Binary Approach Research Articles

Performance Metrics for Multilabel Emotion Classification: Comparing Micro, Macro, and Weighted F1-Scores

This study compares various F1-score variants—micro, macro, and weighted—to assess their performance in evaluating text-based emotion classification. Lexicon distillation is employed using the multilabel emotion-annotated datasets XED and GoEmotions. The aim of this paper is to understand when each F1-score variant is better suited for evaluating text-based multilabel emotion classification. Unigram lexicons were derived from the annotated GoEmotions and XED datasets through a binary classification approach. The distilled lexicons were then applied to the GoEmotions and XED annotated datasets to calculate their emotional content, and the results were compared. The findings highlight the behavior of each F1-score variant under different class distributions, emphasizing the importance of appropriate metric selection for reliable model performance evaluation in imbalanced multilabel datasets. Additionally, this study also investigates the effect of the aggregation of negative emotions into broader categories on said F1 metrics. The contribution of this study is to provide insights into how different F1-score variants could improve the reliability of multilabel emotion classifier evaluation, particularly in the context of class imbalance present in the case of phishing emails.

Accessible Trail Tourism: Trail Accessibility and Difficulty Rating Approach Designed for Individuals, Including With Mobility Impairments

ABSTRACTThis study introduces a novel approach to trail accessibility and difficulty rating tailored specifically for individuals, including those with mobility impairments, aiming to promote accessible trail tourism. Grounded in theoretical frameworks of inclusive outdoor recreation, equality, and complex adaptive systems, the proposed rating system incorporates criteria addressing physical access, terrain challenges, and amenities to accommodate diverse user needs. This study employed a sensor technology, called wheeled instrumentation sensor package (WISP) within the framework of the high‐efficiency trail assessment process (HETAP) to develop a new quantitatively based trail classification scheme. A case study trail and two hypothetical synthetic data trails were used to demonstrate both the trail wheelchair accessibility binary classification approach and the proposed trail difficulty classification approach. This research pioneers trail accessibility and difficulty rating and underscores the importance of integrating accessibility considerations into trail management practices to create truly inclusive outdoor recreational experiences.

Frustration Gap Bridging: A Second Look at Vocabulary Proficiency with the Yes/No Test

This research advances the scrutiny of the Yes/No test's (Meara: 1990) efficacy in evaluating vocabulary proficiency among language learners of high, middle, and low proficiency levels, focusing on its capability to mitigate the frustration commonly encountered by this demographic. As highlighted in the recent investigation (Goetz, 2023), the Yes/No test prompted respondents to signify their word familiarity through binary choices. Yes, they know a word, and No, they don’t. Involving a paltry 56 English language learners of lower proficiency to determine if the test's impact on enhancing vocabulary skills had merit, it was found that contrary to the anticipated outcomes, the test did not yield significant advancements in students' performance on subsequent unit tests compared to their counterparts who were not subjected to the Yes/No test. This absence of tangible benefits, combined with the test's failure to deliver a contextualized and nuanced comprehension of vocabulary, raises questions regarding its efficacy as a pedagogical tool for vocabulary enhancement. Nevertheless, the results did not dismiss the Yes/No test's potential utility. For this study, a second look will address two critical shortcomings: the limited sample size and the absence of a diverse range of proficiency levels among participants. This inquiry reevaluates the Yes/No test's capacity to effectively navigate the intricacies of language acquisition, proposing a more in-depth investigation into whether this binary and straightforward approach could indeed be beneficial or whether it underscores the imperative for a more holistic and contextually aware method in language instruction by expanding the sample size and including more proficiency levels. Questions remain regarding the efficacy of the Yes/No test. Is it optimally utilized as a straightforward, standalone tool, or should it be considered within the broader spectrum of comprehensive, context-sensitive learning strategies? This inquiry invites a nuanced evaluation of the test's role in language acquisition. It challenges researchers and practitioners to contemplate whether its simplicity is a virtue in isolation or if its true value emerges when integrated with a holistic approach to learning.

