Standard Classification Techniques Research Articles

JADES. The diverse population of infant black holes at 4<z<11: Merging, tiny, poor, but mighty

Spectroscopy with the James Webb Space Telescope has opened the possibility of identifying moderate-luminosity active galactic nuclei (AGNs) in the early Universe, at and beyond the epoch of re-ionisation, complementing previous surveys of much more luminous (and much rarer) quasars. We present 12 new AGNs at 4$<$z$<$7 in the JADES survey (in addition to the previously identified AGN in GN-z11 at z=10.6) revealed through the detection of a broad-line region (BLR) seen in the Balmer emission lines. The depth of JADES, together with the use of three different spectral resolutions, enables us to probe a lower-mass regime relative to previous studies. In a few cases, we find evidence for two broad components of Halpha , which suggests that these could be candidate merging black holes (BHs), although a complex BLR geometry cannot be excluded. The inferred BH masses range from $ 10^7 M_ down to $ 10^5 M_ interestingly probing the regime expected for direct collapse BHs. The inferred AGN bolometric luminosities ($ $ erg/s) imply accretion rates that are $< 0.5$ times the Eddington rate in most cases. However, small BHs, with $ BH 10^6 M_ tend to accrete at Eddington or super-Eddington rates. These BHs at zsim 4-11 are over-massive relative to their host galaxies' stellar masses when compared to the local $ BH -M_ star $ relation, even approaching $ BH star $, as was expected from heavy BH seeds and/or super-Eddington accretion scenarios. However, we find that these early BHs tend to be more consistent with the local relation between $ BH $ and velocity dispersion, as well as between $ BH $ and dynamical mass, suggesting that these are more fundamental and universal relations. On the classical, optical narrow-line excitation-diagnostic diagrams, these AGNs are located in the region that is that is locally occupied by star-forming galaxies, implying that they would be missed by the standard classification techniques if they did not display broad lines. Their location on the diagram is consistent with what is expected for AGNs hosted in metal-poor galaxies ($ Z 0.1-0.2 Z_ The fraction of broad-line AGNs with $ AGN erg/s$ among galaxies in the redshift range of $4<z<6$ is about 10<!PCT!>, suggesting that the contribution of AGNs and their hosts to the re-ionisation of the Universe is $>$10<!PCT!>.

On the role of network topology in German-Jewish recommendation letter networks in the early twentieth century

Recommendation letters were an important instrument for orchestrating Jewish emigration from Germany in the late nineteenth and early twentieth century. Here, we present network-based analyses of manually collected meta-data from recommendation letters targeted at the Hebrew University (HU) in Jerusalem. Using standard semi-supervised node classification techniques and differential node centrality analyses, we show that the position of a recommendation letter in content-agnostic recommendation network models is predictive of its success, i.e., of whether or not the letter led to the recommendee obtaining a position at the HU. In particular, we show that authors of successful recommendation letters assume more central positions within the networks than authors of unsuccessful letters, while the opposite holds for the recommendation letters’ receivers. Beyond our application, these results showcase the potential of using network models for generating historical insights. Both the letter meta-data records and Python code to reproduce our analyses are available on GitHub: https://github.com/bionetslab/corrnet.

Multi-Objective Multi-Instance Learning: A New Approach to Machine Learning for eSports.

The aim of this study is to develop a new approach to be able to correctly predict the outcome of electronic sports (eSports) matches using machine learning methods. Previous research has emphasized player-centric prediction and has used standard (single-instance) classification techniques. However, a team-centric classification is required since team cooperation is essential in completing game missions and achieving final success. To bridge this gap, in this study, we propose a new approach, called Multi-Objective Multi-Instance Learning (MOMIL). It is the first study that applies the multi-instance learning technique to make win predictions in eSports. The proposed approach jointly considers the objectives of the players in a team to capture relationships between players during the classification. In this study, entropy was used as a measure to determine the impurity (uncertainty) of the training dataset when building decision trees for classification. The experiments that were carried out on a publicly available eSports dataset show that the proposed multi-objective multi-instance classification approach outperforms the standard classification approach in terms of accuracy. Unlike the previous studies, we built the models on season-based data. Our approach is up to 95% accurate for win prediction in eSports. Our method achieved higher performance than the state-of-the-art methods tested on the same dataset.

