enhancing hand operation ability, have attracted extensive attention. However, existing systems commonly provide only a single-dimensional function, but overlook the composite characteristics of human tactile perception, resulting in poor practicality. To this end, we present VerTouch, a versatile training system for hand function by exploring tactile perception signatures. Specifically, we first investigate the core algorithms utilized in system implementation, including: kinesthetic function quantitative assessment, low-cost haptic signal reconstruction, and haptic perception test threshold generation. Subsequently, the operational realization of VerTouch is described. The system’s hardware framework encompasses a kinesthetic force-feedback interaction module and a haptic recognition module, augmented by a visual software interface. Finally, the key technologies in the VerTouch system are extensive tested, and the experimental results demonstrate that this system has the capacity to satisfy the requirements of compound hand function training.

This paper presents the design and implementation of Fusang, a low-barrier system that brings accurate and robust 3D object recognition to Commercial-Off-The-Shelf mmWave devices. The basic idea of Fusang is leveraging the large bandwidth of mmWave Radars to capture a unique set of fine-grained reflected responses generated by object shapes. Moreover, Fusang constructs two novel graph-structured features to robustly represent the reflected responses of the signal in the frequency domain and IQ domain, and carefully designs a neural network to accurately recognize objects even in different multipath scenarios. We have implemented a prototype of Fusang on a commodity mmWave Radar device. Our experiments with 24 different objects show that Fusang achieves a mean accuracy of 97% in different multipath environments. The code, dataset, and trained models of Fusang can be obtained at https://github.com/OpenNISLab/Pro-Fusang.

Multimodal multi-objective optimization (MMO) not only finds a good Pareto front (PF) approximation in the objective space, but also locates sufficient equivalent Pareto optimal solutions in the decision space. Although the zoning search (ZS) can improve the population diversity and reduce the problem complexity, it searches each subspace independently. This may waste computational resources. To alleviate the above issue, a zoning search and transfer learning- based multimodal multi-objective evolutionary algorithm (called ZSTL-MMOEA) is proposed in the present study. In the ZSTL-MMOEA, the decision space is divided into many subspaces and the transfer learning is used to realize knowledge sharing between two the most similar subspaces. The ZSTL-MMOEA is compared with five recently proposed multimodal multi-objective evolutionary algorithms (MMOE- As) on 22 test functions. Experimental results show that the proposed algorithm outperforms its competitors in most functions.

Deep learning methods can directly extract effective features from original data. However, this type of model is complex and considered to be a “black box”, which leads to low interpretability of the models. Since the results of attack detection are significant to cybersecurity, every decision should be supported with convincing reasons. Hence, the problem of interpretability has become a bottleneck for deep learning methods applied to attack detection. We propose an interpretable deep learning method based on spatial domain attention. The model can discover and locate the feature strings in the packets, thereby providing a meaningful semantic explanation for the detection results. We conducted qualitative and quantitative experiments on the DARPA1998, UNSW-NB15, and CIC-IDS-2017 datasets. Experimental results show that the interpretability of our method is superior to the state-of-the-art interpretable models in quantifiable criteria, while maintaining comparable classification accuracy.

High-dimensional time-series data from a wide variety of domains, such as neuroscience, are being generated every day. Fitting statistical models to such data, to enable parameter estimation and time-series prediction, is an important computational primitive. Existing methods, however, are unable to cope with the high-dimensional nature of these data, due to both computational and statistical reasons. We mitigate both kinds of issues by proposing an M-estimator for Reduced-rank System IDentification ( Mr. Sid ). A combination of low-rank approximations, ℓ 1 and ℓ 2 penalties, and some numerical linear algebra tricks, yields an estimator that is computationally efficient and numerically stable. Simulations and real data examples demonstrate the usefulness of this approach in a variety of problems. In particular, we demonstrate that Mr. Sid can accurately estimate spatial filters, connectivity graphs, and time-courses from native resolution functional magnetic resonance imaging data. Mr. Sid therefore enables big time-series data to be analyzed using standard methods, readying the field for further generalizations including nonlinear and non-Gaussian state-space models.

This paper presents an analysis and optimization of narrowband active noise control (ANC) systems using the filtered-X least mean-square (LMS) algorithm. First, we derive an upper bound for the eigenvalue spread of the filtered reference signal's covariance matrix, which provides insights into the algorithm convergence speed. The amplitude of an internally generated sinusoidal reference signal is optimized as the inverse of the secondary path's magnitude response at the corresponding frequency to improve the convergence speed. Second, we analyze the characteristic of asymmetric out-of-band overshoot. Based on the analysis result, the phase of the sinusoidal reference signal is optimized to compensate for the phase shift of the secondary path. This phase optimization leads to the minimization of the out-of-band overshoot.