Graph neural network-based subgraph analysis for predicting adverse drug events

PurposeAdverse drug events (ADEs) are a significant global public health concern, and they have resulted in high rates of hospital admissions, morbidity, and mortality. Prior to the use of machine learning and deep learning methods, ADEs may not become well recognized until long after a drug has been approved and is widely used, which poses a significant challenge for ensuring patient safety. Consequently, there is a need to develop computational approaches for earlier identification of ADEs not detected during pre-registration clinical trials. MethodsThis paper presents a state-of-the-art network-based approach that models patients as subgraphs composed of nodes of International Classification of Diseases (ICD) codes and directed edges illustrating disease progression. Four Graph Neural Network (GNN) variants were employed to make sub-graph level predictions that answer three Research Questions (RQ): 1) whether ADE(s) would occur given a patient's prior diagnoses history, 2) when an ADE would occur, and 3) which ADE would occur. The first and second RQs were addressed using a binary classification approach. The third RQ was addressed using a multi-label classification model. ResultsThe proposed network-based approach demonstrated superior performance in predicting ADEs, with the GraphSage model exhibiting the highest accuracy for both RQ 1 (0.8863) and RQ 3 (0.9367), while the Graph Attention Networks (GAT) model was found to perform best for RQ 2 (0.8769). Furthermore, an analysis segmented by ADE classification revealed that while RQs 1 and 3 exhibited minimal variance across different ADE categories, a distinct advantage was observed for categories B, C, and E in the context of RQ 2 when applying this sub-graph method. ConclusionThe network-based approach demonstrates the potential of GNNs in supporting the early detection and prevention of ADEs. Accurately predicting ADEs could enable healthcare professionals to make informed clinical decisions, take preventive measures and adjust medication regimens before serious adverse events occur. The proposed prediction method could also lead to optimized usage of healthcare resources by preventing hospital admissions and reducing the overall burden of adverse drug events on the healthcare systems.

Stepwise methods for more nuanced adoption analysis: a case study of harvest and post-harvest mechanization in Bangladesh

The adoption of agricultural harvest and post-harvest mechanization is crucial for addressing drudgery, food losses, climate vulnerability and food security. Despite considerable efforts by government and development partners to prioritize agricultural mechanization, labour-intensive manual (post-)harvest activities continue to dominate in Bangladeshi smallholder systems. Explorations of this has been limited by simplistic binary approaches that ignore the dynamic pathways to usage outcomes. Instead, we apply non-binary analytical methods to district representative data to highlight the value in moving beyond binary adoption analysis. Results highlight that a national (post-)harvest mechanisation rate of 74% is insufficient to capture the true adoption status, given substantial disparity exists across machinery and by district. Deeper exploration of temporal and spatial differences enable the identification of key trends that warrant further in-depth explorations, while only 46% satisfaction with extension systems highlights the need to re-evaluate key information exchange mechanisms. We conclude that there is a clear need for district and machinery specific policy arrangements if Bangladesh is to achieve (post-)harvest mechanisation objectives that aim to reduce food loses and enable greater food security nationwide.

An integrated binary metaheuristic approach in dynamic unit commitment and economic emission dispatch for hybrid energy systems

