Search

In today's evolving landscape of video surveillance, our study introduces SuspAct, an innovative ensemble model designed to detect suspicious activities in real time swiftly. Leveraging advanced Long-term Recurrent Convolutional Networks (LRCN), SuspAct represents a significant advancement in intelligent surveillance technology. By combining insights from various LRCN models through the Majority Voting ensemble technique, SuspAct enhances its overall robustness, outperforming traditional surveillance methods. Through rigorous experimentation on large-scale datasets, we demonstrate SuspAct's superiority in proactive crime prevention, showcasing its potential to revolutionize security protocols and contribute substantially to public safety. Our work addresses the challenges posed by the escalating volume of video data and lays a strong foundation for future advancements in intelligent video surveillance technology. [ABSTRACT FROM AUTHOR]

As a prosthesis made to compensate for the residual loss of the amputee's limb, the shoulder disarticulation upper limb prosthesis replaces the missing arm function of the shoulder amputee to a certain extent. However, the current upper limb prosthesis mainly interacts with the outside world through the prosthetic hand for grasping and gripping, and the interaction between other parts and the environment is often neglected, which is not in line with the use habits of the human arm. To address this problem, this paper proposes a reinforcement learning–based method for controlling the forearm interaction of a shoulder-disconnected upper limb prosthesis, and analyzes and solves the forces during the interaction, reducing the impact of uncertainty on interaction actions and accelerating training while ensuring the stability of handheld items. We evaluated the performance of the control method during the interaction between the upper limb prosthesis and the external environment through simulation experiments. After the training, the bionic arm was able to push the object into the target range for different objects and pushing distance requirements, which showed the good control effect of the method. Also, the control method can be applied to improve the interaction between the robotic arm and the environment. [ABSTRACT FROM AUTHOR]

Abstract This paper presents the use of one-way analysis of variance ANOVA as an effective tool for ranking the features calculated from diagnostic signals and evaluates their impact on the accuracy of the machine learning system's classification of displacement pump wear.The first part includes a review of contemporary diagnostic systems and a description of typical damage of multi-piston displacement pumps and Its causes. The work also contains description of a diagnostic experiment which was conducted in order to obtain the matrix of vibration signals and the matrix of pressures measured at selected locations on the pump housing and at the pump pressure line. The measured signals were subjected to time–frequency analysis. The features of signals calculated in the time and frequency domains were ranked using the ANOVA. The next step involved the use the available classifiers in pump wear evaluation, conducting tests and assessing their effectiveness in terms of the ranking of features and the origin of diagnostic signals.

Advancements in information and communications technology (ICT) have fundamentally transformed computing, notably through the internet of things (IoT) and its healthcare-focused branch, the internet of medical things (IoMT). These technologies, while enhancing daily life, face significant security risks, including ransomware. To counter this, the authors present a scalable, hybrid machine learning framework that effectively identifies IoMT ransomware attacks, conserving the limited resources of IoMT devices. To assess the effectiveness of their proposed solution, the authors undertook an experiment using a state-of-the-art dataset. Their framework demonstrated superiority over conventional detection methods, achieving an impressive 87% accuracy rate. Building on this foundation, the framework integrates a multi-faceted feature extraction process that discerns between benign and malign actions, with a subsequent in-depth analysis via a neural network. This advanced analysis is pivotal in precisely detecting and terminating ransomware threats, offering a robust solution to secure the IoMT ecosystem. [ABSTRACT FROM AUTHOR]

This research paper intends to provide real-life applications of Generative AI (GAI) in the cybersecurity domain. The frequency, sophistication and impact of cyber threats have continued to rise in today’s world. This ever-evolving threat landscape poses challenges for organizations and security professionals who continue looking for better solutions to tackle these threats. GAI technology provides an effective way for them to address these issues in an automated manner with increasing efficiency. It enables them to work on more critical security aspects which require human intervention, while GAI systems deal with general threat situations. Further, GAI systems can better detect novel malware and threatening situations than humans. This feature of GAI, when leveraged, can lead to higher robustness of the security system. Many tech giants like Google, Microsoft etc., are motivated by this idea and are incorporating elements of GAI in their cybersecurity systems to make them more efficient in dealing with ever-evolving threats. Many cybersecurity tools like Google Cloud Security AI Workbench, Microsoft Security Copilot, SentinelOne Purple AI etc., have come into the picture, which leverage GAI to develop more straightforward and robust ways to deal with emerging cybersecurity perils. With the advent of GAI in the cybersecurity domain, one also needs to take into account the limitations and drawbacks that such systems have. This paper also provides some of the limitations of GAI, like periodically giving wrong results, costly training, the potential of GAI being used by malicious actors for illicit activities etc.

