Classification Framework Research Articles

Mixed Cardiogenic Shock: A Proposal for Standardized Classification, a Hemodynamic Definition, and Framework for Management.

The classification of cardiogenic shock (CS) has evolved from a singular cold-and wet-hemodynamic profile. Data from registries and clinical trials have contributed to a broader recognition that although all patients with CS have insufficient cardiac output leading to end organ hypoperfusion, there is considerable variability in CS acuity, underlying etiologies, volume status, and systemic vascular resistance. Mixed CS can be broadly categorized as CS with at least 1 additional shock state. Mixed CS states are now the second leading cause of shock in contemporary coronary intensive care units, but there is little high-quality evidence to guide routine care, and there are no standardized classification frameworks or well-established hemodynamic definitions. This primer summarizes the current epidemiology and proposes a classification framework and invasive hemodynamic parameters to guide categorization that could be applied to help better phenotype patients captured in registries and trials, as well as guide management of mixed CS states.

Equipment Sounds’ Event Localization and Detection Using Synthetic Multi-Channel Audio Signal to Support Collision Hazard Prevention

Construction workplaces often face unforeseen collision hazards due to a decline in auditory situational awareness among on-foot workers, leading to severe injuries and fatalities. Previous studies that used auditory signals to prevent collision hazards focused on employing a classical beamforming approach to determine equipment sounds’ Direction of Arrival (DOA). No existing frameworks implement a neural network-based approach for both equipment sound classification and localization. This paper presents an innovative framework for sound classification and localization using multichannel sound datasets artificially synthesized in a virtual three-dimensional space. The simulation synthesized 10,000 multi-channel datasets using just fourteen single sound source audiotapes. This training includes a two-staged convolutional recurrent neural network (CRNN), where the first stage learns multi-label sound event classes followed by the second stage to estimate their DOA. The proposed framework achieves a low average DOA error of 30 degrees and a high F-score of 0.98, demonstrating accurate localization and classification of equipment near workers’ positions on the site.

A novel image classification framework based on variational quantum algorithms

Image classification is a crucial task in machine learning with widespread practical applications. The existing classical framework for image classification typically utilizes a global pooling operation at the end of the network to reduce computational complexity and mitigate overfitting. However, this operation often results in a significant loss of information, which can affect the performance of classification models. To overcome this limitation, we introduce a novel image classification framework that leverages variational quantum algorithms (VQAs) hybrid approaches combining quantum and classical computing paradigms within quantum machine learning. The major advantage of our framework is the elimination of the need for the global pooling operation at the end of the network. In this way, our approach preserves more discriminative features and fine-grained details in the images, which enhances classification performance. Additionally, employing VQAs enables our framework to have fewer parameters than the classical framework, even in the absence of global pooling, which makes it more advantageous in preventing overfitting. We apply our method to different state-of-the-art image classification models and demonstrate the superiority of the proposed quantum architecture over its classical counterpart through a series of state vector simulation experiments on public datasets. Our experiments show that the proposed quantum framework achieves up to a 9.21% increase in accuracy and up to a 15.79% improvement in F1 score, compared to the classical framework. Additionally, we explore the impact of shot noise on our method through shot-based simulation and find that increasing the number of measurements does not always lead to better results. Selecting an appropriate number of measurements can yield optimal results, even surpassing those obtained from state vector simulation.

Blockchain Tokens, Price Volatility, and Active User Base: An Empirical Analysis Based on Tokenomics

Blockchain tokens have accumulated tremendous market value but remain highly controversial, given their price volatility and seemingly speculative nature. Ironically, this very characteristic can foster token retention as users wait for occasions of appreciation. In this paper, we conduct an empirical analysis with 58 tokens in two steps: first, an investigation of the drivers of user activity and token price volatility using a new blockchain token classification framework, searching for possible tokenomics links. Our findings suggest that there is an intrinsic relationship between the way tokens are used as a means of exchange and how token usage dynamics influence user engagement oppositely to market stability. Only some features, such as earning potential and voting rights, foster token-holding strategies, while only Ethereum ecosystem membership has positive effects on price volatility. Second, we analyze the direct relationship between price volatility and active users. Results show that, on average, a 10% increase in volatility is related to a decrease in active addresses ranging between 3.96% and 5.88%. The finding is supportive of the hypothesis that token price volatility may be treated as an opportunity to increase token retention.

