Robust Classification System Research Articles

Enhanced Mood and Theme Recognition in Music Using Lyrical Sentiment Analysis

This paper presents an innovative approach to mood and theme recognition in music by leveraging lyrical sentiment analysis and audio signal processing techniques. As music plays a crucial role in emotional expression and cultural representation, understanding the mood and thematic elements within songs is essential for enhancing the listening experience. Traditional methods of music analysis often focus separately on audio signals or lyrics, failing to capture the intricate relationship between the two. To address this gap, we propose a hybrid model that integrates deep learning algorithms, such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs), with Natural Language Processing (NLP) techniques to provide a comprehensive understanding of musical content. In our study, we employ the CAL500 dataset, which contains a diverse selection of songs to facilitate effective analysis. The first component of our methodology involves lyrical sentiment analysis, where the preprocess the lyrics through techniques like tokenization, stemming, and stop-word removal to extract emotional context. This is complemented by audio signal processing, where features such as tempo, rhythm, and pitch are extracted using libraries like Librosa, allowing for a nuanced understanding of the music's tonal characteristics. The integration of insights derived from lyrical sentiment and audio signal processing enables the development of a robust classification system that accurately identifies mood and themes in music. Our results indicate that the combined approach significantly enhances mood recognition accuracy and reveals recurring themes within song lyrics, providing deeper insights into the underlying narrative and artistic intent. Ultimately, this research contributes to the fields of music theory, machine learning, and emotional analysis by proposing a novel framework for understanding the emotional landscape of music. The anticipated outcomes include improvements in music classification accuracy, insights into the emotional and cultural significance of songs, and potential applications in music therapy and personalized music experiences. By bridging characteristics, this study aims to transform how listeners interact with music, enhancing their emotional connection and appreciation of this art form

Grain Size Effects on Visible and Near-infrared (0.35–2.5 μm) Laboratory Spectra of Rare Meteorite Classes

Linking near-Earth asteroids to associated meteorites can be a challenging process for many reasons, one being grain size differences. To address this issue for rarer meteorites, we studied visible and near-infrared (0.35–2.5 μm) reflectance spectra of 11 rare meteorite classes over five different grain size bins (45–90 μm, 90–150 μm, 150–300 μm, 300–500 μm, and 500–1000 μm). We analyzed the reflectance properties, diagnostic spectral band parameters (band centers and band area ratios), spectral slope, and taxonomic classification. The spectra were analyzed using principal component analysis to detect trends in principal component (PC) space and the impact on asteroid taxonomic classification in the Bus–DeMeo system. We found that the absolute reflectance (visual albedo) at 0.55 μm (photometric V band) typically decreases with increasing grain size, although there are some variations such as sharp increases for the slabs. Our EH4 and aubrite show a trend of increasing spectral slope with decreasing grain size. Our ureilite, angrite, winonaite, acapculoite, and mesosiderite show a general trend of a decrease in Band I (∼0.9 μm) depth with increasing grain size up to 500–1000 μm. Taxonomic classification of spectra of all grain sizes shows that classification tools generally struggle to differentiate grain size effects from mineralogical variations. This research demonstrates the need for a more robust taxonomic classification system that accounts for grain size and one that accurately classifies small near-Earth asteroids with regolith-free surfaces.

Intelligent fault diagnosis for tribo-mechanical systems by machine learning: Multi-feature extraction and ensemble voting methods