The current generation portfolio is obligated to incorporate zero-emissions energy sources, predominantly wind and solar, due to the depletion of fossil fuels and the alarming rate of global warming. In the current scenario, power engineers must devise a compromised solution that not only advocates for the adoption of renewable energy sources (RES) but also efficiently schedules all conventional power generation units to balance the increasing load demand while simultaneously minimizing fuel costs and harmful emissions that are currently addressed by Unit Commitment (UC) and Combined Economic Emission Dispatch (CEED) problem solutions. However, the integration of renewable energy resources (RES) further complicates the UC-CEED problem due to their intermittent nature. Recently, metaheuristic algorithms are acquiring momentum in resolving constrained UC-CEED problems due to their improved global solution ability, adaptability, and derivative-free construction. In this research, a computationally efficient binary hybrid version of crow search algorithm and improvised grey wolf optimization is proposed, namely Crow Search Improved Binary Grey Wolf Optimization Algorithm (CS-BIGWO) by inclusion of nonlinear control parameter, weight-based position updating, and mutation approach. Statistical results on standard mathematical functions prove the supremacy of the proposed algorithm over conventional algorithms. Further, a novel optimization strategy is devised by integrating enhanced lambda iteration with the CS-BIGWO algorithm (CS-BIGWO-λ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\lambda$$\\end{document}) to solve a day-ahead UC-CEED problem of the hybrid energy system incorporating cost functions of RES. For the model, a day-ahead forecast of wind power and solar photovoltaic power is obtained by using the Levy-Flight Chaotic Whale Optimization Algorithm optimized Extreme Learning Machines(LCWOA-ELM). The proposed algorithm is tested for the UC-CEED solution of an IEEE-39 bus system with two distinct cases: (1) without RES integration and (2) with RES integration. Several independent trial runs are executed, and the performance of the algorithms is assessed based on optimal UC schedules, fuel cost, emission quantization, convergence curve, and computational time. For case 1, the proposed algorithm resulted in a percentage reduction of 0.1021% in fuel cost and 0.7995% in emission. In contrast, for test case 2, it resulted in a percentage reduction of 0.12896% in fuel cost and 0.772% in emission with the proposed algorithm. The results validate the dominance of the proposed methodology over existing methods in terms of lower fuel costs and emissions.

Comparison of Pre-Defined Automatic Machine Learning (AutoML) for MBTI Personality Prediction of Twitter Users using Binary Classification Approach

The Myers-Briggs Type Indicator (MBTI) is a personality test that is globally accepted and used as a method for identifying personality. MBTI uses a four-factor linear model to characterize a person's behaviour patterns. This feature is often used to pursue career opportunities, make decisions, manage leadership, and deal with stress. In particular, MBTI personality prediction has been widely conducted and well performed using Recurrent Neural Network (RNN) based on Twitter data because it indirectly reveals most of a person's personality through their tweets. However, deep understanding is needed in building RNN-based solutions. Hence it will take a lot of time and resources to produce an excellent model architecture and the parameters used. Therefore, this study proposed the Auto Machine Learning (AutoML) method with a pre-defined search space to determine the correct model architecture and hyperparameters based on the results of data analysis. Thus, the search algorithm can exploit environments with suitable configurations in general. There are two pre-defined search spaces employed in this study, i.e. (i) two RNN algorithms, including Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), and (ii) pre-trained Word2Ves as word embedding. In addition, this study compares the model's performance that employs preprocessing and raw data (without preprocessing). The first result shows that the preprocessing increases the F1-Score values for LSTM and GRU by 2.35% and 2.02%, respectively. Subsequently, the LSTM outperformed GRU by the values of F1-Score at 0.35% and accuracy at 0.76%. The implementation of LSTM with pre-processed data in pre-defined AutoML with Word2Vec as a word embedding technique can provide good performance on long and complex data sequences such as Twitter data for predicting its user personality.

