Use Of Classification Research Articles

Evaluating EHS parastomal hernia classification for surgical planning: a retrospective analysis of 160 consecutive cases in a single center.

Parastomal hernia (PH) is a prevalent complication following ostomy formation, presenting significant challenges in surgical management. This study aims to validate the European Hernia Society classification for PH through the application of the Hybrid Parastomal Endoscopic Repair (HyPER) method. The study focuses on establishing the practical utility of the European Hernia Society classification in a clinical setting, particularly in guiding surgical approaches and improving patient outcomes. This retrospective observational study aimed to assess the utility of the European Hernia Society classification in planning surgical strategies for parastomal hernias. The validation of the classification of PH was based on the experience involving 160 patients in single center. Patients were classified according to the European Hernia Society criteria, and data were collected on patient demographics, clinical presentations, and surgical outcomes. Main goal was to assess the consistency and applicability of the European Hernia Society classification in predicting surgical challenges and outcomes. The study found a predominance of complex Type III and IV hernias. The European Hernia Society classification was effective in categorizing PH, aiding in surgical planning and highlighting the increased complication rates associated with more complex hernia types. This study represents the largest single-center cohort treated for PH by a single team, providing a controlled evaluation of the HyPER technique's effectiveness. The validation of the European Hernia Society classification in this study is a significant advancement in the standardization of PH management. The findings demonstrate the classification's utility in enhancing surgical planning and patient-centered care. The study also opens avenues for further research into standardized approaches and techniques in PH treatment.

Are light curve classification metrics good proxies for SN Ia cosmological constraining power?

When selecting a lc classifier for use as part of a photometric supernova Ia (SN Ia) cosmological analysis, it is common to make decisions based on metrics of classification performance, such as the contamination within the photometrically classified SN Ia sample, rather than a measure of cosmological constraining power. If the former is an appropriate proxy for the latter, this practice would save those designing an analysis pipeline from eliminate the computational expense of a full cosmology forecast in the analysis pipeline design process This study tests the assumption that lc classification metrics are an appropriate proxy for cosmology metrics. We emulated photometric SN Ia cosmology lc samples with controlled contamination rates of individual contaminant classes and evaluated each of them under a set of classification metrics. We then derived cosmological parameter constraints from all samples under two common analysis approaches and quantified the impact of contamination by each contaminant class on the resulting cosmological parameter estimates. We observe that cosmology metrics are sensitive to both the contamination rate and the class of the contaminating population, whereas the classification metrics are shown to be insensitive to the latter. Based on these findings, we discourage any exclusive reliance on classification-based metrics for analysis design decisions, which (counterintuitively) include but are not limited to the classifier choice. Instead, we recommend optimising science analysis pipeline design choices using a metric of the information gained about the physical parameters of interest.

Histiocytosis and adult-onset orbital xanthogranuloma in 2023: a review of the literature and mini case series.

Within the large umbrella of histiocytosis are a few similar yet heterogenous entities involving the orbit and periocular tissues with or without systemic infiltration, termed adult onset xanthogranuloma or orbital xanthogranuloma. Due to rarity of these conditions, different classifications in use, diverse clinical presentations and still unknown etiology, the aim of this paper was to provide an up-to-date literature review of the actual understanding of histiocytosis and its subgroups involving the orbit and periocular area, diagnostic strategies and therapeutic modalities. We present a review of literature and small case series comprising four patients diagnosed and treated in the period from 2001 until 2023 in our hospital. Clinical files of 4 patients with adult-onset xanthogranulomatous disease of the orbit and ocular adnexa (AOXGD) were reviewed retrospectively. Clinical, laboratory, radiological, histopathological, and immunohistochemical findings were reexamined. Reviewing medical records of our patients with AOXGD, we found significant overlap between histiocytosis and different immune disorders. A broad workup should be considered in these patients as they can harbour severe immune disfunctions and hematologic disorders. Preferred treatment modality depends on a histopathologic type of AOXGD, clinical presentation and systemic involvement and should be conducted multidisciplinary. The diagnosis is often delayed because of its rarity and diverse clinical findings. Development of molecular genetic tests, detection of BRAF V600E mutation and different types of kinase mutations, mutations in transcriptional regulatory genes as well as tyrosine kinase receptors have shed a new light on the etiopathogenesis and potential targeted treatment of histiocytosis.

