Search

In cognitive neuroscience research, computational models of event-related potentials (ERP) can provide a means of developing explanatory hypotheses for the observed waveforms. However, researchers trained in cognitive neurosciences may face technical challenges in implementing these models. This paper provides a tutorial on developing recurrent neural network (RNN) models of ERP waveforms in order to facilitate broader use of computational models in ERP research. To exemplify the RNN model usage, the P3 component evoked by target and non-target visual events, measured at channel Pz, is examined. Input representations of experimental events and corresponding ERP labels are used to optimize the RNN in a supervised learning paradigm. Linking one input representation with multiple ERP waveform labels, then optimizing the RNN to minimize mean-squared-error loss, causes the RNN output to approximate the grand-average ERP waveform. Behavior of the RNN can then be evaluated as a model of the computational principles underlying ERP generation. Aside from fitting such a model, the current tutorial will also demonstrate how to classify hidden units of the RNN by their temporal responses and characterize them using principal component analysis. Statistical hypothesis testing can also be applied to these data. This paper focuses on presenting the modelling approach and subsequent analysis of model outputs in a how-to format, using publicly available data and shared code. While relatively less emphasis is placed on specific interpretations of P3 response generation, the results initiate some interesting discussion points. [ABSTRACT FROM AUTHOR]

Ultra-short-term HRV features assess minor autonomous nervous system variations such as variations resulting from cognitive stress peaks during demanding tasks. Several studies compare ultra-short-term and short-term HRV measurements to investigate their reliability. However, existing experiments are conducted in low cognitively demanding environments. In this paper, we propose to evaluate these measurements' reliability under cognitively demanding tasks using a near real-life setting. For this purpose, we selected 31 HRV features, extracted from data collected from 21 programmers performing code comprehension, and compared them across 18 different time frames, ranging from 3 min to 10 s. Statistical significance and correlation tests were performed between the features extracted using the larger window (3 min) and the same features extracted with the other 17 time frames. We paired these analyses with Bland–Altman plots to inspect how the extraction window size affects the HRV features. The main results show 13 features that presented at least 50% correlation when using 60-second windows. The HF and mNN features achieved around 50% correlation using a 30-second window. The 30-second window was the smallest time frame considered to have reliable measurements. Furthermore, the mNN feature proved to be quite robust to the shortening of the time resolution. [ABSTRACT FROM AUTHOR]

Performance measures are crucial in selecting the best machine learning model for a given problem. Estimating classical model performance measures by subsampling methods like bagging or cross-validation has several weaknesses. The most important ones are the inability to test the significance of the difference, and the lack of interpretability. Recently proposed Elo-based Predictive Power (EPP)—a meta-measure of machine learning model performance, is an attempt to address these weaknesses. However, the EPP is based on wrong assumptions, so its estimates may not be correct. This paper introduces the Probability-based Ranking Model Approach (PMRA), which is a modified EPP approach with a correction that makes its estimates more reliable. PMRA is based on the calculation of the probability that one model achieves a better result than another one, using the Mixed Effects Logistic Regression model. The empirical analysis was carried out on a real mortgage credits dataset. The analysis included a comparison of how the PMRA and state-of-the-art k-fold cross-validation ranked the 49 machine learning models, an example application of a novel method in hyperparameters tuning problem, and a comparison of PMRA and EPP indications. PMRA gives the opportunity to compare a newly developed algorithm to state-of-the-art algorithms based on statistical criteria. It is the solution to select the best hyperparameters configuration and to formulate criteria for the continuation of the hyperparameters space search. [ABSTRACT FROM AUTHOR]

