Search

Labeled data are fed to learning models of classification tasks to help them learn to classify unlabeled data. Massive papers are hinged by citations to a few influential papers, much smaller than the total size, which, if labeled, would cause the spread of label information to the most of the papers. We utilized the co-reference relationship between papers since the references cited by a paper dataset usually cannot be contained by the dataset. We stated the problem of optimal paper labeling as the problem of picking a given fraction of nodes from a co-reference network to maximize the number of their neighbors, which is a submodular maximization problem with a cardinality constraint, NP-hard for general networks. We approximately solved it by picking nodes according to the ranks of specific network centralities. We further proved that labeling papers according to the rank of degree, the lowest-complexity centrality, can give a near-optimal solution with specific constraints on the maximum degree of co-reference network and labeling proportion. Experimental results show that our method brings a significant improvement in the accuracy of classification. • A model-agnostic optimization objective is proposed to improve paper classification accuracy. • The optimization objective is maximizing a paper set's neighborhood in a co-reference network. • Labeling high-centrality nodes is a labor-saving and approximative way to the maximizing problem. [ABSTRACT FROM AUTHOR]

Highlights • Comparison of the classification system of science between the journal level and the paper level from the same data set. • In the journal classification system, 46.0% of articles were not contributed from their journal's discipline(s). • In a paper classification system, 51.1% of papers were not published in journals of the same discipline(s). • The difference between these two levels varies by discipline and the methodology constructing the classification system. Abstract The classification of science into disciplines is at the heart of bibliometric analyses. While most classifications systems are implemented at the journal level, their accuracy has been questioned, and paper-level classifications have been considered by many to be more precise. However, few studies investigated the difference between journal and the paper classification systems. This study addresses this gap by comparing the journal- and paper-level classifications for the same set of papers and journals. This isolates the effects of classification precision (i.e., journal- or paper-level) to reveal the extent of paper misclassification. Results show almost half of papers could be misclassified in journal classification systems. Given their importance in the construction and analysis of bibliometric indicators, more attention should be given to the robustness and accuracy of these disciplinary classifications schemes. [ABSTRACT FROM AUTHOR]

• France is behind other countries in its consideration of violence in perinatal care • Its consequences on maternal and neonatal health are recognised internationally • Measuring and characterising violence in perinatal care is important • Our Proposal is simplified compared with those currently in use • Focusing in three categories, we may improve the prevention of these violence France is somewhat behind other countries in its consideration of the issue of violence in perinatal care. Its consequences on maternal, but also neonatal and infant health are recognised internationally. Nonetheless, research and data measuring its frequency and its determinants are inadequate, and the relevant definitions are not always consensual. In this context, we, as midwives and researchers in public health and as members of the National College of French Midwives, seek to propose a scientific and clinical contribution to this debate. We propose avenues for measuring and characterising violence in perinatal care. Our objective is to quantify and characterise the situations of violence in perinatal care in population-based studies and based on the perceptions of each woman questioned. This proposal for questions, simplified compared with those currently in used in the international scientific literature, has the advantage of focusing reflection around three categories: inappropriate medical care, inappropriate human behaviours in care, and sexual abuse. It should also allow the identification of the contexts of care during which violence may be experienced, as well as the categories of health-care workers concerned. It seems important to us to distinguish these situations, causal and context, for they require different responses if we hope to reduce the frequency and the effects of violence in perinatal care in the future. We propose questions that could also be used in clinical situations by midwives and other clinicians. [ABSTRACT FROM AUTHOR]

[Display omitted] • ATR-FTIR spectroscopy detects forgeries by analyzing paper aging. • SIMCA models classify paper samples by their age. • Chemometric models distinguish between artificial and natural aging. • Artificially aged paper with UV radiation closely resembles naturally aged samples. One of the great challenges of document analysis is determining document forgeries. The present work proposes a non-destructive approach to discriminate natural and artificially aged papers using infrared spectroscopy and soft independent modeling by class analogy (SIMCA) algorithms. This is of particular interest in cases of document falsifications made by artificial aging, for this study, SIMCA, and Data-Driven SIMCA (DD-SIMCA) classification models were built using naturally aged paper samples, taken from three time periods: 1st period from 1998 to 2003; 2nd period from 2004 to 2009; and 3rd period from 2010 to 2015. Artificially aged samples (exposed to high temperature or UV radiation) were used as test sets. Promising results in detecting document falsifications related to aging were obtained. Samples artificially aged at high temperature were correctly discriminated from the authentic samples (naturally aged) with 100% accuracy. In contrast, the samples under the photodegradation process showed a lower classification performance, with results above 90%. [ABSTRACT FROM AUTHOR]

This paper provides a corrected formulation to the mixed integer programming model proposed by Aydogan et al. (2012) [1] . They proposed a genetic algorithm to learn fuzzy rules for a fuzzy rule-based classification system and developed a Mixed Integer Programming model (MIP) to prune the generated rules by selecting the best set of rules to maximize predictive accuracy. However, their proposed MIP formulation contains errors, which are described in this technical note. We develop corrections and improvements to the original formulation and test it with non-parametric statistical tests on the same data sets used to evaluate the original model. The statistical analysis shows that the results of the correction formulation are significantly different from the original model. [ABSTRACT FROM AUTHOR]

The article by Davies et al. discusses scientific studies on microbially induced sedimentary structures (MISS). The sedimentary structures are caused by benthic microbes in clastic deposits and have the potential to fossilize. In the opinion of Davies et al., it may be problematic to distinguish MISS-like structures (e.g., ‘wrinkle structures’) from similar, but abiotic structures. Therefore, their article argues, there exists a need for an umbrella classification summarizing both biological and abiotic sedimentary structures. However, Davies et al.'s paper does not reflect a thorough understanding of the formation and preservation of MISS. More so, while the authors appreciate the benefit of geological field work, and petrological as well as geochemical laboratory sample analyses, their article appears to widely disregard that this scientific rigor is presented in studies on MISS. The lack of data make the classification by Davies et al. unsupported and difficult to use. It potentially confuses by producing multiple classification possibilities rather than a pragmatic organization, and it contributes an unnecessary terminological ballast to a research area that has progressed far beyond to the concepts that the paper by Davies et al. presents. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we describe the development of a system for evaluating an specific quality characteristic of recycled paper sheets using techniques of image analysis and pattern recognition. We call Bumpiness the phenomenon of interest, which is new in the literature on paper quality. This phenomenon is characterized by the appearance of macroscopic undulations on the paper sheet surface that may emerge shortly or some time after its production. We explore the detection and measurement of this defect by means of computer vision and statistical pattern recognition techniques that may allow early detection at the production site. Our goal is to give an scalar continuous measure of Bumpiness. We propose features computed from Gabor filter banks (GFB) and discrete wavelet transforms (DWT) for the characterization of paper sheet surface Bumpiness in recycled paper images. The starting point is to state the problem as a classification of the paper sheet images into two classes: low and high Bumpiness. In this setting we obtain, with both proposed texture modelling approaches (GFB and DWT), classification accuracies comparable to the agreement between human observers. The best performance is obtained using DWT features. Finally, we propose as the scalar index of Bumpines the fisher discriminant analysis (FDA) function defined on the space of the best features for the classification task. We perform an innovative validation process of this Bumpiness index, based on the ordering of random pairs of images, obtaining a very high agreement with the human observers. [Copyright &y& Elsevier]

