This paper elaborates on a new class of orthonormal power-based algorithms for fast estimation and tracking of the principal or minor subspace of a vector sequence. The proposed algorithms are closely related to the natural power method that has the fastest convergence rate among many power-based methods such as the Oja method, the projection approximation subspace tracking (PAST) method, and the novel

In this paper, we develop methods for efficient and accurate information extraction from calcium-imaging-based neural signals. The particular form of information extraction we investigate involves predicting behavior variables linked to animals from which the calcium imaging signals are acquired. More specifically, we develop algorithms to systematically generate compact deep neural network (DNN) models

Inertial sensors based on micro-electro-mechanical systems (MEMS) technology, such as accelerometers and angular rate sensors, are cost-effective solutions used in inertial navigation systems in a broad spectrum of applications that estimate position, velocity and orientation of a system with respect to an inertial reference frame. Although they present several advantages in terms of cost and form

The integration of FPGA-based accelerators into a complete heterogeneous system is a challenging task faced by many researchers and engineers, especially now that FPGAs enjoy increasing popularity as implementation platforms for efficient, application-specific accelerators for domains such as signal processing, machine learning and intelligent storage. To lighten the burden of system integration from

Starting from medical big data, this article uses data mining technology to analyze and study the pathogenic factors of lung cancer based on the lung cancer electronic medical record data from the oncology department of the authoritative third grade A hospital for many years. With respect to the processing of huge data from electronic medical records for lung cancer, traditional serial Apriori algorithm

Nowadays, processing systems are constrained by the low efficiency of their memory subsystems. Although memories evolved into faster and more efficient devices through the years, they were still unable to keep up with the computational power offered by processors, i.e., feed the processors with the data they require at the rhythm it is consumed. Consequently, with the advent of Big Data, the need for

Network monitoring has been traditionally conducted using Simple Network Management Protocol (SNMP): a network monitoring protocol that allows network administrators to keep track of every node in the network and ensure that it behaves correctly. This paper presents the Constrained Monitored Protocol (CoMP): a lightweight resource-efficient alternative to SNMP that targets the low-end devices of the

From a security perspective, identifying Industrial Internet of Things (IIoT) devices connected to a network has multiple applications such as penetration testing, vulnerability assessment, etc. In this work, we propose a feature-based methodology to perform device-type fingerprinting. A device fingerprint consists of the TCP/IP header features and port-based features extracted from the network traffic

Electric power protocol is a typical kind of industrial protocols, and is widely-used in electric power systems. Since most electric power protocols are private and have no public protocol specification, it poses a great challenge for security analysis and vulnerability discovery. Protocol reverse engineering makes it possible to analyze unknown or private protocols. However, previous reverse engineering

The paper presents a risk-driven behavioral biometric-based user authentication scheme for smartphones. Our scheme delivers one-shot-cum-continuous authentication, thus not only authenticates users at the start of the application sign-in process but also, throughout the active user session. The scheme leverages the widely used PIN/password-based authentication technology by giving flexibility to users

Synchronous DataFlow Graph (SDFG in short) is a formalism frequently considered in electronic design and software compilers to model communications between components with different rates. The development of efficient algorithms to evaluate the maximum throughput of SDFGs is a challenging question. This paper presents a mathematical framework to perform schedulability analysis and to compute the maximum

Internet applications remain exposed to pervasive Domain Name System (DNS)–based threats. Blockchain technologies provide a new way for tackling DNS vulnerability issues, and have been highlighted recently. However, traditional blockchain is still not well suited for big data applications such as DNS, because the performance of blockchain consensus greatly limits its practical adoption. In this paper

Automatic classification of musical instruments from audio relies heavily on datasets of acoustic recordings of the instruments to train models of those instruments. To do this, precise labels of the instrument’s events are mandatory. Also, it is very difficult to obtain such labels, especially in polyphonic performances. OpenMic-2018 is a polyphonic dataset created specifically with the aim to train

The hidden periodicity detection using a cyclic spectral function (CSF) is one of the well-known methods for cyclostationary signals analysis. Many two-dimensional signals (2D-signals), such as textures, can be considered cyclostationary or semi-cyclostationary. Applying such an assumption provides a new effective field for the analysis of 2D-signals. This paper presents two new algorithms for two-dimensional

In this paper, a hardware implementation in reconfigurable logic of a single-pass connected component labelling (CCL) and connected component analysis (CCA) module is presented. The main novelty of the design is the support of a video stream in 2 and 4 pixel per clock format (2 and 4 ppc) and real-time processing of 4K/UHD video stream (3840 x 2160 pixels) at 60 frames per second. We discuss several