A fuzzy set extension known as the hesitant fuzzy set (HFS) has increased in popularity for decision making in recent years, especially when experts have had trouble evaluating several alternatives by employing a single value for assessment when working in a fuzzy environment. However, it has a significant problem in its uses, i.e., considerable data loss. The probabilistic hesitant fuzzy set (PHFS) has been proposed to improve the HFS. It provides probability values to the HFS and has the ability to retain more information than the HFS. Previously, fuzzy regression models such as the fuzzy linear regression model (FLRM) and hesitant fuzzy linear regression model were used for decision making; however, these models do not provide information about the distribution. To address this issue, we proposed a probabilistic hesitant fuzzy linear regression model (PHFLRM) that incorporates distribution information to account for multi-criteria decision-making (MCDM) problems. The PHFLRM observes the input–output (IPOP) variables as probabilistic hesitant fuzzy elements (PHFEs) and uses a linear programming model (LPM) to estimate the parameters. A case study is used to illustrate the proposed methodology. Additionally, an MCDM technique called the technique for order preference by similarity to ideal solution (TOPSIS) is employed to compare the PHFLRM findings with those obtained using TOPSIS. Lastly, Spearman's rank correlation test assesses the statistical significance of two rankings sets. [ABSTRACT FROM AUTHOR]

Tracking multiple targets using a single estimator is a problem that is commonly approached within a trusted framework. There are many weaknesses that an adversary can exploit if it gains control over the sensors. Because the number of targets that the estimator has to track is not known with anticipation, an adversary could cause a loss of information or a degradation in the tracking precision. Other concerns include the introduction of false targets, which would result in a waste of computational and material resources, depending on the application. In this work, we study the problem of detecting compromised or faulty sensors in a multiple-target tracker, starting with the single-sensor case and then considering the multiple-sensor scenario. We propose an algorithm to detect a variety of attacks in the multiple-sensor case, via the application of finite set statistics (FISST), one-class classifiers and hypothesis testing using nonparametric techniques. [ABSTRACT FROM AUTHOR]

As the navigation solution of exclusion-based RAIM follows from a combination of least-squares estimation and a statistically based exclusion-process, the computation of the integrity of the navigation solution has to take the propagated uncertainty of the combined estimation-testing procedure into account. In this contribution, we analyse, theoretically as well as empirically, the effect that this combination has on the first statistical moment, i.e., the mean, of the computed navigation solution. It will be shown, although statistical testing is intended to remove biases from the data, that biases will always remain under the alternative hypothesis, even when the correct alternative hypothesis is properly identified. The a posteriori exclusion of a biased satellite range from the position solution will therefore never remove the bias in the position solution completely. [ABSTRACT FROM AUTHOR]

Physical-layer authentication can address physical layer vulnerabilities and security threats in wireless sensor networks, and has been considered as an effective complementary enhancement to existing upper-layer authentication mechanisms. In this paper, to advance the existing research and improve the authentication performance, we propose a novel physical layer assisted authentication scheme for mobile wireless sensor networks. In our proposed scheme, we explore the reciprocity and spatial uncorrelation of the wireless channel to verify the identities of involved transmitting users and decide whether all data frames are from the same sender. In our proposed scheme, a new method is developed for the legitimate users to compare their received signal strength (RSS) records, which avoids the information from being disclosed to the adversary. Our proposed scheme can detect the spoofing attack even in a high dynamic environment. We evaluate our scheme through experiments under indoor and outdoor environments. Experiment results show that our proposed scheme is more efficient and achieves a higher detection rate as well as keeping a lower false alarm rate. [ABSTRACT FROM AUTHOR]

Nowadays, with the ubiquitous presence of the Internet of Things industry, the application of emerging sensor networks has become a focus of public attention. Unattended sensor nodes can be comprised and cloned to destroy the network topology. This paper proposes a novel distributed protocol and management technique for the detection of mobile replicas to tolerate node failures. In our scheme, sensors' location claims are forwarded to obtain samples only when the corresponding witnesses meet. Meanwhile, sequential tests of statistical hypotheses are applied to further detect the cloned node by witnesses. The combination of randomized detection based on encountering and sequential tests drastically reduces the routing overhead and false positive/negative rate for detection. Theoretical analysis and simulation results show the detection efficiency and reasonable overhead of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, an improved nonlinear Gaussian mixture probability hypothesis density (GM-PHD) filter is proposed to address bearings-only measurements in multi-target tracking. The proposed method, called the Gaussian mixture measurements-probability hypothesis density (GMM-PHD) filter, not only approximates the posterior intensity using a Gaussian mixture, but also models the likelihood function with a Gaussian mixture instead of a single Gaussian distribution. Besides, the target birth model of the GMM-PHD filter is assumed to be partially uniform instead of a Gaussian mixture. Simulation results show that the proposed filter outperforms the GM-PHD filter embedded with the extended Kalman filter (EKF) and the unscented Kalman filter (UKF). [ABSTRACT FROM AUTHOR]