• Robust functional form contains true parameters far more often than popular models. • Matches/outperforms widely used regression and Neural Network models. • Finds appropriate balance between Model Fit, Inference and Prediction (MIPs). • Introduces new large-sample DGP test; can use to improve A.I. models. • For MIS field finds Popularity Parameter to be important for predicting citations. This article introduces a versatile functional form for Generalized Linear Models (GLMs) through a simple, yet effective, transformation of the current framework. The models are applied through a new hierarchical bayesian estimation procedure for logistic regression to highly-cited papers in the Management Information Systems (MIS) field. The results are uniformly better, in regards to model fit and inference for in-sample and out-of-sample data, for simulation studies and real-world data applications, requiring very little time to convergence to true population parameters. In simulation studies, I show that the method contains the true parameters nearly three times as often as widely used existing GLMs, and does so while having confidence intervals that are 54.50% smaller, while requiring around two-thirds the number of MCMC iterations as existing bayesian methods. In Scientometric applications the methodology is shown to be highly robust with predictive/classification accuracy, either equaling or exceeding existing methods for identifying highly-cited articles including Artificial Neural Networks (ANN). Thus, the method is shown to be robust to the amount of asymmetry (or symmetry) of the probability of success (or failure) and robust to unbalanced samples and varying Data Generating Processes. Further, the methodology is equivalent to current methods if the data support them and is therefore complementary to existing methods, without loss of interpretability of model parameters. For the MIS field it finds that Popularity Parameter (PP) of an article Keywords can predict whether a paper will be highly-cited (top 25% of highly-cited articles) between two to three years after publication and beyond. Furthermore, given the small number of iterations needed for convergence, the methodology can also be used as a baseline method in Big Data (BD) settings for both Artificial Intelligence (AI) and Machine Learning (ML) contexts as well. [ABSTRACT FROM AUTHOR]

Frick (2022) presented a narrative review of some literature and made several critical comments regarding the extension of the full psychopathy construct to research and classification of childhood disruptive behavior disorders (DBDs). His arguments cautioned against the use of the multicomponent concept of psychopathy for specification of DBDs for several reasons including definitional issues, symptom sequencing, specifier versus risk factor considerations, potential overlap with other disorders and criteria (e.g., ADHD), and concerns regarding harm. While I agree with Frick (2022) that we need to be cautious when extending personality constructs to the DBDs, the remaining arguments in his paper fall short of calling for the exclusion of psychopathy components in the examination of DBDs. Rather, the counterpoints in this paper further convince that the multidimensional model of psychopathy, when applied to the DBDs, could better facilitate understanding of the etiology and mechanisms for Conduct Disorder (CD), and, it may help us to predict the prognosis and treatment outcomes of children with various forms of DBDs such as CD and Oppositional Defiant Disorder (ODD). To have the most informative designs, future research should examine the broad construct to glean a better understanding of psychopathy and the DBDs. Further, research should continue to examine sequencing and external correlates at the component level and to test the incremental value of the multicomponent model of psychopathy to help us better comprehend how each component may facilitate our understanding of the types and severity of conduct problems exhibited by youth with DBDs (i.e., CD, ODD). [ABSTRACT FROM AUTHOR]

Abstract: The characteristics of paper surface play a central role in the overall quality of paper produced in modern paper machines. Among the surface features, paper formation, i.e., the level of homogeneity in the distribution of fibres on the surface of paper, is a key quality parameter, being currently monitored off-line, at low sampling rates relatively to the high production speeds achieved with modern paper machines. Therefore, in this paper, we address the problem of assessing the quality of paper formation, on-line, in situ, in an autonomous, efficient, objective and fast way, using features derived from images collected by a specially designed sensor, coupled with proper classification methodologies. The results obtained clearly demonstrate the potential of the proposed assessment approach either for the more complex three-class classification problem as well as for less demanding, but still important in practice, two-class “Accept”/“Reject” or “Pass”/“Fail” problem. [ABSTRACT FROM AUTHOR]

Abstract: Surface roughness is one of the most important attributes of paper and its measurement is normally used in quality control applications. Currently, measurement of surface roughness is done by using air leakage, optical, or subjective methods. In this article, an acoustical method for the determination of surface roughness of papers is described. The method is applied off-line and uses the friction noise recorded when a small brush slide over the surface of the paper. The analysis is done consider the friction noise ranging from 300Hz to 10kHz. Considering that friction noise is associated to surface roughness, a signal analysis algorithm was developed to take advantage of this fact. The algorithm consists of a frequency-domain feature extraction routine and an artificial neural network that represents the variation of the spectral features in a roughness scale. The results show that an affordable and efficient friction noise based system can be used for measuring surface roughness of tissue papers and other soft surfaces as an alternative to other methods. [Copyright &y& Elsevier]

Surface-enhanced Raman spectroscopy (SERS) with subsequent chemometric evaluation was performed for the rapid and non-destructive differentiation of seven important meat-associated microorganisms, namely Brochothrix thermosphacta DSM 20171T, Pseudomonas fluorescens DSM 4358, Salmonella enterica subsp. enterica sv. Enteritidis DSM 14221, Listeria monocytogenes DSM 19094, Micrococcus luteus DSM 20030T, Escherichia coli HB101 and Bacillus thuringiensis sv. israelensis DSM 5724. A simple method for collecting spectra from commercial paper-based SERS substrates without any laborious pre-treatments was used. In order to prepare the spectroscopic data for classification at genera level with a subsequent chemometric evaluation consisting of principal component analysis and discriminant analysis, a data pre-processing method with spike correction and sum normalisation was performed. Because of the spike correction rather than exclusion, and therefore the use of a balanced data set, the multivariate analysis of the data is significantly resilient and meaningful. The analysis showed that the differentiation of meat-associated microorganisms and thereby the detection of important meat-related pathogenic bacteria was successful on genera level and a cross-validation as well as a classification of ungrouped data showed promising results, with 99.5% and 97.5%, respectively. Image 1 • Development of a sampling-, measurement- and data pre-processing method for SERS. • Evaluation by principal component analysis and canonical discriminant analysis. • Balanced data set leads to resilient chemometric model and meaningful evaluation. • Differentiation of spoilage related microorganisms on genera level with SERS. • Classification of ungrouped data showed only an error rate of 2.5%. [ABSTRACT FROM AUTHOR]

Abstract: This article investigates and discusses 3D property research, as evidenced by conference papers and other publications written in English, to analyze the distribution of interest areas and the occurrence of legal aspects and trends within 3D property research occurring between 2001 and 2011. A total of 156 publications on 3D property were examined. The publications were classified in four different categories, which represent different aspects of 3D property: legal, technical, registration and organizational. More 3D property research has been conducted on technical aspects and registration than legal aspects. In the legal category, most studies addressed national legislation and the practical use of (national) legislation. The authors believe that further fundamental legal research on 3D property is needed. The quantity of research could be increased, for example, by promoting international discussion and increasing the number of comparative legal studies on 3D property rights. Additional and more focused attention should be given to international matters, such as comparative studies on the use of 3D property concepts, the development of (international) 3D property terminology and cooperation between 3D property unit owners. [Copyright &y& Elsevier]