Age at marriage and its determinants in Kerala and Bihar

BackgroundMarriage is a significant milestone in one’s life, and the age at which individuals choose to get married can have various implications. By examining the age at marriage and its determinants in different regions, such as Kerala and Bihar, we can gain insights into Socio-demographic factors that influence this decision.MethodsThe National Family Health Survey (2019–2021) data was used. A total of 41,392 ever married women from Kerala (8, 579) and Bihar (32,813) were analysed using bivariate and multiple binary logistic regression approaches to meet the study aim.ResultThe significant association was found between explanatory factors and age at first marriage in Karala and Bihar. In Bihar, educated women from the poorest families had a higher rate of early marriages. Conversely, in Kerala, uneducated women from non-majority religions and larger households (more than 6 members) were more likely to be married before18. After accounting major effects of background characteristics, the adjusted odds ratio showed that In Kerala Muslim religion women have significantly higher odds of getting married before 18 (OR: 3.09, CI 2.67–3.57) then the Hindu women whereas in Bihar Muslim religion women has the significantly lower chance of getting married before turning 18 (OR: 0.87, CI 0.81–0.93) compared to Hindu. In both the states Kerala and Bihar General social group women had the significantly lower odds of getting married below 18 (OR: 0.73, CI 0.57–0.93 and OR: 0.88, CI 0.81–0.96) with respect to SC/ST social group women’s.ConclusionWomen in Bihar usually marry in younger age due to socioeconomic and traditional reasons, whereas in Kerala reverse is true, because of a greater emphasis on education and a more progressive social outlook. These regional variations reflect different cultural norms and socioeconomic environments, shape different marriage age patterns between the two regions.

Explainable Machine-Learning Models to Predict Weekly Risk of Hyperglycemia, Hypoglycemia, and Glycemic Variability in Patients With Type 1 Diabetes Based on Continuous Glucose Monitoring.

The aim of this study was to develop and validate explainable prediction models based on continuous glucose monitoring (CGM) and baseline data to identify a week-to-week risk of CGM key metrics (hyperglycemia, hypoglycemia, glycemic variability). By having a weekly prediction of CGM key metrics, it is possible for the patient or health care personnel to take immediate preemptive action. We analyzed, trained, and internally tested three prediction models (Logistic regression, XGBoost, and TabNet) using CGM data from 187 type 1 diabetes patients with long-term CGM monitoring. A binary classification approach combined with feature engineering deployed on the CGM signals was used to predict hyperglycemia, hypoglycemia, and glycemic variability based on consensus targets (time above range ≥5%, time below range ≥4%, coefficient of variation ≥36%). The models were validated in two independent cohorts with a total of 223 additional patients of varying ages. A total of 46 593 weeks of CGM data were included in the analysis. For the best model (XGBoost), the area under the receiver operating characteristic curve (ROC-AUC) was 0.9 [95% confidence interval (CI) = 0.89-0.91], 0.89 [95% CI = 0.88-0.9], and 0.8 [95% CI = 0.79-0.81] for predicting hyperglycemia, hypoglycemia, and glycemic variability in the interval validation, respectively. The validation test showed good generalizability of the models with ROC-AUC of 0.88 to 0.95, 0.84 to 0.89, and 0.80 to 0.82 for predicting the glycemic outcomes. Prediction models based on real-world CGM data can be used to predict the risk of unstable glycemic control in the forthcoming week. The models showed good performance in both internal and external validation cohorts.

Probio-Ichnos: A Database of Microorganisms with In Vitro Probiotic Properties.

Probiotics are live microorganisms that, when consumed in adequate amounts, exert health benefits on the host by regulating intestinal and extraintestinal homeostasis. Common probiotic microorganisms include lactic acid bacteria (LAB), yeasts, and Bacillus species. Here, we present Probio-ichnos, the first manually curated, literature-based database that collects and comprehensively presents information on the microbial strains exhibiting in vitro probiotic characteristics (i.e., resistance to acid and bile, attachment to host epithelia, as well as antimicrobial, immunomodulatory, antiproliferative, and antioxidant activity), derived from human, animal or plant microbiota, fermented dairy or non-dairy food products, and environmental sources. Employing a rigorous methodology, we conducted a systematic search of the PubMed database utilizing the keyword 'probiotic' within the abstracts or titles, resulting in a total of 27,715 studies. Upon further manual filtering, 2207 studies presenting in vitro experiments and elucidating strain-specific probiotic attributes were collected and used for data extraction. The Probio-ichnos database consists of 12,993 entries on the in vitro probiotic characteristics of 11,202 distinct strains belonging to 470 species and 143 genera. Data are presented using a binary categorization approach for the presence of probiotic attributes according to the authors' conclusions. Additionally, information about the availability of the whole-genome sequence (WGS) of strains is included in the database. Overall, the Probio-ichnos database aims to streamline the navigation of the available literature to facilitate targeted validation and comparative investigation of the probiotic properties of the microbial strains.

