Hierarchical Classification Research Articles

Hierarchical Classification of Transversal Skills in Job Advertisements Based on Sentence Embeddings

This paper proposes a classification methodology aimed at identifying correlations between job ad requirements and transversal skill sets, with a focus on predicting the necessary skills for individual job descriptions using a deep learning model. The approach involves data collection, preprocessing, and labeling using ESCO (European Skills, Competences, and Occupations) taxonomy. Hierarchical classification and multi-label strategies are used for skill identification, while augmentation techniques address data imbalance, enhancing model robustness. A comparison between results obtained with English-specific and multi-language sentence embedding models reveals close accuracy. The experimental case studies detail neural network configurations, hyperparameters, and cross-validation results, highlighting the efficacy of the hierarchical approach and the suitability of the multi-language model for the diverse European job market. Thus, a new approach is proposed for the hierarchical classification of transversal skills from job ads.

Assessment and Optimization of the Insecticidal Properties of γ-Al2O3 Nanoparticles Derived from Mentha pulegium By-Products to Xylosandrus crassiusculus (Carob Beetle).

This study concentrates on assessing the insecticidal attributes of the γ-Al2O3 nanoparticles derived from the remnants of Mentha pulegium, which include essential oil, ethanolic extract, and plant waste. The synthesis of the γ-Al2O3 nanoparticles was executed using a direct sol-gel procedure, affirming the crystal structure according to extensive physicochemical analyses such as UV-Vis, XRD, FTIR, and SEM. Evaluation of the insecticidal activity in vitro was conducted against Xylosandrus crassiusculus, a pest that infests carob wood, utilizing strains from diverse forests in the Khenifra region, situated in the Moroccan Middle Atlas. The lethal doses 50 ranged from 40 mg/g to 68 mg/g, indicating moderate effectiveness compared to the commercial insecticide Permethrin. Optimization of the conditions for the efficiency of the γ-Al2O3 nanoparticles was determined using experimental plans, revealing that time, humidity, and temperature were influential factors in the lethal dose 50 of these nanomaterials. Moreover, this study encompasses the establishment of correlations using Principal Component Analysis (PCA) and Ascending Hierarchical Classification (AHC) among various geographic, biological, and physical data, amalgamating geographic altitude and γ-Al2O3 nanoparticle insecticide parameters, as well as the attributes of the mechanical tests conducted on the carob wood affected by insects. The correlations highlight the close connections between the effectiveness of the insecticide, mountain altitude, and the mechanical parameters that were examined. Ultimately, these nanoparticles demonstrate promising potential as alternative insecticides, thus opening up encouraging prospects for safeguarding against carob wood pests.

"What will you do after?": Lessons from Academia and the World Beyond.

Determining post-PhD career options is a challenge for many Psychology PhD graduates. Here I provide a comprehensive overview of the diverse career trajectories available to graduates, drawing from interviews with 53 PhD graduates conducted as part of the two-volume Academia and the World Beyond book series. From these, I conducted a hierarchical qualitative classification to categorise and characterise potential career paths. The findings reveal a spectrum of opportunities, from traditional academic roles to "academic adjacent" and "skill-transfer" careers. This work underscores the versatility of Psychology doctoral training, providing skills that can support a wide array of career possibilities. The results serve as a guide for current and prospective PhD students-and their mentors-emphasising the variety of professional contexts where doctoral training is beneficial.

Fine-resolution land cover mapping over large and mountainous areas for Lāna‘i, Hawaii using posterior probabilities, and expert knowledge

ABSTRACT The task of accurately mapping species-specific vegetation cover in remote and topographically complex regions like those found in Hawaiʻi presents unique challenges. This study leverages a machine learning approach to accurately classify vegetation into fine species-specific classes across the island of Lāna‘i, Hawaii, offering a novel methodology for tackling such challenges. Utilizing high-resolution WordView-2 satellite imagery, a neural network classifier and a custom lidar-based geometric correction, we introduced two new approaches to refine our high-resolution land cover classifications. This included the implementation of prior-based adjustments to class posterior probabilities to enhance land cover classification accuracy. Moreover, we developed mixed hierarchical classification maps that use class posterior probabilities to identify, at the pixel level, the finest land cover class that meets a user-defined confidence threshold. The resulting high-resolution land cover map for Lāna‘i captures the rich diversity and distribution of native and invasive plant species with high overall accuracy, generally exceeding 95%, based on independent ground control data. The capacity to produce wall-to-wall species-level vegetation maps provides a new window into monitoring vegetation dynamics on Lāna‘i and similarly remote and topographically complex regions, and contributes to our broader understanding of ecosystem responses to invasive species, climatic changes, and land management practices such as erosion and sediment control planning. Our approach offers a blueprint for similar efforts in other complex and remote ecosystems.