• Artificial intelligence can facilitate inclusive approach to heritage planning. • This paper reveals the cultural significance attached to the heritage property. • Artificial intelligence can contribute to value-based heritage planning. Experts have always played an important role in heritage planning, practice, and theory. There is a wealth of literature published every year regarding heritage and its cultural significance. Experts also contribute to heritage planning and developing policy documents. Still, literature is rarely used as a source of primary research to systematically reveal and compare experts' opinions on the cultural significance of built heritage. Analyzing them as a whole is costly and time-consuming, especially on built heritage, when much has been written about. While the automation of methods has proven to mitigate such restrictions in other fields, as digital humanities, their application in heritage planning, practice, and theory is still scarce. Hence, this paper aims to investigate the potentials of AI models (e.g., multi label text classification) in analyzing scientific documents, revealing the cultural significance of built heritage, values and attributes. This was done to better understand the similarities and differences between the experts' opinions. Yazd, Iran, is taken a case study, with a particular focus on windcatchers, a key attribute conveying cultural significance, of outstanding universal value, due to its inscription on the UNESCO World Heritage List. This paper has three subsequent phases: 1) state of the art on the application of AI in heritage planning; 2) methodology of data collection and data analysis related to coding values and attributes of windcatchers, addressed in relevant documents; 3) preliminary findings on the experts' opinions over values and attributes of windcatchers. Results contribute to the scientific discussion, revealing the cultural significance of windcatchers of Yazd from experts' point of view. Besides, the potential of AI for heritage planning is revealed in terms of (de)coding and measuring the cultural significance of built heritage from the available documents, showing the opinions of experts with various backgrounds. This model can be applied to other key attributes in Yazd and other case studies and scales to support heritage planning, practice, and theory. [ABSTRACT FROM AUTHOR]

This paper discusses the role of Transfer Learning (TL) and transformers in cancer detection based on image analysis. With the enormous evolution of cancer patients, the identification of cancer cells in a patient's body has emerged as a trend in the field of Artificial Intelligence (AI). This process involves analyzing medical images, such as Computed Tomography (CT) scans and Magnetic Resonance Imaging (MRIs), to identify abnormal growths that may help in cancer detection. Many techniques and methods have been realized to improve the quality and performance of cancer classification and detection, such as TL, which allows the transfer of knowledge from one task to another with the same task or domain. TL englobes many methods, particularly those used in image analysis, such as transformers and Convolutional Neural Network (CNN) models trained on the ImageNet dataset. This paper analyzes and criticizes each method of TL based on image analysis and compares the results of each method, showing that transformers have achieved the best results with an accuracy of 97.41% for colon cancer detection and 94.71% for Histopathological Lung cancer. Future directions for cancer detection based on image analysis are also discussed. [ABSTRACT FROM AUTHOR]

A novel type of spectrum, the one-dimensional power spectrum (1D-PS), was designed for the discrimination of adhesive packing tapes, i.e., kraft tapes. The 1D-PS offered complementary information to that provided by the improved two-dimensional PS (2D-PS), which was calculated using our previously established image processes combined with a two-dimensional fast Fourier transform (2D-FFT) to obtain information about the spatial periodicity within kraft tapes. The 1D-PS was calculated using a three-step image process: (i) the 2D-FFT was applied to 50 randomly selected areas in a transmitted light image; (ii) the obtained 2D-PSs were accumulated without applying a logarithmic transform; (iii) the wavenumber and the maximum intensity were plotted on the x-axis and y-axis, respectively. Through an intra-roll comparison, the 1D-PSs collected from single rolls showed similar profiles. In an inter-roll comparison, the 1D-PSs from 50 commercially available brand-name products were classified into 29 groups. The 1D-PSs contained other useful information than that provided by the improved 2D-PSs: they presented more peaks and absolute intensity with a wider range. The 1D-PSs enabled us to compare the spectra quickly and easily, owing to their unchanging profiles regardless of the orientation of the scanned images. A combined use of the 1D-PSs with the improved 2D-PSs-both spectrum types being convenient, rapid, non-destructive, and applicable to dirty and/or damaged samples-could further improve the identification of kraft tapes. [ABSTRACT FROM AUTHOR]

Breast cancer (BC) continues to be a prominent issue in global public health, emphasizing the need for precise and timely detection. This paper employs a deep learning (DL) approach to introduce an extensive methodology for categorizing histopathology images associated with breast cancer into automated binary classifications. The proposed framework architecture is validated on the standard database which is accessible to the public, called Breast Cancer Histopathological Database (BreakHis). Data augmentation techniques are employed for the pre-processing stage. This paper uses the DenseNet 121 pre-trained model for feature extraction and fully connected layers (FCL) to fine-tune the model further. In this experiment, the highest accuracy of 96.09% is observed with the 100X. The experimental results showed an improvement in accuracy for all the magnification factors compared to the existing works. [ABSTRACT FROM AUTHOR]

Skin cancer is one of the most prevalent forms of cancer around the world. Initial diagnosis relies on visual assessment of the affected area, followed by detailed dermoscopic analysis. The development of an automated system for classifying skin lesions poses a considerable challenge due to inherent noise and subtle variability in lesion images. Deep convolutional neural networks have demonstrated exceptional proficiency in image classification tasks spanning diverse domains. This paper demonstrates an end-to-end classification architecture built on top of transfer learning with data augmentation. The proposed model capitalizes on pre-trained architectures such as DenseNet, VGG-16, and Inception for feature extraction, and employs fully connected dense layers for categorizing seven distinct types of lesions. Several data augmentation techniques are also used to handle the class imbalance problem. Extensive experimentation encompassing various hyperparameters, imbalanced data scenarios, and balanced datasets was conducted to refine the automated skin lesion system. The proposed approach achieved a notable accuracy of 98% on the HAM10000 dataset and 94% on the ISIC-2019 dataset. Importantly, the experimental findings surpassed the performance of current state-of-the-art models for lesion classification. Furthermore, this paper examines the impact of class imbalance and data augmentation on the model's accuracy. [ABSTRACT FROM AUTHOR]

Major Depressive Disorder (MDD) is characterized by low mood, loss of interest and even suicidal ideation. Electroencephalogram based diagnosis of a variety of neurological conditions has been conducted in recent years using modern neurocomputing and deep learning approaches. Privacy is a high concern for medical data over distributed training scenarios. Hence, this paper aims to develop an EEG-based privacy-preserved system to identify MDD through the Federated Learning (FL) approach. In this study, training for 3-channel EEG-based MDD screening is introduced over FL using deep learning (DL) algorithms such as Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), Gated Recurrent Unit (GRU), and One Dimensional Convolutional Neural Network (1D-CNN). A privacy-preserving solution for MDD patients utilizing FL is advantageous because clinical data is sensitive and most people do not want to share their personal information. Hence, the analysis of the comparative results for multiple applicable strategies including Independent and Identically Disturbed (IID) data, non-IID data, and algorithms provide proof that FL can be used to train DL models. The MODMA dataset of 3-channel EEG with 26 MDD and 29 non-MDD individuals is used in this paper. Future study on MDD has several potential areas of use and these FL approaches can also be coupled with new technologies. [ABSTRACT FROM AUTHOR]

