Human identification by walk recognition using relevance vector machine

Biometric identification provides a reliable performance on recognition of identity for different security and authentication management problems. With the development of technology, the privacy and security is the main concern as technology can be falsified. In recent decades biometric traits are the trusted choice to the researchers and there are strong documentations on biometric traits like human electrocardiogram which is the time changing electrical impulse signal passing through heart is able to use for identity subject identification. In this work, an analytic and serviceable analysis of the ECG for human identification is presented. A new approach based on chaotic encryption (CE) of continuous wavelet transformed (CWT) ECG signal has been proposed. The CWT used here to obtain similarity pattern of each individual and CE of the CWT decomposed signal used for subject identification. The proposed approach has been tested using 11 different subjects ECG signal available at MIT-BIH arrhythmia database. The obtained results show that the identification rate is 96.82%. The findings of this study can be helpful to develop effective biometric human identification system.

The study introduces a novel approach to short-term wind speed forecasting, which amalgamates statistical and machine learning techniques through the utilization of a hybrid model consisting of the broad learning system (BLS) and the relevance vector machine (RVM), to account for the nonstationary characteristics of wind speed data. Firstly, the initial wind speed time series is preprocessed using singular spectrum analysis to achieve noise reduction. Subsequently, the denoised wind speed time series is predicted using generalized learning system (BLS), and the prediction error is obtained. Finally, the prediction error of BLS is further predicted using RVM, and the final prediction result is obtained by combining it with the prediction results of BLS. By integrating multiple algorithms, this novel wind speed forecasting hybrid model improves prediction accuracy and can adapt to different wind speed characteristics and complex wind speed fluctuations. Through a case study, we find that this model outperforms other comparative models in terms of prediction, fully demonstrating its superiority.

With the advances in information science, vast amounts of financial time series data can been collected and analyzed. In modern time series analysis, sequential pattern mining (SPM) and association discovery (AD) are the most important techniques to predict the future trends. This study aims at developing advanced SPM and AD for financial data by cutting edge techniques from artificial intelligence and machine learning. The nonlinearity and non-stationarity of financial time series dynamics pose a major challenge for SPM and AD. This study employs time–frequency analysis to extract features for SPM. Then, a sparse multi-manifold clustering (SMMC) is used to partition the feature space into several disjointed regions for better AD. Finally, local relevance vector machines (RVMs) are employed for AD and perform the forecasting. Different from traditional methods, the novel forecasting system operates on multiple resolutions and multiple dynamic regimes. SMMC finds both the neighbors and the weights automatically by a sparse solution, which approximately spans a low-dimensional affine subspace at that point. RVM, the Bayesian kernel machines, can produce parsimonious models with excellent generalization properties. Taking multiple time series data from financial markets as an example, the empirical results demonstrate that the proposed model outperforms traditional models and significantly reduces the forecasting errors. The framework is effective and suitable for other time series forecasting.

Microcalcification (MC) clusters in mammograms can be important early signs of breast cancer in women. Accurate detection of MC clusters is an important but challenging problem. In this paper, we propose the use of a recently developed machine learning technique -- relevance vector machine (RVM) -- for automatic detection of MCs in digitized mammograms. RVM is based on Bayesian estimation theory, and as a feature it can yield a decision function that depends on only a very small number of so-called <i>relevance vectors</i>. We formulate MC detection as a supervised-learning problem, and use RVM to classify if an MC object is present or not at each location in a mammogram image. MC clusters are then identified by grouping the detected MC objects. The proposed method is tested using a database of 141 clinical mammograms, and compared with a support vector machine (SVM) classifier which we developed previously. The detection performance is evaluated using the free-response receiver operating characteristic (FROC) curves. It is demonstrated that the RVM classifier matches closely with the SVM classifier in detection performance, and does so with a much sparser kernel representation than the SVM classifier. Consequently, the RVM classifier greatly reduces the computational complexity, making it more suitable for real-time processing of MC clusters in mammograms.

The Internet of Things (IoT) incorporates software-based physical devices with sensors which require interconnectivity to communicate through the internet and be able to exchange data. IoT traffic can be thought of as the aggregate of packets created by various devices in various contexts, such as smart homes or smart cities. These settings contain several sensors, each of which is dedicated to a certain duty, such as monitoring schemes or gathering cyber-physical information. Thus, unlike internet traffic, which has some human-centric features, IoT traffic and sensor devices consistently perform different tasks and make uncertain quantities of data on a regular basis. The proposed method is based on calculating the entropy values of various uncertain traffic aspects. We describe a novel scheme for identifying IoT devices based on uncertain traffic entropy in this paper. The testbed consists of five popular Smart Home IoT devices with a Raspberry Pi acting as a gateway. Machine learning (ML) algorithms such as support vector machine (SVM), [Formula: see text]-nearest neighbor (KNN) and relevance vector machines (RVM) classifier are used to classify the devices which produce IoT traffic based on uncertain entropy significance. The learning rate of the classifier model is improved by using the flower pollination optimization (FPO) technique to increase the classifier performance. The suggested approach minimizes the amount of time spent on optimization operations while maintaining the predictive performance of the induced uncertain models. We work out the entropy standards of traffic characteristics and categorize the uncertain traffic using ML techniques. Our technique successfully identifies devices in a variety of uncertain network situations, with consistent performance in all scenarios. Our technique is also resistant to unpredictability in network behavior, with abnormalities or uncertainties propagating throughout the network.

