Set Of Novel Features Research Articles

Ventricular Arrhythmia Classification Using Similarity Maps and Hierarchical Multi-Stream Deep Learning.

Ventricular arrhythmias are the primary arrhythmias that cause sudden cardiac death. We address the problem of classification between ventricular tachycardia (VT), ventricular fibrillation (VF) and non-ventricular rhythms (NVR). To address the challenging problem of the discrimination between VT and VF, we develop similarity maps - a novel set of features designed to capture regularity within an ECG trace. These similarity maps are combined with features extracted through learnable Parzen band-pass filters and derivative features to discriminate between VT, VF, and NVR. To combine the benefits of these different features, we propose a hierarchical multi-stream ResNet34 architecture. Our empirical results demonstrate that the similarity maps significantly improve the accuracy of distinguishing between VT and VF. Overall, the proposed approach achieves an average class sensitivity of 89.68%, and individual class sensitivities of 81.46% for VT, 89.29% for VF, and 98.28% for NVR. The proposed method achieves a high accuracy of ventricular arrhythmia detection and classification. Correct detection and classification of ventricular fibrillation and ventricular tachycardia are essential for effective intervention and for the development of new therapies and translational medicine.

Advanced computational predictive models of miRNA-mRNA interaction efficiency

The modeling of miRNA-mRNA interactions holds significant implications for synthetic biology and human health. However, this research area presents specific challenges due to the multifaceted nature of mRNA downregulation by miRNAs, influenced by numerous factors including competition or synergism among miRNAs and mRNAs. In this study, we present an improved computational model for predicting miRNA-mRNA interactions, addressing aspects not previously modeled. Firstly, we integrated a novel set of features that significantly enhanced the predictor's performance. Secondly, we demonstrated the cell-specific nature of certain aspects of miRNA-mRNA interactions, highlighting the importance of designing models tailored to specific cell types for improved accuracy. Moreover, we introduce a miRNA binding site interaction model (miBSIM) that, for the first time, accounts for both the distribution of miRNA binding sites along the mRNA and their respective strengths in regulating mRNA stability. Our analysis suggests that distant miRNA sites often compete with each other, revealing the intricate interplay of binding site interactions. Overall, our new predictive model shows a significant improvement of up to 6.43% over previous models in the field.The code of our model is available at https://www.cs.tau.ac.il/~tamirtul/miBSIM

Adaptive Normalization and Feature Extraction for Electrodermal Activity Analysis

Electrodermal Activity (EDA) has shown great potential for emotion recognition and the early detection of physiological anomalies associated with stress. However, its non-stationary nature limits the capability of current analytical and detection techniques, which are highly dependent on signal stability and controlled environmental conditions. This paper proposes a framework for EDA normalization based on the exponential moving average (EMA) with outlier removal applicable to non-stationary heteroscedastic signals and a novel set of features for analysis. The normalized time series preserves the morphological and statistical properties after transformation. Meanwhile, the proposed features expand on typical time-domain EDA features and profit from the resulting normalized signal properties. Parameter selection and validation were performed using two different EDA databases on stress assessment, accomplishing trend preservation using windows between 5 and 20 s. The proposed normalization and feature extraction framework for EDA analysis showed promising results for the identification of noisy, relaxed and arousal-like patterns in data with conventional clustering approaches like K-means over the aforementioned normalized features.

Improved fetal heartbeat detection using pitch shifting and psychoacoustics

ObjectiveFetal phonocardiography is a cost-effective and non-invasive method for monitoring of fetal health. However, the captured signal is often too noisy and unstable for reliable analysis. Detection of fetal heartbeats therefore requires a robust set of features to differentiate relevant sounds from background noise. We propose a novel set of features based on pitch shifting and psychoacoustics which lead to significant improvements of automatic fetal heartbeat detection. MethodsWe collected, annotated, cleaned, processed and segmented microphone recordings taken from pregnant women. In addition, we employed a well-known simulated dataset to validate the methodology further. A total of 212 features were extracted, including classical audio features, psychoacoustic features, and features based on Empirical Mode Decomposition. Methods from statistical analysis and machine learning were applied to demonstrate the relevance of specific features. Afterwards, we trained a set of machine learning algorithms with different subsets of features. ResultsPsychoacoustic features extracted from pitch-shifted signals are generally shown to be relevant and useful features for fetal heartbeat detection. When psychoacoustic features were added to the baseline features, classification accuracy of a robust classifier significantly increased from 69.24% to 76.16% for the real-world signals, and from 92.69% to 97.42% for one of the simulated datasets. ConclusionThe results demonstrate considerable gains in detection accuracy once pitch shifting and psychoacoustic modeling are applied to the input signal. SignificanceImprovements achieved from applying psychoacoustics on fetal phonocardiographic signals might be an important finding in the effort of making remote monitoring of fetal wellbeing inexpensive and accessible.