The chromatic index , χ ′ (G) , is the smallest integer k for which a graph G has a proper edge coloring. The Classification Problem involves determining whether a graph G is Class 1 ( χ ′ (G) = Δ (G)) or Class 2 ( χ ′ (G) = Δ (G) + 1). It is known that subgraph-overfull graphs must be Class 2. In this paper we are concerned with the Classification Problem for split graphs G [ Q ∪ S ] where Q is a clique and S is an independent set. When Δ (G) is odd, G is known to be Class 1. The original proof presented by Chen et al. (1995) has a minor flaw which we detail in this paper while also clarifying that it does not compromise their result. We prove that their technique can be adapted in a non-trivial way to show that some split graphs with even Δ (G) are also Class 1. We show that to solve the Classification Problem for split graphs it suffices to consider that all vertices in Q have degree Δ (G). Considering the subset X of S of the vertices of degree at most Δ (G) / 2 , we show that if the neighborhood of X has at least ⌊ | Q | / 2 ⌋ vertices, then G is Class 1; in the remaining cases we characterize the subgraph-overfull split graphs. • Correction of a flaw in the proof that odd maximum degree split graphs are Class 1. • Proof that certain split graphs with even maximum degree are Class 1. • Characterization of the split graphs which are subgraph-overfull, and thus Class 2. [ABSTRACT FROM AUTHOR]

Phishing emails, which masquerade as legitimate correspondence, are a significant modern hazard that cybercriminals use to deceive people into disclosing personal information. This paper presents the complex tactics used by cyber adversaries in the always changing field of phishing detection by using a real-time dataset and sophisticated classification tools to thoroughly examine email properties. In addition to detection, this paper highlights the need for constant watchfulness, delves into the psychological and social engineering elements included in phishing emails, and promotes continuous user awareness. Furthermore, the research broadens its scope to encompass the wider implications for enterprises, clarifying possible financial and reputational fallout. It offers helpful advice on strengthening defences and acts as a crucial manual for protecting private and corporate data against the ever-changing and persistent danger landscape that phishing attempts provide. This research gives an exploration of new insights by cybercriminals used for insertion of malicious software using emails. By using attributes like email text, Email type, the research identifies the signs of fraud emails. [ABSTRACT FROM AUTHOR]

Condition monitoring and predictive maintenance applications receive ongoing scientific attention in production technology. Larger companies, especially machine and component manufacturers, already offer related products. Small and medium-sized enterprises (SMEs) in particular show interest in developing and offering solutions in this market themselves to gain economic advantages, to improve resource utilization of their machines or to be able to offer these advantages to their own customers. In the development process, however, they often encounter problems already in the digitization of the machines. The first hurdle is to obtain an analysis-capable data set. This is due to the fact that common and established general data mining development process models, such as CRISP-DM, do not focus on production technology, causing difficulties for engineers during deployment. A problem with existing process models is the limited practicality in the engineering domain due to restricted adaptability. In a previous paper, a guideline for engineers for data mining suitable digitization of production machines was developed in order to solve these problems. The related results were provided in the context of a project for condition monitoring of mixing machines. In this paper, the proposed method is applied to components of a 5-axis CNC milling machine in three different monitoring use cases. A complete workflow is presented, including effect analysis, sensor selection, formulation of predictive scenarios, data preparation, training of machine learning algorithms and vizualization. Data and documentation are provided alongside this publication. [ABSTRACT FROM AUTHOR]

Cancer is a condition in which abnormal cells uncontrollably split and damage the body tissues. Hence, detecting cancer at an early stage is highly essential. Currently, medical images play an indispensable role in detecting various cancers; however, manual interpretation of these images by radiologists is observer-dependent, time-consuming, and tedious. An automatic decision-making process is thus an essential need for cancer detection and diagnosis. This paper presents a comprehensive survey on automated cancer detection in various human body organs, namely, the breast, lung, liver, prostate, brain, skin, and colon, using convolutional neural networks (CNN) and medical imaging techniques. It also includes a brief discussion about deep learning based on state-of-the-art cancer detection methods, their outcomes, and the possible medical imaging data used. Eventually, the description of the dataset used for cancer detection, the limitations of the existing solutions, future trends, and challenges in this domain are discussed. The utmost goal of this paper is to provide a piece of comprehensive and insightful information to researchers who have a keen interest in developing CNN-based models for cancer detection. [ABSTRACT FROM AUTHOR]

Ethno-pedology, the systematic definition and classification of indigenous technical knowledge of soil attributes, has often ignored scientific knowledge of soil properties. This paper considers one ethno-pedological class, cesa–goz soils, managed by Kanuri and Shuwa Arab peoples in the Kala–Balge region, northeast Nigeria. Soil micromorphology demonstrates that these soils have been managed in different ways over extended periods, defined by optically stimulated luminescence (OSL) dating. This has resulted in discrete soil types, indicating that ethno-pedological soil classification can be enhanced by integrating it with scientifically defined soil properties and chronologies. These observations carry major implications for the application of ethno-pedology approaches to land management development and the understanding of landscape history. [Copyright &y& Elsevier]

This paper focuses on the classification problem of multi-view data, aiming to improve the classification accuracy of current algorithms on multi-view data. Previous multi-view classification algorithms are usually based on exploiting the complementarity of different views and fusing features from different views. A representative category is the graph-based method, which builds a graph matrix for each view, and then fuses the graph matrices of different views to obtain a unified graph. These methods have the following problems: firstly, the graph matrix is simply based on sample similarity usually; secondly, the learned graph matrix does not change dynamically; thirdly, the weight of the graph representation matrix for a single view cannot be learned in the unified graph matrix. Therefore, this paper designs a Two-step classification algorithm based on Dynamic Graph-ELM, called TSDGELM. In the TSDGELM, the dynamic Graph-ELM is used to obtain the graph representation matrix of each view to save the local neighbor information of the data, and then a joint graph learning algorithm is designed based on the GBS (Graph-Based System) mechanism to fuse the graph matrix of the single-view, and finally the united graph is input into the classifier. To evaluate the effectiveness of the proposed method in this work, we conduct a series of experiments on eight datasets, and the results demonstrate the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

• The DTFA method showed higher extraction and classification accuracy compared to the SVM and k-means++ methods. • HY-1C has the most effective extraction, followed by Landsat 8. • Landsat 8 is able to extract new ice, grey ice, and grey-white ice with the best effect, while HY-1C has a better effect in extracting white ice. MODIS data has advantages in coverage and data updating. This paper presents the extraction and classification of sea ice in the Yellow and Bohai seas using multi-source remote sensing products, including Landsat 8, HY-1C, and MODIS. We propose a Dynamic Thresholding Fully Automated (DTFA) method for sea ice extraction and classification. The accuracy of sea ice extraction and classification is evaluated using four metrics: confusion matrix accuracy rate, overall accuracy, user accuracy, and kappa coefficient. The DTFA method showed higher extraction and classification accuracy compared to the SVM and k-means++ methods. HY-1C has the most effective extraction, followed by Landsat 8. Landsat 8 is able to extract new ice, grey ice, and grey-white ice with the best effect, while HY-1C has a better effect in extracting white ice. MODIS data has advantages in coverage and data updating. Finally, the fusion of multi-source remote sensing images was used to obtain the sea ice extent of the entire Chinese offshore. This method is also applicable to remote sensing monitoring of sea ice in other sea areas. [ABSTRACT FROM AUTHOR]

