The aim of the study is to analyze viruses using parameters obtained from distributions of nucleotide sequences in the viral RNA. Seeking for the input data homogeneity, we analyze single-stranded RNA viruses only. Two approaches are used to obtain the nucleotide sequences; In the first one, chunks of equal length (four nucleotides) are considered. In the second approach, the whole RNA genome is divided into parts by adenine or the most frequent nucleotide as a "space". Rank--frequency distributions are studied in both cases. Within the first approach, the P\'olya and the negative hypergeometric distribution yield the best fit. For the distributions obtained within the second approach, we have calculated a set of parameters, including entropy, mean sequence length, and its dispersion. The calculated parameters became the basis for the classification of viruses. We observed that proximity of viruses on planes spanned on various pairs of parameters corresponds to related species. In certain cases, such a proximity is observed for unrelated species as well calling thus for the expansion of the set of parameters used in the classification. We also observed that the fourth most frequent nucleotide sequences obtained within the second approach are of different nature in case of human coronaviruses (different nucleotides for MERS, SARS-CoV, and SARS-CoV-2 versus identical nucleotides for four other coronaviruses). We expect that our findings will be useful as a supplementary tool in the classification of diseases caused by RNA viruses with respect to severity and contagiousness.
This paper proposes a new appliance identification scheme by introducing a novel approach for extracting highly discriminative characteristic sets that can considerably distinguish between various appliance footprints. In this context, a precise and powerful characteristic projection technique depending on fuzzy-neighbors-preserving analysis based QR-decomposition (FNPA-QR) is applied on the extracted energy consumption time-domain features. The FNPA-QR aims to diminish the distance among the between class features and increase the gap among features of dissimilar categories. Following, a novel bagging decision tree (BDT) classifier is also designed to further improve the classification accuracy. The proposed technique is then validated on three appliance energy consumption datasets, which are collected at both low and high frequency. The practical results obtained point out the outstanding classification rate of the time-domain based FNPA-QR and BDT.
This paper investigates the problem of classification of unmanned aerial vehicles (UAVs) from radio frequency (RF) fingerprints at the low signal-to-noise ratio (SNR) regime. We use convolutional neural networks (CNNs) trained with both RF time-series images and the spectrograms of 15 different off-the-shelf drone controller RF signals. When using time-series signal images, the CNN extracts features from the signal transient and envelope. As the SNR decreases, this approach fails dramatically because the information in the transient is lost in the noise, and the envelope is distorted heavily. In contrast to time-series representation of the RF signals, with spectrograms, it is possible to focus only on the desired frequency interval, i.e., 2.4 GHz ISM band, and filter out any other signal component outside of this band. These advantages provide a notable performance improvement over the time-series signals-based methods. To further increase the classification accuracy of the spectrogram-based CNN, we denoise the spectrogram images by truncating them to a limited spectral density interval. Creating a single model using spectrogram images of noisy signals and tuning the CNN model parameters, we achieve a classification accuracy varying from 92% to 100% for an SNR range from -10 dB to 30 dB, which significantly outperforms the existing approaches to our best knowledge.
Source camera model identification (CMI) and image manipulation detection are of paramount importance in image forensics. In this paper, we propose an L2-constrained Remnant Convolutional Neural Network (L2-constrained RemNet) for performing these two crucial tasks. The proposed network architecture consists of a dynamic preprocessor block and a classification block. An L2 loss is applied to the output of the preprocessor block, and categorical crossentropy loss is calculated based on the output of the classification block. The whole network is trained in an end-to-end manner by minimizing the total loss, which is a combination of the L2 loss and the categorical crossentropy loss. Aided by the L2 loss, the data-adaptive preprocessor learns to suppress the unnecessary image contents and assists the classification block in extracting robust image forensics features. We train and test the network on the Dresden database and achieve an overall accuracy of 98.15%, where all the test images are from devices and scenes not used during training to replicate practical applications. The network also outperforms other state-of-the-art CNNs even when the images are manipulated. Furthermore, we attain an overall accuracy of 99.68% in image manipulation detection, which implies that it can be used as a general-purpose network for image forensic tasks.