Plant Leaf Disease Detection

Abstract: The research presents an automated vision a system that makes use of the processing of images techniques to identify plant diseases in agricultural contexts. In order to monitor vast crop fields and automatically identify disease symptoms as soon that they occur on plant leaves, research on automated identification of plant infections is crucial to the agricultural industry. This method uses segmentation, colour modifications, and masking of green pixels to classify data based on learning from some training examples of that category. The simulated outcome, in the end, demonstrates that the network classifier in use offers reduced training error and increased classification accuracy

SecureML Based Classification for Internet of Things Based Secured Transaction of Data

The Internet of Things (IoTs) is a rapidly developing technology that enables a wide range of applications to interact with each other. The IoT is an emerging technology that can be used to collect, and analyse data from various sources. In this paper, we present SecureML, a unique privacy-preserving CART training scheme that employs blockchain principles to develop a secure CART classifier for use in multipart scenarios in which data is collected from many data sources. SecureML uses the homomorphic cryptosystem to develop secure building blocks such as secure polynomial multiplication and safe comparison. The proposed method is capable of training classifiers in a risk-free manner while retaining an acceptable degree of accuracy.

Consensus classification of pediatric hepatocellular tumors: A report from the Children's Hepatic tumors International Collaboration (CHIC).

Liver tumors are rare in children with histologic heterogeneity that makes diagnosis challenging. Systematic histopathological review, performed as part of collaborative therapeutic protocols, identified relevant histologic subtypes that are important to distinguish. The Children's Hepatic tumors International Collaboration (CHIC) was established to study pediatric liver tumors on a global scale and led to establishment of a provisional consensus classification for use in international clinical trials. The current study is the validation of this initial classification and first large-scale application by international expert reviewers. The CHIC initiative includes data from 1605 children treated on eight multicenter hepatoblastoma (HB) trials. Review of 605 available tumors was performed by seven expert pathologists from three consortia (US, EU, Japan). Cases with discordant diagnoses were collectively reviewed to reach a final consensus diagnosis. Of 599 cases with sufficient material for review, 570 (95.2%) were classified as HB by all consortia, and 29 (4.8%) as non-HB, which included "hepatocellular neoplasm, NOS" and malignant rhabdoid tumors. 453 of 570 HBs were classified as epithelial by final consensus. Some patterns (i.e., small cell undifferentiated, macrotrabecular, cholangioblastic) were selectively identified by reviewers from different consortia. All consortia identified a similar number of mixed epithelial-mesenchymal HB. This study represents the first large-scale application and validation of the pediatric malignant hepatocellular tumors consensus classification. It is a valuable resource to train future generations of investigators on accurate diagnosis of these rare tumors and provides a framework for further international collaborative studies and refinement of the current classification of pediatric liver tumors.

Concordance of circulating and solid tumor DNA through comprehensive genomic profiling in a large integrated cancer network.