Innovative binary nanofluid approach with copper (Cu - EO) and Magnetite ([formula omitted] - EO) for enhanced thermal performance

In this study, we present an innovative and detailed analysis of the motion of a binary nanofluid, specifically copper (Cu - EO) and Magnetite (Fe3O4 - EO), in a porous medium under solar radiation. Our research is driven by the potential to significantly enhance the thermal performance of a Parabolic Trough Solar Collector (PTSC) using a binary nanofluid. The boundary conditions, partial differential restrictions, and the governing PDEs are transformed into the ODEs system with appropriate similarity transformations. The finite element method (FEM) and semi-analytical technique memad Akbari-Ganji's Method (AGM) are used to solve the approximate solutions of ODEs. The findings of evaluating Copper (Cu - EO) and Magnetite (Fe3O4 - EO) were the two different nanofluids based on engine oil that were presented. Furthermore, the model's overall entropy variations are enhanced using Reynolds. Moreover, our study contributes to understanding fluidity and viscosity alterations in such systems. We use the Brinkman number to observe these alterations. We reveal that the thermal efficiency of (Cu - EO) is lower than (Fe3O4 - EO) by a range of 0.005–0.6. This indicates a substantial enhancement in the thermal performance of the PTSC.

FL-DSFA: Securing RPL-Based IoT Networks against Selective Forwarding Attacks Using Federated Learning.

The Internet of Things (IoT) is a significant technological advancement that allows for seamless device integration and data flow. The development of the IoT has led to the emergence of several solutions in various sectors. However, rapid popularization also has its challenges, and one of the most serious challenges is the security of the IoT. Security is a major concern, particularly routing attacks in the core network, which may cause severe damage due to information loss. Routing Protocol for Low-Power and Lossy Networks (RPL), a routing protocol used for IoT devices, is faced with selective forwarding attacks. In this paper, we present a federated learning-based detection technique for detecting selective forwarding attacks, termed FL-DSFA. A lightweight model involving the IoT Routing Attack Dataset (IRAD), which comprises Hello Flood (HF), Decreased Rank (DR), and Version Number (VN), is used in this technique to increase the detection efficiency. The attacks on IoT threaten the security of the IoT system since they mainly focus on essential elements of RPL. The components include control messages, routing topologies, repair procedures, and resources within sensor networks. Binary classification approaches have been used to assess the training efficiency of the proposed model. The training step includes the implementation of machine learning algorithms, including logistic regression (LR), K-nearest neighbors (KNN), support vector machine (SVM), and naive Bayes (NB). The comparative analysis illustrates that this study, with SVM and KNN classifiers, exhibits the highest accuracy during training and achieves the most efficient runtime performance. The proposed system demonstrates exceptional performance, achieving a prediction precision of 97.50%, an accuracy of 95%, a recall rate of 98.33%, and an F1 score of 97.01%. It outperforms the current leading research in this field, with its classification results, scalability, and enhanced privacy.

Exchanging International Lessons on Contemporary Coalition-Led Governments: Implications for the “Political-Administrative Dichotomy”

ABSTRACT The discipline of public administration has long grappled with the issue of the political-administrative dichotomy. A lopsided binary and categorical approach to political and administrative relationships seems to have been unable to reveal the complexity and multifaceted contextual nature of most contemporary coalition-led governments. This article draws on international lessons from subject experts exposed to coalition-led governments and the political-administrative dichotomy in developed and developing countries. The article proposes an alternative multifaceted contextualized approach to creating a positive and engaging learning environment between developed and developing countries in order to improve the contemporary political-administrative interface.

