Classification Tool Research Articles

Versatile method for grapevine row detection in challenging vineyard terrains using aerial imagery

Accurate detection and differentiation of grapevine canopies from other vegetation, along with individual grapevine row identification, pose significant challenges in precision viticulture (PV), especially within irregularly structured vineyards shaped by natural terrain slopes. This study employs aerial imagery captured by unmanned aerial vehicles (UAVs) and introduces an image processing methodology that relies on the orthorectified raster data obtained through UAVs. The proposed method adopts a data-driven approach that combines visible indices and elevation data to achieve precise grapevine row detection. Thoroughly tested across various vineyard configurations, including irregular and terraced landscapes, the findings underscore the method’s effectiveness in identifying grapevine rows of diverse shapes and configurations. This capability is crucial for accurate vineyard monitoring and management. Furthermore, the method enables clear differentiation between inter-row spaces and grapevine vegetation, representing a fundamental advancement for comprehensive vineyard analysis and PV planning. This study contributes to the field of PV by providing a reliable tool for grapevine row detection and vineyard feature classification. The proposed methodology is applicable to vineyards with varying layouts, offering a versatile solution for enhancing precision viticulture practices.

Rapid and accurate identification of steel alloys by femtosecond laser-ablation spark-induced breakdown spectroscopy and machine learning

This work investigates the application of femtosecond laser-ablation spark-induced breakdown spectroscopy (fs-LA-SIBS) combined with machine learning algorithms for the rapid and accurate identification of steel alloys. Three algorithms, namely random forest (RF), support vector machine (SVM), and partial least squares identification analysis (PLS-DA), were compared and evaluated. The results indicate that, in 100 independent classifications, the RF model demonstrated an average accuracy of 0.9337, significantly surpassing the accuracies of the SVM model at 0.8281 and the PLS-DA model at 0.8646. In addition, in the evaluation of 5-fold cross-validation and the prediction set, the RF model achieved a near-perfect micro-average area under curve (AUC) of 0.9996, surpassing the AUCs of the SVM model at 0.9761 and the PLS-DA model at 0.9847. The PCA results provided valuable insights into the spectral features that most significantly contributed to the classification accuracy, further confirming the RF model's robustness and effectiveness. This integrated approach offers a powerful tool for the rapid classification and accurate identification of steel alloys in industrial applications.

Performance of a NLP Tool for Text Classification from Orthopaedic Operative Reports, Using Data from the Large Network of Clinical Data Warehouses of the West of France: The HACRO-HUGORTHO Project.

Electronic health data concerning implantable medical devices (IMD) opens opportunities for dynamic real-world monitoring to assess associated risks related to implanted materials. Due to population ageing and expanding demands, total hip, knee, and shoulder arthroplasties are increasing. Automating the collection and analysis of orthopedic device features could benefit physicians and public health policies enabling early issue detection, IMD monitoring and patient safety assessment. A machine learning tool using natural language processing (NLP) was developed for the automated extraction of operation information from medical reports in orthopedics. A corpus of 959 orthopaedic operative reports from 5 centres was manually annotated using the Prodigy software® with a strong inter-annotator agreement of 0.80. Data to extract concerned key clinical and procedure information (n= 9) selected by a multidisciplinary group based on the French health authority checklist. Performances parameters of the NLP model estimated an overall strong precision and recall of respectively 97.0 and 96.0 with a F1-score 96.3. Systematic monitoring of orthopedic devices could be ensured by an automated tool, leveraging clinical data warehouses. Traceability of medical devices with implantation modalities will allow detection of implant factors leading to complications. The evidence from real-world data could provide concrete and dynamic insights to surgeons and infectious disease specialists concerning implant follow-up, guiding therapeutic decision-making, and informing public health policymakers. The tool will be applied on clinical data warehouses to automate information extraction and presentation, providing feedback on mandatory information completion and contents of operative reports to support improvements, and thereafter implant research projects.

