Electrical Impedance of Upper Limb Enables Robust Wearable Identity Recognition against Variation in Finger Placement and Environmental Factors

Most biometric authentication technologies commercialized in various fields mainly rely on acquired images of structural information, such as fingerprints, irises, and faces. However, bio-recognition techniques using these existing physical features are always at risk of template forgery threats, such as fake fingerprints. Due to the risk of theft and duplication, studies have recently been attempted using the internal structure and biological characteristics of the human body, including our previous works on the ratiometric biological impedance feature. However, one may still question its accuracy in real-life use due to the artifacts from sensing position variability and electrode–skin interfacing noise. Moreover, since the finger possesses more severe thermoregulatory vasomotion and large variability in the tissue properties than the core of the body, it is necessary to mitigate the harsh changes occurring at the peripheral extremities of the human body. To address these challenges, we propose a biometric authentication method through robust feature extraction from the upper-limb impedance acquired based on a portable wearable device. In this work, we show that the upper limb impedance features obtained from wearable devices are robust against undesirable factors such as finger placement deviations and day-to-day physiological changes, along with ratiometric impedance features. Overall, our upper-limb impedance-based analysis in a dataset of 1627 measurement from 33 subjects lowered the classification error rate from 22.38% to 4.3% (by a factor of 5), and further down to 2.4% (by a factor of 9) when combined with the ratiometric features.

Adaptive Network Detector for Radar Target in Changing Scenes

Data-driven deep learning has been well applied in radar target detection. However, the performance of the detection network is severely degraded when the detection scene changes, since the trained network with the data from one scene is not suitable for another scene with different data distribution. In order to address this problem, an adaptive network detector combined with scene classification is proposed in this paper. Aiming at maximizing the posterior probability of the feature vectors, the scene classification network is arranged to control the output ratio of a group of detection sub-networks. Due to the uncertainty of classification error rate in traditional machine learning, the classifier with a controllable false alarm rate is constructed. In addition, a new network training strategy, which freezes the parameters of the scene classification network and selectively fine-tunes the parameters of detection sub-networks, is proposed for the adaptive network structure. Comprehensive experiments are carried out to demonstrate that the proposed method guarantees a high detection probability when the detection scene changes. Compared with some classical detectors, the adaptive network detector shows better performance.

The Impact of Pressure on the Fingerprint Impression: Presentation Attack Detection Scheme

Fingerprint recognition systems have been widely deployed in authentication and verification applications, ranging from personal smartphones to border control systems. Recently, the biometric society has raised concerns about presentation attacks that aim to manipulate the biometric system’s final decision by presenting artificial fingerprint traits to the sensor. In this paper, we propose a presentation attack detection scheme that exploits the natural fingerprint phenomena, and analyzes the dynamic variation of a fingerprint’s impression when the user applies additional pressure during the presentation. For that purpose, we collected a novel dynamic dataset with an instructed acquisition scenario. Two sensing technologies are used in the data collection, thermal and optical. Additionally, we collected attack presentations using seven presentation attack instrument species considering the same acquisition circumstances. The proposed mechanism is evaluated following the directives of the standard ISO/IEC 30107. The comparison between ordinary and pressure presentations shows higher accuracy and generalizability for the latter. The proposed approach demonstrates efficient capability of detecting presentation attacks with low bona fide presentation classification error rate (BPCER) where BPCER is 0% for an optical sensor and 1.66% for a thermal sensor at 5% attack presentation classification error rate (APCER) for both.

Sports Sequence Images Based on Convolutional Neural Network

Convolution neural network has become a hot research topic in the field of computer vision because of its superior performance in image classification. Based on the above background, the purpose of this paper is to analyze sports sequence images based on convolutional neural network. In view of the low detection rate of single-frame and the complexity of multiframe detection algorithms, this paper proposes a new algorithm combining single-frame detection and multiframe detection, so as to improve the detection rate of small targets and reduce the detection time. Based on the traditional residual network, an improved, multiscale, residual network is proposed in this paper. The network structure enables the convolution layer to “observe” data from different scales and obtain more abundant input features. Moreover, the depth of the network is reduced, the gradient vanishing problem is effectively suppressed, and the training difficulty is reduced. Finally, the ensemble learning method of relative majority voting is used to reduce the classification error rate of the network to 3.99% on CIFAR-10, and the error rate is reduced by 3% compared with the original residual neural network.

