Best subset selection is considered the `gold standard' for many sparse learning problems. A variety of optimization techniques have been proposed to attack this non-convex and NP-hard problem. In this paper, we investigate the dual forms of a family of $\ell_0$-regularized problems. An efficient primal-dual method has been developed based on the primal and dual problem structures. By leveraging the dual range estimation along with the incremental strategy, our algorithm potentially reduces redundant computation and improves the solutions of best subset selection. Theoretical analysis and experiments on synthetic and real-world datasets validate the efficiency and statistical properties of the proposed solutions.

This paper explores Deep Learning (DL) methods that are used or have the potential to be used for traffic video analysis, emphasizing driving safety for both Autonomous Vehicles (AVs) and human-operated vehicles. We present a typical processing pipeline, which can be used to understand and interpret traffic videos by extracting operational safety metrics and providing general hints and guidelines to improve traffic safety. This processing framework includes several steps, including video enhancement, video stabilization, semantic and incident segmentation, object detection and classification, trajectory extraction, speed estimation, event analysis, modeling and anomaly detection. Our main goal is to guide traffic analysts to develop their own custom-built processing frameworks by selecting the best choices for each step and offering new designs for the lacking modules by providing a comparative analysis of the most successful conventional and DL-based algorithms proposed for each step. We also review existing open-source tools and public datasets that can help train DL models. To be more specific, we review exemplary traffic problems and mentioned requires steps for each problem. Besides, we investigate connections to the closely related research areas of drivers' cognition evaluation, Crowd-sourcing-based monitoring systems, Edge Computing in roadside infrastructures, Automated Driving Systems (ADS)-equipped vehicles, and highlight the missing gaps. Finally, we review commercial implementations of traffic monitoring systems, their future outlook, and open problems and remaining challenges for widespread use of such systems.

Nowadays wireless communication is rapidly reshaping entire industry sectors. In particular, mobile edge computing (MEC) as an enabling technology for industrial Internet of things (IIoT) brings powerful computing/storage infrastructure closer to the mobile terminals and, thereby, significant lowers the response latency. To reap the benefit of proactive caching at the network edge, precise knowledge on the popularity pattern among the end devices is essential. However, the complex and dynamic nature of the content popularity over space and time as well as the data-privacy requirements in many IIoT scenarios pose tough challenges to its acquisition. In this article, we propose an unsupervised and privacy-preserving popularity prediction framework for MEC-enabled IIoT. The concepts of local and global popularities are introduced and the time-varying popularity of each user is modelled as a model-free Markov chain. On this basis, a novel unsupervised recurrent federated learning (URFL) algorithm is proposed to predict the distributed popularity while achieve privacy preservation and unsupervised training. Simulations indicate that the proposed framework can enhance the prediction accuracy in terms of a reduced root-mean-squared error by up to $60.5\%-68.7\%$. Additionally, manual labeling and violation of users' data privacy are both avoided.

There has been a surge in research in multimodal machine translation (MMT), where additional modalities such as images are used to improve translation quality of textual systems. A particular use for such multimodal systems is the task of simultaneous machine translation, where visual context has been shown to complement the partial information provided by the source sentence, especially in the early phases of translation. In this paper, we propose the first Transformer-based simultaneous MMT architecture, which has not been previously explored in simultaneous translation. Additionally, we extend this model with an auxiliary supervision signal that guides the visual attention mechanism using labelled phrase-region alignments. We perform comprehensive experiments on three language directions and conduct thorough quantitative and qualitative analyses using both automatic metrics and manual inspection. Our results show that (i) supervised visual attention consistently improves the translation quality of the simultaneous MMT models, and (ii) fine-tuning the MMT with supervision loss enabled leads to better performance than training the MMT from scratch. Compared to the state-of-the-art, our proposed model achieves improvements of up to 2.3 BLEU and 3.5 METEOR points.

Many have heralded artificial intelligence as a force-multiplier for defence and intelligence capabilities. Do you want armed autonomous vehicles to comply with legal and ethical obligations as set out in the Royal Australian Navy's robotics, autonomous systems and AI strategy? Do you want to more effectively analyse intelligence to predict what an adversary will do next? And AI's proponents are right--it could, and likely will, do all of those things, but not yet. Its ability to spot patterns, compute figures and calculate optimum solutions on an'if X happens then do Y' basis is now unmatched by any human being.

