The sun is highly complex in nature and its observatory imagery features is one of the most important sources of information about the sun activity, space and Earth's weather conditions. The NASA, solar Dynamics Observatory captures approximately 70,000 images of the sun activity in a day and the continuous visual inspection of this solar observatory images is challenging. In this study, we developed a technique of tracking the sun's activity using 2D circular kernel time series transformation, statistical and entropy measures, with machine learning approaches. The technique involves transforming the solar observatory image section into 1-Dimensional time series (1-DTS) while the statistical and entropy measures (Approach 1) and direct classification (Approach 2) is used to capture the extraction features from the 1-DTS for machine learning classification into 'solar storm' and 'no storm'. We found that the potential accuracy of the model in tracking the activity of the sun is approximately 0.981 for Approach 1 and 0.999 for Approach 2. The stability of the developed approach to rotational transformation of the solar observatory image is evident. When training on the original dataset for Approach 1, the match index (T90) of the distribution of solar storm areas reaches T90 ~ 0.993, and T90 ~ 0.951 for Approach 2. In addition, when using the extended training base, the match indices increased to T90 ~ 0.994 and T90 ~ 1, respectively. This model consistently classifies areas with swirling magnetic lines associated with solar storms and is robust to image rotation, glare, and optical artifacts.

Tensor networks are factorizations of high-dimensional tensors into network-like structures composed of smaller tensors. Originating from condensed matter physics and acclaimed for their efficient representation of quantum many-body systems [1-10], these structures have allowed researchers to comprehend the intricate properties of such systems and, additionally, simulate them using classical computers [11-13]. Notably, tensor networks are the most successful method for simulating the results of quantum advantage experiments [14-16]. Furthermore, tensor networks were rediscovered within the numerical linear algebra community [17-19], where the techniques have been adapted to other high-dimensional problems such as numerical integration [20], signal processing [21], or epidemic modelling [22]. With the advent of machine learning and the the quest for expressive yet easy-to-train models, tensor networks have been suggested as promising candidates, due to their ability to parameterize regions of the complex space of size exponential in the number of input features. Since the pioneering works [23, 24] that used simple, 1-dimensional networks known as Matrix Product States (MPS) in the physics literature [4, 25] and as Tensor Trains in the numerical linear algebra literature [18], these have been applied in both supervised and unsupervised learning settings [26-28].

The diagnosis of faults present in a REM is integrated by the detection, identification and isolation of an anomaly, which can be achieved by using the information obtained on the state of operation of the equipment or drive [3]. As a result, it is possible to consider fault diagnosis as a pattern recognition problem with respect to the condition of a REM [4]. To effectively diagnose faults in a REM, it is essential to distinguish between failures originating from the machine itself, whether electrical or mechanical, and those corresponding to the associated load [5]. In recent decades, with the advancement of communication technologies and the inclusion of control devices in REM, non-invasive faults detection and diagnosis techniques based on the use of electrical variables have been studied more than those that use acoustic emissions, analysis lubrication, thermography and vibrations. The latter have been the techniques most widely used for some time, in which different methods are used for analysis, among the most common, Fast Fourier Transform (FFT) in the frequency domain, and wavelet analysis and empirical model decomposition in the domain time-frequency [6].

Automatic emotion recognition has recently gained significant attention due to the growing popularity of deep learning algorithms. One of the primary challenges in emotion recognition is effectively utilizing the various cues (modalities) available in the data. Another challenge is providing a proper explanation of the outcome of the learning.To address these challenges, we present Explainable Multimodal Emotion Recognition with Situational Knowledge (EMERSK), a generalized and modular system for human emotion recognition and explanation using visual information. Our system can handle multiple modalities, including facial expressions, posture, and gait, in a flexible and modular manner. The network consists of different modules that can be added or removed depending on the available data. We utilize a two-stream network architecture with convolutional neural networks (CNNs) and encoder-decoder style attention mechanisms to extract deep features from face images. Similarly, CNNs and recurrent neural networks (RNNs) with Long Short-term Memory (LSTM) are employed to extract features from posture and gait data. We also incorporate deep features from the background as contextual information for the learning process. The deep features from each module are fused using an early fusion network. Furthermore, we leverage situational knowledge derived from the location type and adjective-noun pair (ANP) extracted from the scene, as well as the spatio-temporal average distribution of emotions, to generate explanations. Ablation studies demonstrate that each sub-network can independently perform emotion recognition, and combining them in a multimodal approach significantly improves overall recognition performance. Extensive experiments conducted on various benchmark datasets, including GroupWalk, validate the superior performance of our approach compared to other state-of-the-art methods.

Cognitive science and psychology suggest that object-centric representations of complex scenes are a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep reinforcement learning approaches rely on only pixel-based representations that do not capture the compositional properties of natural scenes. For this, we need environments and datasets that allow us to work and evaluate object-centric approaches. We present OCAtari, a set of environment that provides object-centric state representations of Atari games, the most-used evaluation framework for deep RL approaches. OCAtari also allows for RAM state manipulations of the games to change and create specific or even novel situations. The code base for this work is available at github.com/k4ntz/OC_Atari.