Timely fault detection is crucial for preventing issues like worn clutch plates and excessive friction material degradation, enhancing fuel efficiency, and prolonging clutch lifespan. This study focuses on early fault diagnosis in dry friction clutch systems using machine learning (ML) techniques. Vibration data is analyzed under different load and fault conditions, extracting statistical, histogram, and auto-regressive moving average (ARMA) features. Feature selection employs the J48 decision tree algorithm, evaluated with eight ML classifiers: support vector machines (SVM), k-nearest neighbor (kNN), linear model tree (LMT), random forest (RF), multilayer perceptron (MLP), logistic regression (LR), J48, and Naive Bayes. The evaluation revealed that individual classifiers achieved the highest testing accuracies with statistical feature selection as 83% for both MLP and LR at no load, 90% for MLP at 5 kg, and 93% for KNN at 10 kg. For histogram feature selection, KNN and MLP both reached 85% at no load, MLP achieved 91% at 5 kg, and RF attained 97% at 10 kg. With ARMA feature selection, KNN reached 93% at no load, LR achieved 94% at 5 kg, and RF reached 86% at 10 kg. The voting strategy notably improved these results, with the RF-KNN-J48 ensemble reaching 98% for histogram features at 10 kg, the KNN-LMT-RF ensemble achieving 94% for ARMA features at no load, and the SVM-MLP-LMT ensemble attaining 95% for ARMA features at 5 kg. Hence, a combination of three classifiers using the majority voting rule consistently outperforms standalone classifiers, striking a balance between diversity and complexity, facilitating robust decision-making. In practical applications, selecting the optimal combination of feature selection method and classifier is vital for accurate fault classification. This study provides valuable guidance for engineers and practitioners implementing robust load classification systems in industrial settings.

Current Situation of Non-cleft Craniofacial Anomalies in Thailand: A Multicenter Study.

Non-cleft craniofacial anomalies significantly impact patients' lives and health care systems. This study addresses the gap in the literature concerning these anomalies. Conducted at 4 major hospitals across Thailand, the research aims to provide an overview and understand the experiences of caregivers. The authors conducted a cross-sectional descriptive study in a 3-year period involving 224 primary caregivers of young patients with non-cleft craniofacial anomalies (demographics, medical history, psychosocial aspects). The authors found the highest prevalence of anomalies in the Northern (26.8%) region and the lowest in the Western (3.1%) region. Craniosynostosis and clefts were the predominant anomalies (67.0%), with a surprising lack of family history (7%). Diagnoses were frequently established at regional hospitals (42.0%). Notably, the average outpatient visit was 18.22. A substantial portion of patients required multiple hospital stays: 65.6% with 1 to 5 stays and 9.8% with more than 5 stays. Despite frequent visits, 29% had not received necessary surgery. Of caregivers, 78% had a family income in the middle range (5000-50,000 Thai baht/mo), yet a significant proportion (59.4%) perceived their income as adequate. Their education was bachelor's and higher in only 27.2%. Although stress was common (62.1%), most caregivers (79.0%) did not consider it a burden. The study highlights the challenges faced by both patients and caregivers. It reveals a need for improved access to specialized care, more specialists, dedicated centers, and support networks. A more robust classification system is also essential. To optimize care, a comprehensive and region-specific health care approach is crucial.

Classification of Rice Grains by Image Processing

General Background: The assessment of the surface quality of pre-treated rice grains is crucial for determining their market acceptability, storage stability, processing quality, and overall consumer satisfaction. Traditional evaluation methods are often time-consuming and yield subjective classifications. Specific Background: The lack of a comprehensive tagged image dataset hinders the application of advanced convolutional neural networks (CNN) for detailed damage classification of healthy rice grains. Knowledge Gap: Existing datasets and methods limit the effective exploration of sophisticated CNN models for categorizing rice types, particularly in identifying subtle damage characteristics. Aims: The study aims to create a robust rice grain classification system using image processing techniques, primarily deep learning algorithms, to improve the classification of rice varieties. Results: Utilizing a dataset of 75,000 images across five widely cultivated rice varieties in Turkey, we achieved classification accuracies of 100% for CNN, 99.95% for deep neural networks (DNN), and 99.87% for artificial neural networks (ANN). Novelty: The proposed approach represents a significant advancement in rice classification technology, employing a combination of image acquisition, feature extraction, and machine learning to streamline the process, effectively addressing the challenges faced in traditional methods. Implications: The findings underscore the potential for improved sorting and grading efficiency in the rice industry, facilitating better market outcomes and consumer satisfaction through enhanced quality control Highlights: Innovative: Uses CNN for accurate rice variety classification. Data-Driven: Analyzes 75,000 images for enhanced quality evaluation. Impactful: Increases efficiency in sorting and grading processes. Keywords: Rice Classification, Image Processing, CNN, Machine Learning, Agricultural Technology

