Search

Pilots face complex working environments during flight missions, which can easily lead to excessive workload and affect flight safety. Physiological signals are commonly used to evaluate a pilot’s workload because they are objective and can directly reflect physiological mental states. However, existing methods have shortcomings in temporal modeling, making it challenging to fully capture the dynamic characteristics of physiological signals over time. Moreover, fusing features of data from different modalities is also difficult.To address these problems, we proposed a temporal relation modeling and multimodal adversarial alignment network (TRM-MAAN) for pilot workload evaluation. Specifically, a Transformer-based temporal relationship modeling module was used to learn complex temporal relationships for better feature extraction. In addition, an adversarial alignment-based multi-modal fusion module was applied to capture and integrate multi-modal information, reducing distribution shifts between different modalities. The performance of the proposed TRM-MAAN method was evaluated via experiments of classifying three workload states using electroencephalogram (EEG) and electromyography (EMG) recordings of eight healthy pilots.Experimental results showed that the classification accuracy and F1 score of the proposed method were significantly better than the baseline model across different subjects, with an average recognition accuracy of $91.90~\pm ~1.72\%$ and an F1 score of $91.86~\pm ~1.75\%$ .This work provides essential technical support for improving the accuracy and robustness of pilot workload evaluation and introduces a promising way for enhancing flight safety, offering broad application prospects. Clinical and Translational Impact Statement: The proposed scheme provides a promising solution for workload evaluation based on electrophysiological signals, with potential applications in aiding the clinical monitoring of fatigue, mental status, cognitive psychology, and other disorders.

Cooperative communication techniques are widely used in large-scale wireless networks for improving network throughput. This is achieved through the creation of transmission diversity by forming multiple cooperative transmission links which involve several relaying nodes as helpers for an end-to-end data transmission. Consequently, link interference range will inevitably be enlarged, which will adversely hamper the diversity created and offset the network throughput improvement as a result. This problem has not been properly addressed by most cooperative communication protocols reported so far. In this paper, a novel protocol that performs cooperative medium access control as well as minimizes the interference range, namely MIR-CMAC, is proposed to directly address the enlarged link interference range problem introduced by cooperative communication. Specifically, functions like channel reservation, cooperative priority differentiation and contention for relay selection are collectively enabled in MIR-CMAC to reduce channel access collision and select the suitable helper node that can maximize the integrated link data rate and minimize the link interference concerned. In addition, a full interference model is established to evaluate the effect of interference across the whole process from channel access to packet transmission and derive a new network throughput analysis method for MIR-CMAC. Both numerical and simulation results demonstrate the effectiveness of MIR-CMAC and its performance improvements over other protocols.

Nuclei detection is a fundamental task for numerous downstream analysis of histopathology images. Usually, it requires a large number of labeled images for fully supervised nuclei detection to achieve optimal performance. However, the process of collecting sufficient and high-quality ground truth labels is extremely labor intensive. To alleviate this problem, in this paper, a novel semi-supervised learning framework is proposed for nuclei detection, which optimizes the detection network with the involvement of unlabeled image reconstruction. Specifically, we reconstruct unlabeled images from their detection maps representing detailed information about individual location of candidate nucleus, which will aid in regularizing the training process of the detection network by encouraging spatial consistency between original and reconstructed images. Moreover, to further facilitate image reconstruction, we adopt an adversarial learning scheme using image and instance level discriminators for the classification of original and reconstructed images t. In this way, the capability of the detection network is successfully enhanced by taking advantage of both labeled and unlabeled images, thus leading to more accurate nuclei detection results. Extensive experiments show that we compare favorably with previous studies in various settings, which highlights the effectiveness of our proposed framework.