Pattern classification of time-series signals using Fisher kernels and support vector machines

The objective of this study is to assess the performance and capability of a kernel-based machine learning method for time-series signal classification. Applying various stages of dimension transformation, training, testing and cross-validation, we attempt to perform a binary classification using the time-series signals from each category. This study has been applied to two domains: Financial and Biomedical. The financial domain study involves identifying the possibility of collapse or survival of a company trading in the stock market. For assessing the fate of each company, we collect its real stock market data, which is basically a financial time-series composed of weekly closing stock prices in a common time-series interval. This study has been applied to various economic sectors such as Pharmaceuticals and Biotechnology, Automobiles, Oil & Gas, Water Supply etc. The data has been collected using Thomson’s Datastream software. In the biomedical study we are dealing with knee signals collected using the Vibration arthrometry technique. This study involves using the severity of cartilage degeneration for assessing the possibility omachinf a subject getting affected by Osteoarthritis or undergoing knee replacement surgery at a later stage. This non-invasive diagnostic method can also prove be an alternative to various invasive procedures used for detecting osteoarthritis. For this analysis we have used the vibroarthro-signals for about 38 abnormal and 51 normal knee joint case studies. In both studies we apply Fisher Kernels incorporated with Gaussian Mixture Model (GMM) for dimension transformation into feature space created as a three-dimensional plot for visualization. The transformed data is then trained and tested using support vector machines for performing binary classification. From our experiments we observe that our method fits really well for both the studies with the classification error rate between 10% to 15%.

Pattern classification of time-series signals using Fisher kernels and support vector machines

The objective of this study is to assess the performance and capability of a kernel-based machine learning method for time-series signal classification. Applying various stages of dimension transformation, training, testing and cross-validation, we attempt to perform a binary classification using the time-series signals from each category. This study has been applied to two domains: Financial and Biomedical. The financial domain study involves identifying the possibility of collapse or survival of a company trading in the stock market. For assessing the fate of each company, we collect its real stock market data, which is basically a financial time-series composed of weekly closing stock prices in a common time-series interval. This study has been applied to various economic sectors such as Pharmaceuticals and Biotechnology, Automobiles, Oil & Gas, Water Supply etc. The data has been collected using Thomson’s Datastream software. In the biomedical study we are dealing with knee signals collected using the Vibration arthrometry technique. This study involves using the severity of cartilage degeneration for assessing the possibility omachinf a subject getting affected by Osteoarthritis or undergoing knee replacement surgery at a later stage. This non-invasive diagnostic method can also prove be an alternative to various invasive procedures used for detecting osteoarthritis. For this analysis we have used the vibroarthro-signals for about 38 abnormal and 51 normal knee joint case studies. In both studies we apply Fisher Kernels incorporated with Gaussian Mixture Model (GMM) for dimension transformation into feature space created as a three-dimensional plot for visualization. The transformed data is then trained and tested using support vector machines for performing binary classification. From our experiments we observe that our method fits really well for both the studies with the classification error rate between 10% to 15%.

Bi-FPNFAS: Bi-Directional Feature Pyramid Network for Pixel-Wise Face Anti-Spoofing by Leveraging Fourier Spectra

The emergence of biometric-based authentication using modern sensors on electronic devices has led to an escalated use of face recognition technologies. While these technologies may seem intriguing, they are accompanied by numerous implicit drawbacks. In this paper, we look into the problem of face anti-spoofing (FAS) on a frame level in an attempt to ameliorate the risks of face-spoofed attacks in biometric authentication processes. We employed a bi-directional feature pyramid network (BiFPN) that is used for convolutional multi-scaled feature extraction on the EfficientDet detection architecture, which is novel to the task of FAS. We further use these convolutional multi-scaled features in order to perform deep pixel-wise supervision. For all of our experiments, we performed evaluations across all major datasets and attained competitive results for the majority of the cases. Additionally, we showed that introducing an auxiliary self-supervision branch tasked with reconstructing the inputs in the frequency domain demonstrates an average classification error rate (ACER) of 2.92% on Protocol IV of the OULU-NPU dataset, which is significantly better than the currently available published works on pixel-wise face anti-spoofing. Moreover, following the procedures of prior works, we performed inter-dataset testing, which further consolidated the generalizability of the proposed models, as they showed optimum results across various sensors without any fine-tuning procedures.