Simultaneous speech translation (SimulST) translates partial speech inputs incrementally. Although the monotonic correspondence between input and output is preferable for smaller latency, it is not the case for distant language pairs such as English and Japanese. A prospective approach to this problem is to mimic simultaneous interpretation (SI) using SI data to train a SimulST model. However, the size of such SI data is limited, so the SI data should be used together with ordinary bilingual data whose translations are given in offline. In this paper, we propose an effective way to train a SimulST model using mixed data of SI and offline. The proposed method trains a single model using the mixed data with style tags that tell the model to generate SI- or offline-style outputs. Experiment results show improvements of BLEURT in different latency ranges, and our analyses revealed the proposed model generates SI-style outputs more than the baseline.

Random graph models are playing an increasingly important role in science and industry, and finds their applications in a variety of fields ranging from social and traffic networks, to recommendation systems and molecular genetics. In this paper, we perform an in-depth analysis of the random Kronecker graph model proposed in \cite{leskovec2010kronecker}, when the number of graph vertices $N$ is large. Built upon recent advances in random matrix theory, we show, in the dense regime, that the random Kronecker graph adjacency matrix follows approximately a signal-plus-noise model, with a small-rank (of order at most $\log N$) signal matrix that is linear in the graph parameters and a random noise matrix having a quarter-circle-form singular value distribution. This observation allows us to propose a ``denoise-and-solve'' meta algorithm to approximately infer the graph parameters, with reduced computational complexity and (asymptotic) performance guarantee. Numerical experiments of graph inference and graph classification on both synthetic and realistic graphs are provided to support the advantageous performance of the proposed approach.

Millions of slum dwellers suffer from poor accessibility to urban services due to inadequate road infrastructure within slums, and road planning for slums is critical to the sustainable development of cities. Existing re-blocking or heuristic methods are either time-consuming which cannot generalize to different slums, or yield sub-optimal road plans in terms of accessibility and construction costs. In this paper, we present a deep reinforcement learning based approach to automatically layout roads for slums. We propose a generic graph model to capture the topological structure of a slum, and devise a novel graph neural network to select locations for the planned roads. Through masked policy optimization, our model can generate road plans that connect places in a slum at minimal construction costs. Extensive experiments on real-world slums in different countries verify the effectiveness of our model, which can significantly improve accessibility by 14.3% against existing baseline methods. Further investigations on transferring across different tasks demonstrate that our model can master road planning skills in simple scenarios and adapt them to much more complicated ones, indicating the potential of applying our model in real-world slum upgrading. The code and data are available at https://github.com/tsinghua-fib-lab/road-planning-for-slums.

End-to-end deep learning approaches has been proven to be efficient in autonomous driving and robotics. By using deep learning techniques for decision-making, those systems are often referred to as a black box, and the result is driven by data. In this paper, we propose PaaS (Planning as a Service), a vanilla module to generate local trajectory planning for autonomous driving in CARLA simulation. Our method is submitted in International CARLA Autonomous Driving Leaderboard (CADL), which is a platform to evaluate the driving proficiency of autonomous agents in realistic traffic scenarios. Our approach focuses on reactive planning in Frenet frame under complex urban street's constraints and driver's comfort. The planner generates a collection of feasible trajectories, leveraging heuristic cost functions with controllable driving style factor to choose the optimal-control path that satisfies safe travelling criteria. PaaS can provide sufficient solutions to handle well under challenging traffic situations in CADL. As the strict evaluation in CADL Map Track, our approach ranked 3rd out of 9 submissions regarding the measure of driving score. However, with the focus on minimizing the risk of maneuver and ensuring passenger safety, our figures corresponding to infraction penalty dominate the two leading submissions for 20 percent.

Selective prediction aims to learn a reliable model that abstains from making predictions when the model uncertainty is high. These predictions can then be deferred to a human expert for further evaluation. In many real-world scenarios, the distribution of test data is different from the training data. This results in more inaccurate predictions, necessitating increased human labeling, which can be difficult and expensive. Active learning circumvents this by only querying the most informative examples and, in several cases, has been shown to lower the overall labeling effort. In this work, we bridge selective prediction and active learning, proposing a new learning paradigm called active selective prediction which learns to query more informative samples from the shifted target domain while increasing accuracy and coverage. For this new problem, we propose a simple but effective solution, ASPEST, that utilizes ensembles of model snapshots with self-training with their aggregated outputs as pseudo labels. Extensive experiments on numerous image, text and structured datasets, particularly those suffer from domain shifts, demonstrate that our proposed method can significantly outperform prior work on selective prediction and active learning (e.g. on the MNIST$\to$SVHN benchmark with the labeling budget of $100$, ASPEST improves the AUC metric from $79.36\%$ to $88.84\%$) and achieves more optimal utilization of humans in the loop.