Pore size classification and prediction based on distribution of reservoir fluid volumes utilizing well logs and deep learning algorithm in a complex lithology

Pore size analysis plays a pivotal role in unraveling reservoir behavior and its intricate relationship with confined fluids. Traditional methods for predicting pore size distribution (PSD), relying on drilling cores or thin sections, face limitations associated with depth specificity. In this study, we introduce an innovative framework that leverages nuclear magnetic resonance (NMR) log data, encompassing clay-bound water (CBW), bound volume irreducible (BVI), and free fluid volume (FFV), to determine three PSDs (micropores, mesopores, and macropores). Moreover, we establish a robust pore size classification (PSC) system utilizing ternary plots, derived from the PSDs.Within the three studied wells, NMR log data is exclusive to one well (well-A), while conventional well logs are accessible for all three wells (well-A, well-B, and well-C). This distinction enables PSD predictions for the remaining two wells (B and C). To prognosticate NMR outputs (CBW, BVI, FFV) for these wells, a two-step deep learning (DL) algorithm is implemented. Initially, three feature selection algorithms (f-classif, f-regression, and mutual-info-regression) identify the conventional well logs most correlated to NMR outputs in well-A. The three feature selection algorithms utilize statistical computations. These algorithms are utilized to systematically identify and optimize pertinent input features, thereby augmenting model interpretability and predictive efficacy within intricate data-driven endeavors. So, all three feature selection algorithms introduced the number of 4 logs as the most optimal number of inputs to the DL algorithm with different combinations of logs for each of the three desired outputs. Subsequently, the CUDA Deep Neural Network Long Short-Term Memory algorithm(CUDNNLSTM), belonging to the category of DL algorithms and harnessing the computational power of GPUs, is employed for the prediction of CBW, BVI, and FFV logs. This prediction leverages the optimal logs identified in the preceding step. Estimation of NMR outputs was done first in well-A (80% of data as training and 20% as testing). The correlation coefficient (CC) between the actual and estimated data for the three outputs CBW, BVI and FFV are 95%, 94%, and 97%, respectively, as well as root mean square error (RMSE) was obtained 0.0081, 0.098, and 0.0089, respectively. To assess the effectiveness of the proposed algorithm, we compared it with two traditional methods for log estimation: multiple regression and multi-resolution graph-based clustering methods. The results demonstrate the superior accuracy of our algorithm in comparison to these conventional approaches. This DL-driven approach facilitates PSD prediction grounded in fluid saturation for wells B and C.Ternary plots are then employed for PSCs. Seven distinct PSCs within well-A employing actual NMR logs (CBW, BVI, FFV), in conjunction with an equivalent count within wells B and C utilizing three predicted logs, are harmoniously categorized leading to the identification of seven distinct pore size classification facies (PSCF). this research introduces an advanced approach to pore size classification and prediction, fusing NMR logs with deep learning techniques and extending their application to nearby wells without NMR log. The resulting PSCFs offer valuable insights into generating precise and detailed reservoir 3D models.