The ability to perceive and recognize objects is fundamental for the interaction with the external environment. Studies that investigate them and their relationship with brain activity changes have been increasing due to the possible application in an intuitive brain-machine interface (BMI). In addition, the distinctive patterns when presenting different visual stimuli that make data differentiable enough to be classified have been studied. However, reported classification accuracy still low or employed techniques for obtaining brain signals are impractical to use in real environments. In this study, we aim to decode electroencephalography (EEG) signals depending on the provided visual stimulus. Subjects were presented with 72 photographs belonging to 6 different semantic categories. We classified 6 categories and 72 exemplars according to visual stimuli using EEG signals. In order to achieve a high classification accuracy, we proposed an attention driven convolutional neural network and compared our results with conventional methods used for classifying EEG signals. We reported an accuracy of 50.37% and 26.75% for 6-class and 72-class, respectively. These results statistically outperformed other conventional methods. This was possible because of the application of the attention network using human visual pathways. Our findings showed that EEG signals are possible to differentiate when subjects are presented with visual stimulus of different semantic categories and at an exemplar-level with a high classification accuracy; this demonstrates its viability to be applied it in a real-world BMI.
Imagined speech is spotlighted as a new trend in the brain-machine interface due to its application as an intuitive communication tool. However, previous studies have shown low classification performance, therefore its use in real-life is not feasible. In addition, no suitable method to analyze it has been found. Recently, deep learning algorithms have been applied to this paradigm. However, due to the small amount of data, the increase in classification performance is limited. To tackle these issues, in this study, we proposed an end-to-end framework using Siamese neural network encoder, which learns the discriminant features by considering the distance between classes. The imagined words (e.g., arriba (up), abajo (down), derecha (right), izquierda (left), adelante (forward), and atr\'as (backward)) were classified using the raw electroencephalography (EEG) signals. We obtained a 6-class classification accuracy of 31.40% for imagined speech, which significantly outperformed other methods. This was possible because the Siamese neural network, which increases the distance between dissimilar samples while decreasing the distance between similar samples, was used. In this regard, our method can learn discriminant features from a small dataset. The proposed framework would help to increase the classification performance of imagined speech for a small amount of data and implement an intuitive communication system.
The application of deep learning to time series forecasting is one of the major challenges in present machine learning. We propose a novel methodology that combines machine learning and image processing methods to define and predict market states with intraday financial data. A wavelet transform is applied to the log-return of stock prices for both image extraction and denoising. A convolutional neural network then extracts patterns from denoised wavelet images to classify daily time series, i.e. a market state is associated with the binary prediction of the daily close price movement based on the wavelet image constructed from the price changes in the first hours of the day. This method overcomes the low signal-to-noise ratio problem in financial time series and gets a competitive prediction accuracy of the market states 'Up' and 'Down' of financial data as tested on the S&P 500.
To improve the utility and scalability of distributed radio frequency (RF) sensor and communication networks, reduce the need for convolutional neural network (CNN) retraining, and efficiently share learned information about signals, we examined a supervised bootstrapping approach for RF modulation classification. We show that CNN-bootstrapped features of new and existing modulation classes can be considered as mixtures of truncated Gaussian distributions, allowing for maximumlikelihood-based classification of new classes without retraining the network. In this work, the authors observed classification performance using maximum likelihood estimation of CNNbootstrapped features to be comparable to that of a CNN trained on all classes, even for those classes on which the bootstrapping CNN was not trained. This performance was achieved while reducing the number of parameters needed for new class definition from over 8 million to only 200. Furthermore, some physical features of interest, not directly labeled during training, e.g. signal-to-noise ratio (SNR), can be learned or estimated from these same CNN-derived features. Finally, we show that SNR estimation accuracy is highest when classification accuracy is lowest and therefore can be used to calibrate a confidence in the classification.
