Search

Finding relevant papers is a non-trivial problem for scholars due to the tremendous amount of academic information in the era of scholarly big data. Scientific paper recommendation systems have been developed to solve such problem by recommending relevant papers to scholars. However, previous paper recommendations calculate paper similarity based on hand-engineered features which are inflexible. To address this problem, we develop a scientific paper recommendation system, namely VOPRec, by vector representation learning of paper in citation networks. VOPRec takes advantages of recent research in both text and network representation learning for unsupervised feature design. In VOPRec, the text information is represented with word embedding to find papers of similar research interest. Then, the structural identity is converted into vectors to find papers of similar network topology. After bridging text information and structural identity with the citation network, vector representation of paper can be learned with network embedding. Finally, top- $Q$ Q recommendation list is generated based on the similarity calculated with paper vectors. Through the APS data set, we show that VOPRec outperforms state-of-the-art paper recommendation baselines measured by precision, recall, F1, and NDCG.

In this paper, we present a new scheme for implementing virtual keyboards, which uses only two to four motion-recognition rings per hand and a two-dimensional keyboard template (e.g., an A4 size paper with printed key positions). It has the benefit of portability, customizability, and low-cost when compared with existing approaches. Essentially, we have shown that wearing two wireless IoT rings on the middle phalanges of two fingers of each hand, users can input the alphabetic characters into a computing device by typing on a flat paper on a desk, and potentially in mid-air. We have demonstrated that two rings are sufficient in capturing the gestures and motions of all fingers in a typing hand for keystrokes recognition. A single wireless IoT ring, which weighs 7.8 grams, consists of a Bluetooth low energy (BLE) unit, a micro inertial measurement unit (mIMU), and a cell battery. The 3-axes attitude angles and the Z-axis acceleration of each ring are adopted as the features for keystroke recognition. The overall keystroke recognition accuracy rate can reach as high as 94.8% when two IoT rings are worn by a user on each hand; this accuracy rate increases to 98.6%, when four rings are worn on each typing hand.

This paper studies the authentication problem of specific pieces of paper using mobile imaging devices. Prior work showing high matching accuracy has used the normal vector field , which serves as a unique, microscopic, physically unclonable feature of paper surfaces, estimated by consumer grade scanners. Industrial cameras were also used to capture the appearance of the surface rendered after the normal vector field based on the laws of optics under a semi-controlled lighting condition. In comparison, past explorations based on mobile cameras were very limited and have not had substantial success in obtaining consistent appearance images due to the uncontrolled nature of the ambient light. We show in this paper that images captured by mobile cameras can be used for authentication when the camera flashlight is exploited for creating a semi-controlled lighting condition. We have proposed new algorithms to demonstrate that the normal vector field of paper surface can be estimated by using multiple camera-captured images of different viewpoints. Perturbation analysis shows that the proposed method is robust to inaccurate estimates of camera locations, and a matching accuracy of $10^{-\textrm {4}}$ in equal error rate can be achieved using 6 to 8 images under a lab-controlled ambient light environment. Our findings can relax the restricted imaging setups and enable paper authentication under a more casual, ubiquitous setting with a mobile imaging device, which may facilitate duplicate detection of paper documents and counterfeit mitigation of merchandise packaging.

Parallel test paper generation is a biobjective distributed resource optimization problem, which aims to generate multiple similarly optimal test papers automatically according to multiple user-specified assessment criteria. Generating high-quality parallel test papers is challenging due to its NP-hardness in both of the collective objective functions. In this paper, we propose a submodular memetic approximation algorithm for solving this problem. The proposed algorithm is an adaptive memetic algorithm (MA), which exploits the submodular property of the collective objective functions to design greedy-based approximation algorithms for enhancing steps of the multiobjective MA. Synergizing the intensification of submodular local search mechanism with the diversification of the population-based submodular crossover operator, our algorithm can jointly optimize the total quality maximization objective and the fairness quality maximization objective. Our MA can achieve provable near-optimal solutions in a huge search space of large datasets in efficient polynomial runtime. Performance results on various datasets have shown that our algorithm has drastically outperformed the current techniques in terms of paper quality and runtime efficiency.

A course on the emerging topic “Smart Sensors and Internet of Things (IoT)” has been designed, developed, and delivered from 21st March 2016 to 31st March 2016 in the Department of Electrical Engineering, Jamia Millia Islamia (Central University), New Delhi-110025, India. This course was organized under a program initiated by the Government of India, entitled “Global Initiative of Academic Networks” for higher education. The basic objective is to bring the internationally and nationally acclaimed scientists on a single platform to motivate young minds of India so that India’s scientific and technological capacity reach global excellence. The course was designed to develop the technical skills for the students, the researchers, the engineers, and the faculties, who desire to address some of the issues faced by the people around the world in the fields of smart sensors and IoTs with applications in smart homes, smart cities, smart grids, smart environment, smart transport, and so on. The assessment of the course by the participants shows extreme usefulness of it.

The difficulty of very high resolution image change detection lies in the low interclass separability between the changed class and the unchanged class. According to experiments, we found that this separability can be improved by mining the relationship contained in the training samples. Based on this observation, a supervised change detection approach is proposed in this paper based on relationship learning. The proposed approach begins with enriching the training samples based on their neighborhood relationship and label coherence; this relationship is then learned simultaneously with the classifier, and, finally, the latter classification performance benefits from the learned relationship. Experiments demonstrate the effectiveness of the proposed approach.

If you follow discussions about the Internet of Things, you've probably heard this stunning prediction at least once: The world will have 50 billion Internet-connected devices by 2020. Ericsson's former CEO, Hans Vestburg, was among the first to toss out that number, when he gave a 2010 presentation to shareholders. The following year, Dave Evans, who worked for Cisco at the time, published the same prediction in a white paper.

This paper aims to predict a set of apps a user will open on her mobile device in the next time slot. Such an information is essential for many smartphone operations, e.g., app pre-loading and content pre-caching, to improve user experience. However, it is hard to build an explicit model that accurately captures the complex environment context and predicts a set of apps at one time. This paper presents a deep reinforcement learning framework, named as DeepAPP, which learns a model-free predictive neural network from historical app usage data. Meanwhile, an online updating strategy is designed to adapt the predictive network to the time-varying app usage behavior. To transform DeepAPP into a practical deep reinforcement learning system, several challenges are addressed by developing a context representation method for complex contextual environment, a general agent for overcoming data sparsity and a lightweight personalized agent for minimizing the prediction time. Extensive experiments on a large-scale anonymized app usage dataset reveal that DeepAPP provides high accuracy (precision 70.6% and recall of 62.4%) and reduces the prediction time of the state-of-the-art by 6.58 times. A field experiment of 29 participants demonstrates DeepAPP can effectively reduce launch time of apps.