Trends in the Adoption of Outpatient Joint Arthroplasties and Patient Risk: A Retrospective Analysis of 2019 to 2021 Medicare Claims Data.

Total joint arthroplasties (TJAs) have recently been shifting toward outpatient arthroplasty. This study aims to explore recent trends in outpatient total joint arthroplasty (TJA) procedures and examine whether patients with a higher comorbidity burden are undergoing outpatient arthroplasty. Medicare fee-for-service claims were screened for patients who underwent total hip, knee, or shoulder arthroplasty procedures between January 2019 and December 2022. The procedure was considered to be outpatient if the patient was discharged on the same date of the procedure. The Hierarchical Condition Category Score (HCC) and the Charlson Comorbidity Index (CCI) scores were used to assess patient comorbidity burden. Patient adverse outcomes included all-cause hospital readmission, mortality, and postoperative complications. Logistic regression analyses were used to evaluate if higher HCC/CCI scores were associated with adverse patient outcomes. A total of 69,520, 116,411, and 41,922 respective total knee, hip, and shoulder arthroplasties were identified, respectively. Despite earlier removal from the inpatient-only list, outpatient knee and hip surgical volume did not markedly increase until the pandemic started. By 2022Q4, 16%, 23%, and 36% of hip, knee, and shoulder arthroplasties were discharged on the same day of surgery, respectively. Both HCC and CCI risk scores in outpatients increased over time ( P < 0.001). TJA procedures are shifting toward outpatient surgery over time, largely driven by the COVID-19 pandemic. TJA outpatients' HCC and CCI risk scores increased over this same period, and additional research to determine the effects of this should be pursued. Level III, therapeutic retrospective cohort study.

Multi-task supervised contrastive learning for chest X-ray diagnosis: A two-stage hierarchical classification framework for COVID-19 diagnosis

Global pandemics have posed great challenges, such as limited samples and the scarcity of carefully curated datasets, in creating reliable models for chest X-ray (CXR) diagnosis. A common approach is to leverage pre-trained deep learning models using large datasets and then fine-tune model parameters on the target CXR dataset. However, in the presence of data bias, it is prone to shortcut learning, where the model learns non-disease-related features. To enable the model to learn robust features from the target dataset, we propose a new training framework called Multi-task Supervised Contrastive Learning (MTSCL). In MTSCL, we concatenate the weighted representations of two supervised tasks and implicitly contrast the representations from the large-scale and target datasets. It helps the model focus on disease-related features in the target dataset. This paper applies the MTSCL model to a two-stage hierarchical classification framework. In the first stage, the MTSCL model detects lung abnormalities, and then tree-based models are applied to classify the abnormalities as pneumonia or COVID-19 in the second stage. The experimental results show that, in the first stage, the MTSCL model outperforms other training methods in terms of generalization with an average AUC improvement of 1.03%-5.33% and has better abnormality localization capability. In the second stage, the model generalization is enhanced by incorporating lung masks and using MTSCL model-generated lesion masks for image preprocessing. Furthermore, the addition of wavelet components manipulation on top of the previous improvements further increases the generalization performance for distinguishing COVID-19 from typical pneumonia with an average AUC improvement of 12.38%. Overall, the two-stage hierarchical classification framework exhibits superior generalization ability for normal, pneumonia, and COVID-19 classification, achieving an average accuracy of 75.19% in two external datasets, outperforming state-of-the-art deep learning models (71.00%-74.08%) and classical machine learning models (67.80%-68.67%).