This paper proposes a novel ensemble learning-based adaptive stochastic model predictive control (SMPC) algorithm for constrained linear systems with unknown nonlinear terms and random disturbances. The ensemble network combining a feedforward neural network and a Bayesian network is used to offline learn the nonlinear dynamics and disturbance distribution parameters. Then, the mixed-tube scheme is designed to cope with input constraints and state chance constraints while decreasing computational demands and conservativeness. The reliability of the stochastic tube is guaranteed using the Hoeffding inequality-based verification mechanism, which results in a chance constraint with double probabilities. The feasibility and exponential stability of the SMPC are rigorously proven. A numerical example verifies the merits of the proposed algorithm in terms of the control performance and the feasible domain. [ABSTRACT FROM AUTHOR]

This article considers the subject of information losses arising from the finite data sets used in the training of neural classifiers. It proves a relationship between such losses as the product of the expected total variation of the estimated neural model with the information about the feature space contained in the hidden representation of that model. It then bounds this expected total variation as a function of the size of randomly sampled data sets in a fairly general setting, and without bringing in any additional dependence on model complexity. It ultimately obtains bounds on information losses that are less sensitive to input compression and in general much smaller than existing bounds. This article then uses these bounds to explain some recent experimental findings of information compression in neural networks that cannot be explained by previous work. Finally, this article shows that not only are these bounds much smaller than existing ones, but they also correspond well with experiments.

Hydraulic power systems are commonly used in heavy industry (usually highly energy-intensive) and are often associated with high power losses. Designing a suitable system to allow an early assessment of the wear conditions of components in a hydraulic system (e.g., an axial piston pump) can effectively contribute to reducing energy losses during use. This paper presents the application of a deep machine learning system to determine the efficiency state of a multi-piston positive displacement pump. Such pumps are significant in high-power hydraulic systems. The correct operation of the entire hydraulic system often depends on its proper functioning. The wear and tear of individual pump components usually leads to a decrease in the pump's operating pressure and volumetric losses, subsequently resulting in a decrease in overall pump efficiency and increases in vibration and pump noise. This in turn leads to an increase in energy losses throughout the hydraulic system, which releases excess heat. Typical failures of the discussed pumps and their causes are described after reviewing current research work using deep machine learning. Next, the test bench on which the diagnostic experiment was conducted and the selected operating signals that were recorded are described. The measured signals were subjected to a time–frequency analysis, and their features, calculated in terms of the time and frequency domains, underwent a significance ranking using the minimum redundancy maximum relevance (MRMR) algorithm. The next step was to design a neural network structure to classify the wear state of the pump and to test and evaluate the effectiveness of the network's recognition of the pump's condition. The whole study was summarized with conclusions. [ABSTRACT FROM AUTHOR]

Graph learning is a popular approach for perfor ming machine learning on graph-structured data. It has revolutionized the machine learning ability to model graph data to address downstream tasks. Its application is wide due to the availability of graph data ranging from all types of networks to information systems. Most graph learning methods assume that the graph is static and its complete structure is known during training. This limits their applicability since they cannot be applied to problems where the underlying graph grows over time and/or new tasks emerge incrementally. Such applications require a lifelong learning approach that can learn the graph continuously and accommodate new information whilst retaining previously learned knowledge. Lifelong learning methods that enable continuous learning in regular domains like images and text cannot be directly applied to continuously evolving graph data, due to its irregular structure. As a result, graph lifelong learning is gaining attention from the research community. This survey paper provides a comprehensive overview of recent advancements in graph lifelong learning, including the categorization of existing methods, and the discussions of potential applications and open research problems. [ABSTRACT FROM AUTHOR]

Android is a growing target for malicious software (malware) because of its popularity and functionality. Malware poses a serious threat to users’ privacy, money, equipment and file integrity. A series of data-driven malware detection methods were proposed. However, there exist two key challenges for these methods: (1) how to learn effective feature representation from raw data; (2) how to reduce the dependence on the prior knowledge or human labors in feature learning. Inspired by the success of deep learning methods in the feature representation learning community, we propose a malware detection framework which starts with learning rich-features by a novel unsupervised feature learning algorithm Merged Sparse Auto-Encoder (MSAE). In order to extract more compact and discriminative feature from the rich-features to further boost the malware detection capability, a hybrid deep network learning algorithm Stacked Hybrid Learning MSAE and SDAE (SHLMD) is established by further incorporating a classical deep learning method Stacked Denoising Auto-encoders (SDAE). After that, we feed the feature learned by MSAE and SHLMD respectively to classification algorithms, e.g., Support Vector Machine (SVM) or K-NearestNeighbor (KNN), to train a malware detection model. Evaluation results on two real-world datasets demonstrate that SHLMD achieves 94.46 and 90.57 percent accuracy respectively, which outperforms the classical unsupervised feature representation learning Sparse Auto-encoder (SAE). MSAE performs similarly to SAE. SHLMD can further improve the performance of MSAE and the supervised fine-tuned method SDAE. Besides, we compare the performance of our methods with that of state-of-the-art detection approaches, including classical deep-learning-based methods. Extensive experiments show that our proposed methods are effective enough to detect Android malware. [ABSTRACT FROM AUTHOR]

