Features Matrix Research Articles

Health Condition Identification of Rolling Element Bearing Based on Gradient of Features Matrix and MDDCs-MRSVD

Bearing is a key component in rotary machines, and the performance of the rotary machines mostly depends on the bearing health condition. In order to improve the safety and maintenance plan of the product based on the bearing condition, a monitoring indicator is constructed to identify the health condition of bearings in real time. Firstly, the vibration signal is processed by the proposed Maximal Difference of the Detail Components in Multi-Resolution Singular Value Decomposition (MDDCs-MRSVD) algorithm. Secondly, the features matrix is constructed by selected features to reflect the health condition of bearings. Then, the gradient standard deviation of each sampling time is obtained by the gradient in the amplitude direction of the features matrix. Finally, a monitoring indicator can be constructed to identify healthy stages of bearing. The proposed methods are verified via the tested datasets provided by Intelligent Maintenance Systems, and Xi’an Jiaotong University and the Changxing Sumyoung Technology Co., Ltd. (XJTU-SY). The results indicate that the proposed method is efficient and accurate to monitor and identify the health stages of bearing in real time.

Human Face Recognition Based on Local Ternary Pattern and Singular Value Decomposition

There is various human biometrics used nowadays, one of the most important of these biometrics is the face. Many techniques have been suggested for face recognition, but they still face a variety of challenges for recognizing faces in images captured in the uncontrolled environment, and for real-life applications. Some of these challenges are pose variation, occlusion, facial expression, illumination, bad lighting, and image quality. New techniques are updating continuously. In this paper, the singular value decomposition is used to extract the features matrix for face recognition and classification. The input color image is converted into a grayscale image and then transformed into a local ternary pattern before splitting the image into the main sixteen blocks. Each block of these sixteen blocks is divided into more to thirty sub-blocks. For each sub-block, the SVD transformation is applied, and the norm of the diagonal matrix is calculated, which is used to create the 16x30 feature matrix. The sub-blocks of two images, (thirty elements in the main block) are compared with others using the Euclidean distance. The minimum value for each main block is selected to be one feature input to the neural network. Classification is implemented by a backpropagation neural network, where a 16-feature matrix is used as input to the neural network. The performance of the current proposal was up to 97% when using the FEI (Brazilian) database. Moreover, the performance of this study is promised when compared with recent state-of-the-art approaches and it solves some of the challenges such as illumination and facial expression.

ESTIMATION OF THE DEFECT HAZARD CLASS IN BUILDING STRUCTURES: A DECISION SUPPORT SYSTEM

Technical condition monitoring of building structures located on hazardous facilities is a necessary requirement for their sustainable functioning. In this regard, the problem of development intellectual monitoring systems that allow to detect and classify operating defects by the hazardous level becomes very urgent. The study presents an approach of building decision support system (DSS) for detecting defects in building structures and estimation of their hazard class. Proposed approach is based on multi-criteria assessment of consecutive measurements acquired by acoustic emission method. A distinctive characteristic of the proposed approach is the ability to take into account the evolution of defects by mapping each AE time-series to diagnostic features matrix and analysing these matrices in sliding windows with overlay. Each matrix is validated by two criteria that form the necessary and sufficient conditions of the existence the evolving defects in building structure. They include the criterion for changing the number of clusters and the criterion for changing the acoustic emission activity. Proposed method was verified on the experimental data acquired from the technical condition monitoring of the vertical oil tanks. The results obtained fromthe experiment confirm the proposal that this approach can be utilized for effectively solving the problem of conditionalmonitoring of building structures located on the hazardous facilities allowing to detect and classify defects by theirhazardous level.

Enhanced Epileptic Seizure diagnosis using EEG Signals with Support vector machine and Bagging Classifiers

Many approaches have been proposed using Electroencephalogram (EEG) to detect epilepsy seizures in their early stages. Epilepsy seizure is a severe neurological disease. Practitioners continue to rely on manual testing of EEG signals. Artificial intelligence (AI) and Machine Learning (ML) can effectively deal with this problem. ML can be used to classify EEG signals employing feature extraction techniques. This work focuses on automated detection for epilepsy seizures using ML techniques. Various algorithms are investigated, such as Bagging, Decision Tree (DT), Adaboost, Support vector machine (SVM), K-nearest neighbors(KNN), Artificial neural network(ANN), Naïve Bayes, and Random Forest (RF) to distinguish injected signals from normal ones with high accuracy. In this work, 54 Discrete wavelet transforms (DWTs) are used for feature extraction, and the similarity distance is applied to identify the most powerful features. The features are then selected to form the features matrix. The matrix is subsequently used to train ML. The proposed approach is evaluated through different metrics such as F-measure, precision, accuracy, and Recall. The experimental results show that the SVM and Bagging classifiers in some data set combinations, outperforming all other classifiers