The present paper addresses the task of reliably identifying critical contacts by using COVID-19 tracing apps. A reliable classification is crucial to ensure a high level of protection, and at the same time to prevent many people from being sent to quarantine by the app. Tracing apps are based on the capabilities of current smartphones to enable a broadest possible availability. Existing capabilities of smartphones include the exchange of Bluetooth Low Energy (BLE) signals and of audio signals, as well as the use of gyroscopes and magnetic sensors. The Bluetooth power measurements, which are often used today, may be complemented by audio ranging and attitude estimation in the future. Smartphones are worn in different ways, often in pockets and bags, which makes the propagation of signals and thus the classification rather unpredictable. Relying on the cooperation of users to wear their phones hanging from their neck would change the situation considerably. In this case the performance, achievable with BLE and audio measurements, becomes predictable. Our analysis identifies parameters that result in accurate warnings, at least within the scope of validity of the models. A significant reduction of the spreading of the disease can then be achieved by the apps, without causing many people to unduly go to quarantine. The present paper is the first of three papers which analyze the situation in some detail.
Developments in the distributed ledger technology have led to new types of assets with a broad range of purposes. Although some classification frameworks for common instruments from traditional finance and some for these new, so called cryptographic assets already exist and are used, a holistic approach to integrate both worlds is missing. The present paper fills this research gap by identifying 14 attributes, each of which is assigned different characteristics, that can be used to classify all types of assets in a structured manner. Our proposed taxonomy which is an extension of existing classification frameworks, summarises these findings in a morphological box and is tested for practicability by classifying exemplary assets like cash and bitcoin. The final classification framework can help to ensure that the various stakeholders, such as investors or supervisors, have a consistent view of the different types of assets, and in particular of their characteristics, and also helps to establish standardised terminology.
Brain-Computer Interfaces (BCIs) are systems allowing people to interact with the environment bypassing the natural neuromuscular and hormonal outputs of the peripheral nervous system (PNS). These interfaces record a user's brain activity and translate it into control commands for external devices, thus providing the PNS with additional artificial outputs. In this framework, the BCIs based on the P300 Event-Related Potentials (ERP), which represent the electrical responses recorded from the brain after specific events or stimuli, have proven to be particularly successful and robust. The presence or the absence of a P300 evoked potential within the EEG features is determined through a classification algorithm. Linear classifiers such as SWLDA and SVM are the most used for ERPs' classification. Due to the low signal-to-noise ratio of the EEG signals, multiple stimulation sequences (a.k.a. iterations) are carried out and then averaged before the signals being classified. However, while augmenting the number of iterations improves the Signal-to-Noise Ratio (SNR), it also slows down the process. In the early studies, the number of iterations was fixed (no stopping), but recently, several early stopping strategies have been proposed in the literature to dynamically interrupt the stimulation sequence when a certain criterion is met to enhance the communication rate. In this work, we explore how to improve the classification performances in P300 based BCIs by combining optimization and machine learning. First, we propose a new decision function that aims at improving classification performances in terms of accuracy and Information Transfer Rate both in a no stopping and early stopping environment. Then, we propose a new SVM training problem that aims to facilitate the target-detection process. Our approach proves to be effective on several publicly available datasets.
Locked-in Syndrome patients are often misdiagnosed and face pessimistic prognosis because of similarities with disorders of consciousness, a lack of objective biomarkers and a difficult-to-recognize pathogenesis. Biomarkers show promise in identifying similar conditions, utilizing electroencephalography (EEG) data. This data, particularly in the form of event-related potentials (ERPs), while successful in varying applications, suffers from methodological constraints and interpretation obstacles. The study documented in this body of work explores a machine learning paradigm with regards to N400 ERP data retrieved from a sentence comprehension task to tackle these hindrances and proposes a new auxiliary diagnostic tool for LIS and possibly disorders of consciousness. A support vector machine (SVC) and a random forest classifier (RF) were able to classify conscious individuals from unconscious ones with optimistic performance metrics. Based on these results, the proposed models and continuations thereof present valuable opportunities for the development of an auxiliary diagnostic tool for the classification of LIS patients, aiding diagnosis, improving prognosis, stimulating recovery and reducing mortality rates.