The rapid contemporary development of wearable devices offers non-invasive and effective approaches for monitoring the human brain. Recent studies have investigated the prediction of epileptic seizures (ESs) using wearable measurements, such as scalp electroencephalography and functional near-infrared spectroscopy. The signal processing tasks are the core component of emerging closed-loop ES prediction

Recently, NB-IoT, LTE Cat-M1, Sigfox, and LoRa have been proposed as promising Low-Power Wide Area Networks (LPWANs) technologies for Internet-of-Things (IoT) applications. These technologies are aimed for IoT applications such as smart meters that can tolerate long transmission delays and only need a narrow band to periodically transmit a small amount of data. Although the performances of these technologies

At present, autonomous management and operation of spacecraft are the main direction and objective of the development of space technology to lighten the burden of ground measurement and control, reduce the cost of operation and management, and expand the application scope of spacecraft. To select the suitable periodic variable stars with a certain quantity at the given conditions of spacecraft, we

On the one hand, processors for hearing aids are highly specialized for audio processing, on the other hand they have to meet challenging hardware restrictions. This paper aims to provide an overview of the requirements, architectures, and implementations of these processors. Special attention is given to the increasingly common application-specific instruction-set processors (ASIPs). The main focus

In recent years, Convolutional Neural Network CNN have been incorporated in a large number of applications, including multimedia retrieval and image classification. However, CNN based algorithms are computationally and resource intensive and therefore difficult to be used in embedded systems. FPGA based accelerators are becoming more and more popular in research and industry due to their flexibility

In recent years, the neural architecture search has continuously made significant progress in the field of image recognition. Among them, the differentiable method has obvious advantages compared with other search methods in terms of computational cost and accuracy to deal with image classification. However, the differentiable method is usually composed of single cell, which cannot efficiently extract

As big data analytics systems are squeezing out the last bits of performance of CPUs and GPUs, the next near-term and widely available alternative industry is considering for higher performance in the data center and cloud is the FPGA accelerator. We discuss several challenges a developer has to face when designing and integrating FPGA accelerators for big data analytics pipelines. On the software

Coarse Grained Reconfigurable Arrays (CGRAs) or Architectures are a concept for hardware accelerators based on the idea of distributing workload over Processing Elements. These processors exploit instruction level parallelism, while being energy efficient due to their simplistic internal structure. However, the incorporation into a complete computing system raises severe challenges at the hardware

Over the last decade, Convolutional Neural Networks (CNNs) have become the go to technique to perform tasks in deep learning applications such as computer vision, speech recognition, etc. LeCun et al (Nature 521(7553), 436–44) 2015. Even though CNNs are very efficient at these tasks they are not suitable for embedded applications due to the limited power budget. In this work we present an improved

Periodic variable navigation can realize the integration of positioning, attitude determination, timing and other functions. As a novel autonomous navigation method, autonomous management and autonomous operation of spacecraft are the main direction of great significance to reduce the burden of ground measurement and control, to improve the viability of spacecraft, While, the precision of the navigation

As a part of a growing information society, nowadays the issue of security is more crucial than ever. In order to achieve high level of security, the potential of accurately recognize subjects based on their unique measurable physiological or behavioral characteristics has been receiving an increased concern by the research and development community. As biometrics has advanced, iris has been considered

Convolutional neural networks (CNNs) exhibit state-of-the-art performance while performing computer-vision tasks. CNNs require high-speed, low-power, and high-accuracy hardware for various scenarios, such as edge environments. However, the number of weights is so large that embedded systems cannot store them owing to their limited on-chip memory. A different method is used to minimize the input image

Whilst FPGAs have been used in cloud ecosystems, it is still extremely challenging to achieve high compute density when mapping heterogeneous multi-tasks on shared resources at runtime. This work addresses this by treating the FPGA resource as a service and employing multi-task processing at the high level, design space exploration and static off-line partitioning in order to allow more efficient mapping

Voice user interface (VUI) has become increasingly popular in recent years. Speaker recognition system, as one of the most common VUIs, has emerged as an important technique to facilitate security-required applications and services. In this paper, we propose to design, for the first time, a real-time, robust, and adaptive universal adversarial attack against the state-of-the-art deep neural network

In this paper, we consider deep unfolding the standard iterative conjugate gradient (CG) algorithm to solve a linear system of equations. Instead of being adjusted with known rules, the parameters are learned via backpropagation to yield the optimal results. However, the proposed unfolded CG (UCG) is extended wherein a scalar parameter is substituted by a matrix-parameter to augment the degrees of