Thermal optimization of ivermectin in supercritical carbon dioxide and ethanol to produce nano medicine

The solubility of ivermectin in high pressure carbon dioxide (CO2) at 338, 328, 318, and 308 K temperatures was investigated with and without an ethanol. Several methods were employed to model the data obtained from the experiments. ivermectin exhibited solubility values ranging from 0.130 × 10−5 to 1.760 × 10−4 in the binary system and 1.880 × 10−5 to 1.237 × 10−4 in the ternary system. The outcome indicated that the addition of ethanol significantly increased the mole fraction of ivermectin in CO2. The highest impact of ivermectin solubility was found in the ivermectin -Ethanol- CO2 system at 338 K and 12 MPa, which was about 14.35 times greater than binary system under the same conditions. The models proposed by Jouyban et al. and Sodeifian-Sajadian models showed the best correlation with average absolute relative deviation (AARD%) and Akaike information criterion (AICc) for binary and ternary approaches, respectively. The results confirmed that rapid expansion supercritical solution (RESS) and gas antisolvent (GAS) method can be apply for producing nanoparticles at the suitable ranges of the drug solubility.

Optimized differential evolution and hybrid deep learning for superior drug-target binding affinity prediction

Investigating Drug-Target Interactions (DTI) is crucial for drug repositioning and discovery tasks. However, discovering DTIs through experimental approaches is time-consuming and requires substantial financial resources. To address these challenges, machine learning-based methodologies have been adopted to reduce costs and save time. Unfortunately, the effectiveness of these methods has been limited due to the binary classification approach and the lack of empirically validated negative samples. The availability of abundant DTI datasets and protein structure data has enabled the development of new approaches, such as redefining the DTI problem as a regression task. Given this context, we propose an innovative deep-learning approach to predict binding affinities between drugs and targets. Our model, named the Convolution Self-Attention Network with Attention-based Bidirectional Long Short-Term Memory Network (CSAN-BiLSTM-Att), integrates convolutional neural network (CNN) blocks with self-attention mechanisms to create an attention-based bidirectional long short-term memory (BiLSTM) model, followed by fully connected layers. Due to the model's complexity, proper hyperparameter tuning is essential. To optimize this, we employ the Differential Evolution (DE) technique to select the most suitable hyperparameters. Experimental results demonstrate that the DE-based CSAN-BiLSTM-Att model outperforms previous approaches. Specifically, the model achieved a concordance index of 0.898 and a mean square error of 0.228 on the DAVIS dataset, and a concordance value of 0.971 with a mean square error of 0.014 on the KIBA dataset.

EU membership and income inequality: escaping the single and binary treatment approach

EU membership and income inequality: escaping the single and binary treatment approach

Lithology identification of coal-bearing strata based on data-driven dual-channel relevance networks in coal mine roadway drilling process

The accurate prediction of coal seam thickness and the identification of the lithology of coal-bearing strata represent a crucial aspect of the intelligent perception of the stratigraphic environment. These technologies represent a fundamental aspect of intelligent mining operations with respect to coal. Accordingly, this paper concentrates on the investigation of lithology identification in coal-bearing strata through the utilization of data-driven dual-channel relevance networks in the context of coal mine roadway drilling operations. In consideration of the impact of coal seam thickness fluctuations on lithology identification, the region in question is initially delineated into two distinct categories: those comprising relatively stable coal seams and those comprising unstable coal seams. This is achieved through the application of coal seam thickness prediction and stability evaluation techniques. Subsequently, in consideration of the varying challenges posed by the region's coal seams, which can be either relatively stable or unstable, distinct lithology identification schemes are employed in different regions. In regions where the coal seam is relatively stable, there is a significant demand for classification of soft and hard coal seams. Additionally, the non-coal seam samples belong to a limited number of classes, necessitating the use of the SMOTE-GBDT algorithm to classify the coal-bearing strata into soft coal seam, hard coal seam, and non-coal seam. In the case of an unstable coal seam, the ability to distinguish between different seams is of paramount importance for lithology identification purposes. To this end, a double-layer binary classification RVM approach is employed to categorize coal-bearing strata into weak interlayer, coal seam and mudstone layer. The proposed methodology entails the utilization of diverse techniques in accordance with the specific characteristics of varying coal seam stability regions, with the objective of meticulously delineating the targets of lithology identification. This approach facilitates the generation of a comprehensive understanding of the coal-bearing strata environment, which can subsequently inform the implementation of intelligent adaptive control strategies.