Detection and Classification of Acute Lymphoblastic Leukemia using CNN

Acute lymphoblastic leukemia is a very important cancer in childhood but quite prominent in later years of life for the genetic defects in lymphoid progenitors, which are hallmarks of the disease. In children, ALL mostly affects those aged between 2 and 6 years old and, against the background of contemporary biology knowledge and treatment approaches, is associated with more than 80% cure rates. However, approximately 20% of children with ALL relapse; therefore, there is a huge need for better risk identification and treatment optimization. In adults, ALL mainly affects B-cell precursors and is treated with chemotherapy and, in some cases, stem cell transplantation. An accurate and early diagnosis of ALL is of key importance but difficult to realize due to morphological similarities between normal cells and leukemic cells. This study, therefore, proposes a CNN model to improve diagnostic accuracy. Furthermore, it exploits the capabilities of CNN in feature extraction with Adamax Optimizer and the Categorical Cross-Entropy Loss Function to deal with imbalances and noise in the dataset. RESNET50-CNN has achieved 98.63% accuracy in classification and is hence a very strong tool in ALL detection and classification.

Defining Vaginal Community Dynamics: daily microbiome transitions, the role of menstruation, bacteriophages, and bacterial genes

BackgroundThe composition of the vaginal microbiota during the menstrual cycle is dynamic, with some women remaining eu- or dysbiotic and others transitioning between these states. What defines these dynamics, and whether these differences are microbiome-intrinsic or mostly driven by the host is unknown. To address this, we characterized 49 healthy, young women by metagenomic sequencing of daily vaginal swabs during a menstrual cycle. We classified the dynamics of the vaginal microbiome and assessed the impact of host behavior as well as microbiome differences at the species, strain, gene, and phage levels.ResultsBased on the daily shifts in community state types (CSTs) during a menstrual cycle, the vaginal microbiome was classified into four Vaginal Community Dynamics (VCDs) and reported in a classification tool, named VALODY: constant eubiotic, constant dysbiotic, menses-related, and unstable dysbiotic. The abundance of bacteria, phages, and bacterial gene content was compared between the four VCDs. Women with different VCDs showed significant differences in relative phage abundance and bacterial composition even when assigned to the same CST. Women with unstable VCDs had higher phage counts and were more likely dominated by L. iners. Their Gardnerella spp. strains were also more likely to harbor bacteriocin-coding genes.ConclusionsThe VCDs present a novel time series classification that highlights the complexity of varying degrees of vaginal dysbiosis. Knowing the differences in phage gene abundances and the genomic strains present allows a deeper understanding of the initiation and maintenance of permanent dysbiosis. Applying the VCDs to further characterize the different types of microbiome dynamics qualifies the investigation of disease and enables comparisons at individual and population levels. Based on our data, to be able to classify a dysbiotic sample into the accurate VCD, clinicians would need two to three mid-cycle samples and two samples during menses. In the future, it will be important to address whether transient VCDs pose a similar risk profile to persistent dysbiosis with similar clinical outcomes. This framework may aid interdisciplinary translational teams in deciphering the role of the vaginal microbiome in women’s health and reproduction.9k3PVfrRnyX1V_8jfg2U5DVideo

Diagnosing the MRI brain tumour images through RNN-LSTM

According to the World Health Organization, cancer is the second most common cause of death worldwide (WHO). Death from cancer may sometimes be avoided through early diagnosis, although this is not always practicable. A tumour, unlike cancer, may be benign, pre-cancerous, or malignant. Contrary to malignant tumours, benign tumours may frequently be surgically removed and seldom metastasize to other organs or tissues. The method most often used to differentiate between various types of tumours is magnetic resonance imaging (MRI) (MRI). But because it depends on human subjectivity, it could be challenging for one person to see a lot of data. The radiologist's ability to identify brain tumours early mostly depends on their level of training. Before determining whether the tumour is benign or malignant, the diagnostic process for it could not be finished. A biopsy is often carried out to determine if the tissue is benign or cancerous. The biopsy of a brain tumour is often delayed until the last brain operation, in contrast to tumours discovered elsewhere in the body. An efficient diagnostics tool for tumour segmentation and classification from MRI images is crucial to obtaining accurate diagnoses, avoiding surgery, and eliminating subjectivity. The classification and segmentation of the tumour part of the MRI brain picture is the goal of this study. Prior to feature extraction in the first study, pre-processing is done using the Gray Level Co-occurrence Matrix (GLCM). Based on these features, the data is then separated into normal, glioma, meningioma, and pituitary groups. In prior studies, classification was handled by traditional Deep Neural Networks (DNN), with the best weights selected using optimization methods. Accordingly, a recent study recommends including Long Short-Term Memory based on Recurrent Neural Networks (RNN) (LSTM). The Local Direction Ternary Pattern (LDTP), the Gray Level Co-occurrence Matrix (GLCM), and the Le-Net features are all combined in the proposed Hybrid GLCM-LDTP-Le-Net Feature extraction approach. The hybrid parameters produced by the feature extraction process and the brain MRI data are used by the RNN-LSTM model to categorise the data as benign or malignant. By removing mixed features from the input data, the suggested hybrid feature extraction improves the learnt models' accuracy. The accuracy of 98.99 % of the suggested hybrid feature extraction approach was higher than the current CNN-based model methodologies.