Optimizing poultry audio signal classification with deep learning and burn layer fusion

This study introduces a novel deep learning-based approach for classifying poultry audio signals, incorporating a custom Burn Layer to enhance model robustness. The methodology integrates digital audio signal processing, convolutional neural networks (CNNs), and the innovative Burn Layer, which injects controlled random noise during training to reinforce the model's resilience to input signal variations. The proposed architecture is streamlined, with convolutional blocks, densely connected layers, dropout, and an additional Burn Layer to fortify robustness. The model demonstrates efficiency by reducing trainable parameters to 191,235, compared to traditional architectures with over 1.7 million parameters. The proposed model utilizes a Burn Layer with burn intensity as a parameter and an Adamax optimizer to optimize and address the overfitting problem. Thorough evaluation using six standard classification metrics showcases the model's superior performance, achieving exceptional sensitivity (96.77%), specificity (100.00%), precision (100.00%), negative predictive value (NPV) (95.00%), accuracy (98.55%), F1 score (98.36%), and Matthew’s correlation coefficient (MCC) (95.88%). This research contributes valuable insights into the fields of audio signal processing, animal health monitoring, and robust deep-learning classification systems. The proposed model presents a systematic approach for developing and evaluating a deep learning-based poultry audio classification system. It processes raw audio data and labels to generate digital representations, utilizes a Burn Layer for training variability, and constructs a CNN model with convolutional blocks, pooling, and dense layers. The model is optimized using the Adamax algorithm and trained with data augmentation and early-stopping techniques. Rigorous assessment on a test dataset using standard metrics demonstrates the model's robustness and efficiency, with the potential to significantly advance animal health monitoring and disease detection through audio signal analysis.

Optimized feature selection approaches for accident classification to enhance road safety

In the modern era, the issue of road accidents has become an increasingly critical global concern, requiring urgent attention and innovative solutions. This investigation has compiled an extensive dataset of 10,356 accident occurrences that occurred between the years 2018 and 2022 in Ernakulam district. By utilizing advanced feature selection methodologies, such as genetic algorithm and coyote optimization, this research has identified pivotal accident determinants. The study harnesses the potential of deep learning techniques, encompassing recurrent neural network (RNN), gated recurrent unit (GRU), long short-term memory (LSTM), and multilayer perceptron (MLP) for classifying accidents according to severity (categorized as fatal, grievous, and severe). Eight predictive models are trained using the dataset, and the top two are ensembled. Integrating deep learning and optimization strategies, this research aims to create a robust accident classification system. The system will help in developing proactive policies that can reduce the frequency and severity of accidents in Ernakulam district. <div style="position: absolute; display: none; z-index: 16777271;"> </div>

Recognition of Mesoscalpellum Hoek, 1907 sensu Newman & Ross, 1971 (Cirripedia: Scalpellidae: Scalpellinae) as a valid genus: a novel approach using ontogenetic patterns in the classification of scalpellid barnacles.

Our ability to reconstruct the evolutionary history of deep-water scalpellid barnacles (Crustacea: Cirripedia: Scalpellidae) and to understand their geographical distributions and ecology, is limited by the lack of a robust classification system. Analysis of the ontogeny of scalpellids highlights the significant morphological changes that occur during development from the smallest, recently settled juveniles up to full-grown specimens. Externally, these ontogenetic alterations can include changes in size, shape, and in the capitulum/peduncle ratio, as well as changes in the shape of plates resulting from modifications in the patterns of calcification. Using an exemplar developmental series of Mesoscalpellum carinatum (Hoek, 1881), we reveal how the misinterpretation of such changes has resulted in the recognition of polyphyletic and paraphyletic taxonomic units and how this has impacted all previous classifications proposed for the Scalpellidae. Our study explores a novel approach to the recognition of Mesoscalpellum Hoek, 1907 sensu Newman & Ross, 1971 as a monophyletic unit, based on the incorporation of data derived from developmental patterns. The re-establishment of this genus leads to significant systematic rearrangement. Multiple taxa currently placed in three scalpellid subfamilies and five genera were recognised as synonyms of just three Mesoscalpellum species-M. carinatum (Hoek, 1881), Mesoscalpellum sanctaebarbarae (Pilsbry, 1907) and Mesoscalpellum japonicum (Hoek, 1883). Two scalpellid genera, Barbascalpellum Zevina, 1978 and Pteroscalpellum Zevina, 1978, are no longer regarded as valid. In future, if study of scalpellid developmental series demonstrates that the holotype of a species is ambiguous and cannot be used for the precise application of the name of a taxon, a level of type status should be assigned to the full-grown specimen to promote its use for comparative study. We suggest that our perspective will help to resolve the confusion around the traditional typological grouping of other scalpellid genera and will foster the creation of a robust scalpellid classification.