Retraction Note: Volumetric analysis framework for accurate segmentation and classification (VAF-ASC) of lung tumor from CT images

Retraction Note: Volumetric analysis framework for accurate segmentation and classification (VAF-ASC) of lung tumor from CT images

Is metadata of articles about COVID-19 enough for multilabel topic classification task?

The ever-increasing volume of COVID-19-related articles presents a significant challenge for the manual curation and multilabel topic classification of LitCovid. For this purpose, a novel multilabel topic classification framework is developed in this study, which considers both the correlation and imbalance of topic labels, while empowering the pretrained model. With the help of this framework, this study devotes to answering the following question: Do full texts, MeSH (Medical Subject Heading), and biological entities of articles about COVID-19 encode more discriminative information than metadata (title, abstract, keyword, and journal name)? From extensive experiments on our enriched version of the BC7-LitCovid corpus and Hallmarks of Cancer corpus, the following conclusions can be drawn. Our framework demonstrates superior performance and robustness. The metadata of scientific publications about COVID-19 carries valuable information for multilabel topic classification. Compared to biological entities, full texts and MeSH can further enhance the performance of our framework for multilabel topic classification, but the improved performance is very limited. Database URL: https://github.com/pzczxs/Enriched-BC7-LitCovid.

A hybrid feature fusion deep learning framework for multi-source medical image analysis

Despite the widespread adoption of deep learning to enhance image classification, significant obstacles remain. First, multisource data with diverse sizes and formats is a great challenge for most current deep learning models. Second, lacking manual labeled data for model training limits the application of deep learning. Third, the widely used CNN-based methods shows their limitations in extracting global features and yield poor performance for image topology. To address these issues, we propose a Hybrid Feature Fusion Deep Learning (HFFDL) framework for image classification. This framework consists of an automated image segmentation module, a two-stream backbone module, and a classification module. The automatic image segmentation module utilizes the U-Net model and transfer learning to detect region of interest (ROI) in multisource images; the two-stream backbone module integrates the Swin Transformer architecture with the Inception CNN, with the aim of simultaneous extracting local and global features for efficient representation learning. We evaluate the performance of HFFDL framework with two publicly available image datasets: one for identifying COVID-19 through X-ray scans of the chest (30,386 images), and another for multiclass skin cancer screening using dermoscopy images (25,331 images). The HFFDL framework exhibited greater performance in comparison to many cutting-edge models, achieving the AUC score 0.9835 and 0.8789, respectively. Furthermore, a practical application study conducted in a hospital, identifying viable embryos using medical images, revealed the HFFDL framework outperformed embryologists.

Software architecture-based self-adaptation in robotics

Context:Robotics software architecture-based self-adaptive systems (RSASSs) are robotics systems made robust to runtime uncertainty by adapting their software architectures. The research landscape of RSASS approaches is multidisciplinary and fragmented, with many aspects still unexplored or ineffectively shared among communities involved. Objective:We aim at identifying, classifying, and analyzing the state of the art of existing approaches for RSASSs from the following perspectives: (i) the key characteristics of approaches and (ii) the evaluation strategies applied by researchers. Method:We apply the systematic mapping research method. We selected 37 primary studies via automatic, manual, and snowballing-based search and selection procedures. We rigorously defined and applied a classification framework composed of 32 parameters and synthesize the obtained data to produce a comprehensive overview of the state of the art. Results:This work contributes (i) a rigorously defined classification framework for studies on RSASSs, (ii) a systematic map of the research efforts on RSASSs, (iii) a discussion of emerging findings and implications for future research, and (iv) a publicly available replication package. Conclusion:This study provides a solid evidence-based overview of the state of the art in RSASS approaches. Its results can benefit RSASS researchers at different levels of seniority and involvement in RSASS research.Editor’s note: Open Science material was validated by the Journal of Systems and Software Open Science Board.