A wideband vertically-polarized end-fire magneto-electric (ME) dipole antenna fed by an asymmetrical substrate integrated coaxial line (ASICL) is proposed for millimeter-wave (mm-wave) applications. The proposed ME dipole antenna has an impedance bandwidth of 60% and produces an end-fire radiation with a stable gain between 5.8 and 6.9 dBi in simulation. To verify the design concept and its application in arrays, a 1 × 8 linear array with a fixed beam and a 1 × 4 linear array with multiple beams are designed, fabricated and measured. The fabricated fixed-beam array prototype exhibits an impedance bandwidth of 62%, a peak gain of 15.9 dBi and a radiation efficiency of 79%. The multi-beam array is fed by a 4 × 4 ASICL Butler matrix. Experimentally, excellent beam scanning radiation patterns with reasonably low side lobes and low cross polarizations are demonstrated at 24, 30 and 36 GHz. And an overlapped operating bandwidth of 28.6% is achieved by the fabricated prototype.

As a core step in clustering analysis, distance measurement results can influence clustering accuracy. Existing measurement methods are mostly based on cluster feature information. However, these cluster features may be insufficient and result in losing data information for clusters containing a number of objects. To improve measurement accuracy, we make full use of the distribution characteristics of objects in clusters, i.e., we use descriptive statistics and the Wilcoxon-Mann-Whitney rank sum test in nonparametric statistics to measure distances during clustering. Furthermore, we propose a two-stage clustering algorithm to improve clustering analysis performance. In terms of avoiding preliminarily assuming the number of clusters, with the proposed distance measurement method, the clustering algorithm can discover clusters with arbitrary shapes and improve clustering accuracy. Experiments with multiple datasets compared with other clustering algorithms illustrate the accuracy and efficiency of the proposed clustering algorithm.

Recent advances in evolutionary algorithms based on membrane computing have shown that the mechanism of membrane computing is an effective way to solve optimization problems. In this work, we propose a new evolutionary multi-objective algorithm that uses membrane systems to solve multi-objective optimization problems. Based on the mechanism of living cell structure and function, the algorithm introduces three factors, including membrane structure, multiset and reaction rules. The membrane structure of the proposed algorithm is inspired by the structure of the membrane system, which has multiple layers and nested structures in the skin membrane. Two special symbol-objects are designed to improve the search efficiency of the algorithm. In addition, some reaction rules are used to evolve the symbol-objects of multiset in the inner region of the membrane. In addition, the proposed method combines external archive to maintain the diversity of non-dominated solutions and enhance the search capabilities of the solutions. Our proposed method is compared to five state-of-the-art multi-objective heuristic algorithms. For comparison, six different criteria were used: the quality of the resulting approximate set, the diversity of candidate solutions, and the rate of convergence to the Pareto front. Experimental results show that the proposed method is competitive in performance in qualitative and quantitative measurements of selected test functions. Therefore, the algorithm is feasible and effective for solving multi-objective optimization problems.

This paper proposes an optimal generation scheduling approach based on linear relaxation and mixed integer programming, which is used to solve the generation dispatch problem. The quadratic transmission loss constraint of each transmission line is converted into linear constraints by using the linear relaxation and mixed integer programming technique. Consequently, the original optimal generation scheduling problem is formulated as a quadratic programming or mixed integer quadratic programming problem that can be solved by commercial optimization solver. In order to improve the efficiency of algorithm, this paper further analyses the generation scheduling model and deletes the redundant variables and constraints. Three test systems, including IEEE 30-node system, IEEE 118-node system, and Polish 2746-node system, are employed to examine the effectiveness of the proposed method. The comparative results obtained by the proposed method, quadratically constrained quadratic programming method (QCQP), and solving constraint integer programs solver (SCIP) verify the effectiveness of the proposed method in solving the optimal generation scheduling problem.

Accurate protein contact map prediction is essential for de novo protein structure prediction. Over the past few years, deep learning has brought a significant breakthrough in protein contact map prediction and optimized deep learning architectures are highly desired for performance improvement. As an emerging deep learning architecture, the generative adversarial network (GAN) has shown the powerful capability of learning intrinsic patterns, which inspires us to comprehensively exploit GAN for predicting accurate protein contact maps. In this study, we present GANcon, a novel GAN-based deep learning architecture for protein contact map prediction, which to the best of our knowledge is the first GAN-based approach in this field. Instead of using a single neural network, GANcon is composed of two competitive networks that are evolving through adversarial learning. The generator network employs a dedicated encoder-decoder architecture that can efficiently capture the underlying contact information from versatile protein features to generate contact maps, while the discriminator network learns the differences between generated contact maps and real ones and promotes the generator network to produce more accurate contact maps. Moreover, to deal with the imbalance problem and take into account the symmetry of contact maps, we also propose a novel symmetrical focal loss, which can further enhance the effectiveness of adversarial learning for better performance. The experimental results on several datasets demonstrate that GANcon outperforms many state-of-the-art methods, indicating the effectiveness of our method for predicting protein contact maps. GANcon is freely available at https://github.com/melissaya/GANcon.