A Geographic Object-Based Image Approach Based on the Sentinel-2 Multispectral Instrument for Lake Aquatic Vegetation Mapping: A Complementary Tool to In Situ Monitoring

Aquatic vegetation is an essential component of lake ecosystems, used as a biological indicator for in situ monitoring within the Water Framework Directive. We developed a hierarchical object-based image classification model with multi-seasonal Sentinel-2 imagery and suitable spectral indices in order to map the aquatic vegetation in a Mediterranean oligotrophic/mesotrophic deep lake; we then applied the model to another lake with similar abiotic and biotic characteristics. Field data from a survey of aquatic macrophytes, undertaken on the same dates as EO data, were used within the accuracy assessment. The aquatic vegetation was discerned into three classes: emergent, floating, and submerged aquatic vegetation. Geographic object-based image analysis (GEOBIA) proved to be effective in discriminating the three classes in both study areas. Results showed high effectiveness of the classification model in terms of overall accuracy, particularly for the emergent and floating classes. In the case of submerged aquatic vegetation, challenges in their classification prompted us to establish specific criteria for their accurate detection. Overall results showed that GEOBIA based on spectral indices was suitable for mapping aquatic vegetation in oligotrophic/mesotrophic deep lakes. EO data can contribute to large-scale coverage and high-frequency monitoring requirements, being a complementary tool to in situ monitoring.

Uncertainty-aware single-cell annotation with a hierarchical reject option.

Automatic cell type annotation methods assign cell type labels to new datasets by extracting relationships from a reference RNA-seq dataset. However, due to the limited resolution of gene expression features, there is always uncertainty present in the label assignment. To enhance the reliability and robustness of annotation, most machine learning methods address this uncertainty by providing a full reject option, i.e. when the predicted confidence score of a cell type label falls below a user-defined threshold, no label is assigned and no prediction is made. As a better alternative, some methods deploy hierarchical models and consider a so-called partial rejection by returning internal nodes of the hierarchy as label assignment. However, because a detailed experimental analysis of various rejection approaches is missing in the literature, there is currently no consensus on best practices. We evaluate three annotation approaches (i) full rejection, (ii) partial rejection, and (iii) no rejection for both flat and hierarchical probabilistic classifiers. Our findings indicate that hierarchical classifiers are superior when rejection is applied, with partial rejection being the preferred rejection approach, as it preserves a significant amount of label information. For optimal rejection implementation, the rejection threshold should be determined through careful examination of a method's rejection behavior. Without rejection, flat and hierarchical annotation perform equally well, as long as the cell type hierarchy accurately captures transcriptomic relationships. Code is freely available at https://github.com/Latheuni/Hierarchical_reject and https://doi.org/10.5281/zenodo.10697468.

Hierarchical categories in colored searching

In colored range counting (CRC), the input is a set of points where each point is assigned a “color” (or a “category”) and the goal is to store them in a data structure such that the number of distinct categories inside a given query range can be counted efficiently. CRC has strong motivations as it allows data structure to deal with categorical data.However, colors (i.e., the categories) in the CRC problem do not have any internal structure, whereas this is not the case for many datasets in practice where hierarchical categories exist or where a single input belongs to multiple categories. Motivated by these, we consider variants of the problem where such structures can be represented. We define two variants of the problem called hierarchical range counting (HCC) and sub-category colored range counting (SCRC) and consider hierarchical structures that can either be a DAG or a tree. We show that the two problems on some special trees are in fact equivalent to other well-known problems in the literature. Based on these, we also give efficient data structures when the underlying hierarchy can be represented as a tree. We show a conditional lower bound for the general case when the existing hierarchy can be any DAG, through a reduction from the orthogonal vectors problem.

‘Soon you will go far’: discourse analysis on vocational education policy of Israel

ABSTRACT This article performs a discourse analysis on the recent interest of the Israeli Ministry of Education in vocational education by examining governmental and organisational texts. This article addresses two key questions. What is the government’s justification for its renewed interest in vocational education? What are its discursive practices to promote vocational education in the context of the current neoliberal discourse on equality and meritocracy? Highlighting three major justifications and discursive practices in the Ministry of Education’s current educational policy, this discursive analysis shows that the policy is related to culture, ethnicity, and class hierarchies in Israel. The analysis also underscores ambiguity as a governmental and organisational tool and the ramifications of the government’s ethnic blindness related to the social construction of a specific reality in vocational education.