The objective of this research is to present the state of the art of the safety assurance of Artificial Intelligence (AI)-based systems and guidelines on future correlated work. For this purpose, a Systematic Literature Review comprising 5090 peer-reviewed references relating safety to AI has been carried out, with focus on a 329-reference subset in which the safety assurance of AI-based systems is directly conveyed. From 2016 onwards, the safety assurance of AI-based systems has experienced significant effervescence and leaned towards five main approaches: performing black-box testing, using safety envelopes, designing fail-safe AI, combining white-box analyses with explainable AI, and establishing a safety assurance process throughout systems’ lifecycles. Each of these approaches has been discussed in this paper, along with their features, pros and cons. Finally, guidelines for future research topics have also been presented. They result from an analysis based on both the cross-fertilization among the reviewed references and the authors’ experience with safety and AI. Among 15 research themes, these guidelines reinforce the need for deepening guidelines for the safety assurance of AI-based systems by, e.g., analyzing datasets from a safety perspective, designing explainable AI, setting and justifying AI hyperparameters, and assuring the safety of hardware-implemented AI-based systems.

Using machine learning to obtain solutions to AC optimal power flow has recently been a very active area of research due to the astounding speedups that result from bypassing traditional optimization techniques. However, generally ensuring feasibility of the resulting predictions while maintaining these speedups is a challenging, unsolved problem. In this letter, we train a neural network to emulate an iterative solver in order to cheaply and approximately iterate towards the optimum. Once we are close to convergence, we then solve a power flow to obtain an overall AC-feasible solution. Results shown for networks up to 1,354 buses indicate the proposed method is capable of finding feasible, near-optimal solutions to AC OPF in milliseconds on a laptop computer. In addition, it is shown that the proposed method can find “difficult” AC OPF solutions that cause flat-start or DC-warm started algorithms to diverge. [ABSTRACT FROM AUTHOR]

The environment around general-purpose service robots has a dynamic nature. Accordingly, even the robot’s programmer cannot predict all the possible external failures which the robot may confront. This research proposes an online incremental learning method that can be further used to autonomously handle external failures originating from a change in the environment. Existing research typically offers special-purpose solutions. Furthermore, the current incremental online learning algorithms cannot generalize well with just a few observations. In contrast, our method extracts a set of hypotheses, which can then be used for finding the best recovery behavior at each failure state. The proposed argumentation-based online incremental learning approach uses an abstract and bipolar argumentation framework to extract the most relevant hypotheses and model the defeasibility relation between them. This leads to a novel online incremental learning approach that overcomes the addressed problems and can be used in different domains including robotic applications. We have compared our proposed approach with state-of-the-art online incremental learning approaches, an approximation-based reinforcement learning method, and several online contextual bandit algorithms. The experimental results show that our approach learns more quickly with a lower number of observations and also has higher final precision than the other methods. Note to Practitioners—This work proposes an online incremental learning method that learns faster by using a lower number of failure states than other state-of-the-art approaches. The resulting technique also has higher final learning precision than other methods. Argumentation-based online incremental learning generates an explainable set of rules which can be further used for human-robot interaction. Moreover, testing the proposed method using a publicly available dataset suggests wider applicability of the proposed incremental learning method outside the robotics field wherever an online incremental learner is required. The limitation of the proposed method is that it aims for handling discrete feature values. [ABSTRACT FROM AUTHOR]

In this paper, we reveal that metric learning would suffer from serious inseparable problem if without informative sample mining. Since the inseparable samples are often mixed with hard samples, current informative sample mining strategies used to deal with inseparable problem may bring up some side-effects, such as instability of objective function, etc. To alleviate this problem, we propose a novel distance metric learning algorithm, named adaptive neighborhood metric learning (ANML). In ANML, we design two thresholds to adaptively identify the inseparable similar and dissimilar samples in the training procedure, thus inseparable sample removing and metric parameter learning are implemented in the same procedure. Due to the non-continuity of the proposed ANML, we develop an ingenious function, named log-exp mean function to construct a continuous formulation to surrogate it, which can be efficiently solved by the gradient descent method. Similar to Triplet loss, ANML can be used to learn both the linear and deep embeddings. By analyzing the proposed method, we find it has some interesting properties. For example, when ANML is used to learn the linear embedding, current famous metric learning algorithms such as the large margin nearest neighbor (LMNN) and neighbourhood components analysis (NCA) are the special cases of the proposed ANML by setting the parameters different values. When it is used to learn deep features, the state-of-the-art deep metric learning algorithms such as Triplet loss, Lifted structure loss, and Multi-similarity loss become the special cases of ANML. Furthermore, the log-exp mean function proposed in our method gives a new perspective to review the deep metric learning methods such as Prox-NCA and N-pairs loss. At last, promising experimental results demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