3059 Background: Comprehensive Genomic Profiling (CGP) of solid tumors is crucial in diagnosing and treating cancer patients. Circulating Tumor DNA (ctDNA) is a potential biomarker for detecting mutations when tissue samples are limited or unavailable. However, the sensitivity of ctDNA tests vary greatly, making concordance studies with tissue samples critical to validate clinical use. This study presents results of CGP in paired tumor tissue and plasma samples from representative cancer patients treated in a community-based, Integrated Network Cancer Program. Methods: Over 2000 cancer patients have provided solid tumor and/or blood samples to date including serial follow-up blood samples. To optimize ctDNA integrity, we collected blood using a membrane stabilizer (Streck), ensured courier transport in ≤ 72 hours, separated plasma via differential centrifugation x 3, extracted cell free DNA with magnetic beads, and performed Next Generation Sequencing (NGS) using the ct-TSO500 assay (Illumina). In cases where patients provided both a solid tumor and concurrent blood sample, st-TSO500 NGS results from the solid tumor were compared to the ctDNA results for these matching specimens. Clinical actionability of variants was determined using the OncoKB database at levels 1, 2, and R1. Results: 146 matched blood and solid tumor specimens were analyzed to date. CGP studies revealed 1179 ± 102 unique variants across 20 different cancer types. Coding mutations from these specimens averaged 183 ± 25 variants. The ctDNA contained 96.5% of initial variants (1088 ± 95) and 95.1% of coding mutations (163 ± 20) found in the respective matched solid tumor. 76 patients had one or more oncogenic mutations detected only in the ctDNA and 28 (36.8%) of these included an actionable anticancer pharmacotherapy. Concordance by selective tumor type for clinical oncogenic variants was 95.8% (prostate), 95.0% (pancreas), 92.8% (lung and ovarian), 90.0% (endometrium), 84.3% (colon) and 82.4% for breast cancer. There was no difference in concordance between stage IV (91.0%) and stage I-III (86.5%) tumors (p = 0.14). An average of 6.2 ± 2.5 oncogenic variants were detected in both ctDNA and tissue. 99.3% of all patients contained an oncogenic biomarker in both ctDNA and tissue assays. Conclusions: We developed a prospective tissue and plasma repository of patients across a large integrated cancer network. These data demonstrate high concordance between circulating and solid tumor DNA using an “in-house” CGP assay. With no loss of concordance across cancer stages, ctDNA can identify actionable mutations not found in solid tumor analysis. This study is an important step toward incorporating “in-house” ctDNA CGP into routine cancer care. Future goals are to utilize these data for development of novel prognostic and predictive classifiers for use in a community-based hospital system across various disease sites.

Methylation classifier array and classification of solitary fibrous tumors.

e23522 Background: Solitary fibrous tumors (SFTs) are fibroblastic tumors which carry a characteristic NAB2::STAT6 gene rearrangement. SFTs represent a heterogenous group that may arise in multiple locations and have variable risk of progression. Despite a consistent oncogenic driver, there is little biological data explaining this variability. Recently, the German Cancer Research Network (DKFZ) have modified their brain tumor methylation classifier for use in sarcomas. We subjected solitary fibrous tumors diagnosed at our institution to a validated, in-house sarcoma methylation array classifier modeled after that of the DKFZ in order to assess for differences in methylation patterns that may account for biological or clinical variances. Methods: Twenty-eight primary site SFTs from 2011-2021 were subjected to the sarcoma methylation classifier. Histologic diagnosis was confirmed by STAT6 immunohistochemistry or by the presence of the NAB2::STAT6 fusion. The methylation classifier was run on the Illumina iScan platform and the resulting IDAT files were analyzed via a custom bioinformatics pipeline. The sarcoma classifier was trained using the same samples and normalization strategies used by the DKFZ group and validated using the same publicly available samples. Results: Methylation data for each tumor was collected, given a classification score, and visualized by t-distributed stochastic neighbor embedding (t-SNE). We noted three distinct groups of SFTs on the t-SNE plot. Group 1 was comprised of all eight intracranial SFTs and were correctly classified as SFT (classifier score ≥0.9). Group 2 contained nine pleural-based tumors and one SFT each from the mediastinum and bladder wall. Classification was successful in only seven of eleven tumors. Group 3 SFTs predominantly arose in the soft tissues or bone (two pelvis, four extremity, and one mediastinum) and all failed accurate classification. Finally, two orbital SFTs stratified separately from all groups on t-SNE plot but did achieve an appropriate classification. There were no significant differences in grade or risk stratification among the three groups. Conclusions: Our preliminary data show differential clustering based on tumor location, suggesting biological differences between intracranial, pleural/visceral, and connective tissue locations. These results highlight the heterogeneity of these tumors and the inadequacy of the current methylation classification scheme for SFT. Future directions will include analysis of additional cases, gene expression patterns, and outcome data.

OP55 Classification System For Innovative Medicines In The Pipeline: New Or Repurposed?