MaLeFICE: Machine learning support for continuous performance improvement in computational engineering

SummaryComputer aided engineering (CAE) practices improved drastically within the last decade due to ease of access to computing resources and open‐source software. However, increasing complexity of hardware and software settings and the scarcity of multiskilled personnel rendered the practice inefficient and infeasible again. In this article, we present a method for continuous performance improvement in computational engineering that combines online performance profiling with machine learning (ML). To test the viability of this method, we provide a detailed analysis for solution time estimation of finite element analysis (FEA) jobs based on multidimensional models. These models combine numerous matrix features (matrix size, density, bandwidth, etc.), solver features (direct‐iterative, preconditioning, tolerance), and hardware features (core count, virtual–physical). We repeat our analysis over different machines as well as docker containers to demonstrate applicability over different platforms. Next, we train supervised and unsupervised ML algorithms over commonly used, realistic FEA benchmarks and compare accuracy of different models. Finally, we design two new ML‐based online batch schedulers called shortest predicted time first (SPTF) and shortest cluster time first (SCTF), which are comparable in performance to the optimal, but offline shortest job first (SJF) scheduler. We find that ML‐based profiling and scheduling can reduce the average turnaround times by 2–5 over other alternatives.

Optimization the Accuracy of FFNN Based Speaker Recognition System Using PSO Algorithm

Speaker recognition systems use a model that learns a speaker's speech by inputting an audio recording and processing it. Time-varying signal, with frequencies that continuously change, is identified as a speech signal. There are many uncertain attributes to speech; thus traditional speech recognition techniques such as using zero crossings and the Fourier Transform are not up to the task. It aims to be accomplished with the aim of helping two causes. The first part is designed to address speaker identification technology that is resistant to noise. While most prior solutions have relied on changing mel frequency cepstrum coefficients, with a Fundamental frequency feature coefficient, this proposal integrates both of these modifications with a new cepstrum component. In order to construct the feature matrix, the system is fed with two-hundred and fifty speech imprints that are used to apply features extraction techniques. The matrix is used to teach the algorithm about features, and each one is then evaluated using incomplete data (thirty percent of total data in features matrix). Speaker recognition models with improved accuracy are developed by studying the algorithms invasively. These variables (metrics) are generated for each algorithm and applied to the algorithm for recognition accuracy and the time required to achieve that accuracy. When tested against previous research, the findings show that the Feed Forward Neural Network-based Particle Swarm Optimization method has been better. This model can accurately identify 96% of the input with less processing time. According to the findings, optimization utilizing advanced particle swarm optimization (a.k.a. Particle Swarm Optimization) is most likely responsible for the higher accuracy seen in speaker identification.

Quantificando as diferenças entre as categorias léxicas

The Cambridge grammar of the English language (HUDDLESTON; PULLUM, 2002) attempts to present a comprehensive and rigorous description of Modern Standard English. Much of the book is taken up with describing the properties of the various lexical categories, including determinative and pronoun. The distinction between these categories has been questioned by various authors in English (ABNEY, 1987; CROFT, 2001; HUDSON, 2004; MATTHEWS, 2014; POSTAL, 2014/1966; SOMMERSTEIN, 1972) and other languages (e.g., NAU, 2016). Here, I employ energy distance, a novel family of non-parametric statistics, to adjudicate between these positions. Following Crystal (1967), I binarily encode the features (has/doesn’t have feature) of the determinatives and pronouns from CGEL in a 138 word-forms by 232 features matrix. The results provide support for CGEL’s analysis (k-groups produces a 93% correspondence with CGEL’s categorization) and show that energy distance statistics applied to such matrices can help us adjudicate between competing lexical category analyses without resorting to methodological opportunism (CROFT, 2001).

AF episodes recognition using optimized time-frequency features and cost-sensitive SVM.