The objective of this paper is twofold. First, I present a framework called historical coherentism (Chang, 2004; Tal, 2016; Van fraassen 2008) and argue that it is the best epistemological framework available to tackle the problem of coordination, an epistemic conundrum that arises with every attempt to provide empirical content to scientific theories, models or statements. Second, I argue that the problem of coordination, which has so far been theorized only in the context of measurement practices (Reichenbach, 1927; Chang, 2001; Tal, 2012; Van fraassen 2008), can be generalized beyond the philosophy of measurement. Specifically, it will be shown that the problem is embodied in classificatory practices and that, consequently, historical coherentism is well suited to analyze these practices as well as metrological ones. As a case study, I look at a contemporary debate in phylogenetics, regarding the evolutionary origin of a newly identified archaeal phylum called Methanonatronarchaeia. Exploring this debate through the lens of historical coherentism provides a detailed understanding of the dynamics of the field and a foothold for critical analyses of the standard rationale used by practitioners. [ABSTRACT FROM AUTHOR]

• There are at least ten different methods to classify bloodstain patterns. • Most of the current methods are mechanistic and prone to contextual bias. • A lack of clearly defined, unambiguous classification criteria is a key limitation. • An unambiguous method for bloodstain classification resolves current limitations. • Further research in statistical descriptions and fluid dynamics is required. Classifying bloodstains is an essential part of Bloodstain Pattern Analysis. Various experts have developed methods. Each method considers the same basic bloodstain pattern types. These use either terminology based on the observable characteristics or the mechanistic cause of the bloodstain patterns as part of the classification process. This review paper considers ten classification methods from fourteen sources, which are used to classify bloodstain patterns. There are fundamental differences in how the patterns are classified, how differentiated the classification is, and whether the classification process uses clear, unambiguous criteria, and is susceptible to contextual bias. Experts have also reported issues with classifying bloodstains that have indistinguishable features. These differences expose key limitations with current classification methods: mechanistic terminology is too heavily relied on, and the classification process is susceptible to contextual bias. The development of an unambiguous classification method, based on directly observable characteristics within bloodstain patterns is recommended for future work. [ABSTRACT FROM AUTHOR]

The heart's study holds paramount importance in human physiology, driving valuable research in cardiovascular health. However, assessing Electrocardiogram (ECG) analysis techniques poses challenges due to noise and artifacts in authentic recordings. The advent of machine learning systems for automated diagnosis has heightened the demand for extensive data, yet accessing medical data is hindered by privacy concerns. Consequently, generating artificial ECG signals faithful to real ones is a formidable task in biomedical signal processing. This paper introduces a method for ECG signal modeling using parametric quartic splines and generating a new dataset based on the modeled signals. Additionally, it explores ECG classification using three machine learning techniques facilitated by Orange software, addressing both normal and abnormal sinus rhythms. The classification enables early detection and prediction of heart-related ailments, facilitating timely clinical interventions and improving patient outcomes. The assessment of synthetic signal quality is conducted through power spectrum analysis and cross-correlation analysis, power spectrum analysis of both real and synthetic ECG waves provides a quantitative assessment of their frequency content, aiding in the validation and evaluation of synthetic ECG signal generation techniques. Cross-correlation analysis revealing a robust correlation coefficient of 0.974 and precise alignment with a negligible time lag of 0.000 s between the synthetic and real ECG signals. Overall, the adoption of quartic spline interpolation in ECG modeling enhances the precision, smoothness, and fidelity of signal representation, thereby improving the effectiveness of diagnostic and analytical tasks in cardiology. Three prominent machine learning algorithms, namely Decision Tree, Logistic Regression, and Gradient Boosting, effectively classify the modeled ECG signals with classification accuracies of 0.98620, 0.98965, and 0.99137, respectively. Notably, all models exhibit robust performance, characterized by high AUC values and classification accuracy. While Gradient Boosting and Logistic Regression demonstrate marginally superior performance compared to the Decision Tree model across most metrics, all models showcase commendable efficacy in ECG signal classification. The study underscores the significance of accurate ECG modeling in health sciences and biomedical technology, offering enhanced accuracy and flexibility for improved cardiovascular health understanding and diagnostic tools. [ABSTRACT FROM AUTHOR]

Thanks to its richness in extractable features, Hyperspectral images (HSI) find an accelerated use in medical, industrial, agricultural, and environmental fields. In this paper, we present a wavelet-based reduction technique that creates a Hypercube containing the most significant features extracted from the original HSI and representing a multi-dimensional array that is utilized for training a Convolutional Neural Network (CNN), which is designed here to classify different types of surfaces or materials. The performance of this approach is tested and proved using two distinct datasets. Then, we compare the same approach with the PCA, a widely used reduction method. The most important contribution of this paper is the implementation of an FPGA-based parallel accelerator to train the same suggested CNN in only 10% of the computational time compared to the classical CPU-based techniques. The Microblaze will be explained and exploited here to play the role of an embedded microprocessor. • A Wavelet-based technique gives a reduced Hypercube rich in pixels spectrum features. • A CNN is designed to classify different types of surfaces or materials. • An FPGA-based parallel design is created to reduce 90% of the CNN training time. • The Microblaze is used to play the role of an embedded microprocessor. [ABSTRACT FROM AUTHOR]

Multi-label classification has recently attracted research interest as a data mining task. Many current applications in data mining address problems that have instances belonging to more than one class. This requires the development of new efficient methods. Instance selection has been used in multi-label learning to improve the execution time and classification performance of many learning methods. Following the single-label approach, instance selection has been applied by selecting or unselecting the same instances for all labels. In this paper, we present a different and novel approach. An instance might be useful for some labels and harmful for others; therefore, our algorithm allows each instance to be discarded, selected, or only partially selected for use in the classification of certain labels. An extensive comparison using 45 datasets shows the usefulness of our approach in improving the current instance selection methods for multi-label problems, as well as the ability of our algorithm to compete with other more complex multi-label classification methods. • This paper presents a new framework for instance selection for multi-label datasets. • The method improves several state-of-the-art methods. • The method is scalable to large multi-label datasets. • Interesting new research lines are opened by the framework. [ABSTRACT FROM AUTHOR]