Robust image classification system via cloud computing, aligned multimodal embeddings, centroids and neighbours

We propose a framework for a cloud-based application of an image classification system that is highly accessible, maintains data confidentiality, and robust to incorrect training labels. The end-to-end system is implemented using Amazon Web Services (AWS), with a detailed guide provided for replication, enhancing the ways which researchers can collaborate with a community of users for mutual benefits. A front-end web application allows users across the world to securely log in, contribute labelled training images conveniently via a drag-and-drop approach, and use that same application to query an up-to-date model that has knowledge of images from the community of users. This resulting system demonstrates that theory can be effectively interlaced with practice, with various considerations addressed by our architecture. Users will have access to an image classification model that can be updated and automatically deployed within minutes, gaining benefits from and at the same time providing benefits to the community of users. At the same time, researchers, who will act as administrators, will be able to conveniently and securely engage a large number of users with their respective machine learning models and build up a labelled database over time, paying only variable costs that is proportional to utilization.

Machine Learning-Based Tomato Fruit Shape Classification System.

Fruit shape significantly impacts the quality and commercial value of tomatoes (Solanum lycopersicum L.). Precise grading is essential to elucidate the genetic basis of fruit shape in breeding programs, cultivar descriptions, and variety registration. Despite this, fruit shape classification is still primarily based on subjective visual inspection, leading to time-consuming and labor-intensive processes prone to human error. This study presents a novel approach incorporating machine learning techniques to establish a robust fruit shape classification system. We trained and evaluated seven supervised machine learning algorithms by leveraging a public dataset derived from the Tomato Analyzer tool and considering the current four classification systems as label variables. Subsequently, based on class-specific metrics, we derived a novel classification framework comprising seven discernible shape classes. The results demonstrate the superiority of the Support Vector Machine model in terms of its accuracy, surpassing human classifiers across all classification systems. The new classification system achieved the highest accuracy, averaging 88%, and maintained a similar performance when validated with an independent dataset. Positioned as a common standard, this system contributes to standardizing tomato fruit shape classification, enhancing accuracy, and promoting consensus among researchers. Its implementation will serve as a valuable tool for overcoming bias in visual classification, thereby fostering a deeper understanding of consumer preferences and facilitating genetic studies on fruit shape morphometry.

Improved FasterViT model for citrus disease diagnosis

Despite advances in deep learning for plant leaf disease recognition, accurately distinguishing morphological features under varying environmental conditions continues to pose significant challenges. Traditional deep learning models often fail to effectively merge local and global information, especially in small-scale datasets, impairing performance and elevating training costs. Focusing on citrus diseases, we propose an improved FasterViT Model, an advanced hybrid CNN-ViT framework that builds upon the FasterViT model. The proposed model seamlessly integrates CNN's rapid local learning capabilities with ViT's global information processing strength, thereby effectively extracting complex textures and morphological features from images. Cross-stage alternating Mixup and Cutout methods are strategically employed to enhance model robustness and generalization capabilities, particularly valuable for fast learning on small-scale datasets by simulating a more diverse training environment. Triplet Attention and AdaptiveAvgPool mechanisms are utilized to reduce training costs and optimize training performance. The proposed model is tested on both our specially constructed small-scale citrus disease dataset called in-field small dataset and the comprehensive PlantVillage dataset. The experimental results demonstrated that the model exhibits the capability of fast learning and adaptation to small sample training in plant disease detection tasks, and demonstrates the effectiveness of our improvement approach in improving model accuracy and reducing training costs. Additionally, its exemplary performance in transfer learning scenarios underscores its adaptability and broad applicability. This study not only highlights the efficacy of the improved FasterViT model in addressing the complexities of plant disease image recognition but also pioneers a new paradigm for developing efficient, scalable, and robust classification systems.