Improving river medium–high flow estimation by CM Hierarchical Classification (CMHC) method using Sentinel-2 imagery

River discharge monitoring is one of the most important parts of water resources management. However, due to hydrological stations' high operating and maintenance costs, discharge monitoring data has gradually become scarce. Remote sensing technology has great potential to supplement observations in this field. The close relationship between the reflectance ratio of dry (C) and wet (M) pixels around the river in the near-infrared (NIR) band and river discharge has been effectively proved, and many CM-based methods have also achieved good results, but often underestimate medium–high flow in rivers. However, medium–high flow usually occurs during the rainy season or flood-prone periods, and their underestimation not only affects the risk assessment of possible or already occurred floods but may also cause damage to people's lives, property, and social assets. To improve this phenomenon, we proposed a new CM method called CM Hierarchical Classification (CMHC) based on the Sentinel-2 dataset and Google Earth Engine (GEE) cloud platform to monitor the river discharge at different classes and achieve high-precision discharge estimation at medium–high flow. The study was conducted at four stations along the Po River in Italy, where measured discharge data were used to derive the calibration curve and evaluate the performance of the estimated results. The Nash-Sutcliffe efficiency (NS) values for the estimates reached an average of 0.84 and up to 0.89, indicating the excellent performance of the method. Compared with existing methods, our method substantially improves the monitoring accuracy of medium–high flow of the river. Furthermore, additional experiments in the Han River in China also confirmed the applicability of the CMHC method, implying that this method can be used to improve the ability of Sentinel-2 to estimate river discharge, especially for medium–high flow, and provide support for river discharge monitoring on a global scale.

Christie'nin Ölümle Randevu ve Ölüm Adası Eserlerinde Doğulu Odaklanılanın Karşılaştırmalı Anlatıbilimsel Analizi

The implications of Agatha Christie’s works are multifarious; however, her texts are understudied when compared to those of her contemporaries. Much has been written about the generic qualities of her detective fiction, and the representation of women and class hierarchies in her works. However, her texts are rarely subjected to narratological analysis. Her works of detective fiction Appointment with Death (1938) and A Caribbean Mystery (1964) are set in former colonies of Britain, and through Western narrators and focal characters, Christie presents an Orientalist perspective. While the onlookers and the tellers are Westerners in these novels, the objects of their narration are oriental landscapes and people. As the image of the objects of focalization presented to readers in a literary text is constructed by the focalizers, the narrative abounds with their subjective views. By closely reading a text, a reader can gain insight into the focalizer and its relationship to the focalized. In these novels, the hegemony of the West over the East, and the Westerners’ biased perceptions are made apparent. Through a comparative narratological analysis of the focalized objects in these novels, this study aims to shed new light on how Christie’s novels lay bare the biased attitudes of Westerners towards the Oriental focalized.

Freshwater Aquaculture Mapping in “Home of Chinese Crawfish” by Using a Hierarchical Classification Framework and Sentinel-1/2 Data

The escalating evolution of aquaculture has wielded a profound and far-reaching impact on regional sustainable development, ecological equilibrium, and food security. Currently, most aquaculture mapping efforts mainly focus on coastal aquaculture ponds rather than diverse inland aquaculture areas. Recognizing all types of aquaculture areas and accurately classifying different types of aquaculture areas remains a challenge. Here, on the basis of the Google Earth Engine (GEE) and the time-series Sentinel-1 and -2 data, we developed a novel hierarchical framework extraction method for mapping fine inland aquaculture areas (aquaculture ponds + rice-crawfish fields) by employing distinct phenological disparities within two temporal windows (T1 and T2) in Qianjiang, so-called “Home of Chinese Crawfish”. Simultaneously, we evaluated the classification performance of four distinct machine learning classifiers, namely Random Forest (RF), Support Vector Machine (SVM), Classification and Regression Trees (CART), and Gradient Boosting (GTB), as well as 11 feature combinations. Following an exhaustive comparative analysis, we selected the optimal machine learning classifier (i.e., the RF classifier) and the optimal feature combination (i.e., feature combination after an automated feature selection method) to classify the aquaculture areas with high accuracy. The results underscore the robustness of the proposed methodology, achieving an outstanding overall accuracy of 93.8%, with an F1 score of 0.94 for aquaculture. The result indicates that an area of 214.6 ± 10.5 km2 of rice-crawfish fields, constituting approximately 83% of the entire aquaculture area in Qianjiang, followed by aquaculture ponds (44.3 ± 10.7 km2, 17%). The proposed hierarchical framework, based on significant phenological characteristics of varied aquaculture types, provides a new approach to monitoring inland freshwater aquaculture in China and other regions of the world.