This paper is the second part of a two-part survey series on large-scale global optimization. The first part covered two major algorithmic approaches to large-scale optimization, namely decomposition methods and hybridization methods such as memetic algorithms and local search. In this part we focus on sampling and variation operators, approximation and surrogate modeling, initialization methods, and parallelization. We also cover a range of problem areas in relation to large-scale global optimization, such as multi-objective optimization, constraint handling, overlapping components, the component imbalance issue, and benchmarks, and applications. The paper also includes a discussion on pitfalls and challenges of current research and identifies several potential areas of future research.

Citation recommendation is important in the environment of scholarly big data, where finding relevant papers has become more difficult because of information overload. Applying traditional collaborative filtering (CF) to citation recommendation is rather challenging due to the cold start problem and the lack of paper ratings. To address these two challenges, in this paper, we propose a Collaborative filtering with Network representation learning framework for Citation Recommendation dubbed as CNCRec, which is a hybrid user-based CF considering both paper content and network topology. It aims at recommending citations in heterogeneous academic information networks. CNCRec creates the paper rating matrix based on attributed citation network representation learning, where the attributes are topics extracted from the paper text information. Meanwhile, the learned representations of attributed collaboration network is utilized to improve the selection of nearest neighbors. By harnessing the power of network representation learning, CNCRec is able to make full use of the whole citation network topology compared with previous context-aware network-based models. Extensive experiments on both DBLP and APS datasets show that the proposed method outperforms state-of-the-art methods in terms of precision, recall, and Mean Reciprocal Rank. Moreover, CNCRec can better solve the data sparsity problem compared with other CF-based baselines.

This paper presents a family of algorithms based on sparse decompositions that detect anomalies in video sequences obtained from slow moving cameras. These algorithms start by computing the union of subspaces that best represents all the frames from a reference (anomaly free) video as a low-rank projection plus a sparse residue. Then, they perform a low-rank representation of a target (possibly anomalous) video by taking advantage of both the union of subspaces and the sparse residue computed from the reference video. Such algorithms provide good detection results while at the same time obviating the need for previous video synchronization. However, this is obtained at the cost of a large computational complexity, which hinders their applicability. Another contribution of this paper approaches this problem by using intrinsic properties of the obtained data representation in order to restrict the search space to the most relevant subspaces, providing computational complexity gains of up to two orders of magnitude. The developed algorithms are shown to cope well with videos acquired in challenging scenarios, as verified by the analysis of 59 videos from the VDAO database that comprises videos with abandoned objects in a cluttered industrial scenario.

We present Arianna+, a framework to design networks of ontologies for representing knowledge enabling smart homes to perform human activity recognition online. In the network, nodes are ontologies allowing for various data contextualisation, while edges are general-purpose computational procedures elaborating data. Arianna+ provides a flexible interface between the inputs and outputs of procedures and statements, which are atomic representations of ontological knowledge. Arianna+ schedules procedures on the basis of events by employing logic-based reasoning, i.e., by checking the classification of certain statements in the ontologies. Each procedure involves input and output statements that are differently contextualised in the ontologies based on specific prior knowledge. Arianna+ allows to design networks that encode data within multiple contexts and, as a reference scenario, we present a modular network based on a spatial context shared among all activities and a temporal context specialised for each activity to be recognised. In the paper, we argue that a network of small ontologies is more intelligible and has a reduced computational load than a single ontology encoding the same knowledge. Arianna+ integrates in the same architecture heterogeneous data processing techniques, which may be better suited to different contexts. Thus, we do not propose a new algorithmic approach to activity recognition, instead, we focus on the architectural aspects for accommodating logic-based and data-driven activity models in a context-oriented way. Also, we discuss how to leverage data contextualisation and reasoning for activity recognition, and to support an iterative development process driven by domain experts., The paper has been accepted for publication in the IEEE Transactions on Cybernetics journal on April 2021 and with DOI 10.1109/TCYB.2021.3073539. It is an extension of arXiv:1707.03988v1 and it is related to the arXiv:1809.08208v1 article. It contains 20 pages, 6 figures, 4 tables and 2 Appendices

In recent years driving violations have increased in big and crowded cities specially in developing countries. This has resulted in escalation of traffic congestions and number of accidents, making them difficult to handle by a central managing authority. New technologies can be used in order to mitigate this problem. Hence, in this paper, we propose a novel concept, called self-fining vehicle, using Blockchain infrastructure on top of the Vehicular Edge Computing, VEC. Self-fining vehicle is a vehicle that detects and records driving violations, issues tickets and pays fines without the need for centralized management system. Violations can be coded into OBU and detected by vehicular communications. The conceptual architecture of secure self-fining vehicle is proposed and discussed in this paper. The proposed architecture improves violation data security, processing speed and communication delay using encryption, authentication, Blockchain and edge computing, enhancing quality of service and consumers‘ quality of experience. The performance analysis of the proposed architecture proves its efficiency in terms of latency in service delivery.

The concept of the fifth generation (5G) mobile network system has emerged in recent years as telecommunication operators and service providers look to upgrade their infrastructure and delivery modes to meet the growing demand. Concepts such as softwarization, virtualization, and machine learning will be key components as innovative and flexible enablers of such networks. In particular, paradigms such as software-defined networks, software-defined perimeter, cloud & edge computing, and network function virtualization will play a major role in addressing several 5G networks' challenges, especially in terms of flexibility, programmability, scalability, and security. In this work, the role and potential of these paradigms in the context of V2X communication is discussed. To do so, the paper starts off by providing an overview and background of V2X communications. Then, the paper discusses in more details the various challenges facing V2X communications and some of the previous literature work done to tackle them. Furthermore, the paper describes how softwarization, virtualization, and machine learning can be adapted to tackle the challenges of such networks.

Offloading computation based on mobile edge computing paradigms can augment the computational capabilities of resource-scarce mobile devices. However, the capacity limitations of edge servers constrain the performance improvement achieved through computation offloading. In this paper, we consider a three-tier computation offloading schema with multiple users, edge servers and cloud servers. Computation can be offloaded from mobile devices to edge servers or can be further offloaded to remote cloud servers if necessary. Since a number of mobile devices connected to edge servers will share a common wireless communication network, which may contain both uplink and downlink channels, the assignment of bandwidth assignment the channels also constrains the performance improvement of computation offloading. In this paper, the problems of how to determine the offloading strategy and of how to assign the bandwidth are jointly studied and formulated as a programming problem to minimize the average application response time. We analyze the joint problem and further transform it into a piecewise convex programming problem. We propose an efficient algorithm that can find the optimal solution. Extensive experiments demonstrate that our algorithm significantly outperforms previous algorithms. The experimental results also show that the performance of our algorithm is highly robust.