Although atrial fibrillation (AF) Arrhythmia is highly prevalent within a wide range of populations with major associated risks and due to its episodic occurrence, its recognition remains a challenge for doctors. This paper aims to present and experimentally validate a new efficient approach for the detection and classification of this cardiac anomaly using multiple Electrocardiogram (ECG) signals. This work consists of applying Stockwell transform (ST) with compact support kernel (ST-CSK) for ECG time-frequency analysis. The estimation of the atrial activity (AA) is then achieved after analyzing P-waves of the ECG signals for each heartbeat. ECG signals segmentation allows characterizing the AA by making use of its (t,f) flatness, (t,f) flux, energy concentration and heart rate variability. The features matrix is employed as an input of the support vector machines (SVM) working in binary and asymmetrical mode with an embedded reject option. The proposed algorithm is trained and then tested using different ECG sources namely two databases provided by PhysionNet (MIT-BIH Arrhythmia, MIT-BIH Atrial Fibrillation) and recorded ECG signals using MySignals HW development platform with raspberry Pi 3 model B[Formula: see text]. The used method has achieved [Formula: see text] and [Formula: see text] as sensitivity and specificity, respectively. The obtained results confirm that the proposed approach represents a promising tool for Atrial Fibrillation Episodes (AFE) recognition with significant separability between Normal atrial activity and atrial activity with AF even under real and clinical conditions.

Development of a standardized histopathology scoring system for intervertebral disc degeneration and regeneration in rabbit models-An initiative of the ORSspine section.

BackgroundThe rabbit lumbar spine is a commonly utilized model for studying intervertebral disc degeneration and for the pre‐clinical evaluation of regenerative therapies. Histopathology is the foundation for which alterations to disc morphology and cellularity with degeneration, or following repair or treatment are assessed. Despite this, no standardized histology grading scale has yet been established for the spine field for any of the frequently utilized animal models.AimsThe purpose of this study was to establish a new standardized scoring system to assess disc degeneration and regeneration in the rabbit model.Materials and MethodsThe scoring system was formulated following a review of the literature and a survey of spine researchers. Validation of the scoring system was carried out using images provided by 4 independent laboratories, which were graded by 12 independent graders of varying experience levels. Reliability testing was performed via the computation of intra‐class correlation coefficients (ICC) for each category and the total score. The scoring system was then further refined based on the results of the ICC analysis and discussions amongst the authors.ResultsThe final general scoring system involves scoring 7 features (nucleus pulposus shape, area, cellularity and matrix condensation, annulus fibrosus/nucleus pulposus border appearance, annulus fibrosus morphology, and endplate sclerosis/thickening) on a 0 (healthy) to 2 (severe degeneration) scale. ICCs demonstrated overall moderate to good agreement across graders. An addendum to the main scoring system is also included for use in studies evaluating regenerative therapeutics, which involves scoring cell cloning and morphology within the nucleus pulposus and inner annulus fibrosus.DiscussionOverall, this new scoring system provides an avenue to improve standardization, allow a more accurate comparison between labs and more robust evaluation of pathophysiology and regenerative treatments across the field.ConclusionThis study developed a histopathology scoring system for degeneration and regeneration in the rabbit model based on reported practice in the literature, a survey of spine researchers, and validation testing.

New bearing slight degradation detection approach based on the periodicity intensity factor and signal processing methods

In this article, a new approach has been presented in which novel hybrid features are introduced to detect the time of the beginning of the bearing degradation in the run-to-failure test. At first, the ensemble empirical mode decomposition (EEMD) method and the wavelet packet decomposition (WPD) are used in signal decomposition. The conventional frequency and time domain features, the envelope harmonic-to-noise ratio (EHNR) and the recently introduced periodicity intensity factor (PIF) are utilized for constructing the features matrix. Consequently, the most sensitive feature is identified using the compensation distance evaluation technique. The results show that the hybrid features obtained by the PIF, the EEMD and WPD methods can determine the exact moment of degradation. Also, the new hybrid features are superior to the features introduced in other studies in the early fault detection.

Influence of porosity on anisotropic thermal conductivity of SiC fiber reinforced SiC matrix composite: A microscopic modeling study