Hierarchical LSTM-Based Classification of Household Heating Types Using Measurement Data

Hierarchical LSTM-Based Classification of Household Heating Types Using Measurement Data

The Anesthesiologists' Perception of Malignant Hyperthermia and Availability of Dantrolene in China: A Cross-Sectional Survey.

Malignant hyperthermia (MH) is a hypermetabolic syndrome with high mortality rates. Early detection and prompt intravenous administration of dantrolene are crucial for effective management of MH. However, there is currently a lack of comprehensive nationwide surveys on the availability of dantrolene and anesthesiologists' understanding of MH in China. A nationwide survey was conducted between January 2022 and June 2022. Online questionnaires on the cognition of MH among anesthesiologists in China were sent through social platforms to anesthesiologists in mainland China. Data regarding participants' perception of MH-related knowledge, availability of domestic dantrolene, and reported MH cases were collected in this study. Responses were collected from a total of 11,354 anesthesiologists representing 31 provinces across the Chinese mainland. Among the 11 scoring questions, the highest accuracy rates were observed for the question regarding therapeutic drugs for MH (99.3%) and the characteristics of MH (98.0%). Conversely, the question pertaining to the earliest clinical signs of MH had the lowest accuracy rate (23.5%). Significant variations were observed in the scores among different professional titles (P=0.003), academic degree (P<0.001), hospital classification (P<0.001), and urban hierarchy (P<0.001). Of the respondents, 919 (8.1%) anesthesiologists reported dantrolene availability in their hospitals, and 631 (5.6%) indicated unclear. A total of 136 hospitals in this survey reported at least one previous case of MH. Mainland China faces challenges such as insufficient experience in diagnosing and treating MH, as well as difficulty in obtaining dantrolene. To improve the public awareness of MH, it is imperative to establish and promote a refined MH training system. Additionally, a streamlined and rapid dantrolene linkage emergency system should be implemented to ensure prompt access to the drug.

Incremental feature selection for large-scale hierarchical classification with the arrival of new samples

Incremental feature selection for large-scale hierarchical classification with the arrival of new samples

Quantifying Bias in Hierarchical Category Systems.

Categorization is ubiquitous in human cognition and society, and shapes how we perceive and understand the world. Because categories reflect the needs and perspectives of their creators, no category system is entirely objective, and inbuilt biases can have harmful social consequences. Here we propose methods for measuring biases in hierarchical systems of categories, a common form of category organization with multiple levels of abstraction. We illustrate these methods by quantifying the extent to which library classification systems are biased in favour of western concepts and male authors. We analyze a large library data set including more than 3 million books organized into thousands of categories, and find that categories related to religion show greater western bias than do categories related to literature or history, and that books written by men are distributed more broadly across library classification systems than are books written by women. We also find that the Dewey Decimal Classification shows a greater level of bias than does the Library of Congress Classification. Although we focus on library classification as a case study, our methods are general, and can be used to measure biases in both natural and institutional category systems across a range of domains.

السياسة بين الأخلاق والمقاصد: عرض مقارن بين ابن تيمية والشاطبيّ

Islamic scholars, including philosophers, sociologists, and jurists agree that the ultimate goal of the state or political authority is to achieve the welfare of the citizens and to bring goodness, prosperity, and happiness to the individual and society. This means safeguarding religion and managing worldly affairs. Political authority in Islam is based on a unique system consisting of two elements: ethics and objectives. These two elements constitute the highest goal of the prophetic message, as Sharia consists of the duality of ethics and interests. The article seeks to uncover the foundational moral and objective basis of political authority by providing a comparative analysis of the most important ethical objectives that must be possessed by uli al-amr, according to Imam Ahmad ibn Taymiyyah (d. 728 AH) in his book "Al-Siyasah al-Shar'iyyah fi Islah al-Ra'i wa al-Ra'iyah," and Abu Ishaq al-Shatibi (d. 790 AH) in his book "Al-Muwafaqat." The article concludes that the purpose of establishing political authority cannot be realized unless it is framed within the framework of ethics and virtues that enjoin justice, trustworthiness, truth, and freedom. Furthermore, ethics in the realm of politics must be subjected to the hierarchical classification of objectives into necessities, needs, and improvements. Accordingly, priority should be given to the most crucial virtues, while averting the most harmful vices.