Distracted driving recognition based on functional connectivity analysis between physiological signals and perinasal perspiration index

Automatic detection of distracted driving is essential to ensure safety of drivers. In this paper, a novel set of features were extracted from thermal and physiological signals in order to detect and recognize distraction of drivers. Thermal video data which measured the temperature of different areas of the face, heart rate, breathing rate and behavioural signals were used while various types of distractions including cognitive, emotional and sensory-motor were applied to the subjects. The proposed discriminator features were extracted by different functional connectivity methods between the perinasal perspiration extracted from thermal images of the face and physiological variables of heart rate and breathing rate. After feature extraction, binary classification methods were applied to detect the distractions. The results showed that using functional connectivity features significantly increased the accuracy of distraction detection system (up to 99.16% with a highly acceptable F1 score of 0.99). Hence, the proposed model significantly improved (p-value<0.001) the detection of driver’s distraction compared to previous studies. Functional connectivity between perinasal perspiration and breathing signals was the most informative feature for distraction detection purpose. This feature set explained almost all modulations in physiological changes by distractions. For the first time, we designed a system capable of recognizing types of distractions including sensory-motor, cognitive, emotional distractions and also normal state. We used the same feature set to recognize different types of distractions by using three-class and four-class classifiers. The suggested methods distinguished three types of distractions with the best accuracy of 81.94% related to cognitive, sensory-motor distraction and no-distraction states. We also tried to discriminate two types of cognitive distractions, analytic and mathematical distractions. The recognition system classified two types of cognitive distractions with an accuracy of 91.78%. The results suggest that there is important and complementary information in the connectivity between facial temperature signals and physiological variables for distraction detection and recognition.

Improving Cryptocurrency Crime Detection: CoinJoin Community Detection Approach

The potential of Bitcoin for money laundering and terrorist financing represents a significant challenge in law enforcement. In recent years, the use of privacy-improving CoinJoin transactions has grown significantly and helped criminal actors obfuscate Bitcoin money flows. In this study, we use unsupervised machine learning to analyze the complete Bitcoin user graph in order to identify suspicious actors potentially involved in illegal activities. In contrast to the existing studies, we introduce a novel set of features that we use to identify potential criminal activity more accurately. Furthermore, we apply our clustering algorithm to a CoinJoin-adjusted variant of the Bitcoin user graph, which enables us to analyze the network at a more detailed, user-centric level while still offering opportunities to address advanced privacy-enhancing techniques at a later stage. By comparing the results with our ground truth data set, we find that our improved clustering method is able to capture significantly more illicit activity within the most suspicious clusters. Finally, we find that users associated with illegal activities commonly have significant short paths to CoinJoin wallets and show tendencies toward outlier behavior. Our results have potential contributions to anti-money laundering efforts and combating the financing of terrorism and other illegal activities.

BoundED: Neural boundary and edge detection in 3D point clouds via local neighborhood statistics

Extracting high-level structural information from 3D point clouds is challenging but essential for tasks like urban planning or autonomous driving requiring an advanced understanding of the scene at hand. Existing approaches are still not able to produce high-quality results consistently while being fast enough to be deployed in scenarios requiring interactivity. We propose to utilize a novel set of features describing the local neighborhood on a per-point basis via first and second order statistics as input for a simple and compact classification network to distinguish between non-edge, sharp-edge, and boundary points in the given data. Leveraging this feature embedding enables our algorithm to outperform the state-of-the-art technique PCEDNet in terms of quality and processing time while additionally allowing for the detection of boundaries in the processed point clouds.