Overexpression of TSPAN8 in consensus molecular subtype 3 colorectal cancer

BackgroundRecently, consensus molecular subtypes (CMSs) have been proposed as a robust transcriptome-based classification system for colorectal cancer (CRC). Tetraspanins (TSPANs) are transmembrane proteins. They have been associated with the development of numerous malignancies, including CRC, through their role as “master organizers” for multi-molecular membrane complexes. No previous study has investigated the correlation between TSPANs and CMS classification. Herein, we investigated the expression of TSPANs in patient-derived primary CRC tissues and their CMS classifications. MethodsRNA samples were derived from primary CRC tissues (n = 100 patients diagnosed with colorectal adenocarcinoma) and subjected to RNA sequencing for transcriptome-based CMS classification and TSPAN-relevant analyses. Immunohistochemistry (IHC) and immunofluorescence (IF) stains were conducted to observe the protein expression level. To evaluate the relative biological pathways, gene-set enrichment analysis was performed. ResultsOf the highly expressed TSPAN genes in CRC tissues (TSPAN8, TSPAN29, and TSPAN30), TSPAN8 was notably overexpressed in CMS3-classified primary tissues. The overexpression of TSPAN8 protein in CMS3 CRC was also observed by IHC and IF staining. As a result of gene-set enrichment analysis, TSPAN8 may potentially play a role in organizing signaling complexes for kinase-based metabolic deregulation in CMS3 CRC. ConclusionsThe present study reports the overexpression of TSPAN8 in CMS3 CRC. This study proposes TSPAN8 as a subtype-specific biomarker for CMS3 CRC. This finding provides a foundation for future CMS-based studies of CRC, a complex disease and the second leading cause of cancer mortality worldwide.

SATELLITE LAND COVER CLASSIFICATION USING NEURAL NETWORK

This project develops a robust land cover classification system using CNNs for Sentinel-2 imagery, crucial for detecting land use changes and enhancing mapping. Leveraging Copernicus data ensures accessibility and integration into broader Earth observation initiatives, benefiting various fields. Keywords— Sentinel-2 imagery, Convolutional Neural Networks (CNNs), Copernicus program, remote sensing, land use changes, environmental studies, urban planning.

Exploring the Complexities of Temporomandibular Joint Function and Dysfunction: A Contemporary Review

This contemporary review delves into the intricate realm of temporomandibular joint (TMJ) function and dysfunction, shedding light on its multifaceted nature and offering insights into diagnostic and therapeutic strategies. The TMJ, a vital component of the craniofacial complex, plays a pivotal role in everyday activities such as chewing, speaking, and yawning. Understanding its anatomy and physiology is paramount in the treatment and management of TMJ dysfunction. The biomechanics of TMJ function, from the articular disc to the surrounding ligaments and muscles, have been explored comprehensively. A critical aspect of this review revolves around the diverse etiological factors contributing to TMJ dysfunction. Genetic predispositions, parafunctions, occlusal irregularities, and psychological stress are dissected to illuminate the roles of these factors in the development of TMJ disorders. These complexities prompted the need for a robust classification system elucidating the clinical manifestations and diagnostic criteria for various TMJ disorders. Modern diagnostic modalities, including clinical assessment, imaging techniques, and joint aspiration, are scrutinized for their indispensable roles in accurate diagnosis. The comprehensive overview included management strategies, from conservative measures to surgical interventions. In recognizing the pivotal influence of psychosocial factors, this review underscores the importance of patient-centered care and cognitive-behavioral interventions. Furthermore, regenerative therapies, minimally invasive techniques, and personalized medicine are emerging trends in TMJ research. This review provides a contemporary roadmap for comprehending, diagnosing, and managing TMJ-related conditions.