• To introduce BCOHHS for wrapper-based feature selection • A binary using the X-shaped function of the hybrid, HHO, with chaotic opposition-based initialization and simulated annealing • Evaluated the performance of the BCOHHS using high-dimensional medical data sets Harris Hawks Optimization (HHO) is a relatively new meta-heuristic algorithm that has shown promise in solving various optimization problems. However, HHO suffers from some limitations that can affect its performance. The two main drawbacks of HHO are population diversity and local optima. To overcome these limitations and adapt it to solve feature selection issues, a new meta-heuristic, Chaotic Opposition Harris Hawks Optimization with Simulated Annealing (COHHS), is proposed in this paper. Two main improvements are proposed for the HHO. The first one, the chaotic opposition, is applied at the initialization phase of HHO to improve the population diversity of the search agents. The second one, simulated annealing, is applied to find the optimal solution during each iteration to improve HHO exploitation. The proposed method is a dynamic structure that was originally designed to solve problems with continuous optimization. In this paper, we propose a binary COHHS (BCOHHS) using X-shaped functions to boost the efficiency of feature selection. The KNN classifier is used to evaluate the classification accuracy. The performance of the proposed method is evaluated on nine high-dimensional medical datasets and compared with other optimization methods. The experimental results confirm the superiority of the BCOHHS method over the other methods on the majority of the datasets. [ABSTRACT FROM AUTHOR]

With the rapid development of information technology, knowledge management has become an important means for enterprises, organizations, and individuals to gain advantages in competition. The design and implementation of Knowledge management is one of the key links of knowledge management. This paper discussed the design of Knowledge management based on Support Vector Machine (SVM), in order to improve the efficiency and quality of knowledge management. This paper introduced the application of SVM in Knowledge management, and discussed how to design an excellent Knowledge management. The research results showed that the response time of the Knowledge management designed in this paper was 87 seconds when the number of users was 300. When the number of users exceeded 300, although the response time was longer, its growth rate slowed down. SVM can be used in knowledge classification, entity recognition and relationship extraction, and can greatly improve the efficiency of Information extraction and knowledge management. [ABSTRACT FROM AUTHOR]

In the known Interval Scheduling problem with Machine Availabilities (ISMA), each machine has a contiguous availability interval, and each job has a specific time interval which has to be scheduled. The objective is to schedule all jobs such that the machines' availability intervals are respected or to decide that there exists no such schedule. We extend ISMA by introducing machine capacities and flexible machine end times. Using machine capacities we model parallel processing of multiple jobs per machine, which leads to the Multithread Interval Scheduling with Machine Availabilities (MISMA). Limited machine availabilities are usually due to maintenance. Time slots for maintenance at the end of a processing period are often predetermined by staff schedules before the slots are assigned to specific machines. This motivates a variant of MISMA in which the end times of the machines' availability intervals can be permuted, the Flexible Multithread ISMA (FLEXMISMA). In this paper, we determine a tight classification of conditions that are required for obtaining a polynomial-time algorithm for both MISMA and FLEXMISMA. More specifically, we show that FLEXMISMA is at least as hard as MISMA. For FLEXMISMA, we present polynomial-time algorithms for instances (i) with at most two available machines at a time, and (ii) with constantly many parallel jobs at each point in time, which both also solve MISMA; (iii) with arbitrarily many machines of capacity one each, in which case MISMA is known to be NP -hard; and (iv) with jobs having length one or two, for which the complexity of MISMA remains open Furthermore, we complement result (i) by showing that both problems are NP -hard already for instances with three machines as a special case of the Vertex-Disjoint Paths problem. In contrast to (iii), we prove that increasing the capacity of machines from one to two renders FLEXMISMA NP -hard as well for arbitrarily many machines. [ABSTRACT FROM AUTHOR]

In this paper, we study the representation of an infinite-dimensional Lie algebra C related to the q-analog Virasoro-like Lie algebra. We give the necessary and sufficient conditions for the highest weight irreducible module V (ϕ) of C to be a Harish-Chandra module. We prove that the Verma C -module V ¯ (ϕ) is either irreducible or has the corresponding irreducible highest weight C -module V (ϕ) that is a Harish-Chandra module. We also give the maximal proper submodule of the Verma module V ¯ (ϕ) and the e -character of the irreducible highest weight C -module V (ϕ) when the highest weight ϕ satisfies some natural conditions. Furthermore, we give the classification of the Harish-Chandra C -modules with nontrivial central charge. [ABSTRACT FROM AUTHOR]

In this paper, based on the Diophantine equation technique, we first prove the circulant graph C (Z n , { k 1 , k 2 }) is isomorphic to the disjoint union of gcd (n , k 1 , k 2) identical graphs, which belong to one of the three types of graphs: (i) C (Z n { 1 , k }) ; (i i) the Cartesian graph bundle C s □ φ C t over cycles; (i i i) the Cartesian product of the complete graph K 2 and a cycle. Naturally, to study the dispersability of C (Z n , { k 1 , k 2 }) can be reduced to study that of the above three types. Next, we solve the dispersability of the circulant graph C (Z n , { 1 , k }). Specifically, C (Z n , { 1 , k }) is dispersable if it is a bipartite; otherwise, it is nearly dispersable. In addition, we prove that bipartite circulant graphs are dispersable. [ABSTRACT FROM AUTHOR]

Airborne hyperspectral images can be used to map the land cover in large urban areas, thanks to their very high spatial and spectral resolutions on a wide spectral domain. While the spectral dimension of hyperspectral images is highly informative of the chemical composition of the land surface, the use of state-of-the-art machine learning algorithms to map the land cover has been dramatically limited by the availability of training data. To cope with the scarcity of annotations, semi-supervised and self-supervised techniques have lately raised a lot of interest in the community. Yet, the publicly available hyperspectral data sets commonly used to benchmark machine learning models are not totally suited to evaluate their generalization performances due to one or several of the following properties: a limited geographical coverage (which does not reflect the spectral diversity in metropolitan areas), a small number of land cover classes and a lack of appropriate standard train/test splits for semi-supervised and self-supervised learning. Therefore, we release in this paper the Toulouse Hyperspectral Data Set that stands out from other data sets in the above-mentioned respects in order to meet key issues in spectral representation learning and classification over large-scale hyperspectral images with very few labeled pixels. Besides, we discuss and experiment self-supervised techniques for spectral representation learning, including the Masked Autoencoder (He et al., 2022), and establish a baseline for pixel-wise classification achieving 85% overall accuracy and 77% F1 score. The Toulouse Hyperspectral Data Set and our code are publicly available at www.toulouse-hyperspectral-data-set.com and www.github.com/Romain3Ch216/tlse-experiments/ , respectively. [ABSTRACT FROM AUTHOR]