Sparse measures with swarm-based pliable hidden Markov model and deep learning for EEG classification.

In comparison to other biomedical signals, electroencephalography (EEG) signals are quite complex in nature, so it requires a versatile model for feature extraction and classification. The structural information that prevails in the originally featured matrix is usually lost when dealing with standard feature extraction and conventional classification techniques. The main intention of this work is to propose a very novel and versatile approach for EEG signal modeling and classification. In this work, a sparse representation model along with the analysis of sparseness measures is done initially for the EEG signals and then a novel convergence of utilizing these sparse representation measures with Swarm Intelligence (SI) techniques based Hidden Markov Model (HMM) is utilized for the classification. The SI techniques utilized to compute the hidden states of the HMM are Particle Swarm Optimization (PSO), Differential Evolution (DE), Whale Optimization Algorithm (WOA), and Backtracking Search Algorithm (BSA), thereby making the HMM more pliable. Later, a deep learning methodology with the help of Convolutional Neural Network (CNN) was also developed with it and the results are compared to the standard pattern recognition classifiers. To validate the efficacy of the proposed methodology, a comprehensive experimental analysis is done over publicly available EEG datasets. The method is supported by strong statistical tests and theoretical analysis and results show that when sparse representation is implemented with deep learning, the highest classification accuracy of 98.94% is obtained and when sparse representation is implemented with SI-based HMM method, a high classification accuracy of 95.70% is obtained.

1D Multi-Point Local Ternary Pattern: A Novel Feature Extraction Method for Analyzing Cognitive Engagement of students in Flipped Learning Pedagogy.

Flipped learning is a blended learning method based on academic engagement of students online (outside class) and offline (inside class). In this learning pedagogy, students receive lesson any time from lecture videos pre-loaded on digital platform at their convenience places and it is followed by in-classroom activities such as doubt clearing, problem solving, etc. However, students are constantly exposed to high levels of distraction in this age of the Internet. Therefore, it is hard for an instructor to know whether a student has paid attention while watching pre-loaded lecture video. In order to analyze attention level of individual students, captured brain signal or electroencephalogram (EEG) of students can be utilized. In this study, we utilize a popular feature extraction technique called Local Binary Pattern (LBP) and improvise it to develop an enhanced feature selection method. The adapted feature selection method termed as 1D Multi-Point Local Ternary Pattern (1D MP-LTP) is used to extract unique features from collected electroencephalogram (EEG) signals. Standard classification techniques are exploited to classify the attention level of students. Experiments are conducted with the data captured at Intelligent Data Analysis Lab, NIT Rourkela, to show effectiveness of the proposed feature extraction technique. The proposed 1D Multi-Point Local Ternary Pattern (1D MP-LTP)-based classification techniques outperform traditional and state-of-the-art classification techniques using LBP. This research can be helpful for instructors to identify students who need special care for improving their learning ability. Researchers in educational technology can extend this work by adopting this methodology in other online teaching pedagogy such as Massive Open Online Courses (MOOC).

A Global Training Model for Beat Classification Using Basic Electrocardiogram Morphological Features

Clinical Study and automatic diagnosis of electrocardiogram (ECG) data always remain a challenge in diagnosing cardiovascular activities. The analysis of ECG data relies on various factors like morphological features, classification techniques, methods or models used to diagnose and its performance improvement. Another crucial factor in the methodology is how to train the model for each patient. Existing approaches use standard training model which faces challenges when training data has variation due to individual patient characteristics resulting in a lower detection accuracy. This paper proposes an adaptive approach to identify performance improvement in building a training model that analyze global training methodology against an individual training methodology and identifying a gap between them. We provide our investigation and comparative study on these methods and model with standard classification techniques with basic morphological features and Heart Rate Variability (HRV) that may aid real time application. This approach helps in analyzing and evaluating the performance of different techniques and can suggests adoption of a best model identification with efficient technique and efficient attribute set for real-time systems.