This article investigates the feasibility of applying the broad learning system (BLS) to realize a novel Takagi–Sugeno–Kang (TSK) neuro-fuzzy model, namely a broad learning based dynamic fuzzy inference system (BL-DFIS). It not only improves the accuracy and interpretability of neuro-fuzzy models but also solves the challenging problem that models are incapable of determining the optimal architecture autonomously. BL-DFIS first accomplishes a TSK fuzzy system under the framework of BLS, in which an extreme learning machine auto-encoder is employed to obtain feature representation in a fast and analytical way, and an interpretable linguistic fuzzy rule is integrated into the enhancement node to ensure the high interpretability of the system. Meanwhile, the extended-enhancement unit is designed to achieve the first-order TSK fuzzy system. In addition, a dynamic incremental learning algorithm with internal pruning and updating mechanism is developed for the learning of BL-DFIS, which enables the system to automatically assemble the optimal structure to obtain a compact rule base and an excellent classification performance. Experiments on benchmark datasets demonstrate that the proposed BL-DFIS can achieve a better classification performance than some state-of-the-art nonfuzzy and neuro-fuzzy methods, simultaneously using the most parsimonious model structure. [ABSTRACT FROM AUTHOR]

The difficulties of obtaining sufficient labeled samples have always been one of the factors hindering deep learning models from obtaining high accuracy in hyperspectral image (HSI) classification. To reduce the dependence of deep learning models on training samples, meta learning methods have been introduced, effectively improving the classification accuracy in small sample set scenarios. However, the existing methods based on meta learning still need to construct a labeled source data set with several pre-collected HSIs, and must utilize a large number of labeled samples for meta-training, which is actually time-consuming and labor-intensive. To solve this problem, this paper proposes a novel unsupervised meta learning method with multiview constraints for HSI small sample set classification. Specifically, the proposed method first builds an unlabeled source data set using unlabeled HSIs. Then, multiple spatial-spectral multiview features of each unlabeled sample are generated to construct tasks for unsupervised meta learning. Finally, the designed residual relation network is used for meta-training and small sample set classification based on the voting strategy. Compared with existing supervised meta learning methods for HSI classification, our method can only utilize HSIs without any label for unsupervised meta learning, which significantly reduces the number of requisite labeled samples in the whole classification process. To verify the effectiveness of the proposed method, extensive experiments are carried out on 8 public HSIs in the cross-domain and in-domain classification scenarios. The statistical results demonstrate that, compared with existing supervised meta learning methods and other advanced classification models, the proposed method can achieve competitive or better classification performance in small sample set scenarios. [ABSTRACT FROM AUTHOR]

Much attention is paid to data science and machine learning as an effective means for getting value out of data and as a means for dealing with the large amounts of data we are accumulating at companies and organizations. This has gained importance with the major waves of digitization we have seen, especially with the COVID-19 pandemic accelerating digital everything. However, in reality, most machine learning models, despite achieving good technical solutions to predictive problems wind up not being deployed. The reasons for this are many and have their origin in data scientists and machine learning practitioners not paying enough attention to issues of deployment in production. The issues range all the way from establishing trust by business stakeholders and users, to failure to explain why models work and when they do not, to failing to appreciate the importance of establishing a robust quality data pipeline, to ignoring many constraints that apply to deployed models, and finally to a lack of understanding the true cost of production deployment and the associated ROI. We discuss many of these problems and we provide what we believe is a pragmatic approach to getting data science models successfully deployed in working environments. [ABSTRACT FROM AUTHOR]

Using interviews, we investigated the practices and toolchains for machine learning (ML)-enabled systems from 16 organizations across various domains in Finland. We observed some well-established artificial intelligence engineering approaches, but practices and tools are still needed for the testing and monitoring of ML-enabled systems. [ABSTRACT FROM AUTHOR]

Recently, deep-learning-based denoising methods for hyperspectral images (HSIs) have been comprehensively studied and achieved impressive performance because they can effectively extract complex and nonlinear image features. Compared with deep-learning-based methods, the nonlocal similarity-based denoising methods are more suitable for images containing edges or regular textures. We propose a powerful HSI denoising method, termed non-local 3-D convolutional neural network (NL-3DCNN), combining traditional machine learning and deep learning techniques. NL-3DCNN exploits the high spectral correlation of an HSI using subspace representation, and the corresponding representation coefficients are termed eigenimages. The high spatial correlation in eigenimages is exploited by grouping nonlocal similar patches, which are denoised by a 3-D convolutional neural network. The numerical and graphical denoising results of the simulated and real data show that the proposed method is superior to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Device-free localization (DFL), an important aspect in integrated sensing and communication, can be achieved through exploiting multipath components in ultra-wide bandwidth systems. However, incorrect identification of multipath components in the channel impulse responses will lead to large angle-of-arrival (AoA) estimation errors and subsequently poor localization performance. This letter proposes a learning-based AoA estimation method to improve the DFL accuracy. In the proposed method, we first design a classifier to identify the multipath components and then exploit the phase-difference-of-arrival to mitigate the AoA estimation error through a multilayer perceptron. Our learning-based method is validated using the datasets collected by ultra-wide bandwidth arrays, which significantly outperforms conventional methods in terms of AoA estimation and localization performance. [ABSTRACT FROM AUTHOR]