An increasing number of cloud services are operated globally, where the service data are frequently replicated across geographically distributed datacenters to improve service quality and reliability. Such replication generates many one-to-many bulk data transfers over inter-datacenter networks from one datacenter to many receiver datacenters. To provide end-users with guaranteed services, these data transfers are usually required to be completed within designated deadlines. Despite the exponential growth in data demand, there has been little work on guaranteeing deadlines for one-to-many transfers, which is the subject of this paper. This paper proposes a centralized admission control coupled with a scheduling algorithm, named deAdline-Guaranteed transfEr (AGE), to guarantee the deadline of admitted data transfers and utilize the network capacity efficiently. The key idea is to flexibly select the source datacenter for receiver datacenters and allow the remaining receivers to obtain a replica from either the original source or the other receivers that have already received a copy. By jointly allocating the source for receivers and the bandwidth and routing paths for every data transfer, AGE maximizes the number of deadline-satisfied transfers. Our simulations show that compared to the state-of-the-art, AGE guarantees the deadline for up to 70% more transfers, achieves at least 2× higher network throughput, and reduces the completion time up to 80%.

In recent years, plenty of metrics have been proposed to identify networks that are free of gradient explosion and vanishing. However, due to the diversity of network components and complex serial-parallel hybrid connections in modern DNNs, the evaluation of existing metrics usually requires strong assumptions, complex statistical analysis, or has limited application fields, which constraints their spread in the community. In this paper, inspired by the Gradient Norm Equality and dynamical isometry, we first propose a novel metric called Block Dynamical Isometry, which measures the change of gradient norm in individual block. Because our Block Dynamical Isometry is norm-based, its evaluation needs weaker assumptions compared with the original dynamical isometry. To mitigate the challenging derivation, we propose a highly modularized statistical framework based on free probability. Our framework includes several key theorems to handle complex serial-parallel hybrid connections and a library to cover the diversity of network components. Besides, several sufficient prerequisites are provided. Powered by our metric and framework, we analyze extensive initialization, normalization, and network structures. We find that Gradient Norm Equality is a universal philosophy behind them. Then, we improve some existing methods based on our analysis, including an activation function selection strategy for initialization techniques, a new configuration for weight normalization, and a depth-aware way to derive coefficients in SeLU. Moreover, we propose a novel normalization technique named second moment normalization, which is theoretically 30% faster than batch normalization without accuracy loss. Last but not least, our conclusions and methods are evidenced by extensive experiments on multiple models over CIFAR10 and ImageNet., Comment: Under review as a regular paper in TPAMI

Over the last decades, the cooperative design of complex networked systems has received an increasing attention in real-world engineering practices. Traditionally, each node in the network is assumed to obtain the same signal. However, each agent often possesses different measurement due to the observability or configuration of the systems. To solve the stabilization problem in this case, we aim to establish a unified framework for the cooperative control of complex network with distributed observers. In detail, different from the traditional centralized design, this paper initiates a cooperative approach by only using the local information of the networked systems. In allusion to the three kinds of representative networks, this paper establishes some sufficient or necessary conditions for the existence of network parameters that guarantee the stabilization of the LTI plants. Moreover, some corresponding algorithms are developed to find the suitable parameters of networked observers. Last but not least, numerical simulations are also provided to verify the above theoretical results.

Objective: Longitudinal neuroimaging data have been widely used to predict clinical scores for automatic diagnosis of Alzheimer’s Disease (AD) in recent years. However, incomplete temporal neuroimaging records of the patients pose a major challenge to use these data for accurately diagnosing AD. In this paper, we propose a novel method to learn an enriched representation for imaging biomarkers, which simultaneously captures the information conveyed by both the baseline neuroimaging records of all the participants in a studied cohort and the progressive variations of the available follow-up records of every individual participant. Methods: Taking into account that different participants usually take different numbers of medical records at different time points, we develop a robust learning objective that minimizes the summations of a number of not-squared $\ell _2$ -norm distances, which, though, is difficult to efficiently solve in general. Thus we derive a new efficient iterative algorithm with rigorously proved convergence. Results: We have conducted extensive experiments using the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. Clear performance gains have been achieved when we predict different cognitive scores using the enriched biomarker representations learned by our new method. We further observe that the top selected biomarkers by our proposed method are in perfect accordance with the known knowledge in existing clinical AD studies. Conclusion: All these promising experimental results have demonstrated the effectiveness of our new method. Significance: We anticipate that our new method is of interest to biomedical engineering communities beyond AD research and have open-sourced the code of our method online. 1 1 The code package of this paper have been made publicly available online at https://github.com/lyujian/Improved-Prediction-of-Cognitive-Outcomes

Three-dimensional Morphable Models (3DMMs) are powerful statistical tools for representing the 3D shapes and textures of an object class. Here we present the most complete 3DMM of the human head to date that includes face, cranium, ears, eyes, teeth and tongue. To achieve this, we propose two methods for combining existing 3DMMs of different overlapping head parts: i. use a regressor to complete missing parts of one model using the other, ii. use the Gaussian Process framework to blend covariance matrices from multiple models. Thus we build a new combined face-and-head shape model that blends the variability and facial detail of an existing face model (the LSFM) with the full head modelling capability of an existing head model (the LYHM). Then we construct and fuse a highly-detailed ear model to extend the variation of the ear shape. Eye and eye region models are incorporated into the head model, along with basic models of the teeth, tongue and inner mouth cavity. The new model achieves state-of-the-art performance. We use our model to reconstruct full head representations from single, unconstrained images allowing us to parameterize craniofacial shape and texture, along with the ear shape, eye gaze and eye color., 18 pages, 18 figures, submitted to Transactions on Pattern Analysis and Machine Intelligence (TPAMI) on the 9th of October as an extension paper of the original oral CVPR paper : arXiv:1903.03785

With the development of the information and Internet technology, the public opinions with big data will rapidly emerge in an online-offline social network, and an inefficient management of public opinions often will lead to the security crisis for either firms or governments. To unveil the interaction mechanism among a large number of agents between the online and offline social networks, in this paper we propose the public opinion dynamics model in an online-offline social network context. Next, in the theory aspect we investigate the analytical conditions to form a consensus in the public opinion dynamics model. Furthermore, we conduct the extensive simulations to investigate how the online agents impact the dynamics of public opinion formation, and unfold that the online agents shorten the steady-state time, decrease the number of opinion clusters, and smoothen the opinion changes in the opinion dynamics. The increase in the size of the online agents often enhances these effects. The results in this paper can provide a basis for the management of the public opinions in the Internet age.