The effect of porosity on the effective thermal conductivities calculation for continuous SiC fiber reinforced SiC matrix composites (SiCf/SiC) was studied in this work by finite element modeling. A three-dimensional representative volume element (RVE) containing detailed geometric features (fibers, matrix, fiber coatings and pores) was generated to rebuild the microstructure of SiCf/SiC and used to numerically calculate the effective transversal and longitudinal thermal conductivities of SiCf/SiC. Markworth model and parallel model were chosen as theoretical models to calculate the transversal and longitudinal thermal conductivities respectively. The numerical results obtained by RVE models were validated by comparison with the theoretical and experimental results. The results highlight the existing theoretical models cannot well predict the transversal thermal conductivity of SiCf/SiC with the existence of pores. In the analysis of the effect of porosity, real pore structure in SiCf/SiC was investigated to revel the relationship between porosity and the effective thermal conductivities. In the case of longitudinal thermal conductivity, the parallel model plus the linear term of porosity can still be used to predict the longitudinal thermal conductivity. As for the transversal thermal conductivity, a more proper Markworth model for SiCf/SiC transversal thermal conductivity calculation calibrated by incorporating porosity is proposed to efficiently calculate the transversal thermal conductivity at the end of this paper.

Adaptive Myoelectric Pattern Recognition Based on Hybrid Spatial Features of HD-sEMG Signals

Myoelectric pattern recognition is a useful tool for identifying the user’s intended motion. However, the inherent nonstationary properties of Electromyography (EMG) signals usually limited the use of real time commercial prostheses. These variations cause the degradation of myoelectric control performance and make it unstable over time, across subjects and sessions. In this study, this challenge is overcome by combining the use of robust spatial features and the supervised adaptive learning method to improve the myoelectric performance. Three types of spatial features are proposed based on histogram oriented gradient (HOG) algorithm and intensity features namely H, HI, and AIH features. H features correspond to extracting HOG features from the HD-sEMG map. HI feature is obtained by concatenating the H features with scalar intensity feature that calculated from HD-sEMG map. Finally, the hybrid AIH features are produced by combining the H features with the intensity features matrix (AI) that obtained from the segmented maps. Three sub-databases are used for evaluation. The proposal feature sets are compared with time-domain (TD) and a combination of intensity and center of gravity features (ICG) to show the powerful of these features. The offline results report the superiority of the classifier’s performance in term of precision and sensitivity based on AIH features than other feature sets (i.e. H, HI, TD, ICG) with improvement 4.1%, 3.5%, 2.24%, 5.3% and 6%, 5%, 2.2%, 6.9% respectively. The adaptive classifier based on AIH features outperforms adaptive myoelectric control based on other feature sets and the original version. The adaptive classifier utilized testing data that update the original dataset which in turn has a significant effect on improving the myoelectric performance in the presence of the variation of EMG signal properties.

Upscaling of Elastic Properties in Carbonates: A Modeling Approach Based on a Multiscale Geophysical Data Set

AbstractLinking ultrasonic measurements made on samples, with sonic logs and seismic subsurface data, is a key challenge for the understanding of carbonate reservoirs. To deal with this problem, we investigate the elastic properties of dry lacustrine carbonates. At one study site, we perform a seismic refraction survey (100 Hz), as well as “sonic” (54 kHz) and ultrasonic (250 kHz) measurements directly on outcrop and ultrasonic measurements on samples (500 kHz). By comparing the median of each data set, we show that the P wave velocity decreases from laboratory to seismic scale. Nevertheless, the median of the sonic measurements acquired on outcrop surfaces seems to fit with the seismic data, meaning that sonic acquisition may be representative of seismic scale. To explain the variations due to upscaling, we relate the concept of representative elementary volume with the wavelength of each scale of study. Indeed, with upscaling, the wavelength varies from millimetric to pluri‐metric. This change of scale allows us to conclude that the behavior of P wave velocity is due to different geological features (matrix porosity, cracks, and fractures) related to the different wavelengths used. Based on effective medium theory, we quantify the pore aspect ratio at sample scale and the crack/fracture density at outcrop and seismic scales using a multiscale representative elementary volume concept. Results show that the matrix porosity that controls the ultrasonic P wave velocities is progressively lost with upscaling, implying that crack and fracture porosity impacts sonic and seismic P wave velocities, a result of paramount importance for seismic interpretation based on deterministic approaches.

Communicability Characterization of Structural DWI Subcortical Networks in Alzheimer's Disease.

In this paper, we investigate the connectivity alterations of the subcortical brain network due to Alzheimer’s disease (AD). Mostly, the literature investigated AD connectivity abnormalities at the whole brain level or at the cortex level, while very few studies focused on the sub-network composed only by the subcortical regions, especially using diffusion-weighted imaging (DWI) data. In this work, we examine a mixed cohort including 46 healthy controls (HC) and 40 AD patients from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) data set. We reconstruct the brain connectome through the use of state of the art tractography algorithms and we propose a method based on graph communicability to enhance the information content of subcortical brain regions in discriminating AD. We develop a classification framework, achieving 77% of area under the receiver operating characteristic (ROC) curve in the binary discrimination AD vs. HC only using a subcortical features matrix. We find some interesting AD-related connectivity patterns highlighting that subcortical regions tend to increase their communicability through cortical regions to compensate the physical connectivity reduction between them due to AD. This study also suggests that AD connectivity alterations mostly regard the inter-connectivity between subcortical and cortical regions rather than the intra-subcortical connectivity.