Different from previous work on single skill learning from human demonstrations, an incremental motor skill learning, generalization and control method based on dynamic movement primitives (DMP) and broad learning system (BLS) is proposed for extracting both ordinary skills and instant reactive skills from demonstrations, the latter of which is usually generated to avoid a sudden danger (e.g., touching a hot cup). The method is completed in three steps. First, the ordinary skills are basically learned from demonstrations in normal cases by using DMP. Then, the incremental learning idea of BLS is combined with DMP to achieve multistylistic reactive skill learning such that the forcing function of the ordinary skills will be reasonably extended into multiple stylistic functions by adding enhancement terms and updating weights of the radial basis function kernels. Finally, electromyography signals are collected from human muscles and processed to achieve stiffness factors. By using fuzzy logic system, the two kinds of skills learned are integrated and generalized in new cases such that not only start, end and scaling factors but also the environmental conditions, robot reactive strategies and impedance control factors will be generalized to lead to various reactions. To verify the effectiveness of the proposed method, an obstacle avoidance experiment that enables robots to approach destinations flexibly in various situations with barriers will be undertaken. [ABSTRACT FROM AUTHOR]

Transfer learning algorithm can provide a framework to utilize the previous knowledge to train fuzzy neural network (FNN). However, the performance of TL-based FNN will be destroyed by the knowledge over-fitting problem in the learning process. To solve this problem, an interactive transfer learning (ITL) algorithm, which can alleviate the negative transfer among different domains to improve the learning performance of FNN, is designed and analyzed in this article. This ITL-assisted FNN (ITL-FNN) contains the following advantages. First, a knowledge filter algorithm is developed to reconstruct the knowledge in source scene by balancing the matching accuracy and diversity. Then, the knowledge from source scene can fit the instance of target scene with suitable accuracy. Second, a self-balancing mechanism is designed to balance the driven information between the source and target scenes. Then, the knowledge can be refitted to reduce the useless information. Third, a structural competition algorithm is proposed to adjust the knowledge of FNN. Then, the proposed ITL-FNN can achieve compact structure to improve the generalization performance. Finally, some benchmark problems and industrial applications are provided to demonstrate the merits of ITL-FNN. [ABSTRACT FROM AUTHOR]

In this work, we provide a novel optimal guidance and control strategy for lunar hopper obstacle-avoidance, descent, and landing problem and demonstrate its behavior using numerical simulations. More specifically, the major contributions of this paper are three-fold: 1) proposed a feedback-based reference trajectory design for lunar hopper guidance, 2) developed the mathematical models and equations of linear quadratic tracking (LQT) controller for lunar hopper control, and 3) developed a method using reinforcement learning to optimize the designed reference trajectory in conjunction with the designed LQT controller, the so- called linear quadratic tracking with reinforcement learning based reference trajectory optimization (LQT-RTO). We demonstrated the LQT-RTO under a 2-dimensional (2D) lunar hopper simulation environment with 1) the LQT with heuristic reference trajectory design (LQT-HTD) and 2) reinforcement learning (reinforcement learning based controller, or RLC). We confirmed by numerical simulation that the LTQ-RTO outperformed the LQT-HTD in terms of fuel consumption, and outperformed the RLC in terms of landing success rate. Lastly, we provided theoretical interpretation to the simulation results.

Random walks are at the heart of many existing node embedding and network representation learning methods. However, such methods have many limitations that arise from the use of traditional random walks, e.g., the embeddings resulting from these methods capture proximity (communities) among the vertices as opposed to structural similarity (roles). Furthermore, the embeddings are unable to transfer to new nodes and graphs as they are tied to node identity. To overcome these limitations, we introduce the Role2Vec framework based on the proposed notion of attributed random walks to learn structural role-based embeddings. Notably, the framework serves as a basis for generalizing any walk-based method. The Role2Vec framework enables these methods to be more widely applicable by learning inductive functions that capture the structural roles in the graph. Furthermore, the original methods are recovered as a special case of the framework when each vertex is mapped to its own function that uniquely identifies it. Finally, the Role2Vec framework is shown to be effective with an average AUC improvement of 17.8 percent for link prediction while requiring on average 853x less space than existing methods on a variety of graphs from different domains. [ABSTRACT FROM AUTHOR]