Assessing code readability in Python programming courses using eye‐tracking

AbstractCode readability models are typically based on the code's structural and textual features, considering code readability as an objective category. However, readability is inherently subjective and dependent on the knowledge and experience of the reader analyzing the code. This paper assesses the readability of Python code statements commonly used in undergraduate programming courses. Our readability model is based on tracking the reader's eye movement during the while‐read phase. It uses machine learning (ML) techniques and relies on a novel set of features—observational features—that capture how the readers read the code. We experimented by tracking the eye movement of 90 undergraduate students while assessing the readability of 48 Python code snippets. We trained an ML model that predicts readability based on the collected observational data and the code snippet's structural and textual features. In our experiments, the XGBoost classifier trained using observational features exclusively achieved the best results (0.85 F‐measure). Using correlation analysis, we identified Python statements most affecting readability for undergraduate students and proposed implications for teaching Python programming. In line with findings for Java language, we found that constructs related to the code's size and complexity hurt the code's readability. Numerous comments also hindered readability, potentially due to their association with less readable code. Some Python‐specific statements (list comprehension, lambda function, and dictionary comprehension) harmed code readability, even though they were part of the curriculum. Tracking students' gaze indicated some additional factors, most notably nonlinearity introduced by if, for, while, try, and function call statements.

Early selection of carrot somatic hybrids: a promising tool for species with high regenerative ability

BackgroundSince its discovery, somatic hybridization has been used to overcome the sexual barriers between cultivated and wild species. A combination of two somatic cells might provide a novel set of features, often of agronomical importance. Here, we report a successful approach for production and selection of interspecific somatic hybrid plants between cultivated and wild carrot using dual-labelling of protoplasts and an early selection of fused cells via micromanipulator. Both subspecies used in this study are characterised by a very high regenerative ability in protoplast cultures. Thus, a precise and effective method of hybrid selection is essential to assure the development and regeneration of much less numerous heterokaryons in the post-fusion cell mixture.ResultsElectrofusion parameters, such as alternating current and direct current, were optimised for an efficient alignment of protoplasts and reversible membrane breakdown followed by a cell fusion. Four hundred twenty-nine cells emitting green–red fluorescence, identified as hybrids, were obtained. Co-culture with donor-derived protoplasts in the alginate feeder layer system stimulated re-synthesis of the cell wall and promoted cell divisions of fusants. Somatic embryogenesis occurred in hybrid-derived microcalli cultures, followed by plant regeneration. Regenerated hybrids produced yellowish storage roots and leaves of an intermediate shape between cultivated and wild subspecies. The intron length polymorphism analysis revealed that 123 of 124 regenerated plants were hybrids.ConclusionsThe developed protocol for protoplast fusion and an early selection of hybrids may serve as an alternative to combining genomes and transferring nuclear or cytoplasmatic traits from wild Daucus species to cultivated carrot.

Uncertainty-aware Energy Harvest Prediction and Management for IoT Devices

Internet of things (IoT) devices are popular in several high-impact applications such as mobile healthcare and digital agriculture. However, IoT devices have limited operating lifetime due to their small form factor. Harvesting energy from ambient sources is an effective method to supplement the battery. Energy harvesting necessitates development of energy management policies to manage the harvested energy. Designing optimal policies for energy management is challenging for two key reasons: (1) ambient energy sources are highly stochastic; therefore, energy management policies must consider the associated uncertainty; (2) energy management policies must consider future energy availability while making decisions to ensure that sufficient energy is available when there is no ambient energy. Prior approaches typically consider energy in the immediate future (e.g., 1 hour) and do not account for the uncertainty in future energy harvest. This article proposes novel machine learning and dynamic optimization-based approaches to handle the two challenges. Specifically, we first develop a novel set of features and use it in a low-power neural network architecture to predict future energy availability and uncertainty. The energy predictions and uncertainty are used in a dynamic optimization algorithm to optimally allocate the harvested energy. Experiments on solar energy data over 5 years from Golden, Colorado, show that the proposed energy prediction model achieves 3.4 J mean absolute error while having a coverage of 80%. Moreover, our energy management algorithm provides energy allocations that are within 2.5 J of an optimal Oracle with 2.65 mJ to 36.54 mJ of energy overhead.