Early life consumption of a "processed" diet high in advanced glycation end products impairs memory function and alters the gut microbiome in rats

Recent evidence indicates that “ultra-processed” foods constitute ~65% of total energy intake among children in the U.S. The impacts of excessive processed food consumption during development are poorly understood, in part because there are neither clear definitions of, nor a robust classification system accounting for, the complexity of food processing variables and how they interrelate in final food products. Heat treatment, a common form of food processing, can induce the chemical Maillard reaction and lead to foods rich in advanced glycation end products (AGEs). The neurocognitive implications of high levels of AGE consumption, particularly during early life, are unknown. Here, we used a rat model to evaluate the effects of adolescent consumption of a heat-treated diet high in AGEs on cognition and the gut microbiome in adulthood. In a series of studies, rats received either an otherwise healthy AGE-rich diet (AGE rats; AIN-93G diet heated at 160ºC for 60min) or a non-AGE-rich diet (CTL rats; AIN-93G diet without heat treatment) during adolescence (postnatal days 26-60). Metabolic, behavioral, and gut microbiome assessments were performed in adulthood. Results revealed that AGE rats exhibited hippocampal (HPC)-dependent memory deficits relative to CTL rats in the absence of altered body weight, body composition, glucose tolerance, and behavioral measures of anxiety. Administering a drug to break down AGEs (alagebrium; 1mg/kg/day) concomitantly with the heat-treated diet prevented memory impairments, supporting a causal role of AGEs in early life diet-induced HPC dysfunction. Microbiome sequencing analyses revealed that AGE rats had substantially reduced abundance of the bacterial genus Lactococcus relative to controls, and Lactococcus abundance was strongly correlated with memory performance. Administration of Lactococcus lactis by oral gavage (109 colony forming units/day) from PN 26-40 during exposure to the heat-treated diet rescued the AGE diet-induced memory impairments. Collective findings from this work identify a connection between a specific food processing variable (i.e., increased dietary AGEs through heat treatment), the gut microbiome, and impaired neurocognition. This work was supported by the National Institute of Diabetes and Digestive and Kidney Diseases under grant DK123423 (awarded to SEK and AAF); the National Institute on Aging through a Postdoctoral Ruth L. Kirschstein National Research Service Award under grant F32AG077932 (awarded to AMRH); and a National Science Foundation Graduate Research Fellowship (awarded to LT). This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Ecological versus biogeographical regionalization: Colliding or colluding?

AbstractThis perspective addresses the nature of the past and current relationships between the ecological and biogeographical regionalization of plants and plant communities. It uses four examples (two related to continental scale and two related to regional/local scale) to document the cases of cross‐pollination between both approaches in the past and the need for concerted use of both ecological and distributional data in formulating robust regional spatial classification systems of biotic assemblages.

Child face detection on front passenger seat through deep learning

Objective One of the main causes of death worldwide among young people are car crashes, and most of these fatalities occur to children who are seated in the front passenger seat and who, at the time of an accident, receive a direct impact from the airbags, which is lethal for children under 13 years of age. The present study seeks to raise awareness of this risk by interior monitoring with a child face detection system that serves to alert the driver that the child should not be sitting in the front passenger seat. Methods The system incorporates processing of data collected, elements of deep learning such as transfer learning, fine-tunning and facial detection to identify the presence of children in a robust way, which was achieved by training with a dataset generated from scratch for this specific purpose. The MobileNetV2 architecture was used based on the good performance shown when compared with the Inception architecture for this task; and its low computational cost, which facilitates implementing the final model on a Raspberry Pi 4B. Results The resulting image dataset consisted of 102 empty seats, 71 children (0-13 years), and 96 adults (14-75 years). From the data augmentation, there were 2,496 images for adults and 2,310 for children. The classification of faces without sliding window gave a result of 98% accuracy and 100% precision. Finally, using the proposed methodology, it was possible to detect children in the front passenger seat in real time, with a delay of 1 s per decision and sliding window criterion, reaching an accuracy of 100%. Conclusions Although our 100% accuracy in an experimental environment is somewhat idealized in that the sensor was not blocked by direct sunlight, nor was it partially or completely covered by dirt or other debris common in vehicles transporting children. The present study showed that is possible the implementation of a robust noninvasive classification system made on Raspberry Pi 4 Model B in any automobile for the detection of a child in the front seat through deep learning methods such as Deep CNN.

