On Person Authentication by Fusing Visual and Thermal Face Biometrics

Mental disorders, especially schizophrenia, still pose a great challenge for diagnosis in early stages. Recently, computer-aided diagnosis techniques based on resting-state functional magnetic resonance imaging (Rs-fMRI) have been developed to tackle this challenge. In this work, we investigate different decision-level and feature-level fusion schemes for discriminating between schizophrenic and normal subjects. Four types of fMRI features are investigated, namely the regional homogeneity, voxel-mirrored homotopic connectivity, fractional amplitude of low-frequency fluctuations and amplitude of low-frequency fluctuations. Data denoising and preprocessing were first applied, followed by the feature extraction module. Four different feature selection algorithms were applied, and the best discriminative features were selected using the algorithm of feature selection via concave minimization (FSV). Support vector machine classifiers were trained and tested on the COBRE dataset formed of 70 schizophrenic subjects and 70 healthy subjects. The decision-level fusion method outperformed the single-feature-type approaches and achieved a 97.85% accuracy, a 98.33% sensitivity, a 96.83% specificity. Moreover, feature-fusion scheme resulted in a 98.57% accuracy, a 99.71% sensitivity, a 97.66% specificity, and an area under the ROC curve of 0.9984. In general, decision-level and feature-level fusion schemes boosted the performance of schizophrenia detectors based on fMRI features.

The reason why China’s table tennis can continue to this day is because it is an important heritage sports event in the country. In order to ensure the high-level performance of the Chinese table tennis team in the game, the identification and detection of its sports characteristics is a very meaningful work. With the development of computer technology, the use of multimedia intelligence technology to conduct research on competitive tactics has become a general consensus in the sports world. This paper explores the recognition and detection technology of the strength of table tennis hitting movements from the perspective of biomechanics, aiming to provide scientific basis and technical support for improving the performance of athletes. Based on the principles of biomechanics and combined with multimedia intelligent algorithms, this study developed a spatiotemporal graph convolutional network (STGCN) and a motion detection method based on Kinect technology to identify and quantify the hitting strength of table tennis players. The experimental results of this paper show that in the recognition of different types of movements based on the STGCN method, the correct recognition rate of 100 groups of movement strength is 84%, and the correct recognition rate of 500 groups of movement strength is 91.6%; in the recognition of different types of movement strength based on Kinect, the correct recognition rate of 100 groups of movement strength is 97%, and the correct recognition rate of 500 groups of movement strength is 99.6%; it can be seen that no matter how many groups of hitting movements are made, the correct recognition rate of strength based on Kinect is higher than that of STGCN.

Scene classification from images is a challenging problem in computer vision due to its significant variability of scale, illumination, and view. Recently, Latent Dirichlet Allocation (LDA) model has grown popular in computer vision field, especially in scene labeling and classification. However, the effectiveness of the LDA model for the scene classification has not yet been addressed thoroughly. Especially, there is little experimental evaluation on the model's performance for different types of features. Fusion of multiple types of features is usually necessary in the scene classification due to the complexity of scene images. In this paper, we investigate the effectiveness of the LDA model in scene classification by using 7 types of features (i.e. uniform grid based interest points, Harris corner based interest points, scale invariant feature transform (SIFT), texture, shape, color, and location) and their various combinations. Furthermore, we compare the performance of the LDA model with Support Vector Machine (SVM) classifier. All experiments are performed on the UIUC Sport Scene database. The experiments demonstrate that the performance of the LDA model 1) is significantly lower than the SVM classifier for the scene classification over different types of features; and 2) decreases by fusing multiple features while improvement shown in SVM classifier.

The aim of this study is to authenticate individuals using an electroencephalogram (EEG) evoked by a stimulus. EEGs are highly confidential and enable continuous authentication during the use of or access to the given information or service. However, perceivable stimulation distracts the users from the activity they are carrying out while using the service. Therefore, ultrasound stimuli were chosen for EEG evocation. In our previous study, an Equal Error Rate (EER) of 0 % was achieved; however, there were some features which had not been evaluated. In this paper, we introduce a new type of feature, namely fractal dimension, as a nonlinear feature, and evaluate its verification performance on its own and in combination with other conventional features. As a result, an EER of 0 % was achieved when using five features and 14 electrodes, which accounted for 70 support vector machine (SVM) models. However, the construction of the 70 SVM models required extensive calculations. Thus, we reduced the number of SVM models to 24 while maintaining an EER = 0 %.