An automated multi-web platform voting framework to predict misleading information proliferated during COVID-19 outbreak using ensemble method

The spreading of misleading information on social web platforms has fuelled massive panic and confusion among the public regarding the Corona disease, the detection of which is of paramount importance. Previous studies mainly relied on a specific web platform to collect crucial evidence to detect fake content. The analysis identifies that retrieving clues from two or more different sources/web platforms gives more reliable prediction and confidence concerning a specific claim. This study proposed a novel multi-web platform voting framework that incorporates 4 sets of novel features: content, linguistic, similarity, and sentiments. The features have been gathered from each web-platforms to validate the news. To validate the fact/claim, a unique source platform is designed to collect relevant clues/headlines from two web platforms (YouTube, Google) based on specific queries and extracted features concerning each clue/headline. The proposed idea is to incorporate a unique platform to assist researchers in gathering relevant and vital evidence from diverse web platforms. After evaluation and validation, it has been identified that the built model is quite intelligent, gives promising results, and effectively predicts misleading information. The model correctly detected about 98% of the COVID misinformation on the constraint Covid-19 fake news dataset. Furthermore, it is observed that it is efficient to gather clues from multiple web platforms for more reliable predictions to validate the news. The suggested work depicts numerous practical applications for health policy-makers and practitioners that could be useful in safeguarding and implicating awareness among society from misleading information dissemination during this pandemic.

Melding Fog Computing and IoT for Deploying Secure, Response-Capable Healthcare Services in 5G and Beyond

The fifth generation (5G) of mobile networks is designed to mark the beginning of the hyper-connected society through a broad set of novel features and disruptive characteristics, delivering massive connectivity, coverage and availability paired with unprecedented speed, throughput and capacity. Such a highly capable networking paradigm, facilitated by its integrated segments and available subsystems, will propel numerous cutting-edge, innovative and versatile services, spanning every possible business vertical. Augmented, response-capable healthcare services have already been identified as one of the prime objectives of both vendors and customers; therefore, addressing controversies and shortcomings related to the specific field is considered a priority for all stakeholders. The scope of this paper is to present the architectural elements of 5G which enable efficient, remote healthcare services along with emergency health monitoring and response capability. In addition, we propose a holistic scheme based on technical enablers such as Internet-of-Things (IoT) and Fog Computing, for mitigating common issues and current limitations which may compromise the proclaimed service delivery.

Ali-Bey - an open collaborative georeferencing web application.

Georeferencing preserved specimens represents a major effort at the Museu de Ciències Naturals de Barcelona (MCNB), given the available resources and limited staff that can be allocated to the task. Georeferencing is a labour-intensive and hard-to-automate task that requires software tools that can help in making it as efficient as possible. The tool we present, Ali-Bey, has been slowly developed over 15 years and its functionalities have been gradually built in a process of development, testing, use in production and refinement, rather than as a single development cycle out of a comprehensive specifications requirement document. At the start, the MCNB could not find a tool that fully satisfied the requirements listed as essential and made the decision to develop a custom tool. At the end, the initiative has proved successful since it has delivered a new georeferencing tool that meets the MCNB's needs, all in a context of yearly scarce availability of funds. The tool has been gradually matured and developed over the years, in line with the scarce financing. Only recently, after reaching a notable set of novel features, we considered to release it as an open-source project. The MCNB has supported its development up until this date and decided to open it in order to give the NHC community the opportunity to contribute to its development. We present the software tool Ali-Bey that provides new functionality for the georeferencing of specimens in Natural History Collections, namely the possibility of cooperation between different institutions, the traceability of georeferences and the capability of managing different versions of a same site name, namely for historical reasons. The tool is an open-source web application implemented in Python and the Django framework that leverages other commonly-used specialised geodatabase and map server tools. An API provides access to the geodatabase to externally-developed tools. In addition, for an easy installation, the tool is provided as a multi-container Docker application.

Precision Care in Cardiac Arrest: ICECAP (PRECICECAP) Study Protocol and Informatics Approach.