A Comprehensive Review of Machine Learning Techniques for Pneumonia Detection from Chest X-ray Images

Pneumonia, a significant contributor to global respiratory illnesses, demands prompt diagnosis for successful treatment. Chest X-rays, being widely accessible and cost-effective, serve as the primary imaging modality for pneumonia detection. However, manual interpretation of chest X-rays is subjective and susceptible to errors due to the often subtle and diverse visual indicators of pneumonia. This study delves into the potential of deep learning, a subfield of artificial intelligence, to automate pneumonia detection utilizing chest X-ray images. By leveraging the well-established VGG-16 model, a convolutional neural network architecture renowned for its image recognition capabilities, the study aims to develop a robust and accurate classification system. This system, if successful, has the potential to alleviate the burden on healthcare professionals by assisting in the timely and efficient detection of pneumonia, ultimately contributing to improved patient outcomes. Key Words: Deep Learning, VGG16, CNN, Pneumonia, Chest X-rays .

Abstract 3930: The therapeutic implications of consensus genomic subtypes of gastric adenocarcinoma

Abstract Background: Gastric adenocarcinoma (GAC) is heterogeneous lethal disease in genomic and clinical level. Although the clinical relevance of genomic and molecular subtypes of GAC has been demonstrated, differences in classification methods have made it difficult to use these findings in clinical applications. We aim to examine a consensus of genomic subtypes and correlate them with clinical outcomes. Method: We collected genomic data from 2527 GAC tumors and divided the data into discovery (n = 1427) and validation sets (n = 1100). A cluster of clusters approach (COCA) was used to find consensus subtypes of gastric tumors. We constructed the GAC predictor of the integrated consensus subtype with 120 genes (GPICS120) and applied it to the validation data set in order to validate the clinical significance of the new subtypes. By analyzing genomic and proteomic data we evaluated each subtype's potential response rate to standard and experimental treatments such radiation therapy, targeted therapy, and immunotherapy and further validated their functional significance in cell line models. Results: We identified 6 clinically and molecularly distinct genomic consensus subtypes (CGSs) by integrating 8 previously established genomic subtypes. CGS1 is characterized by worst prognosis, remarkably high stem cell characteristics, high IGF1 expression, and low genomic alterations. CGS2 showed canonical epithelial gene expression patterns. CGS3 and CGS4 are characterized by high copy number alterations and low immune activity. CGS5 has highest mutation burden and moderately elevated immune activity that is characteristics of MSI-high tumors. The majority of CGS6 tumors have extremely high methylation, high immune activity, and are EBV-positive. The most intriguing finding is that CGS1 is the most responsive to immunotherapy whereas CGS3 is significantly associated with benefit of chemoradiation therapy due to high basal level of ferroptosis. Furthermore, we showed that ferroptosis inducer statin sensitized radiation-resistant GAC cells to ionizing radiation, suggesting that statin can be used to enhance the efficacy of chemoradiation in GAC and it would warrant further investigation in preclinical models. Conclusion: Consensus subtype is robust classification system and can serve as the basis for future clinical trials as well as pre-clinical research into targeted subtype-based therapies. Citation Format: Yun Seong Jeong, Young-Gyu Eun, Sung Hwan Lee, Sang-Hee Kang, Sun Young Yim, Eui Hyun Kim, Joo Kyung Noh, Bo Hwa Sohn, Ju-Seog Lee. The therapeutic implications of consensus genomic subtypes of gastric adenocarcinoma [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3930.