Image scene classification aiming to assign specific semantic labels for each image is vitally important for the applications of remote sensing (RS) data. In real world, since the observation environment is open and dynamic, RS images are collected sequentially and the numbers of images and classes grow rapidly over time. Most existing scene classification methods are offline learning algorithms, which are inefficient and unscalable for this scenario. In this article, an incremental learning with open-set recognition (ILOSR) framework is proposed for RS image scene classification in the open and dynamic environment, which can identify the unknown classes from a stream of data and learn these new classes incrementally. Specifically, a controllable convex hull-based exemplar selection strategy is designed to address the catastrophic forgetting issue in incremental learning, which can reduce training time and memory footprint effectively. In addition, a new loss function based on prototype learning and uncertainty measurement is proposed for OSR to enhance the interclass discrimination and intraclass compactness of the learned deep features. Experimental results on real RS datasets demonstrate that the proposed method can not only outperform the state-of-the-art approaches on offline classification, incremental learning, and OSR problem separately but also achieve better and more stable performance in the experiments for ILOSR. [ABSTRACT FROM AUTHOR]

Accurate prediction of a stock price is a challenging task due to the complexity, chaos, and non-linearity nature of financial systems. In this brief, we proposed a multi-indicator feature selection method for stock price prediction based on Pearson correlation coefficient (PCC) and Broad Learning System (BLS), named the PCC-BLS framework. Firstly, PCC was used to select the input features from 35 features, including original stock price, technical indicators, and financial indicators. Secondly, these screened input features were used for rapid information feature extraction and training a BLS. Four stocks recorded on the Shanghai Stock Exchange or Shenzhen Stock Exchange were adopted to evaluate the performance of the proposed method. In addition, we compared the forecasting results with ten machine learning methods, including Support Vector Regression (SVR), Adaptive Boosting (Adaboost), Bootstrap aggregating (Bagging), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Multi-layer Perceptron (MLP), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) and Broad Learning System (BLS). Among all algorithms used in this brief, the proposed model showed the best performance with the highest model fitting ability. [ABSTRACT FROM AUTHOR]

Currently, the highly dynamic fog computing resource requirements introduced by the diverse services of the Internet of Things (IoT) result in an imbalance between computing resource providers and consumers. However, current computing resource scheduling schemes cannot cognize the dynamic resources available and do not possess decision-making or management capabilities, which leads to inefficient use of computing resources and a decreased quality of service (QoS). Balancing computing resources cognitively at the IoT edge remains unresolved. In this paper, a cognition-centric fog computing resource balancing (CFCRB) scheme is proposed for edge intelligence-enabled IoT. First, we propose a cognitive balance architecture with a cognition plane, which includes service demand monitoring, policy processing and knowledge storage of cognitive fog resources. Second, we propose the fog functions structure with sensing, interaction and learning functionalities, realizing the knowledge-based proactive discovery and dynamic orchestration of resource sharing nodes. Finally, a distributed edge learning algorithm is proposed to construct knowledge of the balance between computing resource helpers and requesters in cognitive fogs, which is further proved with mathematics. The simulation results indicate the efficiency of the proposed scheme. [ABSTRACT FROM AUTHOR]

Deep Learning (DL) is becoming more popular in the healthcare sectors due to the exponential growth of data availability and its excellent performance in diagnosing various diseases. This paper has aimed to design a new possible brain tumor diagnostic model to improve accuracy and reliability of radiology. In this paper, an advanced deep learning algorithm is used to detect and classify brain tumors in magnetic resonance (MR) images. Diagnosing brain tumors in radiology is a significant issue, yet it is a difficult and time-consuming procedure that radiologists must pass through. The reliability of their assessment relies completely on their knowledge and personal judgements which are in most cases inaccurate. As a possible remedy to the growing concern in diagnosing brain tumors accurately, in this work a deep learning method is applied to classify the brain tumor MR images with very high performance accuracy. The research leveraged a transfer learning model known as AlexNet's convolutional neural network (CNN) to perform this operation. Our method helps to improve robustness, efficiencies and accuracy in the healthcare sector with the ability to automate the entire diagnostic process with the overall accuracy of 99.62%. Additionally, our model has the ability to detect and classify tumors at their different stages and magnitudes. [ABSTRACT FROM AUTHOR]