Security devices produce huge number of logs which are far beyond the processing speed of human beings. This paper introduces an unsupervised approach to detecting anomalous behavior in large scale security logs. We propose a novel feature extracting mechanism and could precisely characterize the features of malicious behaviors. We design a LSTM-based anomaly detection approach and could successfully

Recently, there is a great demand for experimenting with Artificial Intelligence (AI) algorithms on the Internet of Things (IoT) devices that have only limited computing or transmission resources. Hyper-Dimensional Computing (HDC), which can effectively run on low-cost CPUs, is one of the solutions. However, since the AI algorithms are proved to be vulnerable to Adversarial Examples (AE) in recent

In this paper, we introduce a Back-to-Back Butterfly Network (B2BN) based on multiplexers (MUXs) in which any kind of permutation can be performed. However, for a given permutation, it is not an easy task to select the appropriate paths in B2BN without any conflict in terms of MUXs. In this paper, we propose a formal model to efficiently solve such conflicts. The proposed method relies on collecting

Coarse Grained Reconfigurable Arrays (CGRAs) are emerging as energy efficient accelerators providing a high grade of flexibility in both academia and industry. However, with the recent advancements in algorithms and performance requirements of applications, supporting only integer and logical arithmetic limits the interest of classical/traditional CGRAs. In this paper, we propose a novel CGRA architecture

Deep Learning provided powerful tools for forecasting financial time series data. However, despite the success of these approaches on many challenging financial forecasting tasks, it is not always straightforward to employ DL-based approaches for highly volatile and non-stationary time financial series. To this end, in this paper, an adaptive input normalization layer that can learn to identify the

Establishing conclusive cortical activity dynamics from neuroimages and high dimensional neuronal data post-processing, such as scalp-EEG/ERP or its localized source data, is always challenging. For addressing this, we introduce LEDA, localized-EEG dynamics analyzer, offering our novel techniques, namely (1)the localized source activity to duration (LSAD) ratio that elegantly combines voxel activation

Commonly used remote sensing image de-haze methods include: the image enhancement method and a physical model-based. However, when the above methods are applied to high-resolution remote sensing images, problems with texture information loss and insufficient enhancement often occur. These problems affect further analysis and application of high-resolution remote sensing images. This paper proposes

Quantum computers are imminent threat to secure signal processing because they can break the contemporary public-key cryptography schemes in polynomial time. Ring learning with error (RLWE) lattice-based cryptography (LBC) is considered as the most versatile and efficient family of post-quantum cryptography (PQC). Polynomial multiplication is the most compute-intensive routine in the RLWE schemes.

Noise removal in images denotes an interesting and a relatively challenging problem that has captured the attention of many scholars. Recent denoising methods focus on simultaneously restoring noisy images and recovering their semantic features (edges and contours). But preservation of textures, which facilitate interpretation and analysis of complex images, remains an open-ended research question

This paper proposes a subspace identification method for closed-loop EIV (errors-in-variables) problems based on instrumental variables . First, a unified framework is derived, and then the reason is discussed why some existing subspace methods based on instrumental variables could be biased under closed-loop conditions. Afterwards a remedy is given to eliminate the bias by simply replacing the instrumental

MIMO system identification is a fundamental concern in a variety of applications. Various iterative and recursive MIMO system identification algorithms exist in the literature. The iterative algorithms suffer from high computational cost due to large matrix computations and recursive algorithms suffer from slow convergence speed. This paper proposes a fast recursive exact least squares algorithm for

Computational complexity of state of the art Convolutional Neural Networks (CNNs) makes their integration in embedded systems with low power consumption requirements a challenging task. This requires the joint design and adaptation of hardware and algorithms. In this paper, we propose a new general CNN compression method to reduce both the number of parameters and operations. To solve this, we introduce

The objective of this work is to evaluate the effectiveness of a wearable physiological stress monitoring system in distinguishing between stressed and non-stressed state in older adults using machine learning techniques. This system utilizes EDA and BVP signal to detect occurrence of stress as indicated by salivary cortisol measurement which is a reliable objective measure of physiological stress

This paper presents a reconfigurable frequency response masking (FRM) wideband channelizer architecture which is characterized by low computational and hardware complexity. The proposed hardware efficient architecture is realized by incorporating resource shared non-maximally decimated filter bank in the implementation of the FRM wideband channelizer structure. The coefficients of the proposed architecture

Segmentation of thigh tissues (muscle, fat, inter-muscular adipose tissue (IMAT), bone, and bone marrow) from magnetic resonance imaging (MRI) scans is useful for clinical and research investigations in various conditions such as aging, diabetes mellitus, obesity, metabolic syndrome, and their associated comorbidities. Towards a fully automated, robust, and precise quantification of thigh tissues,