Most trials in critical care have been neutral, in part because between-patient heterogeneity means not all patients respond identically to the same treatment. The Precision Care in Cardiac Arrest: Influence of Cooling duration on Efficacy in Cardiac Arrest Patients (PRECICECAP) study will apply machine learning to high-resolution, multimodality data collected from patients resuscitated from out-of-hospital cardiac arrest. We aim to discover novel biomarker signatures to predict the optimal duration of therapeutic hypothermia and 90-day functional outcomes. In parallel, we are developing a freely available software platform for standardized curation of intensive care unit-acquired data for machine learning applications. The Influence of Cooling duration on Efficacy in Cardiac Arrest Patients (ICECAP) study is a response-adaptive, dose-finding trial testing different durations of therapeutic hypothermia. Twelve ICECAP sites will collect data for PRECICECAP from multiple modalities routinely used after out-of-hospital cardiac arrest, including ICECAP case report forms, detailed medication data, cardiopulmonary and electroencephalographic waveforms, and digital imaging and communications in medicine files (DICOMs). We partnered with Moberg Analytics to develop a freely available software platform to allow high-resolution critical care data to be used efficiently and effectively. We will use an autoencoder neural network to create low-dimensional representations of all raw waveforms and derivative features, censored at rewarming to ensure clinical usability to guide optimal duration of hypothermia. We will also consider simple features that are historically considered to be important. Finally, we will create a supervised deep learning neural network algorithm to directly predict 90-day functional outcome from large sets of novel features. PRECICECAP is currently enrolling and will be completed in late 2025. Cardiac arrest is a heterogeneous disease that causes substantial morbidity and mortality. PRECICECAP will advance the overarching goal of titrating personalized neurocritical care on the basis of robust measures of individual need and treatment responsiveness. The software platform we develop will be broadly applicable to hospital-based research after acute illness or injury.

Detecting Fraud Job Recruitment Using Features Reflecting from Real-world Knowledge of Fraud

A common method for text-analysis and text-based classification is to process for term-frequency or patterns of terms. However, these features alone may not be able to differentiate fake and authentic job advertisements. Thus, in this work, we proposed a method to detect fake job recruitments using a novel set of features designed to reflect the behavior of fraudsters who present fake information. The features were missing information, exaggeration, and credibility. The features were designed to represent in the form of a category and an automatically generatable score of readability. Data from EMSCAD dataset were transformed in accordance with the designed features and used to train a detection model for fake job detection. The experimental results showed that the model from the designed features performed better than those based on the term-frequency approach in every applied machine learning technique. The proposed method yielded 97.64% accuracy, 0.97 precision and 0.99 recall score for its best model when used for classifying fake job advertisements.

Automated Facial Expression Recognition and Age Estimation Using Deep Learning

With the advancement of computer vision techniques in surveillance systems, the need for more proficient, intelligent, and sustainable facial expressions and age recognition is necessary. The main purpose of this study is to develop accurate facial expressions and an age recognition system that is capable of error-free recognition of human expression and age in both indoor and outdoor environments. The proposed system first takes an input image pre-process it and then detects faces in the entire image. After that landmarks localization helps in the formation of synthetic face mask prediction. A novel set of features are extracted and passed to a classifier for the accurate classification of expressions and age group. The proposed system is tested over two benchmark datasets, namely, the Gallagher collection person dataset and the Images of Groups dataset. The system achieved remarkable results over these benchmark datasets about recognition accuracy and computational time. The proposed system would also be applicable in different consumer application domains such as online business negotiations, consumer behavior analysis, E-learning environments, and emotion robotics.

Detecting and Analyzing Collusive Entities on YouTube

YouTube sells advertisements on the posted videos, which in turn enables the content creators to monetize their videos. As an unintended consequence, this has proliferated various illegal activities such as artificial boosting of views, likes, comments, and subscriptions. We refer to such videos (gaining likes and comments artificially) and channels (gaining subscriptions artificially) as “collusive entities.” Detecting such collusive entities is an important yet challenging task. Existing solutions mostly deal with the problem of spotting fake views, spam comments, fake content, and so on, and oftentimes ignore how such fake activities emerge via collusion. Here, we collect a large dataset consisting of two types of collusive entities on YouTube— videos submitted to gain collusive likes and comment requests and channels submitted to gain collusive subscriptions. We begin by providing an in-depth analysis of collusive entities on YouTube fostered by various blackmarket services . Following this, we propose models to detect three types of collusive YouTube entities: videos seeking collusive likes, channels seeking collusive subscriptions, and videos seeking collusive comments. The third type of entity is associated with temporal information. To detect videos and channels for collusive likes and subscriptions, respectively, we utilize one-class classifiers trained on our curated collusive entities and a set of novel features. The SVM-based model shows significant performance with a true positive rate of 0.911 and 0.910 for detecting collusive videos and collusive channels, respectively. To detect videos seeking collusive comments, we propose CollATe , a novel end-to-end neural architecture that leverages time-series information of posted comments along with static metadata of videos. CollATe is composed of three components: metadata feature extractor (which derives metadata-based features from videos), anomaly feature extractor (which utilizes the time-series data to detect sudden changes in the commenting activity), and comment feature extractor (which utilizes the text of the comments posted during collusion and computes a similarity score between the comments). Extensive experiments show the effectiveness of CollATe (with a true positive rate of 0.905) over the baselines.