Synthesis of magnetic-responsive imidazole-based poly (ionic liquid)s as a recycle adsorbent for simultaneously removing iodine molecules and iodide ions

Policy tools are the bridge and link between policy formulation and policy implementation. Examining the perception of training quality brought by different types of policy tools to rural teachers is a starting point for understanding, evaluating, and improving the quality of rural teacher training. Using a questionnaire survey method, a quantitative study was conducted on rural teachers in the western and northern regions of Guangdong Province from dimensions such as quality perception status, influencing factors of quality perception, and the correlation between policy tools and quality perception. Data analysis shows that the overall satisfaction of survey respondents with the quality of training in recent years is close to a “relatively satisfactory” state. The respondents’ recognition of different types of policy tools varies. There is a significant positive correlation between the five types of policy tools and the perception of rural teacher training quality, but the strength of the correlation varies across various variables. On this basis, propose suggestions for the application of various policy tools in rural teacher training practices.

Feature-rank-code-based classifiers have been proposed recently in order to reduce the complexity for electronic nose system (ENS). The performance of these classifiers is degraded when the discriminatory information of gases lie in the actual feature values not in the ranks of features. To overcome the problem, a gas identification system based on a simple distance measure in combination with different type of features is proposed. In order to improve the computational cost of the existing ENS, a novel combination of optimum subset of features is proposed. To achieve the aim of low computational cost, a large feature vector is recursively reduced to a small number of features without compromising the classification accuracy of the system. Discrete binary particle swarm optimization, a metaheuristic for global search is used in a recursive setup to select the optimum subset of features for classification. Euclidian distance is used as a similarity measure for identification of different industrial gases. The proposed system is tested for the identification of 13 different industrial gases, namely, C3H8, Cl2, CO, CO2, SO2, NO2, NH3, C2H4O, C3H6O, C2H4, C2H6O, C7H8, and CH4. These gases are contained in three different data sets; two among these data sets are acquired experimentally in a laboratory setup, while one of these data sets is taken from the University of California at Irvine machine learning repository. Results reveal that the computational cost and the memory requirement of an ENS can be significantly reduced by combining different type of features. An average classification accuracy of 98.17% is achieved by the proposed system with an average 69.04% reduction in memory requirement using only three to five features.

A multi-ensemble method based on deep auto-encoders for fault diagnosis of rolling bearings

Purpose Feature selection is crucial for machine learning to recognize lane-change (LC) maneuver as there exist a large number of feature candidates. Blindly using feature could take up large storage and excessive computation time, while insufficient feature selection would cause poor performance. Selecting high contributive features to classify LC and lane-keep behavior is effective for maneuver recognition. This paper aims to propose a feature selection method from a statistical view based on an analysis from naturalistic driving data. Design/methodology/approach In total, 1,375 LC cases are analyzed. To comprehensively select features, the authors extract the feature candidates from both time and frequency domains with various LC scenarios segmented by an occupancy schedule grid. Then the effect size (Cohen’s d) and p-value of every feature are computed to assess their contribution for each scenario. Findings It has been found that the common lateral features, e.g. yaw rate, lateral acceleration and time-to-lane crossing, are not strong features for recognition of LC maneuver as empirical knowledge. Finally, cross-validation tests are conducted to evaluate model performance using metrics of receiver operating characteristic. Experimental results show that the selected features can achieve better recognition performance than using all the features without purification. Originality/value In this paper, the authors investigate the contributions of each feature from the perspective of statistics based on big naturalistic driving data. The aim is to comprehensively figure out different types of features in LC maneuvers and select the most contributive features over various LC scenarios.

The use of the neural networks in the recognition of the austenitic steel types

Recent advancements in deep learning have opened new prospects in many areas of research. Especially interesting field is biomedical image analysis, where plenty of problems wait for efficient solution. The aim of this work is to develop new approaches to recognition of different types of renal cancer on the basis of Computed Tomography (CT) imaging. Two different directions will be investigated. One uses the texture descriptors of the images to define the diagnostic features. They are next combined with support vector machine responsible for final recognition and classification. The second applies deep learning approach using different configurations of Convolutional Neural Networks. The experimental research for both textural and deep learning approaches was conducted on real world dataset of CT scans consisting of eight types of renal cell carcinomas. The proposed structures of predictive system were able to achieve the level of accuracy around 90% for complex and unbalanced datasets.