IntroductionWhile various criteria exist to define or categorize innovative medicines as new or repurposed, to our knowledge there are no standardized systems that sufficiently capture the range of pipeline products. The National Institute for Health and Care Research Innovation Observatory (NIHR IO) undertakes routine horizon scanning to support health technology assessment (HTA) in England and maintains a comprehensive Medicines Innovation Database (MInD). The aim of this project is to develop a ‘technology type’ (new versus repurposed) classification system for application within the MInD and to provide a high-level analysis of the emergent data.MethodsWe reviewed gray literature, regulatory websites, and drug repositories to identify existing ‘technology type’ classification criteria. Preliminary definitions and classifications for use on the MInD were discussed, refined, and agreed by consensus. Innovative medicines on the MInD were classified as either new or repurposed based on their regulatory approval status (Marketing Authorization) using data from the electronic medicines compendium. For repurposed medicines, further classification was undertaken using abbreviated new drug application (ANDA) data from the FDA Orange Book to identify generic medicines (patency and exclusivity status). We combined a range of semi-automated and manually derived data during this process.ResultsSix technology types were identified and applied to the MInD: (i) new technology; (ii) repurposed technology (on-patent/branded); (iii) repurposed drug (off-patent/generic); (iv) repurposed technology (never commercialized); (v) new and repurposed technology (combinations); and (vi) repurposed technology (combinations). Preliminary analysis of a subset of MInD records identified in July 2021 (n = 113) found mainly 52 percent new technologies, 27 percent new and repurposed technologies (combinations) and 14 percent repurposed technology (never commercialized). Further analysis of approximately 7000 MInD records are ongoing and will report temporal trends, regulatory status, and key challenges.ConclusionsOur novel evidence-based approach to developing classifications for technology types of innovative medicines resulted in six mutually exclusive states that can be applied to a larger dataset. We believe this offers HTA stakeholders a mechanism to gain valuable insights into the innovation trends, gaps, and areas of unmet need.

Z세대 패션디자인전공 학생들의 가상 이미지 수용자 인식 분석

The purpose of this study is to analyze the types of acceptance preferences of Generation Z students majoring in fashion design for fashion images in Science Fiction(SF) films that reflect future fashion design trends in virtual space. Through this, it is meaningful to predict trends and consumption patterns for future fashion images and to inform fashion design education by classifying the characteristics, tastes, and emotions of Generation Z by various types of perception.
 The research is performed with the Q-methodology. Unlike quantitative methodologies based on scientific analysis and objective data, the Q methodology expects to fill the gap in error and values in research due to audience propensity through superficial characteristic analysis by studying the scope of an individual audience's subjective perception. The Q samples used in the Q methodology collected Q-Population through online and SF film-related papers, newspapers, and other magazines, and sampled 30 Q views of fashion images. The subjects of the study were 40 first- to fourthyear students in the textile&fashion design department of universities in the Seoul metropolitan area in August 2022. In this study, a distribution model on a 9-point scale was used for Q classification. Interviews were also conducted on the classification for use as in-depth data to verify the end-acceptor recognition analysis, and why +4 (strong consent) and -4 (strong rejection) responses were selected simultaneously. The program used for the analysis applied the PQ Method, and in the final result, only factors with an eigen value of 1 or more were extracted and applied to increase the validity of the analysis.
 As a result of the analysis, three final types were derived. The first is a realistic compromise type that emphasizes practicality and reflects actual fashion design preferences, The second is a future-oriented type that emphasizes artistic aspects ahead of the times, Lastly, the third is an adventure type that overcomes the future in the social direction.
 In conclusion, the decision-making process for efficiently performing fashion design work should include objectively analyzing design elements, public desires, and changing social phenomena, as well as harmonizing the creative and emotional capabilities of each fashion designer based on the data shown through objectification. The analysis of personal emotions, tastes, and perceptions of Generation Z fashion design students is expected to be an important research material for beneficial results of scientific emotional fashion images.