High-baud-rate coherent optical system is essential to support the ever-increasing demand for high-speed applications. Owing to the recent progress in advanced modulation formats, over 1 Tb/s single-carrier data transmission has been achieved in the laboratory, and its commercial application is envisioned in the near future. This paper presented the trend of increasing baud rate and utilizing high-order quadrature-amplitude modulation (QAM), and several enabling technologies in the coherent optical communication systems. We first discussed recent progress of high-order QAM system and digital signal processing technology. Furthermore, we compared the transmission performance of three different ultrahigh-order QAM formats. The paper then reviewed the commonly used methods of achieving over 100 GBaud optically modulated signals. Besides, five attractive modulators and their corresponding modulation structures are illustrated. Key performance parameters including electrode length, 3-dB bandwidth, half-wave voltage, extinction ratio and optical loss are also compared. Finally, the trade-off between the baud rate and QAM orders in implementing high-speed systems are investigated in simulations. The results show that for the coming 800 GbE or 1.6 TbE, PDM-64-QAM might be an idea choice by considering the trade-off between the link reach and required system bandwidth. By adopting the latest probabilistic shaping technology, higher-order QAM signals, such as PS PDM-256-QAM, could be favorable for long reach applications while using extra system bandwidth.

A silicon nitride horizontal slot waveguide with silicon dioxide cladding is designed to achieve flat negative dispersion (-3 W. After passing through another ideal positive dispersion element, we find that the output pulse peak power can be recompressed close to 1 W in the case of different input pulse widths. Moreover, for the input pulse with a much higher peak power, the pulse width of the output pulse can be compressed to a much narrower level because of the spectral broadening introduced by optical nonlinearity. A 100-fs input pulse with 10-kW peak power can be compressed to 12.5 fs with a peak power of 63 kW. Considering the time-domain broadening and the peak power reduction, such a slot waveguide with a flat negative dispersion could be used as a time stretcher for 10-fs level pulse in on-chip chirped pulse amplification (CPA) system.

The cross-view multimedia are widely existed and attract many attentions in recent years. Nevertheless, it is noted that the phenomenon, that data in different classes from same view are more similar than that in same class from different views, is usually presented for cross-view multimedia data. The intrinsic imperfection leads disappointing performance for cross-view multimedia recognition or classification. To solve this problem, in this paper, we propose a novel discriminative learning framework with low-rank constraint, which can be applied for view-invariant low-dimensional subspace learning. The advantages of our framework include three aspects. Firstly, to unlock the latent class structure and view structure, a self-expressed model by dual low-rank constraints are presented, which can separate the two manifold structures in the learned subspace. Secondly, two effective discriminative graphs are constructed to guide the affinity relationship of data in the above two low-dimensional projected subspaces respectively. Finally, the joint semantic consensus constraint is designed to be integrated into the learning framework, which can explore the shared and view-specific information for enforcing the view-invariant character in semantic space. Experimental results on several public cross-view multimedia datasets demonstrate that our proposed method outperforms existing excellent subspace learning approaches.