In recent years, target detection framework based on deep learning has made brilliant achievements. However, real-life traffic sign detection remains a great challenge for most of the state-of-the-art object detection methods. The existing deep learning models are inadequate to effectively extract the features of small traffic signs from large images in real-world conditions. In this paper, we address

Convolutional Neural Networks (CNNs) have improved several computer vision applications, like object detection and classification, when compared to other machine learning algorithms. Running these models in edge computing devices close to data sources is attracting the attention of the community since it avoids high-latency data communication of private data for cloud processing and permits real-time

With the rapid development of 5G network and Internet of Things, Clustered Look-Ahead (CLA) technique becomes a promising approach to further accelerate recursive digital filters for real-time applications, such as smart robots and automatic driving. However, it is not easy to quickly obtain a stable CLA pipelined VLSI (Very Large Scale Integration) architecture using the existing methods. This paper

With the rise of graphics processing units (GPUs), the parallel computing community needs better tools to productively extract performance from the GPU. While modern compilers provide flags to activate different optimizations to improve performance, the effectiveness of such automated optimization has been limited at best. As a consequence, extracting the best performance from an algorithm on a GPU

Automatic age estimation from the face images is a growing research interest nowadays. Various literature works have contributed towards the age detection scheme, besides only a few have resulted in providing good performance. This is due to the influence of the external factors, such as environment, lifestyle, and various expressions present in the face image. This paper proposes a deep belief network

As nodes have limited resources in the socially aware networks, they will have strong selfish behaviors, such as not forwarding messages and losing packets, which will lead to poor network performance. Thus, an equivalent-exchange-based data forwarding incentive scheme (EEIS) will be proposed in this paper. It is main that messages forwarding will be abstracted into a transaction in EEIS. The buyer

Technological advances allow the production of increasingly complex electronic systems. Nevertheless, technology and voltage scaling increased dramatically the susceptibility of new devices not only to Single Bit Upsets (SBU), but also to Multiple Bit Upsets (MBU). In safety critical applications, it is mandatory to provide fault-tolerant systems, providing high reliability while meeting applications

To develop an automated pulmonary fibrosis (PF) segmentation methodology using a 3D multi-scale convolutional encoder-decoder approach following the robust atlas-based active volume model in thoracic CT for Rhesus Macaques with radiation-induced lung damage. 152 thoracic computed tomography scans of Rhesus Macaques with radiation-induced lung damage were collected. The 3D input data are randomly augmented

Fully homomorphic encryption (FHE) is a post-quantum secure cryptographic technology that enables privacy-preserving computing on an untrusted platform without divulging any secret or sensitive information. The core of FHE is the bootstrapping algorithm, which is the intermediate refreshing procedure of a processed ciphertext. However, this step has been the computational bottleneck that prevents real-world

Dynamic successive cancellation flip (DSCF) decoding of polar codes is a powerful algorithm that can achieve the error correction performance of successive cancellation list (SCL) decoding, with an average complexity that is close to that of successive cancellation (SC) decoding at practical signal-to-noise ratio (SNR) regimes. However, DSCF decoding requires costly transcendental computations to calculate

It is a fact that Artificial Intelligence is having an ever-growing impact on society. That is not just because of advances in computational power and in machine learning models, such as deep neural networks, but also because of the availability of a large volume of heterogeneous data from diverse sources. The Internet of Things (IoT) paradigm is helping gather massive amounts of data from sensor networks

Over the past, deep neural networks have proved to be an essential element for developing intelligent solutions. They have achieved remarkable performances at a cost of deeper layers and millions of parameters. Therefore utilising these networks on limited resource platforms for smart cameras is a challenging task. In this context, models need to be (i) accelerated and (ii) memory efficient without

This paper describes a low cost computer vision system able to obtain traffic metrics at urban intersections. The proposed system is based on a Bayesian network based reasoning model. It employs the data extracted from background subtraction and contrast analysis techniques applied to predefined regions of interest of the video sequences, to evaluate different traffic metrics. The system has been designed

For vehicles with limited computation resources offloading their computational tasks to a mobile edge computing (MEC) server has been studied in the past as an effective means for improving their computational capabilities. However, most of these studies do not consider, in a meaningful way, the economic aspects related to both the computation offloading of the vehicles and the MEC service providers

In computer-assisted pronunciation training (CAPT) system, feedback for non-native mispronunciation verification is important, for the reason that it is beneficial to the second language (L2) learners in respect of pronunciation improving. In pronunciation evaluation at the phone level, the pairwise distances between embeddings of native phones and non-native phones could be an ideal predictor of L2