Automatic Vehicle Identification and Classification Model Using the YOLOv3 Algorithm for a Toll Management System

Vehicle identification and classification are some of the major tasks in the areas of toll management and traffic management, where these smart transportation systems are implemented by integrating various information communication technologies and multiple types of hardware. The currently shifting era toward artificial intelligence has also motivated the implementation of vehicle identification and classification using AI-based techniques, such as machine learning, artificial neural network and deep learning. In this research, we used the deep learning YOLOv3 algorithm and trained it on a custom dataset of vehicles that included different vehicle classes as per the Indian Government’s recommendation to implement the automatic vehicle identification and classification for use in the toll management system deployed at toll plazas. For faster processing of the test videos, the frames were saved at a certain interval and then the saved frames were passed through the algorithm. Apart from toll plazas, we also tested the algorithm for vehicle identification and classification on highways and urban areas. Implementing automatic vehicle identification and classification using traditional techniques is a highly proprietary endeavor. Since YOLOv3 is an open-standard-based algorithm, it paves the way to developing sustainable solutions in the area of smart transportation.

Breast Lesions Screening of Mammographic Images with 2D Spatial and 1D Convolutional Neural Network-Based Classifier

Mammography is a first-line imaging examination that employs low-dose X-rays to rapidly screen breast tumors, cysts, and calcifications. This study proposes a two-dimensional (2D) spatial and one-dimensional (1D) convolutional neural network (CNN) to early detect possible breast lesions (tumors) to reduce patients’ mortality rates and to develop a classifier for use in mammographic images on regions of interest where breast lesions (tumors) may likely occur. The 2D spatial fractional-order convolutional processes are used to strengthen and sharpen the lesions’ features, denoise, and improve the feature extraction processes. Then, an automatic extraction task is performed using a specific bounding box to sequentially pick out feature patterns from each mammographic image. The multi-round 1D kernel convolutional processes can also strengthen and denoise 1D feature signals and assist in the identification of the differentiation levels of normality and abnormality signals. In the classification layer, a gray relational analysis-based classifier is used to screen the possible lesions, including normal (Nor), benign (B), and malignant (M) classes. The classifier development for clinical applications can reduce classifier’s training time, computational complexity level, computational time, and achieve a more accurate rate for meeting clinical/medical purpose. Mammographic images were selected from the mammographic image analysis society image database for experimental tests on breast lesions screening and K-fold cross-validations were performed. The experimental results showed promising performance in quantifying the classifier’s outcome for medical purpose evaluation in terms of recall (%), precision (%), accuracy (%), and F1 score.

Unpacking the black box of voice therapy: A clinical application and revision of the Motor Learning Classification Framework (MLCF)

Purpose: Voice therapy is a complex behavioural intervention. Understanding its components is integral for continued advancement of voice therapy research, translation of evidence into the clinical setting and improved client care. The Motor Learning Classification Framework (MLCF) offers an excellent opportunity for increasing such knowledge, specifically in relation to identifying variables that affect motor learning (ML), an important mechanism hypothesised to bring about voice change during voice therapy. The MLCF has shown promising results in identifying speech-language pathologists’ (SLPs) use of ML variables during experimentally controlled voice therapy contexts. The purpose of this study was to test the feasibility of applying the framework in the clinical context of everyday voice therapy practice. Method: Data consisted of two video-recorded voice therapy sessions representing usual voice therapy care. Classification of ML variables used by SLPs during the recorded sessions was attempted based on the MLCF. Result: Several problematic features of the framework were identified. Based on deliberations between the authors of the current paper, the MLCF was revised using an iterative process. This resulted in the construction of an updated version of the framework (MLCF-V2). The MLCF-V2 organises ML strategies into two broad categories: directly observable behaviours and learning processes. The framework incorporates greater consideration of theory and empirical evidence supporting motivational, attentional focus and subjective error estimation influences on ML. Several examples of each ML variable are included as well as an attempt to provide clearer classification instruction. Conclusion: It is anticipated that the MLCF-V2 will provide a more useful and reliable classification for use in future investigations of SLPs’ use of ML variables during usual voice therapy practice.

Comparing Multiple Models for Section Header Classification with Feature Evaluation.

We present on the performance evaluation of machine learning (ML) and Natural Language Processing (NLP) based Section Header classification. The section headers classification task was performed as a two-pass system. The first pass detects a section header while the second pass classifies it. Recall, precision, and F1-measure metrics were reported to explore the best approach for ML based section header classification for use in downstream NLP tasks.

Evaluation of feature projection techniques in object grasp classification using electromyogram signals from different limb positions.