Advancing Wireless Sensor Networks through Performance Evaluation of M-PDCH Routing Protocol for Enhanced Quality of Service

Objective: The decisive aim of this investigation is to improve the capabilities and limitations of PEGASIS with Double Cluster Head (PDCH), for enhancing the overall Quality of Service (QoS) in Wireless Sensor Networks (WSNs). Methods: This research is intended at the application of efficient routing protocol for wireless sensor networks. It works on the principle of the formation of cluster head and clustering. This is accomplished to achieve high QoS for WSN. Improving the efficacy of a WSN protocol is decisive for optimizing communication, resource utilization, and overall effectiveness. An innovative and novel protocol named Mobile-PDCH (M-PDCH) has been devised, developed, and tested. Here several parameters have been carefully investigated for enhancing the performance of a WSN protocol such as energy consumption, delay, and packet loss. A simulation environment has been created to evaluate, compare, and validate the performance and to suggest the desired applications of the proposed protocol. Findings: In the hierarchical category, PDCH performs better compared to all the other protocols. But it suffers from high packet drop, which decrease the performance of the protocol. To improve the performance of sensor networks, there is a need for adaptive routing protocol. The examination of simulation outcomes for the recommended protocol, M-PDCH, has been conducted in comparison with PDCH. The findings indicate that the protocol exhibits superior performance. The proposed algorithm improves the packet drop by 29.75%, reduces delay by 23.28%, and lowers energy consumption by 19.18% when compared to PDCH. Novelty: A novel adaptive routing protocol termed M-PDCH has been proposed for the enhancement of the WSN life span and durability of the sensor nodes. The simulation results show that the proposed algorithm produces better results compared to PDCH protocol. The various QoS parameter results are compared, verified, and validated with existing protocol PDCH. Keywords: WSN, PDCH, Design issues, Metrics, QoS, HRP

A hierarchical, multi‐sensor framework for peatland sub‐class and vegetation mapping throughout the Canadian boreal forest

AbstractPeatlands in the Canadian boreal forest are being negatively impacted by anthropogenic climate change, the effects of which are expected to worsen. Peatland types and sub‐classes vary in their ecohydrological characteristics and are expected to have different responses to climate change. Large‐scale modelling frameworks such as the Canadian Model for Peatlands, the Canadian Fire Behaviour Prediction System and the Canadian Land Data Assimilation System require peatland maps including information on sub‐types and vegetation as critical inputs. Additionally, peatland class and vegetation height are critical variables for wildlife habitat management and are related to the carbon cycle and wildfire fuel loading. This research aimed to create a map of peatland sub‐classes (bog, poor fen, rich fen permafrost peat complex) for the Canadian boreal forest and create an inventory of peatland vegetation height characteristics using ICESat‐2. A three‐stage hierarchical classification framework was developed to map peatland sub‐classes within the Canadian boreal forest circa 2020. Training and validation data consisted of peatland locations derived from various sources (field data, aerial photo interpretation, measurements documented in literature). A combination of multispectral data, L‐band SAR backscatter and C‐Band interferometric SAR coherence, forest structure and ancillary variables was used as model predictors. Ancillary data were used to mask agricultural areas and urban regions and account for regions that may exhibit permafrost. In the first stage of the classification, wetlands, uplands and water were classified with 86.5% accuracy. In the second stage, within the wetland areas only, peatland and mineral wetlands were differentiated with 93.3% accuracy. In the third stage, constrained to only the peatland areas, bogs, rich fens, poor fens and permafrost peat complexes were classified with 71.5% accuracy. Then, ICESat‐2 ATL08 spaceborne lidar data were used to describe regional variations in peatland vegetation height characteristics and regional and class‐wise variations based on a boreal forest wide sample. This research introduced a comprehensive large‐scale peatland sub‐class mapping framework for the Canadian boreal forest, presenting the first moderate resolution map of its kind.