This article proposes and verifies a novel intelligence approach for modelling forest fire danger, namely ICA-RVM, developed based on Relevance Vector Machine (RVM) and Imperialist Competitive Algorithm (ICA), state-of-the art machine learning techniques that have not been investigated for forest fire danger modeling. RVM is used to establish a prediction model that computes probability of fire danger, whereas ICA is adopted to optimize the prediction model. The tropical forest at Gia Lai province, Central Highland (Vietnam), was used as a case study. Area under the curve (AUC) and statistical measures were used to assess the model performance. The result showed that the proposed model achieves high performances; AUC is 0.842 and 0.793 on the training dataset and the validation dataset, respectively. Compared to two benchmarks, Random Forests and Support Vector Machine, the proposed model performs better. Therefore, the propose ICA-RVM is a valid alternative system for forest fire danger modeling.

Analysis of recent studies and publications. The analysis of the modern market of software and algorithmic solutions for performing the Liveness detection process showed that the currently existing approaches are completely commercial solutions with closed algorithms of their work. In addition, the Liveness detection algorithm is not yet standardized, and has many implementation options that can sometimes lead to am-biguous results [7]. That is why, it was decided to develop our own algorithm and liveness detection system based on obtaining face characteristics using the AWS API [8], because this service offers a high accuracy of face recognition, which is 99.99%, and provides 10,000 free requests to use every month, which enough to fulfill the purpose of our work. Purpose of the study. Development of the algorithm for the Liveness Detection process using AWS and the construction of a video identification system based on it. Main research material. This paper investigates the video identification of a per-son using the Liveness Detection process. The basis of the question, complexity of the Liveness Detection process and the implementation of biometric human video identifica-tion have been studied. An algorithm for conducting the Liveness Detection process based on the execution of random tasks by an identified person has been developed. Integration with the Amazon DetectFaces API was carried out in order to obtain the character of a digital image of the head, as a result of which it becomes possible to analyze a photo of a person for a wide range of key facial features. A manual test of the Amazon DetectFaces API was conducted, in the process of which, empirically, thresh-olds of facial characteristics in the image for the Liveness Detection process were set. Integration with the Amazon CompareFaces API was implemented to execute the bio-metric video identification. The testing of the developed Liveness Detection application system based on the created Liveness passing algorithm and selected AWS API thresholds consisted of 100 tests of different orientations, from direct user-flow testing to tests with a medical mask, glasses and beard, a photo of a face and a video image of a person for the purpose of forgery his personality. Thanks to the initial accuracy of Amazon API facial recognition of 99.99% and the random selection of tasks in the developed Liveness Detection algo-rithm, all tests gave the expected result - the person was either successfully video-identified at the enterprise, or his identity was faked during the Liveness Detection pro-cess. Conclusions. Based on the research, the software system of biometric human video identification has been developed, which allows to automatically establish the presence of a person in front of a video camera and identify it, preventing the use of fake artifacts to falsify a person's identity.

Multivariate analysis of fMRI time series: classification and regression of brain responses using machine learning

To effectively improve the ability of effectiveness evaluation of fighter air combat, a Relevance Vector Machine (RVM) effectiveness evaluation method is proposed. In the method, firstly, on the basis of the system analysis, the index system of effectiveness evaluation of fighter air combat is introduced, then the advantages of RVM in nonlinear system modeling are applied to establish the effectiveness evaluation model of fighter air combat and complete the effectiveness evaluation. The actual example shows that, the root mean square error obtained by proposed method can achieve 0.0104 for effectiveness evaluation of fighter air combat. It has a scientific and reasonable process and an accurate evaluation result. This verifies its feasible and effective in effectiveness evaluation of fighter air combat.

Biometric recognition systems or human identification are very important in security access for identification and verification systems. The biometric recognition system can be used as an identification system based on the characteristics possessed by the body part of each individual. The soles of the feet can be used for identification because the soles of the feet have certain and unique characteristics which include major lines, protrusions, small dots, single points, and textures. The introduction of biometrics in babies is still conventional, which is a standard operating procedure such as attaching bracelets on baby's feet and imprinting or inking on the soles of baby's feet which are affixed to paper and are very vulnerable to the risk of damage or loss of data, there is a need for a system that can store data automatically digital and able to do the baby identification process. The Principal Component Analysis method is used for the extraction process of the characteristics of the baby's feet. The classification uses the K-Nearest Neighbor (K-NN) method with the euclidean distance approach. Tests were carried using 120 images of baby feet, there are 20 classes, each class contains 3 images of the right foot and 3 images of the foot of the left foot, and a dataset of 280 training images. The highest accuracy result obtained in system testing is 91% with a computation time of 5.63 seconds using the Principal Component Analysis method with the K-Nearest Neighbor (K-NN) classification.Keywords: Footprint, Feature Extraction, Principal Component Analysis, K-Nearest Neighbor.