This paper describes a procedure for the determination of antimony (III) by differential pulse anodic stripping voltammetry using a mercury film screen-printed electrode as the working electrode. The procedure has been optimized using experimental design methodology. Under these conditions, in terms of Residual Standard Deviation (RSD), the repeatability (3.81 %) and the reproducibility (5.07 %) of the constructed electrodes were both analyzed. The detection limit for Sb (III) was calculated at a value of 1.27×10-8 M. The linear range obtained was between 0.99 × 10-8 - 8.26 × 10-8 M. An analysis of possible effects due to the presence of foreign ions in the solution was performed and the procedure was successfully applied to the determination of antimony levels in pharmaceutical preparations and sea water samples. [ABSTRACT FROM AUTHOR]

Perceptual decision-making requires transforming sensory information into decisions. An ambiguity of sensory input affects perceptual decisions inducing specific time-frequency patterns on EEG (electroencephalogram) signals. This paper uses a wavelet-based method to analyze how ambiguity affects EEG features during a perceptual decision-making task. We observe that parietal and temporal beta-band wavelet power monotonically increases throughout the perceptual process. Ambiguity induces high frontal beta-band power at 0.3–0.6 s post-stimulus onset. It may reflect the increasing reliance on the top-down mechanisms to facilitate accumulating decision-relevant sensory features. Finally, this study analyzes the perceptual process using mixed within-trial and within-subject design. First, we found significant percept-related changes in each subject and then test their significance at the group level. Thus, observed beta-band biomarkers are pronounced in single EEG trials and may serve as control commands for brain-computer interface (BCI). [ABSTRACT FROM AUTHOR]

The range kernel of bilateral filter degrades image quality unintentionally in real environments because the pixel intensity varies randomly due to the noise that is generated in image sensors. Furthermore, the range kernel increases the complexity due to the comparisons with neighboring pixels and the multiplications with the corresponding weights. In this paper, we propose a noise-aware range kernel, which estimates noise using an intensity difference-based image noise model and dynamically adjusts weights according to the estimated noise, in order to alleviate the quality degradation of bilateral filters by noise. In addition, to significantly reduce the complexity, an approximation scheme is introduced, which converts the proposed noise-aware range kernel into a binary kernel while using the statistical hypothesis test method. Finally, blue a fully parallelized and pipelined very-large-scale integration (VLSI) architecture of a noise-aware bilateral filter (NABF) that is based on the proposed binary range kernel is presented, which was successfully implemented in field-programmable gate array (FPGA). The experimental results show that the proposed NABF is more robust to noise than the conventional bilateral filter under various noise conditions. Furthermore, the proposed VLSI design of the NABF achieves 10.5 and 95.7 times higher throughput and uses 63.6–97.5% less internal memory than state-of-the-art bilateral filter designs. [ABSTRACT FROM AUTHOR]