Parametric Circuit Fault Diagnosis Through Oscillation-Based Testing in Analogue Circuits: Statistical and Deep Learning Approaches

Oscillation-based testing of analogue electronic filters removes the need for test signal synthesis. Parametric faults in the presence of normal component tolerance variation are challenging to detect and diagnose. This study demonstrates the suitability of statistical learning and deep learning techniques for parametric fault diagnosis and detection by investigating several time-series classification techniques. Traditional harmonic analysis is used as a baseline for an in-depth comparison. Eight standard classification techniques are applied and compared. Deep learning approaches, which classify the time-series signals directly, are shown to benefit from the oscillator start-up region for feature extraction. Global average pooling in the convolutional neural networks (CNN) allows for Class Activation Maps (CAM). This enables interpreting the time-series signal’s discriminative regions and confirming the importance of the start-up oscillation signal. The deep learning approach outperforms the harmonic analysis approach on simulated data by an average of 11.77% in classification accuracy for the three parametric fault magnitudes considered in this work.

A rare case of hyperextended bicondylar tibia plateau fracture

Bicondylar tibia plateau fractures are a common injury in day-to-day practice, and categorization and treatment methods have been effectively described in the literature. The Hyperextension bicondylar tibia plateau (HEBTP) fracture is an uncommon fracture that is difficult to classify using standard classification techniques and has no set treatment strategy. Compressed anterior cortex, tension stress failure of the posterior cortex and loss of normal posterior slope of tibia plateau are all symptoms of HEBTP, which is produced by hyperextended high-energy trauma. HEBTP fracture is a kind of tibia plateau fracture which largely affects the tibial condyle' sagittal alignment. They account for fewer than 20% of all bicondylar injuries. As the knee has varus alignment and restraint of the knee's posterolateral capsule-ligamentous complex, there is asymmetric accumulation of force to the medial plateau resulting in a characteristic injury pattern that is often more severe on this side. Hence, we discuss a case of HEBTP managed with bicondylar plate and its functional outcomes. We present a case of a 44-year-old male patient who came to Acharya Vinoba Bhave Rural Hospital, Wardha with 5-day-old history of high-energy trauma to the right knee, with discomfort and swelling over the right knee and inability to bear weight over the right lower limb. The patient initially went to a local doctor and was treated conservatively with an above knee slab over his right lower limb before being sent to AVBRH for further treatment. On examination, there was extensive edema and varus deformity over the right proximal tibia. The tibia had substantial posterior sag, which is unusual in a tibial plateau fracture. Tenderness was present across the proximal one-third of the tibia, although there was no increase in local temperature. Range of motion in the knees was not possible. Clinically, there was a 10° varus deformity. The posterolateral ligament complex and collateral ligaments could not be evaluated. There were no symptoms of compartment syndrome present. There was no neurovascular injury. Distal circulation was intact. The differential diagnosis was posterolateral corner injury, posterior subluxation, or dislocation of the knee. To rule out the differentials, radiological imaging, X-ray, and a computed tomography scan were performed and the patient was diagnosed to have hyperextended bicondylar tibia plateau fracture. Open reduction and internal fixation with bicondylar plate osteosynthesis were used to treat the patient and extensive postoperative physiotherapy regimen was started. The patient was then followed up and results were recorded. The treatment for hyperextension tibia plateau fractures includes reducing fractures while healing critical ligament damage and restoring knee joint stability. If the tibial rim is depressed, the tibial rim should be rebuilt to restore the joint's stability. The features of anterior tibia fractures produced by knee hyperextension injuries are unknown at this time. For anterior tibia plateau fractures, there is very less unanimity on the best technique and fixing methods. The clinical dilemma of deciding how to decrease as well as cure the fractures of the anterior tibia plateau produced by the hyperextension injury remains unsolved. The treatment of hyperextension bicondylar tibia plateau fractures managed with open reduction and bicondylar plate osteosynthesis yields outstanding outcomes.