In general, existing cross-domain recognition methods mainly focus on changing the feature representation of data or modifying the classifier parameter and their efficiencies are indicated by the better performance. However, most existing methods do not simultaneously integrate them into a unified optimization objective for further improving the learning efficiency. In this article, we propose a novel cross-domain recognition algorithm framework by integrating both of them. Specifically, we reduce the discrepancies in both the conditional distribution and marginal distribution between different domains in order to learn a new feature representation which pulls the data from different domains closer on the whole. However, the data from different domains but the same class cannot interlace together enough and thus it is not reasonable to mix them for training a single classifier. To this end, we further propose to learn double classifiers on the respective domain and require that they dynamically approximate to each other during learning. This guarantees that we finally learn a suitable classifier from the double classifiers by using the strategy of classifier fusion. The experiments show that the proposed method outperforms over the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Learning to improve AUC performance for imbalanced data is an important machine learning research problem. Most methods of AUC maximization assume that the model function is linear in the original feature space. However, this assumption is not suitable for nonlinear separable problems. Although there have been some nonlinear methods of AUC maximization, scaling up nonlinear AUC maximization is still an open question. To address this challenging problem, in this paper, we propose a novel large-scale nonlinear AUC maximization method (named as TSAM) based on the triply stochastic gradient descents. Specifically, we first use the random Fourier feature to approximate the kernel function. After that, we use the triply stochastic gradients w.r.t. the pairwise loss and random feature to iteratively update the solution. Finally, we prove that TSAM converges to the optimal solution with the rate of $ \mathcal {O}(1/t)$ O (1 / t) after $t$ t iterations. Experimental results on a variety of benchmark datasets not only confirm the scalability of TSAM, but also show a significant reduction of computational time compared with existing batch learning algorithms, while retaining the similar generalization performance. [ABSTRACT FROM AUTHOR]

A fast architecture for real-time (i.e., minute-based) training of a traffic predictor is studied, based on the so-called broad learning system (BLS) paradigm. The study uses various traffic datasets by the California Department of Transportation, and employs a variety of standard algorithms (LASSO regression, shallow and deep neural networks, stacked autoencoders, convolutional, and recurrent neural networks) for comparison purposes: all algorithms are implemented in MATLAB on the same computing platform. The study demonstrates a BLS training process two-three orders of magnitude faster (tens of seconds against tens-hundreds of thousands of seconds), allowing unprecedented real-time capabilities. Additional comparisons with the extreme learning machine architecture, a learning algorithm sharing some features with BLS, confirm the fast training of least-square training as compared to gradient training. [ABSTRACT FROM AUTHOR]

Traditional classification learning algorithms have several limitations: 1) they are time consuming for the large-scale training multivariate time-series (MTS) data, and unsuitable for the dynamically added training data; 2) as the number of the training MTS data becomes larger, they could not achieve the desired classification accuracy; 3) most of them do not consider how to make use of the unlabeled samples to enhance the classifier performance; and 4) due to the high dimension of MTS and complex relationship among variables, existing online learning algorithms are not effective to update shapelet-based association rules. Up to now, few work touched online classification learning for dynamically added unlabeled examples. To efficiently address these issues, we propose an online rule-based classifier learning framework on dynamically added unlabeled MTS data (ORCL-U). This framework integrates a confidence-based labeling strategy (CLS) and an online rule-based classifier learning approach (ORBCL). Extensive experiments on ten datasets show the effectiveness and efficiency of our proposed approach. [ABSTRACT FROM AUTHOR]

Sensor drift is one of the severe issues that gas sensors suffer from. To alleviate the sensor drift problem, a gas sensor drift compensation approach is proposed based on local discriminant subspace projection (LDSP). The proposed approach aims to find a subspace to reduce the distribution difference between two domains, i.e., the source and target domain. Similar to domain regularized component analysis (DRCA) which is a recently proposed sensor drift correction method, the mean distribution discrepancy is minimized in the common subspace in our approach. LDSP extends DRCA in two aspects, i.e., it not only takes the label information of the source data into consideration to reduce the possibility of the case that samples in the subspace with different class labels stay close to each other, but also borrows the idea of locality-preserving projection to deal with multimodal data. Specifically, inspired by local Fisher discriminant analysis (LFDA), the label information is utilized to maximize the local between-class variance of source data in the latent common subspace and simultaneously minimize the local within-class variance. The formulation of LDSP is a generalized eigenvalue problem that can be readily solved. The experimental results have shown the proposed method outperforms other gas sensor drift compensation methods in terms of classification accuracy on two public gas sensor drift datasets. [ABSTRACT FROM AUTHOR]

The broad learning system (BLS) is designed based on the technology of compressed sensing and pseudo-inverse theory, and consists of feature nodes and enhancement nodes, has been proposed recently. Compared with the popular deep learning structures, such as deep neural networks, BLS has the ability of rapid incremental learning and can remodel the system without the usual tedious retraining process. However, given that BLS is still in its infancy, it still needs analysis, improvements, and verification. In this article, we first analyze the principle of fast incremental learning ability of BLS in depth. Second, in order to provide an in-depth analysis of the BLS structure, according to the novel structure design concept of deep neural networks, we present four brand-new BLS variant networks and their incremental realizations. Third, based on our analysis of the effect of feature nodes and enhancement nodes, a new BLS structure with a semantic feature extraction layer has been proposed, which is called SFEBLS. The experimental results show that SFEBLS and its variants can increase the accuracy rate on the NORB dataset 6.18%, Fashion-MNIST dataset by 3.15%, ORL data by 5.00%, street view house number dataset by 12.88%, and CIFAR-10 dataset by 18.42%, respectively, and the four brand-new BLS variant networks also obviously outperform the original BLS. [ABSTRACT FROM AUTHOR]