Conventional classification assumes a balanced sample distribution among classes. However, such a premise leads to biased performance over the majority class (with the highest number of instances). The Twin Support Vector Machines (TWSVM) obtained great prominence due to their low computational burden compared to the standard SVM. Besides, traditional machine learning seeks methods whose solution depends on a convex problem or semi-positive definite similarity matrices. Yet, this kind of matrix cannot adequately represent many real-world applications. The above defines the need to use non-negative measures as an indefinite function in a Reproducing Kernel Kreĭn Space (RKKS). This paper proposes a novel approach called Kreĭn Twin Support Vector Machines (KTSVM), which appropriately incorporates indefinite kernels within a TWSVM-based gradient optimization. To code pertinent input patterns within an imbalanced data discrimination, our KTSVM employs an implicit mapping to a RKKS. Also, our approach takes advantage of the TWSVM scheme's benefits by creating two parallel hyperplanes. This promotes the KTSVM optimization in a gradient-descent framework. Results obtained on synthetic and real-world datasets demonstrate that our solution performs better in terms of imbalanced data classification than state-of-the-art techniques. • Kreĭn Twin Support Vector Machines (KTSVM) enhances nonlinear TWSVM with indefinite kernels for imbalanced classification. • KTSVM represents high dimensions with indefinite kernels, improving imbalanced classification. • Our approach transforms the traditional TWSVM's convex dual problem into a gradient-based optimization. • KTSVM builds dual hyperplanes in RKKS, refined with gradient descent. • KTSVM excels over SVM, KSVM, and TWSVM in binary imbalanced classification. [ABSTRACT FROM AUTHOR]

In the era of big data processing, numerous techniques prove valuable for analyzing large-scale datasets. However, the efficient processing of small data is equally crucial, particularly in the context of intelligent mobile systems. This importance stems from resource constraints, real-time requirements, privacy concerns, and the emergence of edge computing paradigms. In this paper, we adapt an existing input doubling method to address classification tasks when facing limited training datasets. The proposed solution is implemented by modifying the procedure for aggregating predicted values, based on the principles of majority voting. This approach differs significantly from the existing method, which relies on averaging prediction results. A flowchart of the adapted method is presented, detailing the procedures for training and application based on the use of a plurality voting scheme. Modeling is conducted on a short, imbalanced dataset for solving express diagnostic tasks in the field of transplantology. The results demonstrate the high effectiveness of employing the adapted input doubling method for classification tasks in transplantology, where acquiring a substantial training dataset for analysis is challenging. [ABSTRACT FROM AUTHOR]

• Introduced the Siamese 4D-Alznet, which combines five distinct blocks of CNNs. • We proposed three custom TL models incorporating frozen and replacing layers. • Our methods prove 95.07% binary classification performance in terms of accuracy. • All techniques performed best for NC, EMCI, LMCI, and AD classification. Alzheimer's disease (AD) is the general form of dementia, leading to a progressive neurological disorder characterized by memory loss due to brain cell damage. Artificial Intelligence (AI) assists in the early identification and prediction of AD patients, determining future risks and benefits for radiologists and doctors to save time and cost. Since deep learning (DL) approaches work well with massive datasets and have recently become helpful for AD detection, there remains an area for improvement in automating detection performance. Present approaches somehow addressed the challenges of limited annotated data samples for binary classification. This contrasts with prior state-of-the-art techniques, which were constrained by their incapacity to capture abstract-level information. In this paper, we proposed a Siamese 4D-AlzNet model comprised of four parallel convolutional neural network (CNN) streams (Five CNN layer blocks) and customized transfer learning models (Frozen VGG-19, Frozen VGG-16, and customized AlexNet). Siamese 4D-AlzNet was vertically and horizontally stored, and the spatial features were passed to the final layer for classification. For experiments, T1-weighted MRI images comprised of four distinct subject classes, normal control (NC), mild cognitive impairment (MCI), late mild cognitive impairment (LMCI), and AD, have been employed. Our proposed models achieved outstanding accuracy, with a remarkable 95.05% accuracy distinguishing between normal and AD subjects. The performance across remaining binary class pairs consistently exceeded 90%. We thoroughly compared our model with the latest methods using the same dataset as our reference. Our proposed model improved NC-AD and MCI-AD classification accuracy by 2% 7%. [ABSTRACT FROM AUTHOR]

This paper introduces the problematic of the sensitive business processes (SBP) modeling. First of all, we propose a characterization of SBP (which distinguishes it from classic, structured and conventional BPs). Secondly, we the different SBP modeling aspects and requirements to develop expressive, comprehensive and rigorous models. Besides, we present an in-depth study of the different modeling approaches and languages, in order to analyze their expressiveness and their ability to perfectly and explicitly represent the new specific requirements of SBP modeling. In this study, we choose the better one positioned nowadays, BPMN 2.0, as the best suited standard for SBP representation. [ABSTRACT FROM AUTHOR]

A review of the literature in the field of CSCW shows that the adoption of Enterprise Collaboration Systems (ECS) is challenging and that there is a need for a structured approach for their implementation. The IRECS Framework (Identification of Requirements for Enterprise Collaboration Systems), described in this paper, addresses this call in the form of a comprehensive classification of the digital support of collaborative work and a complementary taxonomy of empirically observed examples. The IRECS classification comprises five layers – from a high-level business view of collaborative work to a detailed consideration of the software modules that fulfil the functional requirements. The development of the framework followed a ten-year Design Science Research process. The framework is designed to serve the needs of researchers and practitioners alike. The detailed classification provides a valuable analytical lens for research. The framework and its concrete examples can also be used in practice as a guidance and checklist in the software selection process of organisations. [ABSTRACT FROM AUTHOR]

To improve convergence speed of deep neural network trained by gradient descent methods (GDMs), this paper proposed a novel fractional order gradient descent optimizer (FOAdam) based on Caputo operator and Adam algorithm, and analyzed the impact of fractional order on convergence performance using optimization theory and simulation. Furthermore, to address the trade-off between convergence speed and precision under fixed-order conditions, a fractional order scheduler (FOS) was designed based on the Connections Cloud Model (CCM). Numerical experiments conducted on MNIST and CIFAR-10 datasets showed that FOS-FOAdam outperformed other mainstream GDMs in terms of convergence speed and precision. Finally, FOS-FOAdam was applied in recognizing and classifying image datasets of cuttings and cores at the logging site, demonstrating good prospects for practical engineering applications. [ABSTRACT FROM AUTHOR]

Automatic identity recognition from ear images is an active research topic in the biometric community. The ability to secretly acquire images of the ear remotely and the stability of the ear shape over time make this technology a promising alternative for surveillance, authentication, and forensic applications. In recent years, significant research has been conducted in this area. Nevertheless, challenges remain that limit the commercial use of this technology. Several phases of the ear recognition system have been studied in the literature, from ear detection, normalization, and feature extraction to classification. This paper reviews the most recent methods used to describe and classify biometric features of the ear. We propose a first taxonomy to group existing approaches to ear recognition, including 2D, 3D, and combined 2D and 3D methods, as well as an overview of historical advances in this field. It is well known that data and algorithms are the essential components in biometrics, particularly in-ear recognition. However, early ear recognition datasets were very limited and collected in laboratory with controlled environments. With the wider use of deep neural networks, a considerable amount of training data has become necessary if acceptable ear recognition performance is to be achieved. As a consequence, current ear recognition datasets have increased significantly in size. This paper gives an overview of the chronological evolution of ear recognition datasets and compares the performance of conventional vs. deep learning methods on several datasets. We proposed a second taxonomy to classify the existing databases, including 2D, 3D, and video ear datasets. Finally, some open challenges and trends are debated for future research. [ABSTRACT FROM AUTHOR]