In a biometric authentication system using protected templates, a pseudonymous identifier is the part of a protected template that can be directly compared. Each compared pair of pseudonymous identifiers results in a decision testing whether both identifiers are derived from the same biometric characteristic. Compared to an unprotected system, most existing biometric template protection methods cause to a certain extent degradation in biometric performance. Fusion is therefore a promising way to enhance the biometric performance in template-protected biometric systems. Compared to feature level fusion and score level fusion, decision level fusion has not only the least fusion complexity, but also the maximum interoperability across different biometric features, template protection and recognition algorithms, templates formats, and comparison score rules. However, performance improvement via decision level fusion is not obvious. It is influenced by both the dependency and the performance gap among the conducted tests for fusion. We investigate in this paper several fusion scenarios (multi-sample, multi-instance, multi-sensor, multi-algorithm, and their combinations) on the binary decision level, and evaluate their biometric performance and fusion efficiency on a multi-sensor fingerprint database with 71,994 samples.

Despite recent advances in deep convolutional neural networks (DCNNs), low-light and nighttime face verification remains challenging. Although state-of-the-art visible-spectrum face verification methods are robust to small changes in illumination, low-light conditions make it difficult to extract discriminative features required for accurate authentication. In contrast, thermal face imagery, which captures body heat emissions, captures discriminative facial features that are invariant to lighting conditions, enabling low-light or nighttime recognition performance. However, due to the increased cost and difficulty of obtaining diverse thermal-spectrum data, directly training face verification systems on small thermal-spectrum datasets results in poor verification performance. This paper presents a synthesis-based algorithm that adapts thermal spectrum face images to the visible spectrum, allowing us to repurpose off-the-shelf visible-spectrum feature extractors without fine-tuning. Our proposed approach achieves state-of-the-art performance on the ARL-VTF dataset. Importantly, we study the impact of face alignment, pixel-level correspondence, identity classification with label smoothing, and synthetic data augmentation for multi-spectral face synthesis and verification. We show that our proposed method is widely applicable, robust, and highly effective on the ARL-VTF dataset. Finally, we present MILAB-VTF(B), a multi-distance, unconstrained thermal-visible dataset. To the best of our knowledge, it is the largest, most diverse dataset of its kind, collected in realistic conditions. We show that our end-to-end thermal-to-visible face verification system serves as a strong baseline for the MILAB-VTF(B) dataset.

In this paper, we investigate identification of human subjects from electrocardiogram (ECG) signals. We segment the ECG records into individual heartbeat based on the localization of R wave peaks. Two types of features, namely analytic and appearance features, are extracted to represent the characteristics of heartbeat signal of different subjects. Feature selection is performed to find out significant attributes. We compared the performance of different classification algorithms. To better utilize the advantages of different types of features, we proposed two schemes for data fusion and classification. Our system achieves promising results with 100% correct human identification rate and 98.90% accuracy for heartbeat identification. The proposed framework reveals the potential of employing appearance based analysis in ECG signal, yet demonstrates the advantage of a hierarchical architecture in pattern recognition problems.

ABSTRACTWaste disposal processes and landfill management are crucial subjects in the field of settlement archaeology. Our study is focused on understanding the processes that are connected to the formation of the infills of settlement features and the recycling of the building materials (daub and wood) and waste management. These research questions are addressed through the analysis of plant macroremains, charcoals, phytoliths, starch, micromorphology, phosphates and magnetic susceptibility. The results show the waste character of feature infills, which reflect the economy of the individual households. The composition of the archaeobotanical assemblages is not influenced by the type of feature, and similarities in the plant spectra often emerge in the features located close to each other. The charcoal and dendrochronological analyses suggest that part of the building's oak timber was recycled and later used as fuelwood. The presence of uncharred remains of vegetative and generative parts in wastes was detected by phytolith and starch analyses and the presence of meat and dung of livestock by animal protein analyses. Anomalies in soil phosphate indicate differing amounts of organic matter in individual features. Magnetic susceptibility measurements showed that each feature infill was formed in a one‐time event. The sedimentological analysis demonstrated that the infills of different types of features were similar, but only the infill of Late and Final Bronze Age cultures' specific trench‐like features was compacted. All proxies combined suggest that prior deposition of waste in sunken features first accumulated elsewhere and became mixed/homogenized.