A myoelectric prosthesis is manipulated using electromyogram (EMG) signals from the existing muscles for performing the activities of daily living. A feature vector that is formed by concatenating data from many EMG channels may result in a high dimensional space, which may cause prolonged computation time, redundancy, and irrelevant information. We evaluated feature projection techniques, namely principal component analysis (PCA), linear discriminant analysis (LDA), t-Distributed Stochastic Neighbor Embedding (t-SNE), and spectral regression extreme learning machine (SRELM), applied to object grasp classification. These represent feature projections that are combinations of either linear or nonlinear, and supervised or unsupervised types. All pairs of the four types of feature projection with seven types of classifiers were evaluated, with data from six EMG channels and an IMU sensors for nine upper limb positions in the transverse plane. The results showed that SRELM outperformed LDA with supervised feature projections, and t-SNE was superior to PCA with unsupervised feature projections. The classification errors from SRELM and t-SNE paired with the seven classifiers were from 1.50% to 2.65% and from 1.27% to 17.15%, respectively. A one-way ANOVA test revealed no statistically significant difference by classifier type when using the SRELM projection, which is a nonlinear supervised feature projection (p = 0.334). On the other hand, we have to carefully select an appropriate classifier for use with t-SNE, which is a nonlinear unsupervised feature projection. We achieved the lowest classification error 1.27% using t-SNE paired with a k-nearest neighbors classifier. For SRELM, the lowest 1.50% classification error was obtained when paired with a neural network classifier.

In-Filter Computing for Designing Ultralight Acoustic Pattern Recognizers

We present a novel in-filter computing framework that can be used for designing ultra-light acoustic classifiers for use in smart internet-of-things (IoTs). Unlike a conventional acoustic pattern recognizer, where the feature extraction and classification are designed independently, the proposed architecture integrates the convolution and nonlinear filtering operations directly into the kernels of a Support Vector Machine (SVM). The result of this integration is a template-based SVM whose memory and computational footprint (training and inference) is light enough to be implemented on an FPGA-based IoT platform. While the proposed in-filter computing framework is general enough, in this paper, we demonstrate this concept using a Cascade of Asymmetric Resonator with Inner Hair Cells (CAR-IHC) based acoustic feature extraction algorithm. The complete system has been optimized using time-multiplexing and parallel-pipeline techniques for a Xilinx Spartan 7 series Field Programmable Gate Array (FPGA). We show that the system can achieve robust classification performance on benchmark sound recognition tasks using only ~ 1.5k Look-Up Tables (LUTs) and ~ 2.8k Flip-Flops (FFs), a significant improvement over other approaches.

Classification of the popliteofibular ligament.

The purpose of this study was to characterize the morphological variations in the distal attachment of the popliteofibular ligament (PFL) and create an accurate classification for use in planning surgical procedures in this area and in evaluating radiological imaging. One hundred and thirty-seven lower limbs of body donors fixed in 10% formalin solution were examined for the presence and course of the PFL. The PFL was present in 88.3% of cases. We propose the following three-fold classification: type I (72.3%), the most common type, characterized by the attachment onto the apex of the head of the fibula, type II (8.7%), characterized by a bifurcation, with the dominant band inserting on the anterior slope of the styloid process of the fibula and the smaller band onto the posterior surface of the styloid process of the fibula and type III (7.3%), characterized by a double PFL: the first PFL (main) originated from the popliteus tendon and inserted onto the anterior slope of the styloid process of thefibula, while the second originated from the musculotendinous junction of the popliteus muscle and inserted on the posterior surface of the styloid process of the fibula. The PFL was characterized by high morphological variation, as reflected in our proposed classification. This variation may present clinical and biomechanical issues for both medical personnel and researchers. Our proposed classification may be valuable for clinicians who evaluate and perform surgical procedures within the knee joint area.

Automated classification of cytogenetic abnormalities in hematolymphoid neoplasms.