Internet of Things (IoT) is considered as a key enabler of health informatics. IoT-enabled devices are used for in-hospital and in-home patient monitoring to collect and transfer biomedical data pertaining to blood pressure, electrocardiography (ECG), blood sugar levels, body temperature, etc. Among these devices, wearables have found their presence in a wide range of healthcare applications. These devices generate data in real-time and transmit them to nearby gateways and remote servers for processing and visualization. The data transmitted by these devices are vulnerable to a range of adversarial threats, and as such, privacy and integrity need to be preserved. In this paper, we present LightIoT, a lightweight and secure communication approach for data exchanged among the devices of a healthcare infrastructure. LightIoT operates in three phases: initialization, pairing, and authentication. These phases ensure the reliable transmission of data by establishing secure sessions among the communicating entities (wearables, gateways and a remote server). Statistical results exhibit that our scheme is lightweight, robust, and resilient against a wide range of adversarial attacks and incurs much lower computational and communication overhead for the transmitted data in the presence of existing approaches., This paper has been accepted for publication by the IEEE Transactions on Green Communications and Networking. The copyright is with the IEEE

In this paper, we consider an Internet-of-Things (IoT) network that supports two types of devices, namely static devices (SDs) and dynamic devices (DDs), with multiple channels. The notion of power-domain non-orthogonal multiple access (NOMA) is applied so that DDs can not only dynamically change channels, but also transmit signals with a high power to reduce collisions with SDs. Thus, learning algorithms are needed for DDs to select channels. To this end, multiarmed bandit (MAB) algorithms can be used. However, in general, it is difficult to analyze the performance of MAB algorithms in the setting due to the interaction of DDs. Thus, in this paper, instead of analyzing MAB algorithms, we formulate an evolutionary game of DDs in NOMA-based IoT networks and analyze the evolutionary game. It is shown that the game has a unique evolutionary stable state (ESS) in terms of the channel selection probability. The performance according to the ESS can be regarded as a baseline performance, because it is the best performance achieved by the DDs competing for multiple channel resources. Thus, the resulting baseline performance can be used to see if a learning algorithm including MAB can achieve a better performance by avoiding competition between DDs.

Practical application of deep learning based non-intrusive load monitoring (NILM) system requires the deep neural network model to generalize on new unseen data. Existing NILM solutions are not suitable for real-world application due to their poor disaggregation accuracy on new unseen data. In order to address this problem, this paper presents a NILM algorithm that uses data augmentation to generate synthetic data for training deep convolutional neural network models for each target appliance. Proposed data augmentation technique works by combining on and off-durations of a target appliance from various datasets, and forms a unified and comprehensive synthetic aggregate and sub-meter profiles. Apart from proposed algorithm, this paper also proposes an evaluation approach that relies on total predicted energy and ground-truth energy of an appliance to provide detailed insights about total overlapping energy, missing energy and extra energy predicted by the algorithm. Comparison results on our proposed evaluation approach showed that proposed disaggregation algorithm was able to predict energy that was 60% overlapping with ground truth energy and 36% energy was extra. Overall results showed that overlapping energy was 2.5 times more, and extra-predicted energy was 60% less than state-of-the-art algorithms in unseen test cases.

Accurate online classification of disturbance events in a transmission network is an important part of wide-area monitoring. Although many conventional machine learning techniques are very successful in classifying events, they rely on extracting information from PMU data at control centers and processing them through CPU/GPUs, which are highly inefficient in terms of energy consumption. To solve this challenge without compromising accuracy, this paper presents a novel methodology based on event-driven neuromorphic computing architecture for classification of power system disturbances. A Spiking Neural Network (SNN)-based computing framework is proposed, which exploits sparsity in disturbances and promotes local event driven operation for unsupervised learning and inference from incoming data. Spatio-temporal information of PMU signals is first extracted and encoded into spike trains and classification is achieved with SNN-based supervised and unsupervised learning framework. Moreover, a QR decomposition-based selection technique is proposed to identify signals participating in the low rank subspace of multiple disturbance events. Performance of the proposed method is validated on data collected from a 16-machine, 5-area New England-New York system., 11 pages, 8 figures. Paper has been accepted for publication in IEEE Transactions on Smart Grid on 26th of November, 2020. The link is as follows. https://ieeexplore.ieee.org/document/9290393/authors#authors

Model checking is a popular formal technique facilitating automatic verification of finite-state transition systems, and it has been applied to almost all of the Web service verification aspects, such as control-flow, data-flow, interaction, time requirements, quality of service, security requirements, etc. However, no systematic literature review focused on model checking of Web services is available. Motivated by this fact, in this paper, we systematically review existing research works on model checking based Web service verification appeared during the period of 2002–2017. We present a verification goal based classification of the collected articles, and for each paper, we identify the verification technique, target Web service standard, flavor of the employed model checking technique and tool, and other supplementary techniques, if any. Further, we highlight some of the issues, gaps, key challenges in this area and propose some future directions.

Person reidentification (Re-ID) aims to match observations of individuals across multiple nonoverlapping camera views. Recently, metric learning-based methods have played important roles in addressing this task. However, metrics are mostly learned in supervised manners, of which the performance relies heavily on the quantity and quality of manual annotations. Meanwhile, metric learning-based algorithms generally project person features into a common subspace, in which the extracted features are shared by all views. However, it may result in information loss since these algorithms neglect the view-specific features. Besides, they assume person samples of different views are taken from the same distribution. Conversely, these samples are more likely to obey different distributions due to view condition changes. To this end, this paper proposes an unsupervised cross-view metric learning method based on the properties of data distributions. Specifically, person samples in each view are taken from a mixture of two distributions: one models common prosperities among camera views and the other focuses on view-specific properties. Based on this, we introduce a shared mapping to explore the shared features. Meanwhile, we construct view-specific mappings to extract and project view-related features into a common subspace. As a result, samples in the transformed subspace follow the same distribution and are equipped with comprehensive representations. In this paper, these mappings are learned in an unsupervised manner by clustering samples in the projected space. Experimental results on five cross-view datasets validate the effectiveness of the proposed method.