Many research studies confirmed that the application of machine learning methods for predicting students at risk of academic failure can be beneficial for improving student performance in higher education institutions. Simultaneously, these studies emphasised the importance of the input data quality, its precise pre-processing and thoroughly selected features on final performance metrics of the applied classification algorithms. However, the stand-alone application of well-known classification algorithms still has performance limitations, which can be outperformed using ensembles of classifiers. Therefore, this paper aims to evaluate the overall contribution of the selected ensemble methods to the early prediction of students at risk of dropping out of learning courses. All phases of CRISP-DM methodology are described in this study to explain the complexity of the problem of the practical adoption of voting-based heterogeneous ensemble methods in the case of data obtained from the course of the university learning management system compared to traditional classification algorithms enhanced by ensemble learning with AdaBoost and XGBoost methods. As a result, the study confirmed that the features which characterise the students' performance and their interactions in the course can be considered the most significant for the identification of the students at risk of dropping out. Moreover, in the case of advanced ensemble algorithms, the overall accuracy, recall, precision, and f1 score were improved by 2-4%. The proposed method has demonstrated exceptional performance. Finally, the paper summarises the findings and their implications for effective prediction. [ABSTRACT FROM AUTHOR]

In recent years, Natural Language Processing (NLP) has gained significant attention, and sentiment analysis is an essential subfield of NLP that deals with identifying the sentiment or emotion conveyed in the text. Tolerance near sets (TNS) is a mathematical framework that has shown promising results in sentiment analysis tasks. However, the choice of word embeddings can significantly impact the performance of TNS-based classifiers. This paper investigates the impact of using different embeddings on the performance of tolerance near sets-based sentiment classifiers. This paper compares the use of different embeddings, including DistilBERT, MiniLM, and Word Embeddings, and their combinations, to understand their impact on TNS-based sentiment analysis. The TSC 2.0 model proposed in this paper achieves a weighted F1 score of 92.1% in one of the datasets, an improvement due to the sentence embeddings used. Experimental results have led to the observation that tie-breaking and variance-based classification may have led to a noticeable improvement in cases with more than three. [ABSTRACT FROM AUTHOR]

• A research article on detection and classification of various types of disfluencies such as Interjection, Sound Repetition, Word Repetition, Phrase Repetition, Revision and Prolongation is presented. • Various feature extraction techniques have been discussed for extracting meaningful information about the speech signals. • Various Machine learning algorithms have studied and analyzed to detect and classify the disfluencies in speech. • Various future research challenges in the present research are highlighted. Speech plays a vital role in communication, from expressing oneself, to utilizing speech-based platforms, speech is a necessity. Any disruption in speech is referred to as disfluency, and can impact one's quality of life. This paper presents an experimental study on various techniques for the detection and classification of speech disfluencies. Six different types of disfluencies are examined in this paper, namely Interjection, Sound Repetition, Word Repetition, Phrase Repetition, Revision and Prolongation (6 classes). However, this paper also goes a step further by including the clean speech signals as an added class alongside the six disfluencies, thereby making this work more robust with 7 classes. Various machine learning approaches have been investigated on the University College London Archive of Stuttered Speech (UCLASS) dataset; a standard disfluency dataset generated by University College London (UCL). Five different feature extraction techniques viz. Mel Frequency Cepstral Coefficients (MFCC), Linear Predictive Cepstral Coefficients (LPCC), Gammatone Frequency Cepstral Coefficients (GFCC), Mel-filterbank energy features, and Spectrograms have been used. Comparative analysis of various classifiers shows that MFCC, GFCC, and Spectrograms achieved greater than 90% accuracy on both 6 and 7 classes with the kNN classifier. As a future scope to this study, the authors aim to focus on tackling the challenges of detecting multiple disfluencies present simultaneously in a speech sample. [ABSTRACT FROM AUTHOR]

In this paper we describe the design and the ideas motivating a new Continual Learning benchmark for Autonomous Driving (CLAD), that focuses on the problems of object classification and object detection. The benchmark utilises SODA10M, a recently released large-scale dataset that concerns autonomous driving related problems. First, we review and discuss existing continual learning benchmarks, how they are related, and show that most are extreme cases of continual learning. To this end, we survey the benchmarks used in continual learning papers at three highly ranked computer vision conferences. Next, we introduce CLAD-C, an online classification benchmark realised through a chronological data stream that poses both class and domain incremental challenges; and CLAD-D, a domain incremental continual object detection benchmark. We examine the inherent difficulties and challenges posed by the benchmark, through a survey of the techniques and methods used by the top-3 participants in a CLAD-challenge workshop at ICCV 2021. We conclude with possible pathways to improve the current continual learning state of the art, and which directions we deem promising for future research. • A review of current continual learning benchmarks and their relations to one-another. • Proposal of two new real-world continual learning benchmarks. • Review of the most successful ICCV'21 challenge entries on the new benchmarks. [ABSTRACT FROM AUTHOR]

• This paper proposes a novel Multi-scale self-attention mixup approach for graph classification. • This paper innovatively introduces multi-scale graph representation for Mixup. • A novel self-attention strategy is proposed to capture the internal dependencies between different scales within a graph. • Extensive experiments are conducted to demonstrate the effectiveness of the proposed MSSA-Mixup. [Display omitted] Data augmentation can effectively improve the generalization performance of neural networks. However, data augmentation for the graph domain is challenging due to the fact of irregular nature of the special non-Euclidean structure. In this paper, we propose a novel graph data augmentation solution, Multi-Scale Self-Attention Mixup (MSSA-Mixup), which extends the training distribution by interpolating multi-scale graph representation with self-attention. The MSSA-Mixup improves the generalization ability of graph neural networks (GNNs) effectively. Extensive experiments illustrate that the proposed method yields consistent and robust performance boost across graph classification tasks on the frequently-used benchmark datasets. [ABSTRACT FROM AUTHOR]

Big data analytics uncovers hidden patterns through classification, prediction and reinforcement of big datasets. In these datasets, some features have a negligible connection with other features and some may be insignificant as their presence does not impact the results of big data analytics. The algorithms of big data analytics generate better classification models when supplied with a dataset consisting of relevant, important and informative features. These features can be classified as important and unimportant. For the selection of important features, different filtrations techniques are used. These techniques filter features on different basis like information gain, information dispersion, Gini index, etc. and have a few drawbacks reviewed in this paper. The first contribution of this paper is to propose a new feature selection technique named "Relevance-diversity algorithm" for selecting important features based on two measures i.e. relevance and diversity for optimizing features as low as possible and reducing the search time used in feature selection. The second contribution of the paper is that it proposes a new supervised classification algorithm based on Naive Bayes classification. The assumption of naive i.e. feature independence is discarded from the algorithm of Naive Bayes classification. The features are considered to be dependent on each other and their combined impact on the class value is evaluated. The newly proposed classification algorithm is then applied to the features selected through the relevance-diversity based feature selection technique. The datasets of Weather, Tic-Tac-Toe, Lenses, Balance-scale and CarEval are used for the evaluation of both the techniques. The results of the proposed feature selection method are compared with the existing methods and the results of Modified-Bayes are compared with the existing Naive Bayes algorithm. Analysis revealed that the proposed method performed better in terms of the number of features, accuracy and time complexity. [ABSTRACT FROM AUTHOR]