Attention Induced Dual Convolutional-Capsule Network (AIDC-CN): A deep learning framework for motor imagery classification

In recent times, Electroencephalography (EEG)-based motor imagery (MI) decoding has garnered significant attention due to its extensive applicability in healthcare, including areas such as assistive robotics and rehabilitation engineering. Nevertheless, the decoding of EEG signals presents considerable challenges owing to their inherent complexity, non-stationary characteristics, and low signal-to-noise ratio. Notably, deep learning-based classifiers have emerged as a prominent focus for addressing the EEG signal decoding process. This study introduces a novel deep learning classifier named the Attention Induced Dual Convolutional-Capsule Network (AIDC-CN) with the specific aim of accurately categorizing various motor imagination class labels. To enhance the classifier’s performance, a dual feature extraction approach leveraging spectrogram and brain connectivity networks has been employed, diversifying the feature set in the classification task. The main highlights of the proposed AIDC-CN classifier includes the introduction of a dual convolution layer to handle the brain connectivity and spectrogram features, addition of a novel self-attention module (SAM) to accentuate the relevant parts of the convolved spectrogram features, introduction of a new cross-attention module (CAM) to refine the outputs obtained from the dual convolution layers and incorporation of a Gaussian Error Linear Unit (GELU) based dynamic routing algorithm to strengthen the coupling among the primary and secondary capsule layers. Performance analysis undertaken on four public data sets depict the superior performance of the proposed model with respect to the state-of-the-art techniques. The code for this model is available at https://github.com/RiteshSurChowdhury/AIDC-CN.

Innovative breast cancer detection using a segmentation-guided ensemble classification framework

Innovative breast cancer detection using a segmentation-guided ensemble classification framework

Secure and Transparent Lung and Colon Cancer Classification Using Blockchain and Microsoft Azure

Background: The global healthcare system faces challenges in diagnosing and managing lung and colon cancers, which are significant health burdens. Traditional diagnostic methods are inefficient and prone to errors, while data privacy and security concerns persist. Objective: This study aims to develop a secure and transparent framework for remote consultation and classification of lung and colon cancer, leveraging blockchain technology and Microsoft Azure cloud services. Dataset and Features: The framework utilizes the LC25000 dataset, containing 25,000 histopathological images, for training and evaluating advanced machine learning models. Key features include secure data upload, anonymization, encryption, and controlled access via blockchain and Azure services. Methods: The proposed framework integrates Microsoft Azure’s cloud services with a permissioned blockchain network. Patients upload CT scans through a mobile app, which are then preprocessed, anonymized, and stored securely in Azure Blob Storage. Blockchain smart contracts manage data access, ensuring only authorized specialists can retrieve and analyze the scans. Azure Machine Learning is used to train and deploy state-of-the-art machine learning models for cancer classification. Evaluation Metrics: The framework’s performance is evaluated using metrics such as accuracy, precision, recall, and F1-score, demonstrating the effectiveness of the integrated approach in enhancing diagnostic accuracy and data security. Results: The proposed framework achieves an impressive accuracy of 100% for lung and colon cancer classification using DenseNet, ResNet50, and MobileNet models with different split ratios (70–30, 80–20, 90–10). The F1-score and k-fold cross-validation accuracy (5-fold and 10-fold) also demonstrate exceptional performance, with values exceeding 99.9%. Real-time notifications and secure remote consultations enhance the efficiency and transparency of the diagnostic process, contributing to better patient outcomes and streamlined cancer care management.

A novel classification framework for genome-wide association study of whole brain MRI images using deep learning.

Genome-wide association studies (GWASs) have been widely applied in the neuroimaging field to discover genetic variants associated with brain-related traits. So far, almost all GWASs conducted in neuroimaging genetics are performed on univariate quantitative features summarized from brain images. On the other hand, powerful deep learning technologies have dramatically improved our ability to classify images. In this study, we proposed and implemented a novel machine learning strategy for systematically identifying genetic variants that lead to detectable nuances on Magnetic Resonance Images (MRI). For a specific single nucleotide polymorphism (SNP), if MRI images labeled by genotypes of this SNP can be reliably distinguished using machine learning, we then hypothesized that this SNP is likely to be associated with brain anatomy or function which is manifested in MRI brain images. We applied this strategy to a catalog of MRI image and genotype data collected by the Alzheimer's Disease Neuroimaging Initiative (ADNI) consortium. From the results, we identified novel variants that show strong association to brain phenotypes.