Non-cooperative communications using non-orthogonal multicarrier signals are challenging since self-created inter carrier interference (ICI) exists, which would prevent successful signal classification. Deep learning (DL) can deal with the classification task without domain-knowledge at the cost of training complexity since neural network hyperparameters have to be extensively tuned. Previous work showed that a tremendously trained convolutional neural network (CNN) classifier can efficiently identify feature-diversity dominant signals while it failed when feature-similarity dominates. Therefore, a pre-processing strategy, which can amplify signal feature diversity is of great importance. This work applies single-level wavelet transform to manually extract time-frequency features from non-orthogonal signals. Composite statistical features are investigated and the wavelet enabled two-dimensional time-frequency feature grid is further simplified into a one-dimensional feature vector via proper statistical transform. The dimensionality reduced features are fed to an error-correcting output codes (ECOC) model, consisting of multiple binary support vector machine (SVM) learners, for multiclass signal classification. Low-cost experiments reveal 100% classification accuracy for feature-diversity dominant signals and 90% for feature-similarity dominant signals, which is nearly 28% accuracy improvement when compared with the CNN classification results.
This paper presents an end-to-end ECG signal classification method based on a novel segmentation strategy via 1D Convolutional Neural Networks (CNN) to aid the classification of ECG signals. The ECG segmentation strategy named R-R-R strategy (i.e., retaining ECG data between the R peaks just before and after the current R peak) for segmenting the original ECG data into segments in order to train and test the 1D CNN models. The novel strategy mimics physicians in scanning ECG to a greater extent, and maximizes the inherent information of ECG segments. The performance of the classification models for 5-class and 6-class are verified with ECG signals from 48 records of the MIT-BIH arrhythmia database. As the heartbeat types are divided into 5 classes (i.e., normal beat, left bundle branch block beat, right bundle branch block beat, ventricular ectopic beat, and paced beat) in the MIT-BIH, the best classification accuracy, the area under the curve (AUC), the sensitivity and the F1-score reach 99.24%, 0.9994, 0.99 and 0.99, respectively. As the heartbeat types are divided into 6 classes (i.e., normal beat, left bundle branch block beat, right bundle branch block beat, ventricular ectopic beat, paced beat and other beats) in the MIT-BIH, the beat classification accuracy, the AUC, the sensitivity, and the F1-score reach 97.02%, 0.9966, 0.97, and 0.97, respectively. Meanwhile, according to the recommended practice from the Association for Advancement of Medical Instrumentation (AAMI), the heartbeat types are divided into 5 classes (i.e., normal beat, supraventricular ectopic beats, ventricular ectopic beats, fusion beats, and unclassifiable beats), the beat classification accuracy, the sensitivity, and the F1-score reach 97.45%, 0.97, and 0.97, respectively. The experimental results show that the proposed method achieves better performance than the state-of-the-art methods.
Craniofacial profile is one of the anatomical causes of obstructive sleep apnea(OSA). By medical research, cephalometry provides information on patients' skeletal structures and soft tissues. In this work, a novel approach to cephalometric analysis using quasi-conformal geometry based local deformation information was proposed for OSA classification. Our study was a retrospective analysis based on 60 case-control pairs with accessible lateral cephalometry and polysomnography (PSG) data. By using the quasi-conformal geometry to study the local deformation around 15 landmark points, and combining the results with three linear distances between landmark points, a total of 1218 information features were obtained per subject. A L2 norm based classification model was built. Under experiments, our proposed model achieves 92.5% testing accuracy.