This paper takes a fresh look at the image authentication problem and proposes an alternative framework for personalized authentication based on the hash learning technology. Conventional image authentication methods tend to provide a general authentication framework for all images with the fixed quantization strategy and fixed control parameters determined based on given limited images and attacks. However, they may suffer from more or less misjudgments in practice, not to mention performance degradation when encountering out-of-sample images. Instead of proposing a new feature extraction algorithm, a novel personalized authentication framework which incorporates the distance metric learning technology and supervised quantization strategy to the process of image authentication is proposed in this paper. The tamper detection task is reformulated as a new supervised manipulation classification problem. For each input image, various content-preserving and content-changing samples are generated automatically firstly. Then, feature representations of all samples can be obtained by existing feature extraction methods. After that, a weighted large margin for manipulation classification (WLMMC) scheme is proposed to learn an effective feature mapping space to improve the classification performance between content-changing samples and content-preserving samples. During the quantization stage, a novel supervised personalized quantization strategy (SPQ), which is motivated by the observation that different attacks have different degrees of influence on feature components, is proposed to learn more compact yet discriminative binary codes for each input image. Effectiveness of the proposed framework is qualitatively and quantitatively demonstrated on a variety of images. Extensive experiments show that the proposed framework can significantly improve the authentication performance over the state-of-the-art techniques while achieve more compact hash codes flexibly as required.

Low level image restoration is an integral component of modern artificial intelligence (AI) driven camera pipelines. Most of these frameworks are based on deep neural networks which present a massive computational overhead on resource constrained platform like a mobile phone. In this paper, we propose several lightweight low-level modules which can be used to create a computationally low cost variant of a given baseline model. Recent works for efficient neural networks design have mainly focused on classification. However, low-level image processing falls under the image-to-image' translation genre which requires some additional computational modules not present in classification. This paper seeks to bridge this gap by designing generic efficient modules which can replace essential components used in contemporary deep learning based image restoration networks. We also present and analyse our results highlighting the drawbacks of applying depthwise separable convolutional kernel (a popular method for efficient classification network) for sub-pixel convolution based upsampling (a popular upsampling strategy for low-level vision applications). This shows that concepts from domain of classification cannot always be seamlessly integrated into image-to-image translation tasks. We extensively validate our findings on three popular tasks of image inpainting, denoising and super-resolution. Our results show that proposed networks consistently output visually similar reconstructions compared to full capacity baselines with significant reduction of parameters, memory footprint and execution speeds on contemporary mobile devices., Comment: Accepted at: IEEE Transactions on Circuits and Systems for Video Technology (Early Access Print) | |Codes Available at: https://github.com/avisekiit/TCSVT-LightWeight-CNNs | Supplementary Document at: https://drive.google.com/file/d/1BQhkh33Sen-d0qOrjq5h8ahw2VCUIVLg/view?usp=sharing

In this paper, we propose a novel human crowd detection method that uses deep convolutional neural networks for drone flight safety purposes. The first contribution of this paper is to provide lightweight architectures, as restricted by the computational capacity of the specific application, capable of effectively distinguishing between crowded and non-crowded scenes from drone-captured images, and provide crowd heatmaps which can be used to semantically enrich the flight maps by defining no-fly zones. The second contribution of this paper is to propose a novel generic regularization technique, based on the graph embedding framework, applicable to different deep architectures for generic classification problems. The experimental validation is performed on a new dataset constructed for the task of human crowd detection from drone-captured images, and indicates the effectiveness of the proposed detector, as well as of the proposed regularizers in terms of classification accuracy. Finally, since the proposed regularization scheme is applicable in generic classification problems, we have also conducted experiments on two additional datasets, where the enhanced performance of the regularizers is also validated.

Electromyography (EMG) has already been broadly used in human-machine interaction (HMI) applications. Determining how to decode the information inside EMG signals robustly and accurately is a key problem for which we urgently need a solution. Recently, many EMG pattern recognition tasks have been addressed using deep learning methods. In this paper, we analyze recent papers and present a literature review describing the role that deep learning plays in EMG-based HMI. An overview of typical network structures and processing schemes will be provided. Recent progress in typical tasks such as movement classification, joint angle prediction, and force/torque estimation will be introduced. New issues, including multimodal sensing, inter-subject/inter-session, and robustness toward disturbances will be discussed. We attempt to provide a comprehensive analysis of current research by discussing the advantages, challenges, and opportunities brought by deep learning. We hope that deep learning can aid in eliminating factors that hinder the development of EMG-based HMI systems. Furthermore, possible future directions will be presented to pave the way for future research.

This position paper summarizes the main visions, opinions, and arguments of four experienced and well known researchers in the area of Internet of Things (IoT) and its relation to Data Science and Machine Learning (ML) as IoT permeates the globe and becomes “very large”. These visions were raised in an enthusiastic discussion panel held during the Third International Workshop on Very Large Internet of Things Systems (VLIoT 2019), in conjunction with VLDB 2019, in Los Angeles, USA. Each panelist delivered a vision statement before the floor was opened for questions and comments from the audience. Instead of reproducing ipsis literis each of the speeches, questions and replies, we decided to structure a two-part paper summarizing in-depth the panel opinions and discussions. In this first installment, we present the panelists' opening statements and views on issues related to IoT infrastructure and how it can support the growing demands for integrated intelligence, including communication, coordination and distribution challenges and how such challenges can be faced in the new generation of IoT systems.

Uncertain data objects are objects that can be characterized by either a probability density function (PDF) or with multiple points. Because of existing levels of uncertainty for uncertain data objects, the scatter of this type of objects might be very different than the scatter of certain data objects. Measures of scatter for uncertain objects have not been defined before. In this paper, we define covariance matrix, within scatter matrix, and between scatter matrix as the measures of scatter for uncertain data objects. Also, in this paper, we extend the idea of Fisher linear discriminant analysis for uncertain objects (UFLDA). We also develop kernel Fisher discriminant analysis for uncertain objects (UKFDA). The developed uncertain kernel Fisher discriminants are for two cases: 1) when the uncertain objects are given with PDF and 2) when the uncertain objects are given with multiple points. We compare the performance of our developed uncertain Fisher discriminants (UFLDA and UKFDA) with a few other methods in classification of uncertain data objects through several examples on both simulated and real-world data. We will show in the experiments that our developed uncertain Fisher discriminants outperform other methods in classifying uncertain data objects.