A modified ResNet152v2 framework for bird species classification

A modified ResNet152v2 framework for bird species classification

Construction Jobsite Image Classification Using an Edge Computing Framework

Image classification is increasingly being utilized on construction sites to automate project monitoring, driven by advancements in reality-capture technologies and artificial intelligence (AI). Deploying real-time applications remains a challenge due to the limited computing resources available on-site, particularly on remote construction sites that have limited telecommunication support or access due to high signal attenuation within a structure. To address this issue, this research proposes an efficient edge-computing-enabled image classification framework for support of real-time construction AI applications. A lightweight binary image classifier was developed using MobileNet transfer learning, followed by a quantization process to reduce model size while maintaining accuracy. A complete edge computing hardware module, including components like Raspberry Pi, Edge TPU, and battery, was assembled, and a multimodal software module (incorporating visual, textual, and audio data) was integrated into the edge computing environment to enable an intelligent image classification system. Two practical case studies involving material classification and safety detection were deployed to demonstrate the effectiveness of the proposed framework. The results demonstrated the developed prototype successfully synchronized multimodal mechanisms and achieved zero latency in differentiating materials and identifying hazardous nails without any internet connectivity. Construction managers can leverage the developed prototype to facilitate centralized management efforts without compromising accuracy or extra investment in computing resources. This research paves the way for edge “intelligence” to be enabled for future construction job sites and promote real-time human-technology interactions without the need for high-speed internet.

A Method for Predicting the Result of University Employment Education Transformation Based on Multi-Source Information Technology

In the data on the outcomes of higher education employment transformation, there is high correlation among multiple independent variables, leading to multicollinearity. If multicollinearity exists, it can complicate the establishment of predictive analysis models and the interpretation of relationships between variables for higher education employment transformation outcomes. The employment issues of college graduates have become a focal point of social concern. These issues not only reflect the employment status of college graduates but also indirectly indicate the quality of higher education and the level of talent cultivation. Therefore, a prediction method for the effectiveness of higher education employment transformation based on multi-source information technology is proposed. According to the theory of multi-source information technology, an employment data classification framework is constructed to integrate multi-source information. The matching operator function output values are calculated, weights are determined, and the final college student information collection results are output. The standard error between employment unit types and salary ranges is analyzed, clustering training samples are trained, and the distance from each employment information sample to the centroid is calculated to obtain preprocessing results of the transformation outcomes, thus avoiding the impact of multicollinearity on the results of higher education employment transformation. A model structure for analyzing factors influencing higher education employment is established, allowing for an understanding of the characteristics of different types of educational resources and enabling the prediction of the effectiveness of higher education employment transformation. Experimental results show that this method can accurately monitor the dynamic employment situation of university students. After applying this method, the standard error and probability error values are significantly reduced, proving to be significantly effective in predicting the outcomes of higher education employment transformation.

Lock Operations Through the Operator’s Eyes: A Qualitative Exploration of Gaze Strategies

This paper reports a qualitative exploration of gaze strategies during closed-circuit television (CCTV) tasks in remote nautical object control of a lock. Previous research has not examined gaze strategies in scenarios where systems, such as nautical objects, are operated remotely using CCTV. As contextual factors matter in nautical object control, a qualitative approach was necessary to uncover domain-specific terminology and insights into gaze strategies. We recorded eye gaze from professional lock operators and then conducted semi-structured interviews with domain experts to assess these recordings. Thematic analysis revealed that experts were able to identify (features of) gaze strategies but did not share the same terminology. Based on this analysis we defined four strategies: anticipating, verifying, overview, and movement-directed gazes (RQ1). All strategies, except movement-directed gaze, were observed consistently across operators (RQ2), with verifying gaze aligning with task steps in a predefined protocol (RQ3). More generally, our classification framework from thematic analysis could help to systematically define and verify gaze strategies based on domain and task features across various CCTV working contexts. For nautical object control, the framework can be instrumental in interpreting and verifying future (quantitative) eye tracking results and informing instructional procedures.

DsAMP and dsAMPGAN: Deep Learning Networks for Antimicrobial Peptides Recognition and Generation.