Nilpotent (anti-)BRST and (anti-)co-BRST symmetries in 2D non-Abelian gauge theory: Some novel observations

We discuss the nilpotent Becchi–Rouet–Stora–Tyutin (BRST), anti-BRST and (anti-) co-BRST symmetry transformations and derive their corresponding conserved charges in the case of a two [Formula: see text]-dimensional (2D) self-interacting non-Abelian gauge theory (without any interaction with matter fields). We point out a set of novel features that emerge out in the BRST and co-BRST analysis of the above 2D gauge theory. The algebraic structures of the symmetry operators (and corresponding conserved charges) and their relationship with the cohomological operators of differential geometry are established too. To be more precise, we demonstrate the existence of a single Lagrangian density that respects the continuous symmetries which obey proper algebraic structure of the cohomological operators of differential geometry. In the literature, such observations have been made for the coupled (but equivalent) Lagrangian densities of the 4D non-Abelian gauge theory. We lay emphasis on the existence and properties of the Curci–Ferrari (CF)-type restrictions in the context of (anti-)BRST and (anti-)co-BRST symmetry transformations and pinpoint their key differences and similarities. All the observations, connected with the (anti-)co-BRST symmetries, are completely novel.

RT-ZooKeeper: Taming the Recovery Latency of a Coordination Service

Fault-tolerant coordination services have been widely used in distributed applications in cloud environments. Recent years have witnessed the emergence of time-sensitive applications deployed in edge computing environments, which introduces both challenges and opportunities for coordination services. On one hand, coordination services must recover from failures in a timely manner. On the other hand, edge computing employs local networked platforms that can be exploited to achieve timely recovery. In this work, we first identify the limitations of the leader election and recovery protocols underlying Apache ZooKeeper, the prevailing open-source coordination service. To reduce recovery latency from leader failures, we then design RT-Zookeeper with a set of novel features including a fast-convergence election protocol, a quorum channel notification mechanism, and a distributed epoch persistence protocol. We have implemented RT-Zookeeper based on ZooKeeper version 3.5.8. Empirical evaluation shows that RT-ZooKeeper achieves 91% reduction in maximum recovery latency in comparison to ZooKeeper. Furthermore, a case study demonstrates that fast failure recovery in RT-ZooKeeper can benefit a common messaging service like Kafka in terms of message latency.

Screening of knee-joint vibroarthrographic signals using time and spectral domain features

It has been determined that variations in vibroarthrographic (VAG) signal characteristics have a direct association with various diseases of the knee joints including degenerative and traumatic etiology. Several studies have proposed temporal and time-frequency parameters for the analysis and classification of VAG signals; however, very few statistical modelling methods have been explored to analyze distinctions in the spectral domain characteristics of VAG signals. The aim of our work is to classify VAG signals into normal and abnormal thus portraying knee health condition by proposing a novel set of features. Spectral domain transformations of VAG signals were derived using the short-time Fourier transform (STFT) approach to extract statistical characteristic features from VAG signals. Several time-domain statistical features; the mean and variance values of spectral domain features namely – spectral mean, peak, skewness, kurtosis, flux, and slope were utilized to express VAG signal fluctuations. Further, mutual information test, ANOVA F-test, and Chi-square test were used to select significant features and assess their effectiveness. Random forest, Gaussian Naive Bayes, and support vector machine (SVM) algorithms were used to perform signal pattern classification. The results showed that subjects with knee joint abnormalities possess higher values of spectral flux, spectral slope, and shape factor than healthy subjects. An overall classification accuracy of 89.23%, sensitivity of 87.09% and specificity of 91.18% were obtained using the random forest classifier trained with features selected by the mutual information test. The proposed system could effectively screen almost 94% of subjects accurately based on area under the ROC curve.