The 55th Design Automation Conference (DAC) held its first System Design Contest (SDC) in 2018. SDC'18 features a lower power object detection challenge (LPODC) on designing and implementing novel algorithms based object detection in images taken from unmanned aerial vehicles (UAV). The dataset includes 95 categories and 150k images, and the hardware platforms include Nvidia's TX2 and Xilinx's PYNQ Z1. DAC-SDC'18 attracted more than 110 entries from 12 countries. This paper presents in detail the dataset and evaluation procedure. It further discusses the methods developed by some of the entries as well as representative results. The paper concludes with directions for future improvements., 12 pages, 21 figures

Fifth-Generation (5G) mobile cellular networks provide a promising platform for new, innovative and diverse IoT applications, such as ultra-reliable and low latency communication, real-time and dynamic data processing, intensive computation, and massive device connectivity. End-to-End (E2E) network slicing candidates present a promising approach to resource allocation and distribution that permit operators to flexibly provide scalable virtualized and dedicated logical networks over common physical infrastructure. Though network slicing promises the provision of services on demand, many of its use cases, such as self-driving cars and Google's Stadia, would require the integration of a Multi-Access Edge Computing (MEC) platform in 5G networks. Edge Computing is envisioned as one of the key drivers for 5G and Sixth-Generation (6G) mobile cellular networks, but its role in network slicing remains to be fully explored. We investigate MEC and network slicing for the provision of 5G service focused use cases. Recently, changes to the cloud-native 5G core are a focus with MEC use cases providing network scalability, elasticity, flexibility, and automation. A cloud-native microservices architecture, along with its potential use cases for 5G network slicing, is envisioned. This paper also elaborates on the recent advances made in enabling E2E network slicing, its enabling technologies, solutions, and current standardization efforts. Finally, this paper identifies open research issues and challenges and provides possible solutions and recommendations.

Machine reading comprehension is a very challenging task, which aims to determine the answer span based on the given context and question. The newly developed pre-training language model has achieved a series of successes in various natural language understanding tasks with its powerful contextual representation ability. However, these pre-training language models generally lack the downstream processing structure for specific tasks, which limits further performance improvement. In order to solve this problem and deepen the model’s understanding of the question and context, this paper proposes S&I Reader. On the basis of the pre-training model, skimming, intensive reading, and gated mechanism modules are added to simulate the behavior of humans reading text and filtering information. Based on the idea of granular computing, a multi-granularity module for computing context granularity and sequence granularity is added to the model to simulate the behavior of human beings to understand the text from words to sentences, from parts to the whole. Compared with the previous machine reading comprehension model, our model structure is novel. The skimming module and multi-granularity module proposed in this paper are used to solve the problem that the previous model ignores the key information of the text and cannot understand the text with multi granularity. Experiments show that the model proposed in this paper is effective for both Chinese and English datasets. It can better understand the question and context and give a more accurate answer. The performance has made new progress on the basis of the baseline model.

Grain-128AEAD is a lightweight authenticated encryption stream cipher and one of the finalists in the National Institute of Standards and Technology (NIST) Lightweight Cryptography (LWC) project. This paper provides an independent third-party analysis of Grain-128AEAD against fault attacks. We investigate the application of three differential fault attack models on Grain-128AEAD. All these attacks can recover the initial state of Grain-128AEAD. First, we demonstrate an attack using a bit-flipping fault that requires access to 27.80 faulty outputs to recover the initial state. Then, we demonstrate an attack with a more relaxed assumption of a random fault with a probabilistic approach. Our probabilistic random fault attack requires access to 211.60 faulty outputs and 210.45 fault injections to recover the initial state with a success rate over 99%. Both of the above two attacks are based on precise control on the fault target. Finally, we apply a random fault attack with a deterministic approach (can conclusively determine the random fault value) and using different precision controls. For the precise control, we use existing approaches that have been applied to other ciphers, such as Tiaoxin-346. We also propose a technique for less stringent precision models, such as moderate control and no control, which are more practical than the precise control. Our result indicates that the deterministic random fault attack with a precise control requires an average of 27.64 fault injections and a data complexity of 28.80. The deterministic random fault attack with moderate control requires a weak assumption on the fault injection and hence, is the best attack presented in this paper; and is expected to require about 29.39 fault injections with a data complexity of about 212.98. All the attacks discussed in this paper are verified experimentally.

Food recognition has captured numerous research attention for its importance for health-related applications. The existing approaches mostly focus on the categorization of food according to dish names, while ignoring the underlying ingredient composition. In reality, two dishes with the same name do not necessarily share the exact list of ingredients. Therefore, the dishes under the same food category are not mandatorily equal in nutrition content. Nevertheless, due to limited datasets available with ingredient labels, the problem of ingredient recognition is often overlooked. Furthermore, as the number of ingredients is expected to be much less than the number of food categories, ingredient recognition is more tractable in the real-world scenario. This paper provides an insightful analysis of three compelling issues in ingredient recognition. These issues involve recognition in either image-level or region level, pooling in either single or multiple image scales, learning in either single or multi-task manner. The analysis is conducted on a large food dataset, Vireo Food-251, contributed by this paper. The dataset is composed of 169,673 images with 251 popular Chinese food and 406 ingredients. The dataset includes adequate challenges in scale and complexity to reveal the limit of the current approaches in ingredient recognition.

This paper aims to provide an in-depth study of the detection of historical alarm subsequences, which are frequently used as an initial step for alarm flood analysis methods. Therefore, state-of-the-art approaches are comprehensively examined, evaluated, and compared. To overcome the limitations of these methods, a novel approach is presented, which uses outlier detection in time distances between alarm events (activation and return to normal) and an alarm coactivation constraint. The effectiveness and performance of the examined methods are illustrated by means of an openly accessible dataset, which is introduced in this paper. It is based on the “Tennessee-Eastman-Process”, a benchmark in process automation. The intent is to provide a suitable dataset for the development and evaluation of alarm management methods in complex industrial processes using both quantitative and qualitative information from different sources. It is shown that the integration of supplementary information is beneficial for the overall performance and robustness of the detection method proposed here. This method allows for a more accurate detection of coherent historical abnormal situations, including phases with active root-cause disturbances and the normalization phases that follow their termination. Furthermore, the proposed method has the advantage that the detection results are less influenced by the alarm count, the propagation velocity, the duration of the situation, and the time distance between two causally independent situations in comparison to state-of-the-art approaches.