Antibiotic resistance is a growing public health challenge. Antimicrobial peptides (AMPs) effectively target microorganisms through non-specific mechanisms, limiting their ability to develop resistance. Therefore, the prediction and design of new AMPs is crucial. Recently, deep learning has spurred interest in computational approaches to peptide drug discovery. This study presents a novel deep learning framework for AMP classification, function prediction, and generation. We developed discoverAMP (dsAMP), a robust AMP predictor using CNN Attention BiLSTM and transfer learning, which outperforms existing classifiers. In addition, dsAMPGAN, a Generative Adversarial Network (GAN)-based model, generates new AMP candidates. Our results demonstrate the superior performance of dsAMP in terms of sensitivity, specificity, Matthew correlation coefficient, accuracy, precision, F1 score, and area under the ROC curve, achieving >95% classification accuracy with transfer learning on a small dataset. Furthermore, dsAMPGAN successfully synthesizes AMPs similar to natural ones, as confirmed by comparisons of physical and chemical properties. This model serves as a reliable tool for the identification of novel AMPs in clinical settings and supports the development of AMPs to effectively combat antibiotic resistance.

Hybrid segmentation and 3D Imaging: Comprehensive framework for breast cancer patient segmentation and classification based on digital breast tomosynthesis

Breast cancer is among the deadliest conditions and the second-leading reason for cancer mortality in women. Breast cells begin to develop into malignant, cancerous tumors, which is how breast cancer develops. Self-tests and routine professional examinations aid in early diagnosis, which increases the likelihood of surviving. A major difficulty for researchers is the categorization of breast cancer as a medical procedure. The prevailing aim of this research is the earlier recognition of breast cancer using 3D images and AI monitors. Initially, the mammogram images are collected and preprocessed to enhance the image quality. Noise removal is done using a Multistage Selective Convolution Filter (MSCF), contrast enhancement is done using an Enhanced Contrast Limited Adaptive Histogram (ECLAH), and an Improved Canny Operator (ICO) is employed for edge detection. Segmentation is done using the DENSE Squeeze Excitation Network (DENSE SE- Net). The preprocessed images are converted to 3D images using Digital Breast Tomosynthesis (DBT). From the hybrid segmented and 3D images, the objects are identified utilizing the You Only Look Once v7 (YOLO v7), and the images are classified into mild, medium, severe, and unaffected women using semi-supervised CNN (SS CNN). Finally, an AI monitor is used to monitor the patients. The simulation findings reveal that the suggested technique yields higher accuracy, precision, recall, and F1 score and better ROC characteristics than the existing approaches.

Scientific Classification of Malware from Practice and Multi-Label Mechanism for Risky Behaviors

Objective: In order to respond to the demand of academia and industry for scientific malware classification methods Method: based on the existing work, this study draws on the advantages of Kaspersky's relatively rigorous multi-segment classification and naming, and is carried out according to the idea of emphasizing mutual exclusivity, complete coverage, and convergence, and is combined with the threat risk behavior labels. Results: A set of malware classification framework that conforms to MECE principles, converges classification, and is compatible with industrial fact classification has been formed. Implication: It can effectively support security defense and governance.

A NOVEL WAY TO CLASSIFY THE SLAKE DURABILITY INDEX OF ROCKS

Slaking, the disintegration of rocks upon exposure to moisture and air, poses significant challenges in engineering applications, such as in slope stability and embankment design. This study improves the slake durability index test by introducing several enhancements to better reflect the field conditions of rocks. A new test methodology is developed which includes a revised slake durability classification table, a novel Discard Method for calculating weight retention in the test drum, and an updated classification chart. The improved methodology considers parameters such as porosity and strength, evaluated through index, Schmidt hammer rebound and point load tests. The new classification table categorizes rocks into durability classes according to the field observations and laboratory test results. The Discard Method improves accuracy by eliminating broken pieces from the durability calculation, addressing the limitations in the suggested method. A Configured Discard Method equation further defines the durability estimation by combining porosity, strength and slake durability data. Field investigations and laboratory tests conducted with various rock types demonstrate that the new classification system provides more accurate and practical assessments of rock durability. This study highlights the importance of effective porosity and strength impact which enhance the reliability of slake durability evaluations, offering a revised classification framework that simplifies field assessments while maintaining the accuracy. Future research should focus on developing these methods and expanding their applicability to diverse geological contexts by including more material to test.