One-Shot Learning-Based SAR Ship Classification Using New Hybrid Siamese Network

Synthetic aperture radar (SAR) ship classification research mainly focuses on large ships with distinctive features. Also, ship types are expanding nowadays. Traditional standard image classification techniques are not adequate for the effective classification of SAR ships due to their fewer available data in some classes (unbalanced data). We are introducing a one-shot learning-based deep learning model built from scratch to classify 16 ship classes to solve these. It generates embeddings of size 20 and uses distance measure for classification. Also, we propose a preprocessing stage (PP-stage) and feature fusion (FF-stage) technique to improve classification accuracy. Experimental results on the OpenSARShip dataset for ship classification reveal that the accuracy is superior to the other state-of-the-art SAR image classifiers.

HCBST: An Efficient Hybrid Sampling Technique for Class Imbalance Problems

Class imbalance problem is prevalent in many real-world domains. It has become an active area of research. In binary classification problems, imbalance learning refers to learning from a dataset with a high degree of skewness to the negative class. This phenomenon causes classification algorithms to perform woefully when predicting positive classes with new examples. Data resampling, which involves manipulating the training data before applying standard classification techniques, is among the most commonly used techniques to deal with the class imbalance problem. This article presents a new hybrid sampling technique that improves the overall performance of classification algorithms for solving the class imbalance problem significantly. The proposed method called the Hybrid Cluster-Based Undersampling Technique (HCBST) uses a combination of the cluster undersampling technique to under-sample the majority instances and an oversampling technique derived from Sigma Nearest Oversampling based on Convex Combination, to oversample the minority instances to solve the class imbalance problem with a high degree of accuracy and reliability. The performance of the proposed algorithm was tested using 11 datasets from the National Aeronautics and Space Administration Metric Data Program data repository and University of California Irvine Machine Learning data repository with varying degrees of imbalance. Results were compared with classification algorithms such as the K-nearest neighbours, support vector machines, decision tree, random forest, neural network, AdaBoost, naïve Bayes, and quadratic discriminant analysis. Tests results revealed that for the same datasets, the HCBST performed better with average performances of 0.73, 0.67, and 0.35 in terms of performance measures of area under curve, geometric mean, and Matthews Correlation Coefficient, respectively, across all the classifiers used for this study. The HCBST has the potential of improving the performance of the class imbalance problem, which by extension, will improve on the various applications that rely on the concept for a solution.

Video recording and vegetation classification elucidate sheep foraging ecology in species-rich grassland.

Factors influencing grazing behavior in species‐rich grasslands have been little studied. Methodologies have mostly had a primary focus on grasslands with lower floristic diversity.We test the hypothesis that grazing behavior is influenced by both animal and plant factors and investigate the relative importance of these factors, using a novel combination of video technology and vegetation classification to analyze bite and step rates.In a semi‐natural, partially wooded grassland in northern Estonia, images of the vegetation being grazed and records of steps and bites were obtained from four video cameras, each mounted on the sternum of a sheep, during 41 animal‐hours of observation over five days. Plant species lists for the immediate field of view were compiled. Images were partnered by direct observation of the nearest‐neighbor relationships of the sheep. TWINSPAN, a standard vegetation classification technique allocating species lists to objectively defined classes by a principal components procedure, was applied to the species lists and 25 vegetation classes (15 open pasture and 10 woodland) were identified from the images.Taking bite and step rates as dependent variables, relative importance of animal factors (sheep identity), relative importance of day, and relative importance of plant factors (vegetation class) were investigated. The strongest effect on bite rates was of vegetation class. Sheep identity was less influential. When the data from woodland were excluded, sheep identity was more important than vegetation class as a source of variability in bite rate on open pasture.The original hypothesis is therefore supported, and we further propose that, at least with sheep in species‐rich open pastures, animal factors will be more important in determining grazing behavior than plant factors. We predict quantifiable within‐breed and between‐breed differences, which could be exploited to optimize conservation grazing practices and contribute to the sustainability of extensive grazing systems.