An intrusion detection system (IDS) is an important protection instrument for detecting complex network attacks. Various machine learning (ML) or deep learning (DL) algorithms have been proposed for implementing anomaly-based IDS (AIDS). Our review of the AIDS literature identifies some issues in related work, including the randomness of the selected algorithms, parameters, and testing criteria, the application of old datasets, or shallow analyses and validation of the results. This paper comprehensively reviews previous studies on AIDS by using a set of criteria with different datasets and types of attacks to set benchmarking outcomes that can reveal the suitable AIDS algorithms, parameters, and testing criteria. Specifically, this paper applies 10 popular supervised and unsupervised ML algorithms for identifying effective and efficient ML-AIDS of networks and computers. These supervised ML algorithms include the artificial neural network (ANN), decision tree (DT), k-nearest neighbor (k-NN), naive Bayes (NB), random forest (RF), support vector machine (SVM), and convolutional neural network (CNN) algorithms, whereas the unsupervised ML algorithms include the expectation-maximization (EM), k-means, and self-organizing maps (SOM) algorithms. Several models of these algorithms are introduced, and the turning and training parameters of each algorithm are examined to achieve an optimal classifier evaluation. Unlike previous studies, this study evaluates the performance of AIDS by measuring the true positive and negative rates, accuracy, precision, recall, and F-Score of 31 ML-AIDS models. The training and testing time for ML-AIDS models are also considered in measuring their performance efficiency given that time complexity is an important factor in AIDSs. The ML-AIDS models are tested by using a recent and highly unbalanced multiclass CICIDS2017 dataset that involves real-world network attacks. In general, the k-NN-AIDS, DT-AIDS, and NB-AIDS models obtain the best results and show a greater capability in detecting web attacks compared with other models that demonstrate irregular and inferior results.

With the rapid development of remote-sensing imaging technology, remote-sensing images have become increasingly diverse, and people are paying more attention to ocean remote-sensing research. Because ocean remote-sensing data are complex, and the ocean environment is diverse, results will differ, even if the same target is detected at different times in the same scene. To obtain more semantic features and better pixel-level prediction capabilities, this paper proposes a pixel-level ocean remote-sensing image algorithm (GLPO-Net) that combines local and global features. First, texture features, color features, and spatial relationship features are extracted. Second, the algorithm constructs a multiscale local cross-attention mechanism strategy to obtain feature weight information in different directions to fully mine the local features of ocean remote-sensing images. Concurrently, an algorithm constructs a multiscale global cross-attention mechanism strategy to obtain global features. Then, the fusion of global features and local features is described in each submodule to obtain more representative deep features. Finally, small-sample ocean remote-sensing is described via image pixel-level prediction. The algorithm proposed in this paper has been tested with three public ocean remote-sensing datasets. The experimental results show that the proposed GLPO-Net algorithm can learn features from small samples of ocean remote-sensing images. Compared to the prediction results of other remote-sensing image algorithms, GLPO-Net exhibits better prediction capabilities.

Handwritten mathematical expressions are an essential part of many domains, including education, engineering, and science. The pervasive availability of computationally powerful touch-screen devices, similar to the recent emergence of deep neural networks as high-quality sequence recognition models, result in the widespread adoption of online recognition of handwritten mathematical expressions. Also, a deeper study and improvement of such technologies is necessary to address the current challenges posed by the extensive usage of distance learning, and remote work due to the world pandemic. This paper delineates the state-of-the-art recognition methods along with the user's experience in pen-centric applications for operating with handwritten mathematical expressions. Recognition methods have been categorized into classes, with a description of their merits and limitations. Particular attention is paid to end-to-end approaches based on encoder-decoder architecture and multi-modal input. Evaluation protocols and open benchmark datasets are considered as well as the comparison of the recognition performance, based on open competition results. The use of handwritten math recognition is illustrated by examples of applications for various fields and platforms. A distinctive part of the survey is that we also considered how UI design relies on the use of different recognition approaches, which is aimed at helping potential researchers improve the performance of the introduced approaches toward the best responses in practical applications. Finally, this paper presents the prospective survey of future research directions in handwritten mathematical expression recognition and their applications.

For the on-orbit service spacecraft attitude tracking task with external disturbances, considering the limited capacity of its actuators and high control performance required, an improved performance constraint control algorithm based on command filters is proposed in this paper. For the proposed control algorithm, before the theoretical control signal is transmitted to the actuator, it needs to be filtered by the command filter. This filter can constrain the rate, magnitude, and bandwidth of the signals, smooth the command signals and avoid peak interference. In terms of performance constraints, inspired by the performance constraint curve, this paper uses the determined points to re-design a new performance constraint function, which shows the maximum settling time parameters, allowing designers to pre-defined this limited time of the closed-loop system according to needs. Therefore, the maximum settling time of the actual closed-loop system will be less than the pre-defined maximum settling time. The controller based on the command filter is designed, and on this basis, the corresponding performance-constrained control algorithm with pre-defined maximum settling time guaranteed is proposed. Through the proof and simulation, the rationality and effectiveness of the proposed controller are further demonstrated.

Digital image watermarking is the process of embedding and extracting a watermark covertly on a cover-image. To dynamically adapt image watermarking algorithms, deep learning-based image watermarking schemes have attracted increased attention during recent years. However, existing deep learning-based watermarking methods neither fully apply the fitting ability to learn and automate the embedding and extracting algorithms, nor achieve the properties of robustness and blindness simultaneously. In this paper, a robust and blind image watermarking scheme based on deep learning neural networks is proposed. To minimize the requirement of domain knowledge, the fitting ability of deep neural networks is exploited to learn and generalize an automated image watermarking algorithm. A deep learning architecture is specially designed for image watermarking tasks, which will be trained in an unsupervised manner to avoid human intervention and annotation. To facilitate flexible applications, the robustness of the proposed scheme is achieved without requiring any prior knowledge or adversarial examples of possible attacks. A challenging case of watermark extraction from phone camera-captured images demonstrates the robustness and practicality of the proposal. The experiments, evaluation, and application cases confirm the superiority of the proposed scheme., Comment: This paper has been accepted for publication by the IEEE Transactions on Multimedia. The copyright is with the IEEE. DOI: 10.1109/TMM.2020.3006415

The selection of the system-architecture is critical step in software-engineering lifecycle. Unfortunately, the selecting a suitable architecture is a hard mission. The difficulty of the adopting architecture increases in inconsistence case as in SOA and MSA. The paper answers “when architecture transform”, “to which architecture migrate” and “how”. The paper addresses the lack of evaluation ERPs in post-implementation phase. The paper provides static and dynamic analysis for monolith, SOA and MSA by numerical-comparison and Benchmark. This paper proposes a roadmap for migration-architecture. The roadmap consists of flowchart of migration and migration-decision model that is supported with criteria of evaluation form for assessing system’s baseline and making a consistence decision by Neutrosophic-ANP. Because of the dependency between factors of information system evolution, ANP is used. Furthermore, Neutrosophic set is selected because its accuracy in inconsistence. Benchmark assesses OpenBravoERP, Odoo12 and Metasfresh5.144 to represent monolith, SOA and MSA respectively. Benchmark assesses performance, time to the market, stability, future proof, network issue and cost. They are tested based on scenario tests which grantee that transactions are executed within more than one module of ERPS, simulates real business’s procedures, huge number of records and concurrent load by virtual users. The proposed model and benchmark help “Hitac’ enterprise in two decisions for its expansion-plan in COVID-19 crisis. The numerical steps of this case-study are provided. Most published papers and literatures about Microservices are not empirical. The main paper’s result is filling this gap by a one of the empirical aspects with an academic study support.