Algorithms for classifying chromosomes, like convolutional deep neural networks (CNNs), show promise to augment cytogeneticists' workflows; however, a critical limitation is their inability to accurately classify various structural chromosomal abnormalities. In hematopathology, recurrent structural cytogenetic abnormalities herald diagnostic, prognostic and therapeutic implications, but are laborious for expert cytogeneticists to identify. Non-recurrent cytogenetic abnormalities also occur frequently cancerous cells. Here, we demonstrate the feasibility of using CNNs to accurately classify many recurrent cytogenetic abnormalities while being able to reliably detect non-recurrent, spurious abnormal chromosomes, as well as provide insights into dataset assembly, model selection and training methodology that improve overall generalizability and performance for chromosome classification. Our top-performing model achieved a mean weighted F1 score of 96.86% on the validation set and 94.03% on the test set. Gradient class activation maps indicated that our model learned biologically meaningful feature maps, reinforcing the clinical utility of our proposed approach. Altogether, this work: proposes a new dataset framework for training chromosome classifiers for use in a clinical environment, reveals that residual CNNs and cyclical learning rates confer superior performance, and demonstrates the feasibility of using this approach to automatically screen for many recurrent cytogenetic abnormalities while adeptly classifying non-recurrent abnormal chromosomes. Software is freely available at https://github.com/DaehwanKimLab/Chromosome-ReAd. The data underlying this article cannot be shared publicly due to it being protected patient information. Supplementary data are available at Bioinformatics online.

Quantification of the Spectral Variability of Ore-Bearing Granodiorite under Supervised and Semisupervised Conditions: An Upscaling Approach

Reflectance spectroscopy is a nondestructive, rapid, and easy-to-use technique which can be used to assess the composition of rocks qualitatively or quantitatively. Although it is a powerful tool, it has its limitations especially when it comes to measurements of rocks with a phaneritic texture. The external variability is reflected only in spectroscopy and not in the chemical-mineralogical measurements that are performed on crushed rock in certified laboratories. Hence, the spectral variability of the surface of an uncrushed rock will, in most cases, be higher than the internal chemical-mineralogical variability, which may impair statistical models built on field measurements. For this reason, studying ore-bearing rocks and evaluating their spectral variability in different scales is an important procedure to better understand the factors that may influence the qualitative and quantitative analysis of the rocks. The objectives are to quantify the spectral variability of three types of altered granodiorite using well-established statistical methods with an upscaling approach. With this approach, the samples were measured in the laboratory under supervised ambient conditions and in the field under semisupervised conditions. This study further aims to conclude which statistical method provides the best practical and accurate classification for use in future studies. Our results showed that all statistical methods enable the separation of the rock types, although two types of rocks have exhibited almost identical spectra. Furthermore, the statistical methods that supplied the most significant results for classification purposes were principal component analysis combined with k-nearest neighbor with a classification accuracy for laboratory and field measurements of 68.1% and 100%, respectively.

Natural Disaster on Twitter: Role of Feature Extraction Method of Word2Vec and Lexicon Based for Determining Direct Eyewitness

Researchers have collected Twitter data to study a wide range of topics, one of which is a natural disaster. A social network sensor was developed in existing research to filter natural disaster information from direct eyewitnesses, none eyewitnesses, and non-natural disaster information. It can be used as a tool for early warning or monitoring when natural disasters occur. The main component of the social network sensor is the text tweet classification. Similar to text classification research in general, the challenge is the feature extraction method to convert Twitter text into structured data. The strategy commonly used is vector space representation. However, it has the potential to produce high dimension data. This research focuses on the feature extraction method to resolve high dimension data issues. We propose a hybrid approach of word2vec-based and lexicon-based feature extraction to produce new features. The Experiment result shows that the proposed method has fewer features and improves classification performance with an average AUC value of 0.84, and the number of features is 150. The value is obtained by using only the word2vec-based method. In the end, this research shows that lexicon-based did not influence the improvement in the performance of social network sensor predictions in natural disasters.
 HIGHLIGHTS
 
 Implementation of text classification is generally only used to perform sentiment analysis, it is still rare to use it to perform text classification for use in determining direct eyewitnesses in cases of natural disasters
 One of the common problems in text mining research is the extracted features from the vector space representation method generate high dimension data
 A hybrid approach of word2vec-based and lexicon-based feature extraction experiment was conducted in order to find a method that can generate new features with low dimensions and also improve the classification performance
 
 GRAPHICAL ABSTRACT