Random Forest for Data Aggregation to Monitor and Predict COVID-19 Using Edge Networks

Medical sensors and distributed edge networks hold promise in advanced control and prediction of infectious diseases, such as COVID-19. Their integration can lower communication latency, bandwidth utilization, and energy consumption while achieving high application scalability and reliability. Existing edge-devices-enabled e-healthcare frameworks face two serious challenges that affect their success. First, real-time medical sensors generate similar or redundant readings used for disease prediction, mostly for non-COVID-19 patients, which increases data transmission latency and energy consumption. Second, predicting the risk level of COVID-19 patients using lightweight machine learning requires minimal training time to be useful. To address these challenges, we develop an edge-centric e-healthcare framework for online health data monitoring and analysis to predict the risk level of COVID-19 patients. In the proposed framework, a statistical data aggregation method (MEAN function) is deployed at local gateway devices to remove redundant data to minimize communication latency and energy usage. Geo-distributed edge servers are used to predict with 97 percent accuracy the risk level to each patient with Random Forest (RF) on the aggregated data. Finally, the efficiency of the RF algorithm is demonstrated with standard classification techniques.

Prediction of paroxysmal atrial fibrillation using new heart rate variability features

Paroxysmal atrial fibrillation (PAF) is a cardiac arrhythmia that can eventually lead to heart failure or stroke if left untreated. Early detection of PAF is therefore crucial to prevent any further complications and avoid fatalities. An implantable defibrillator device could be used to both detect and treat the condition though such devices have limited computational capability. With this constraint in mind, this paper presents a novel set of features to accurately predict the presence of PAF. The method is evaluated using ECG signals from the widely used atrial fibrillation prediction database (AFPDB) from PhysioNet. We analysed 106 signals from 53 pairs of ECG recordings. Each pair of signals contains one 5-min ECG segment that ends just before the onset of a PAF event and another 5-min ECG segment at least 45 min distant from the PAF event, to represent a non-PAF event. Seven novel features are extracted through the Poincaré representation of R-R interval signals, and are prioritised through feature ranking schemes. The features are used with four standard classification techniques for PAF prediction and compared to the existing state of the art from the literature. Using only the seven proposed features, classification performance outperforms those of the classical state-of-the-art feature set, registering sensitivity and specificity measurements of over 96%. The results further improve when the features are combined with several of the classical features, with an accuracy increasing to 98% using a linear kernel SVM. The results show that the proposed features provide a useful representation of the PAF condition and achieve good prediction with off-the-shelf classification techniques that would be suitable for ICU deployment.

Participatory Mapping with High-resolution Satellite Imagery: A Mixed method Assessment of Land Degradation and Rehabilitation in Northern Burkina Faso.

Sahelian West Africa is a region that suffers from high population densities, frequent severe droughts, and enormous pressure on natural resources. Because of these challenges, it is the place where the term "desertification" was originally coined. Recently, however, experts have identified large zones of "greening" where the amount of vegetation exceeds what one would expect based on rainfall alone. This pattern is well documented, but its mechanisms remain poorly understood. This research employs participatory mapping linked with high-resolution satellite imagery to better understand the human role behind regional vegetation trends. Through a case study of three communities in northern Burkina Faso, this paper presents a pilot methodology for explicitly mapping perceived areas of both land degradation and rehabilitation. Combining participatory mapping exercises with standard image classification techniques allows areas of land degradation and rehabilitation to be precisely located and their extents measured for individual communities and their surrounding terroirs. Results of the spatial analysis show that the relative proportion of greening and browning varies among communities. In the case of Sakou, nearly 60 percent of its terroir is degraded. While in another, Kouka, this is 48 percent. This method also elicits perspectives of Burkinabè agro-pastoralists on the local land-use practices driving these twin environmental processes. Altogether, this case study demonstrates the analytical power of integrating ethnography and high-resolution satellite imagery to provide a bottom-up perspective on social-ecological dynamics.

Event Classification with Quantum Machine Learning in High-Energy Physics

We present studies of quantum algorithms exploiting machine learning to classify events of interest from background events, one of the most representative machine learning applications in high-energy physics. We focus on variational quantum approach to learn the properties of input data and evaluate the performance of the event classification using both simulators and quantum computing devices. Comparison of the performance with standard multi-variate classification techniques based on a boosted-decision tree and a deep neural network using classical computers shows that the quantum algorithm has comparable performance with the standard techniques at the considered ranges of the number of input variables and the size of training samples. The variational quantum algorithm is tested with quantum computers, demonstrating that the discrimination of interesting events from background is feasible. Characteristic behaviors observed during a learning process using quantum circuits with extended gate structures are discussed, as well as the implications of the current performance to the application in high-energy physics experiments.