Hybrid feature-based analysis of video’s affective content using protagonist detection

Extracting an effective representation to analyze affection in videos is an inherent challenge. To address this problem, we present a novel emotion recognition system that can intelligently analyze and automatically recognize video emotions. We observe that most of the emotions in a video are closely related to the roles, especially those of the protagonist, which motivates us to explore how to utilize the protagonist’s information to help recognize video emotions. By analyzing the traits of the protagonists, we suggest a new solution to detect the protagonists to adapt not only to the whole video but also to a video clip. Moreover, a new keyframe selection strategy based on the protagonist is designed to select a set of representative frames from video clips. Furthermore, the scale invariant feature transform (SIFT) features matrix, built from each keyframe, is fed into a convolutional neural network (CNN) to learn the discriminative representations, which makes the CNN and local features complement each other. Considering that emotions are usually continuous, we introduce temporal information into the CNN by using optical flow images. Additionally, we extract some handcrafted visual and audio features as a supplement. Finally, all the features, including the features learned from the CNN and the handcrafted features, are fused and input into a support vector machine (SVM) and a support vector regression (SVR) for video emotion recognition. The proposed system is validated on a public dataset (LIRIS-ACCEDE) and a new dataset (PMSZU). The experimental results demonstrate the promising performance of the proposed system, which achieves better performance than the compared methods. Our designed system for recognizing video emotions could also facilitate the development of similar video expert systems, for applications such as video recommendations, video classification and video retrieval.

The implementation of k-means partitioning algorithm in HOPACH clustering method

Hierarchical Ordered Partitioning And Collapsing Hybrid (HOPACH) is one of the powerful clustering methods which combine the strengths of partitioning and agglomerative clustering methods. Several partition clustering methods such as PAM, K-Means, SOM, or other partitioning algorithms can be used in the partitioning process. This process is followed by the ordering steps, then continued with the agglomerative process. The number of main clusters is determined by MSS (Mean Split Silhouette) value. MSS is used to measure the heterogeneity of the clustering result. The lower the MSS value, the more homogenous each cluster members. We select the number of clusters from the clustering results with minimum MSS. In this implementation of HOPACH, we incorporate k-Means partitioning algorithm in this HOPACH clustering method, to cluster and analyze 136 DNA sequences of Ebola viruses. The clustering process is started with collecting DNA sequences of Ebola viruses from GenBank, then followed by performing features extraction of these DNA sequences using N-Mers frequency. The extraction results are compiled to be a features matrix and normalized using the min-max normalization with the interval [0, 1] as an input data to generate genetic distance matrix using Euclidian distance. The genetic distance matrix is used in partitioning process by the K-Means algorithm in HOPACH clustering. As the results, we obtained 8 clusters with minimum MSS (Mean Split Silhouette) 0.50266. The clustering process in this article uses the open source program R.

Inter- and intra-tumoural heterogeneity in cancer-associated fibroblasts of human pancreatic ductal adenocarcinoma.

Cancer‐associated fibroblasts (CAF) are orchestrators of the pancreatic ductal adenocarcinoma (PDAC) microenvironment. Stromal heterogeneity may explain differential pathophysiological roles of the stroma (pro‐ versus anti‐tumoural) in PDAC. We hypothesised that multiple CAF functional subtypes exist in PDAC, that contribute to stromal heterogeneity through interactions with cancer cells. Using molecular and functional analysis of patient‐derived CAF primary cultures, we demonstrated that human PDAC‐derived CAFs display a high level of inter‐ and intra‐tumour heterogeneity. We identified at least four subtypes of CAFs based on transcriptomic analysis, and propose a classification for human PDAC‐derived CAFs (pCAFassigner). Multiple CAF subtypes co‐existed in individual patient samples. The presence of these CAF subtypes in bulk tumours was confirmed using publicly available gene expression profiles, and immunostainings of CAF subtype markers. Each subtype displayed specific phenotypic features (matrix‐ and immune‐related signatures, vimentin and α‐smooth muscle actin expression, proliferation rate), and was associated with an assessable prognostic impact. A prolonged exposure of non‐tumoural pancreatic stellate cells to conditioned media from cancer cell lines (cancer education experiment) induced a CAF‐like phenotype, including loss of capacity to revert to quiescence and an increase in the expression of genes related to CAF subtypes B and C. This classification demonstrates molecular and functional inter‐ and intra‐tumoural heterogeneity of CAFs in human PDAC. Our subtypes overlap with those identified from single‐cell analyses in other cancers, and pave the way for the development of therapies targeting specific CAF subpopulations in PDAC. © 2018 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of Pathological Society of Great Britain and Ireland.