Although there has been significant research in egocentric action recognition, most methods and tasks, including EPIC-KITCHENS, suppose a fixed set of action classes. Fixed-set classification is useful for benchmarking methods, but is often unrealistic in practical settings due to the compositionality of actions, resulting in a functionally infinite-cardinality label set. In this work, we explore generalization with an open set of classes by unifying two popular approaches: few- and zero-shot generalization (the latter which we reframe as cross-modal few-shot generalization). We propose a new set of splits derived from the EPIC-KITCHENS dataset that allow evaluation of open-set classification, and use these splits to show that adding a metric-learning loss to the conventional direct-alignment baseline can improve zero-shot classification by as much as 10%, while not sacrificing few-shot performance.
Accurate online classification of disturbance events in a transmission network is an important part of wide-area monitoring. Although many conventional machine learning techniques are very successful in classifying events, they rely on extracting information from PMU data at control centers and processing them through CPU/GPUs, which are highly inefficient in terms of energy consumption. To solve this challenge without compromising accuracy, this paper presents a novel methodology based on event-driven neuromorphic computing architecture for classification of power system disturbances. A Spiking Neural Network (SNN)-based computing framework is proposed, which exploits sparsity in disturbances and promotes local event driven operation for unsupervised learning and inference from incoming data. Spatio-temporal information of PMU signals is first extracted and encoded into spike trains and classification is achieved with SNN-based supervised and unsupervised learning framework. Moreover, a QR decomposition-based selection technique is proposed to identify signals participating in the low rank subspace of multiple disturbance events. Performance of the proposed method is validated on data collected from a 16-machine, 5-area New England-New York system.
Deep learning has been recently applied to many problems in wireless communications including modulation classification and symbol decoding. Many of the existing end-to-end learning approaches demonstrated robustness to signal distortions like frequency and timing errors, and outperformed classical signal processing techniques with sufficient training. However, deep learning approaches typically require hundreds of thousands of floating points operations for inference, which is orders of magnitude higher than classical signal processing approaches and thus do not scale well for long sequences. Additionally, they typically operate as a black box and without insight on how their final output was obtained, they can't be integrated with existing approaches. In this paper, we propose a novel neural network architecture that combines deep learning with linear signal processing typically done at the receiver to realize joint modulation classification and symbol recovery. The proposed method estimates signal parameters by learning and corrects signal distortions like carrier frequency offset and multipath fading by linear processing. Using this hybrid approach, we leverage the power of deep learning while retaining the efficiency of conventional receiver processing techniques for long sequences. The proposed hybrid approach provides good accuracy in signal distortion estimation leading to promising results in terms of symbol error rate. For modulation classification accuracy, it outperforms many state of the art deep learning networks.
This paper proposes a Decision Tree (DT) based detection and classification of internal faults in a power transformer. The faults are simulated in Power System Computer Aided Design (PSCAD)/ Electromagnetic Transients including DC (EMTDC) by varying the fault resistance, fault inception angle, and percentage of winding under fault. A series of features are extracted from the differential currents in phases a, b, and c belonging to the time, and frequency domains. Out of these, three features are selected to distinguish the internal faults from the magnetizing inrush and another three to classify faults in the primary and secondary of the transformer. DT, Random Forest (RF), and Gradient Boost (GB) classifiers are used to determine the fault types. The results show that DT detects faults with 100\% accuracy and the GB classifier performed the best among the three classifiers while classifying the internal faults.
Recently, visual perception (VP) and visual imagery (VI) paradigms are investigated in several brain-computer interface (BCI) studies. VP and VI are defined as a changing of brain signals when perceiving and memorizing visual information, respectively. These paradigms could be alternatives to the previous visual-based paradigms which have limitations such as fatigue and low information transfer rates (ITR). In this study, we analyzed VP and VI to investigate the possibility to control BCI. First, we conducted a time-frequency analysis with event-related spectral perturbation. In addition, two types of decoding accuracies were obtained with convolutional neural network to verify whether the brain signals can be distinguished from each class in the VP and whether they can be differentiated with VP and VI paradigms. As a result, the 6-class classification performance in VP was 32.56% and the binary classification performance which classifies two paradigms was 90.16%.