Hasit Trivedi, CTO Digital Technologies & Global Head -- AI, Tech Mahindra explains how Artificial Intelligence will reshape the future, what technologies Tech Mahindra is using right now, and more. We are on the verge of a watershed moment in our species' history, one in which a product of our own ingenuity has the potential to change everything. Some see it as humanity's salvation, while others see it as our undoing. The age of artificial intelligence has arrived (AI). While AI is still a long way from the sentient machines depicted in science fiction, developing algorithms that can learn, understand language, and mimic some aspects of the human mind has resulted in tremendous progress.

Machine learning (ML) is one of the most profitable sectors of software development right now. That's because of how useful machine learning techniques are in the rapidly growing field of data science. Data science, a field of applied mathematics and statistics, gleans useful information by the analysis and modeling of large amounts of data. Machine learning involves developing computer systems that learn and adapt using algorithms and statistical models. Applying ML techniques to data science makes it possible to advance from insights to actionable predictions.

Isolation of spacecraft microvibrations is essential for the successful deployment of instruments relying on high-precision pointing. Hexapod platforms represent a promising solution, but the difficulties associated with attaining desirable 3D dynamics within acceptable mass and complexity budgets have led to a minimal practical adoption. This paper addresses the influence of strut boundary conditions (BCs) on system-level mechanical disturbance suppression. Inherent limitations of the traditional all-rotational joint configuration are highlighted and shown to originate in link mass and rotational inertia. A pin-slider BC alternative is proposed and analytically proven to alleviate them in both 2D and 3D. The advantages of the new BC hold for arbitrary parallel manipulators and are demonstrated for several hexapod geometries through numerical tests. A configuration with favourable performance is suggested. Finally, a novel planar joint that allows the physical realisation of the proposed BC is described and validated. Consequently, this work enables the development of platforms for microvibration attenuation that do not require active control.

Decision making algorithms, in practice, are often trained on data that exhibits a variety of biases. Decision-makers often aim to take decisions based on some ground-truth target that is assumed or expected to be unbiased, i.e., equally distributed across socially salient groups. In many practical settings, the ground-truth cannot be directly observed, and instead, we have to rely on a biased proxy measure of the ground-truth, i.e., biased labels, in the data. In addition, data is often selectively labeled, i.e., even the biased labels are only observed for a small fraction of the data that received a positive decision. To overcome label and selection biases, recent work proposes to learn stochastic, exploring decision policies via i) online training of new policies at each time-step and ii) enforcing fairness as a constraint on performance. However, the existing approach uses only labeled data, disregarding a large amount of unlabeled data, and thereby suffers from high instability and variance in the learned decision policies at different times. In this paper, we propose a novel method based on a variational autoencoder for practical fair decision-making. Our method learns an unbiased data representation leveraging both labeled and unlabeled data and uses the representations to learn a policy in an online process. Using synthetic data, we empirically validate that our method converges to the optimal (fair) policy according to the ground-truth with low variance. In real-world experiments, we further show that our training approach not only offers a more stable learning process but also yields policies with higher fairness as well as utility than previous approaches.

Bingxin Gu and Mingyuan Meng contributed equally to this work. Abstract Objective: Deep Learning-based Radiomics (DLR) has achieved great success in medical image analysis and has been considered as a replacement to conventional radiomics that relies on handcrafted features. In this study, we aimed to explore the capability of DLR for the prediction of 5-year Progression-Free Survival (PFS) in advanced Nasopharyngeal Carcinoma (NPC) using pretreatment PET/CT images. Methods: A total of 257 patients (170/87 patients in internal/external cohorts) with advanced NPC (TNM stage III or IVa) were enrolled. We developed an end-to-end multi-modality DLR model, in which a 3D convolutional neural network was optimized to extract deep features from pretreatment PET/CT images and predict the probability of 5-year PFS. TNM stage, as a high-level clinical feature, could be integrated into our DLR model to further improve the prognostic performance. For a comparison between conventional radiomics and DLR, 1456 handcrafted features were extracted, and optimal conventional radiomics methods were selected from 54 cross-combinations of 6 feature selection methods and 9 classification methods. In addition, risk group stratification was performed with clinical signature, conventional radiomics signature, and DLR signature. Results: Our multi-modality DLR model using both PET and CT achieved higher prognostic performance (AUC = 0.842 0.034 and 0.823 0.012 for the internal and external cohorts) than the optimal conventional radiomics method (AUC = 0.796 0.033 and 0.782 0.012). Furthermore, the multi-modality DLR model outperformed single-modality DLR models using only PET (AUC = 0.818 0.029 and 0.796 0.009) or only CT (AUC = 0.657 0.055 and 0.645 0.021). For risk group stratification, the conventional radiomics signature and DLR signature enabled significant difference between the high-and low-risk patient groups in the both internal and external cohorts (P < 0.001), while the clinical signature failed in the external cohort (P = 0.177).