Distance between sequences is structural by nature because it needs to establish the temporal alignments among the temporally correlated vectors in sequences with varying lengths. Generally, distances for sequences heavily depend on the ground metric between the vectors in sequences to infer the alignments and hence can be viewed as meta-distances upon the ground metric. Learning such meta-distance from multi-dimensional sequences is appealing but challenging. We propose to learn the meta-distance through learning a ground metric for the vectors in sequences. The learning samples are sequences of vectors for which how the ground metric between vectors induces the meta-distance is given. The objective is that the meta-distance induced by the learned ground metric produces large values for sequences from different classes and small values for those from the same class. We formulate the ground metric as a parameter of the meta-distance and regress each sequence to an associated pre-generated virtual sequence w.r.t. the meta-distance, where the virtual sequences for sequences of different classes are well-separated. We develop general iterative solutions to learn both the Mahalanobis metric and the deep metric induced by a neural network for any ground-metric-based sequence distance. Experiments on several sequence datasets demonstrate the effectiveness and efficiency of the proposed methods. [ABSTRACT FROM AUTHOR]

QA systems have had various approaches to achieve their goal of solving naturally formed questions, recent works use state of the art techniques such as neural networks, QA systems in different languages are increasing, as evidenced, they are advancing at different rates, despite the fact that there are efforts to increase research in this type of systems. In this research we analyze the main aspects of the contributions to Question Answering and present an architecture that is capable of answering questions in Spanish. The initial question is received by the system, which may or may not have a document corpus from which to extract the answer, if it does not have a specified document corpus, the Answer Generation module returns the answer to the initial question. The purpose of the system is to provide answers to factoid questions posed by users through a web and mobile platform. BI-LSTM was used for document retrieval and BERT was used to generate the answers. We tested the architecture with ten thousand questions reaching an accuracy of 0.7856. The result improved by entering QA to a more specialized BERT model adapted for the Spanish language, the multilingual version of BERT and the Spanish version of BETO were used. [ABSTRACT FROM AUTHOR]

The inverse Potts problem to infer a Boltzmann distribution for homologous protein sequences from their single-site and pairwise amino acid frequencies recently attracts a great deal of attention in the studies of protein structure and evolution. We study regularization and learning methods and how to tune regularization parameters to correctly infer interactions in Boltzmann machine learning. Using $L_2$ L 2 regularization for fields, group $L_1$ L 1 for couplings is shown to be very effective for sparse couplings in comparison with $L_2$ L 2 and $L_1$ L 1 . Two regularization parameters are tuned to yield equal values for both the sample and ensemble averages of evolutionary energy. Both averages smoothly change and converge, but their learning profiles are very different between learning methods. The Adam method is modified to make stepsize proportional to the gradient for sparse couplings and to use a soft-thresholding function for group $L_1$ L 1 . It is shown by first inferring interactions from protein sequences and then from Monte Carlo samples that the fields and couplings can be well recovered, but that recovering the pairwise correlations in the resolution of a total energy is harder for the natural proteins than for the protein-like sequences. Selective temperature for folding/structural constrains in protein evolution is also estimated. [ABSTRACT FROM AUTHOR]

Multi-view representation learning is a promising and challenging research topic, which aims to integrate multiple data information from different views to improve the learning performance. The recent deep Gaussian processes (DGPs) have the advantages of good uncertainty estimates, powerful non-linear mapping ability and great generalization capability, which can be used as an excellent data representation learning method. However, DGPs only focus on single view data and are rarely applied to the multi-view scenario. In this paper, we propose a multi-view representation learning algorithm with deep Gaussian processes (named MvDGPs), which inherits the advantages of deep Gaussian processes and multi-view representation learning, and can learn more effective representation of multi-view data. The MvDGPs consist of two stages. The first stage is multi-view data representation learning, which is mainly used to learn more comprehensive representations of multi-view data. The second stage is classifier design, which aims to select an appropriate classifier to better employ the representations obtained in the first stage. In contrast with DGPs, MvDGPs support asymmetrical modeling depths for different views of data, resulting in better characterizations of the discrepancies among different views. Experimental results on real-world multi-view data sets verify the effectiveness of the proposed algorithm, which indicates that MvDGPs can integrate the complementary information in multiple views to discover a good representation of the data. [ABSTRACT FROM AUTHOR]