Vividness of Visual Imagery and Personality Impact Motor-Imagery Brain Computer Interfaces

Brain-computer interfaces (BCIs) are communication bridges between a human brain and external world, enabling humans to interact with their environment without muscle intervention. Their functionality, therefore, depends on both the BCI system and the cognitive capacities of the user. Motor-imagery BCIs (MI-BCI) rely on the users’ mental imagination of body movements. However, not all users have the ability to sufficiently modulate their brain activity for control of a MI-BCI; a problem known as BCI illiteracy or inefficiency. The underlying mechanism of this phenomenon and the cause of such difference among users is yet not fully understood. In this study, we investigated the impact of several cognitive and psychological measures on MI-BCI performance. Fifty-five novice BCI-users participated in a left- versus right-hand motor imagery task. In addition to their BCI classification error rate and demographics, psychological measures including personality factors, affinity for technology, and motivation during the experiment, as well as cognitive measures including visuospatial memory and spatial ability and Vividness of Visual Imagery were collected. Factors that were found to have a significant impact on MI-BCI performance were Vividness of Visual Imagery, and the personality factors of orderliness and autonomy. These findings shed light on individual traits that lead to difficulty in BCI operation and hence can help with early prediction of inefficiency among users to optimize training for them.

Prediction of hepatocellular carcinoma risk in patients with chronic liver disease from dynamic modular networks

Background Discovering potential predictive risks in the super precarcinomatous phase of hepatocellular carcinoma (HCC) without any clinical manifestations is impossible under normal paradigm but critical to control this complex disease. Methods In this study, we utilized a proposed sequential allosteric modules (AMs)-based approach and quantitatively calculated the topological structural variations of these AMs. Results We found the total of 13 oncogenic allosteric modules (OAMs) among chronic hepatitis B (CHB), cirrhosis and HCC network used SimiNEF. We obtained the 11 highly correlated gene pairs involving 15 genes (r > 0.8, P < 0.001) from the 12 OAMs (the out-of-bag (OOB) classification error rate < 0.5) partial consistent with those in independent clinical microarray data, then a three-gene set (cyp1a2-cyp2c19-il6) was optimized to distinguish HCC from non-tumor liver tissues using random forests with an average area under the curve (AUC) of 0.973. Furthermore, we found significant inhibitory effect on the tumor growth of Bel-7402, Hep 3B and Huh7 cell lines in zebrafish treated with the compounds affected those three genes. Conclusions These findings indicated that the sequential AMs-based approach could detect HCC risk in the patients with chronic liver disease and might be applied to any time-dependent risk of cancer.

OPTICAL+: a frequency-based deep learning scheme for recognizing brain wave signals

A human–computer interaction (HCI) system can be used to detect different categories of the brain wave signals that can be beneficial for neurorehabilitation, seizure detection and sleep stage classification. Research on developing HCI systems using brain wave signals has progressed a lot over the years. However, real-time implementation, computational complexity and accuracy are still a concern. In this work, we address the problem of selecting the appropriate filtering frequency band while also achieving a good system performance by proposing a frequency-based approach using long short-term memory network (LSTM) for recognizing different brain wave signals. Adaptive filtering using genetic algorithm is incorporated for a hybrid system utilizing common spatial pattern and LSTM network. The proposed method (OPTICAL+) achieved an overall average classification error rate of 30.41% and a kappa coefficient value of 0.398, outperforming the state-of-the-art methods. The proposed OPTICAL+ predictor can be used to develop improved HCI systems that will aid in neurorehabilitation and may also be beneficial for sleep stage classification and seizure detection.