Abstract WMP26: Using Machine Learning Pattern Recognition in Aneurysmal Subarachnoid Hemorrhage Patients to Determine Patterns in Central versus Infectious Fever

Introduction: Patients with acute neurologic injury such as aneurysmal subarachnoid hemorrhage (aSAH) are at risk of central fever and infections. Fever has been found to independently increase morbidity and mortality. These patients are at risk of exposure to antibiotic overuse, resistant infections, and extensive fever work-ups as central fever remains a diagnosis of exclusion. Methods: We included 28 patients who underwent treatment for aSAH at the University of California, San Francisco’s Neurointensive Care Units from 2012-2016. We retrospectively reviewed their fever curves, with every 2 seconds temperature data, and used strict CDC infection criteria to delineate between central and infectious fever. For every patient, we extracted one or multiple 12-hours-fever-windows (FW) for a total of 289 FW. We then extracted 40 features in either time or frequency domain such as signal skewness, kurtosis, and variance for each FW, and trained a Random Forest model to classify between central and infectious fever. Our model was trained and cross-validated using 19 patients and tested using the remaining 9 patients. Results: Our initial machine learning model shows a cross-validated ROC AUC score of 0.825 ± 0.150, and a testing ROC AUC score of 0.75 on 30% test patients. Conclusion: These preliminary results suggest that there are combinations of characteristics or patterns that can differentiate between central and infectious fever through a machine learning model. To our knowledge, this has never been done before. Our next steps include the development of a more robust features matrix and the use of other machine learning models such as the Recurrent Neural Network (RNN). If this machine learning model can effectively identify central versus infectious fevers, we can optimize antibiotic stewardship, tailor the work up and treatment of this critically ill population and open the door for prospective central fever and temperature management research.

Classification enhancement of breast cancer histopathological image using penalized logistic regression

<p>Classification of breast cancer histopathological images plays a significant role in computer-aided diagnosis system. Features matrix was extracted in order to classify those images and they may contain outlier values adversely that affect the classification performance. Smoothing of features matrix has been proved to be an effective way to improve the classification result via eliminating of outlier values. In this paper, an adaptive penalized logistic regression is proposed, with the aim of smoothing features and provides high classification accuracy of histopathological images, by combining the penalized logistic regression with the smoothed features matrix. Experimental results based on a publicly recent breast cancer histopathological image datasets show that the proposed method significantly outperforms penalized logistic regression in terms of classification accuracy and area under the curve. Thus, the proposed method can be useful for histopathological images classification and other classification of diseases types using DNA gene expression data in the real clinical practice.</p>

Cancelable biometric authentication system based on ECG

Biometrics are widely deployed in various security systems; however, they have drawbacks in the form of leakage or stealing, therefore numerous solutions have been proposed to secure biometric template such as cancelable biometric, which is one of the possible solutions for canceling and securing biometric template. However, this problem is still open and to the best of our knowledge, few previous studies have proposed a complete authentic system using the cancelable biometric techniques based on electrocardiogram (ECG). In this paper, we have applied two cancelable biometric techniques for developing a human authentication system based on ECG signals. The first one is an improved Bio-Hashing and the second one is matrix operation technique. The improved Bio-Hash technique solves the problem of accuracy loss, which is the main drawback of basic Bio-Hash technique. The protected feature vector (Bio-Hashed code) is generated from the inner product between the ECG features matrix and tokenize number matrix. While the matrix operation technique is applied on the ECG feature matrix to produce a transformed template which is irreversible to the original features of the ECG. In the authentication stage, Feed-Forward Neural Network (FFNN) is used to verify individuals. After applying the two cancelable techniques on three public available ECG databases, experimental results show that the proposed system performs better regarding authentication and outperforms state-of-the-art techniques considered.