Survival analysis is a branch of statistics to analyze the time duration that is expected until some events of interest happen, like the death in the organisms of biology. Currently, survival analysis based on pathological images has turned out to be a truly energetic area in the research of healthcare for making primary decisions on therapy and improving patients' quality of treatment. In this regard, the interest to design convolutional neural networks for survival analysis with pathological images is increasing greatly at present. Furthermore, to consider the important spatial hierarchies between features and improve the robustness to affine transformation, capsule network (referred to as CapsNet) has been put forward in recent years. A novel capsule network named CapSurv is introduced in this paper, with a new loss function named survival loss to make survival analysis with whole slide pathological images. In addition, to train CapSurv preferably, semantic-level features extracted by VGG16, are used to distinguish discriminative patches from whole slide pathological images. Our method is applied to the predictions of the survival of glioblastoma and lung squamous cell carcinoma with a public cancer dataset. The results illustrate the proposed CapSurv model has the ability to improve the performance of the prediction by comparing with state-of-the-art survival models.

Modifying and generating facial images with desired attributes are two important and highly related tasks in the field of computer vision. Some current methods can take advantage of their relationship and use a unified model to handle them simultaneously. However, producing high visual quality images on both tasks is still a challenge. To tackle this issue, we propose a novel model called adversarially regularized U-net (ARU-net)-based generative adversarial networks (ARU-GANs). The ARU-net is the major part of the ARU-GAN and is inspired by the design principle of U-net. It uses skip connections to pass different-level features from encoder to decoder, which preserves sufficient attribute-independent details for the modification task. Besides, this U-net-like architecture employs an adversarial regularization term to guide the distribution of latent representation to match the prior distribution, which guarantees to generate meaningful faces from this prior. We also propose a joint training technique for the ARU-GAN, which enables the facial attribute modification and generation tasks to learn together during training. We perform experiments on celebfaces attributes (CelebA) dataset and make visual analysis and quantitative evaluation on both tasks, which demonstrates that our model can successfully produce high visual quality facial images. Also, the results show that learning two tasks jointly can lead to performance improvement compared with learning them individually. At last, we further validate the effectiveness of our method by making an ablation study and experimenting on another dataset.

A dual linearly polarized antenna array with end-fire radiation of the 60-GHz band is proposed by combining two types of magneto-electric dipoles (ME-dipole), which operate in vertical polarization (V-pol) and horizontal polarization (H-pol), respectively. Based on the substrate integrated waveguide structure, two kinds of ME-dipole are placed closely by sharing the same metallic post wall between them, achieving an element space of 0.77λ0. Besides, mutual coupling between the close elements is numerically analyzed and then suppressed by making modifications to the antenna structure. The proposed dual-polarized element achieves bandwidths of 26% and 32% (|S11|

Next-generation sequencing has been widely used in cancer-focused studies for comprehensive landscape of tumor genomes. Detection of genomic aberrations is one of the focal points in this area. Analysis of tumor sequencing data is usually complicated by several critical issues, such as GC-content bias, mappability bias, tumor impurity, and aneuploidy. Efficient computational methods are still in great demand for comprehensively addressing these issues. We introduce GPHMM-SEQ, a novel algorithm for inferring tumor impurity and ploidy as well as detecting copy number alterations and loss of heterozygosity from paired tumor-normal samples. Read depth signals derived from sequencing data are analyzed using a novel hidden Markov model that employs integrated representation of GC-content bias, mappability bias, tumor impurity, and aneuploidy. The evaluation on simulated and real tumor sequencing data demonstrates GPHMM-SEQ has the superior performance compared to existing methods.

Multi-task learning has received great interest recently in the area of machine learning. It shows a considerable capacity to jointly learn multiple latent relationships hidden among tasks, and has been widely used in data mining and computer vision problems. In this paper, we propose a new multi-task based collaborative linear regression framework to address the image classification problem, which allows the class-specific and collaboratively shared latent structure components to be explored simultaneously. The proposed framework takes multi-target regression of each class as a task to transfer shared structures among them. To be more efficient and adaptive, the class-wise nonlinear subspace is also learned in this framework to earn inter-class discrimination and model adaptability. The proposed framework provides a unified and flexible perceptiveness for jointly learning the nonlinear projected features and regression parameters. Furthermore, a numerical scheme via iterative alternating optimization is also developed to solve the novel objective function in the proposed framework and guarantee the convergence. Extensive experimental results tested on several datasets demonstrated that our proposed framework outperforms existing competitive methods and achieves consistently high performance.