Matrix Relevance Learning From Spectral Data for Diagnosing Cassava Diseases

We discuss the use of matrix relevance learning, a popular extension to prototype learning algorithms, applied to a three-class classification task of diagnosing cassava diseases from spectral data. Previously this diagnosis has been done using plant image data taken with a smartphone. However for this method disease symptoms need to be visible. Unfortunately for some cassava diseases, once symptoms have manifested on the aerial part of the plant, the root which is the edible part of the plant has been totally destroyed. This research is premised on the hypothesis that diseased crops without visible symptoms can be detected using spectral information, allowing for early interventions. In this paper, we analyze visible and near-infrared spectra captured from leaves infected with two common cassava diseases (cassava brown streak disease and cassava mosaic virus disease) found in Sub-Saharan Africa. We also take spectra from leaves of healthy plants. The spectral data come with thousands of dimensions, therefore different wavelengths are analyzed in order to identify the most relevant spectral bands for diagnosing these disease. To cope with the nominally high number of input dimensions of data, functional decomposition of the spectra is applied. The classification task is addressed using Generalized Matrix Relevance Learning Vector Quantization and compared with the standard classification techniques performed in the space of expansion coefficients.

ADVANCED CLASSIFICATION OF OPTICAL AND SAR IMAGES FOR URBAN LAND COVER MAPPING

Abstract. The aim of this research is to classify urban land cover types using an advanced classification method. As the input bands to the classification, the features derived from Landsat 8 and Sentinel 1A SAR data sets are used. To extract the reliable urban land cover information from the optical and SAR features, a rule-based classification algorithm that uses spatial thresholds defined from the contextual knowledge is constructed. The result of the constructed method is compared with the results of a standard classification technique and it indicates a higher accuracy. Overall, the study demonstrates that the multisource data sets can considerably improve the classification of urban land cover types and the rule-based method is a powerful tool to produce a reliable land cover map.

A Decision Support System for the Prediction of Wastewater Pumping Station Failures Based on CBR Continuous Learning Model

Nowadays the communities are facing the problem of waste and wastewater. While wastewater systems have become more complex, the need for development of sustainable solution for wastewater management emerged. Therefore, the development of a Decision Support System (DSS) for wastewater disposal management became necessary. This paper presents a new DSS for predicting the failure of wastewater pumping stations, the system architecture and its implementation. The prediction model is based on the Case Based Reasoning (CBR) classification method. The standard CBR classification technique has been upgraded with an algorithm for continuous learning. The paper describes the system structure, its connection to the wastewater system, the internal processes involved in the prediction process and the implemented algorithm for continuous learning. Furthermore, the features used in the prediction are indicated along with the achieved results and the method of results evaluation. The test and obtained results indicate that the proposed DSS is efficient and capable of providing very good results in the prediction process.

RGB Inter-Channel Measures for Morphological Color Texture Characterization

The perception of textures is based on high-level features such as symmetry, brightness, color or direction. Texture characterization is a widely studied topic in the image processing community. The normalized volume of morphological series is used as a texture descriptor in RGB images. However, the correlation between different color channels is not exploited with this descriptor. We propose the usage of inter-channel measures in addition to the volume, to enhance the descriptors potential to discriminate textures. The experiments show that standard texture classification techniques increase between 3%–10% in performance when using our descriptor instead of other state of the art descriptors that do not use inter-channel measures.

A new non-parametric classifier to predict small-business failures in Italy via performance ratios

We considered the case of small-medium enterprises (SMEs) in Italy introducing a new classifier to predict bankruptcy up to eight years prior to failure. We considered a stratified random sample of 100 non-listed Italian SMEs, 50 of which filed for bankruptcy during the years 2000 to 2011. Results suggest that the proposed method more than holds its own when compared with standard non-parametric classification techniques. The performance of the proposed method based on recognition rate, sensitivity and specificity shows that the proposed technique is effective in predicting the failure of a firm up to eight years prior to the event. The high specificity makes the proposed technique very effective as a warning signal to determine if a firm is in distress with a sufficient enough time to take proper actions. The performance assessment has been achieved via cross-validation to get unbiased estimates of the performances.