Autonomous driving (AD) provides a reliable solution for safe driving by replacing human drivers responsible for the majority of accidents. The emergence of Machine Learning, specifically Deep Reinforcement Learning (DRL), and its ability to solve complex games proved its potential to address AD challenges. However, model-free methods still suffer from safety-related issues that can be resolved using safe-DRL approaches. The addition of model-based safety filters to the learning-based algorithms provides safety bounds on their performance and constraint satisfaction. In this paper, we investigate the addition of a safety filter based on Model Predictive Control and show an increase in mean testing episode reward by 110% from −75 mean episode reward during testing for 50 episodes for Deep Deterministic Policy Gradient ( $DDPG$ ) to 7.758. We study the impacts of safety filters (7.758 mean reward), heuristic rules, bounded additive noises (0.49% performance increase comparing to noise-free case), and exploration (3.425 mean reward) on the learning algorithm. We compare the effects of filters in the context of simulated exploration and bounded exploration and prove that bounded exploration results in 9.86% increase in mean reward and 12.95% decrease in std comparing to the other method. Additionally, inspired by Deep Internal Learning and biological mechanisms like brain plasticity, we investigate the idea of using each sample for training only once instead of utilizing stochastic batches which increases the mean testing accumulated reward by 1.87% and leads to the best performance (7.942 mean reward and 0.048 std). Finally, the results demonstrate better automotive results for our proposed method than DDPG. Our proposed method, DDPG with safety filter in bounded exploration and adaptive learning under noisy input conditions, has a success rate of 100% under different traffic densities for the simulation environment used in this paper and our assumptions. The proposed method’s automotive results are shown for a braking scenario to avoid collision with other road users.

This paper discusses impact of recovering missing Electroencephalography (EEG) data on classification accuracy of hand movements using tensor-based methods. Improvement in classification accuracy is important for efficient performance of prosthesis. Classification accuracy relies on quality of the observed data. In practice, observed data is usually incomplete because of disconnection of electrodes and other artefacts, which negatively affect the classification accuracy. In this paper, we employ tensor-based imputation methods (canonical/polyadiac decomposition (CPD), weighted optimization version of CPD (CP-WOPT and Nonnegative Matrix Factorization (NMF)) to recover missing data in EEG signals and apply various classifiers to classify hand movements on recovered data. In particular, structured missing data was considered because that is how data gets missed in real-life data acquisition. Percentage of missing data was changed from 10% to 50%. Classifiers are applied on complete, missing and recovered data explicitly to test the performance of our framework. Results show that mean classification accuracy on complete data, missing data and recovered data was 71%, 53% and 64% respectively which shows applicability of our framework.

As connected Internet-of-things (IoT) devices in smart homes, smart cities, and smart industries continue to grow in size and complexity, managing and securing them in distributed edge networks have become daunting but crucial tasks. The recent spate of cyber attacks exploiting the vulnerabilities and insufficient security management of IoT devices have highlighted the urgency and challenges for securing billions of IoT devices and applications. As a first step towards understanding and mitigating diverse security threats of IoT devices, this paper develops an IoT traffic measurement framework on programmable and intelligent edge routers to automatically collect incoming, outgoing, and internal network traffic of IoT devices in edge networks, and to build multidimensional behavioral profiles which characterize who, when, what, and why on the behavioral patterns of IoT devices based on continuously collected traffic data. To the best of our knowledge, this paper is the first effort to shed light on the IP-spatial, temporal, entropy, and cloud service patterns of IoT devices in edge networks, and to explore these multidimensional behavioral fingerprints for IoT device classification, anomaly traffic detection, and network security monitoring for vulnerable and resource-constrained IoT devices on the Internet.

Grasshopper Optimization Algorithm (GOA) is a recent swarm intelligence algorithm inspired by the foraging and swarming behavior of grasshoppers in nature. The GOA algorithm has been successfully applied to solve various optimization problems in several domains and demonstrated its merits in the literature. This paper proposes a comprehensive review of GOA based on more than 120 scientific articles published by leading publishers: IEEE, Springer, Elsevier, IET, Hindawi, and others. It provides the GOA variants, including multi-objective and hybrid variants. It also discusses the main applications of GOA in various fields such as scheduling, economic dispatch, feature selection, load frequency control, distributed generation, wind energy system, and other engineering problems. Finally, the paper provides some possible future research directions in this area.

Hyperspectral and multispectral information processing systems and technologies have demonstrated its usefulness for the improvement of agricultural productivity and practices by providing useful information to farmers and crop managers on the factors affecting crop status and growth. These technologies are widely used in a range of agriculture applications such as crop management, crop yield forecasting, crop disease detection, and the monitoring of agriculture land usage, water, and soil conditions. Hyperspectral information sensing can acquire several hundred spectral bands that cover the electromagnetic spectrum of an observational scene in a single acquisition. The resulting hyperspectral data cube contains a large volume of spatial and spectral information. The hyperspectral sequence of images or video further increases the data generation velocity and volume which lead to the Big data challenges particularly in agricultural remote sensing applications. This paper is structured to first give a comprehensive review of representative studies to provide insights into significant research efforts in agriculture using Big data, machine learning and deep learning with the focus on frameworks or architectures, information processing and analytics with hyperspectral and multispectral data. The potential for utilizing Big data, machine learning and deep learning for hyperspectral and multispectral data in agriculture is very promising. The paper then further explores the potential of using ensemble machine learning and scalable parallel discriminant analysis which takes into consideration the spatial and spectral components for Big data in agriculture. To the best of our knowledge, no similar review study on agriculture with Big data, machine learning and deep learning for hyperspectral and multispectral information processing has been reported. Furthermore, the potential of ensemble machine learning and scalable parallel discriminant analysis has not been explored in agriculture information processing. Experiments and data analytics have been performed on hyperspectral data from agriculture for validation. The results have shown the good performance of our approach.