Currently, expert systems and applied machine learning algorithms are widely used to automate network intrusion detection. In critical infrastructure applications of communication technologies, the interaction among various industrial control systems and the Internet environment intrinsic to the IoT technology makes them susceptible to cyber-attacks. Given the existence of the enormous network traffic in critical Cyber-Physical Systems (CPSs), traditional methods of machine learning implemented in network anomaly detection are inefficient. Therefore, recently developed machine learning techniques, with the emphasis on deep learning, are finding their successful implementations in the detection and classification of anomalies at both the network and host levels. This paper presents an ensemble method that leverages deep models such as the Deep Neural Network (DNN) and Long Short-Term Memory (LSTM) and a meta-classifier (i.e., logistic regression) following the principle of stacked generalization. To enhance the capabilities of the proposed approach, the method utilizes a two-step process for the apprehension of network anomalies. In the first stage, data pre-processing, a Deep Sparse AutoEncoder (DSAE) is employed for the feature engineering problem. In the second phase, a stacking ensemble learning approach is utilized for classification. The efficiency of the method disclosed in this work is tested on heterogeneous datasets, including data gathered in the IoT environment, namely IoT-23, LITNET-2020, and NetML-2020. The results of the evaluation of the proposed approach are discussed. Statistical significance is tested and compared to the state-of-the-art approaches in network anomaly detection. [ABSTRACT FROM AUTHOR]

In this study, we performed uni- and multivariate data analysis on the extended binding curves of several affinity pairs: immobilized acetylcholinesterase (AChE)/bioconjugates of aflatoxin B1(AFB1) and immobilized anti-AFB1 monoclonal antibody/AFB1-protein carriers. The binding curves were recorded on three mass sensitive cells operating in batch configurations: one commercial surface plasmon resonance (SPR) sensor and two custom-made Love wave surface-acoustic wave (LW-SAW) sensors. We obtained 3D plots depicting the time-evolution of the sensor response as a function of analyte concentration using real-time SPR binding sensograms. These "calibration" surfaces exploited the transient periods of the extended kinetic curves, prior to equilibrium, creating a "fingerprint" for each analyte, in considerably shortened time frames compared to the conventional 2D calibration plots. The custom-made SAW sensors operating in different experimental conditions allowed the detection of AFB1-protein carrier in the nanomolar range. Subsequent statistical significance tests were performed on unpaired data sets to validate the custom-made LW-SAW sensors. [ABSTRACT FROM AUTHOR]

Environmental sensors are exploited in smart homes for many purposes. Sensor data inherently carries behavioral information, possibly useful to infer wellness and health-related insights in an indirect fashion. In order to exploit such features, however, powerful analytics are needed to convert raw sensor output into meaningful and accessible knowledge. In this paper, a complete monitoring architecture is presented, including home sensors and cloud-based back-end services. Unsupervised techniques for behavioral data analysis are presented, including: (i) regression and outlier detection models (also used as feature extractors for more complex models); (ii) statistical hypothesis testing frameworks for detecting changes in sensor-detected activities; and (iii) a clustering process, leveraging deep learning techniques, for extracting complex, multivariate patterns from daily sensor data. Such methods are discussed and evaluated on real-life data, collected within several EU-funded projects. Overall, the presented methods may prove very useful to build effective monitoring services, suitable for practical exploitation in caregiving activities, complementing conventional telemedicine techniques. [ABSTRACT FROM AUTHOR]

The cubature Kalman filter (CKF) is widely used in the application of GPS/INS integrated navigation systems. However, its performance may decline in accuracy and even diverge in the presence of process uncertainties. To solve the problem, a new algorithm named improved strong tracking seventh-degree spherical simplex-radial cubature Kalman filter (IST-7thSSRCKF) is proposed in this paper. In the proposed algorithm, the effect of process uncertainty is mitigated by using the improved strong tracking Kalman filter technique, in which the hypothesis testing method is adopted to identify the process uncertainty and the prior state estimate covariance in the CKF is further modified online according to the change in vehicle dynamics. In addition, a new seventh-degree spherical simplex-radial rule is employed to further improve the estimation accuracy of the strong tracking cubature Kalman filter. In this way, the proposed comprehensive algorithm integrates the advantage of 7thSSRCKF’s high accuracy and strong tracking filter’s strong robustness against process uncertainties. The GPS/INS integrated navigation problem with significant dynamic model errors is utilized to validate the performance of proposed IST-7thSSRCKF. Results demonstrate that the improved strong tracking cubature Kalman filter can achieve higher accuracy than the existing CKF and ST-CKF, and is more robust for the GPS/INS integrated navigation system. [ABSTRACT FROM AUTHOR]