To ensure high reliability of the Grid-Connected Photovoltaic (GCPV) systems, promptly faults detection, diagnosis and automatic process monitoring are essential tools to keep the PV and the grid network under optimal functioning. Regardless of fault types, incipient faults are usually more difficult to detect and accurately isolate. As an alternative and effective method, the principal components analysis (PCA) is proposed to extract and select more relevant features and support vector machines (SVM) technique is applied to quickly detect the faults that occur in a GCPV system. The T2 and squared weighted errors (SWE) statistics, generally used as fault detection indices, are appropriately extracted and selected within the PCA framework. Both of these features are fed to a SVM classifier handling the incipient fault detection. This task is carried out on a simulated GCPV operating under maximum power point trackers (MPPT) and matching realistic outdoor to demonstrate the effectiveness and robustness of the proposed technique.

Human Identification Using Pyroelectric Infrared Sensors by Aron E. Suppes Dr. Evangelos Yfantis, Examination Committee Chair Professor of Computer Science University of Nevada, Las Vegas The objective of this thesis is to discuss the viability of using pyroelectric infrared (PIR) sensors as a biometric system for human identification. The human body emits infrared radiation, the distribution of which varies throughout the body, and depends upon the shape and composition of the particular body part. A PIR sensor utilizing a Fresnel lens will respond to this infrared radiation. When a human walks, the motion of the body's individual components form a characteristic gait that is likely to affect a PIR sensor field in a unique way. A statistical model, such as a Hidden Markov Model, could be used for the identification process. The model would consist of two phases; learning and testing. The learning phase would train the model on a particular feature or signature. The testing phase would take a signature as input and determine which of the trained models it matches with the highest probability.

Agriculture has been one of the most under-investigated areas in technology, and the development of Precision Agriculture (PA) is still in its early stages. This paper proposes a data-driven methodology on building PA solutions for collection and data modeling systems. Soil moisture, a key factor in the crop growth cycle, is selected as an example to demonstrate the effectiveness of our data-driven approach. On the collection side, a reactive wireless sensor node is developed that aims to capture the dynamics of soil moisture using MicaZ mote and VH400 soil moisture sensor. The prototyped device is tested on field soil to demonstrate its functionality and the responsiveness of the sensors. On the data analysis side, a unique, site-specific soil moisture prediction framework is built on top of models generated by the machine learning techniques SVM (support vector machine) and RVM (relevance vector machine). The framework predicts soil moisture n days ahead based on the same soil and environmental attributes that can be collected by our sensor node. Due to the large data size required by the machine learning algorithms, our framework is evaluated under the Illinois historical data, not field collected sensor data. It achieves low error rates (15%) and high correlations (95%) between predicted values and actual values across 9 different sites when forecasting soil moisture about 2 weeks ahead. Also, it is shown that the prediction outputs can remain accurate over a long period of time (one year) when reliable data are fed to the model every 45 days.

Intrusion detection is one of the important security problems in todays cyber world. A significant number of techniques have been developed which are based on machine learning approaches. However, they are not very successful in identifying all types of intrusions. In this paper, a detailed investigation and analysis of various machine learning techniques have been carried out for finding the cause of problems associated with various machine learning techniques in detecting intrusive activities. Attack classification and mapping of the attack features is provided corresponding to each attack. Issues which are related to detecting low-frequency attacks using network attack dataset are also discussed and viable methods are suggested for improvement. Machine learning techniques have been analyzed and compared in terms of their detection capability for detecting the various category of attacks. Limitations associated with each category of them are also discussed. Various data mining tools for machine learning have also been included in the paper. At the end, future directions are provided for attack detection using machine learning techniques.

The demand for safety-boosting systems is increasing, especially nowadays, to limit the rapid spread of COVID-19. Real-time life-logging is an essential application towards tracking infected cases and thus containing the pandemic outbreak. This application raises the need for an accurate human identification technology where cameras cannot be adopted due to privacy. Recently, LiDAR sensor has attracted attention due to its ability to represent the surrounding environment in the form of 3D point cloud. In this paper, we introduce a novel wearable device of a micro-size LiDAR to build an onboard human identification system for life-logging. The system acquires 3D point cloud data of the surrounding environment from which subject-discriminative signatures are extracted. This is achieved by removing noise and background using Spatio-temporal density clustering and fisher vector representations. The extracted features are then used to train a random forest classifier for subject identification. We have implemented and evaluated the proposed system on six different subjects. The results show that the proposed system can effectively remove noise and background and accurately identify subjects with 99.9% accuracy.