Let it go, let it go: Stop measuring child maltreatment as a binary yes/no

Numerous methods are used in the measurement of child maltreatment (CM) exposure. As a science, it is necessary that the field of CM research evaluate its measurement approaches periodically to ensure that the common approaches are the best approaches. A prominent method for measuring CM in research as a predictor variable is to conceptualize CM as a two-level, yes/no binary variable (e.g., 0 = No CM exposure, 1 = CM exposure). While there is no consensus on what method is the best approach for measuring CM, empirical evidence suggests that the binary measurement approach to CM has significant limitations. The current paper sought to progress the field of CM and trauma research forward by reviewing several lines of research demonstrating why the use of a binary yes/no CM measurement approach is problematic. As evidence for why a binary measurement of CM should be halted, this paper reviews research on: why the characteristics or details of CM exposure matter, risk of CM “contamination,” and CM's relation with environmental or systemic factors. The ethical and clinical implications of a CM binary measurement approach are also discussed. Several recommendations for the field are provided on how researchers can improve the measurement of CM and ensure accurate and replicable studies are being published.

W(Hole). Matter and its absence in woven textiles

Weaving is a binary approach to being, in which a perpendicular entanglement of threads allows for cloth to exist. For millennia, the primacy of threads has shaped the making of woven textiles. However, a seemingly inherent element has been overlooked: negative spaces. In this reflection, such spaces relate to “holes” or the empty spaces adjoining warp and weft. Drawing on textile theory, language, mathematics and the question of emergence, the paper critically explores the ways in which weavers understand weave structure construction. The reflection interrogates our comprehension of the negative space in weaving. Seen as an absence, a “not-something” as opposed to a “nothing,” how can we capture the woven hole? And in doing so, what is our intention? The paper juxtaposes concept and technique to further the craft’s essence and potentially develop a new textile language visualisation.

A binary particle swarm optimization-based pruning approach for environmentally sustainable and robust CNNs

Deep Convolutional Neural Networks (CNNs), continue to demonstrate remarkable performance across various tasks. However, their computational demands and energy consumption present significant drawbacks, restricting their practical deployment and contributing to a substantial carbon footprint. This paper addresses this challenge by proposing a novel method named Binary Particle Swarm Optimization Layer Pruner (BPSO-LPruner), aimed at achieving substantial computational reduction and mitigating environmental impact during CNN inference. BPSO-LPruner utilizes a constrained Binary Particle Swarm Optimization for CNN layer pruning, integrating a masked-bit strategy and a new population initialization strategy to enhance search performance. We illustrate the effectiveness of our method in reducing model computational costs and carbon footprint emissions while improving performance across multiple models (VGG16, VGG19, DenseNet-40, ResNet18, ResNet20, ResNet34, ResNet44, ResNet56, ResNet110, ResNet50, and MobileNetv2) and diverse datasets (CIFAR-10, CIFAR-100, Tiny-ImageNet, COVID-19 X-ray dataset). Promising results underscore the performance of the proposed method. Additionally, we demonstrate that layer pruning yields benefits beyond enhanced computational performance. Our experimentation reveals that BPSO-LPruner enhances the model’s reliability and robustness by effectively addressing variations in input data, inherent ambiguity in model parameters, and adversarial images.