A modelling study to explore the effects of regional socio-economics on the spreading of epidemics

AbstractEpidemics, apart from affecting the health of populations, can have large impacts on their social and economic behavior and subsequently feed back to and influence the spreading of the disease. This calls for systematic investigation which factors affect significantly and either beneficially or adversely the disease spreading and regional socio-economics. Based on our recently developed hybrid agent-based socio-economy and epidemic spreading model we perform extensive exploration of its six-dimensional parameter space of the socio-economic part of the model, namely, the attitudes towards the spread of the pandemic, health and the economic situation for both, the population and government agents who impose regulations. We search for significant patterns from the resulting simulated data using basic classification tools, such as self-organizing maps and principal component analysis, and we monitor different quantities of the model output, such as infection rates, the propagation speed of the epidemic, economic activity, government regulations, and the compliance of population on government restrictions. Out of these, the ones describing the epidemic spreading were resulting in the most distinctive clustering of the data, and they were selected as the basis of the remaining analysis. We relate the found clusters to three distinct types of disease spreading: wave-like, chaotic, and transitional spreading patterns. The most important value parameter contributing to phase changes and the speed of the epidemic was found to be the compliance of the population agents towards the government regulations. We conclude that in compliant populations, the infection rates are significantly lower and the infection spreading is slower, while the population agents’ health and economical attitudes show a weaker effect.

Intelligent Microcontroller-Based Infrared Attenuated Total Reflection Spectroscopy for High–Throughput Screening and Discrimination of Foodborne Fungi

Food safety became one of the most critical issues owing to the large expansion of international trading and emission of various pollutants in air, water and soil. Fungal contamination of food and feed has attracted most of the attention in the last decade because of the emerging analytical tools that facilitate the detection and discrimination of fungal species in imported foodstuff, seeds, grains, plants, meats …etc. In this work, we give an insight on the application of integrated attenuated total reflection–Fourier transform infrared (ATR–FTIR) spectroscopy and artificial–intelligence algorithms to the determination and discrimination of fungal species/strains which potentially infect plants, seeds and grains. The proposed method is based on a microcontroller which allows the PC to analyze a large number of samples via serial connection with an UART module. Penicillium chrysogenum, Aspergillus niger, Aspergillus fumigatus, Aspergillus solani, Aspergillus flavus and two different strains of Fusarium oxysporum were used as model microorganisms. The use of artificial–intelligence algorithms herein provides the advantage of automation enabling high throughput screening of large numbers of food samples in less than 5 s. In addition, the classification accuracy is enhanced by applying these machine–learning classification techniques. Principle component analysis (PCA) was used in order to extract the spectral discriminative features from the recorded fungal FTIR spectra. Three intelligent methods of classification; namely, artificial neural network (ANN), support–vector machine (SVM) and k–nearest neighbor (KNN), were used in this study in order to prove that integration of spectroscopic measurements with varying machine–learning methods give a simple analytical tool for detection and classification of foodborne pathogens. All the utilized classifiers gave an accuracy of 100 % and were able to discriminate different species and/or strains of the investigated fungi in few milliseconds.

Exploring Aptamer‐Based Metasurfaces for Label‐Free Plasmonic Biosensing of Breast Tumor‐Derived Exosomes

AbstractExosomes are critical tumor biomarkers, which can be detected by label‐free sensing of plasmonic metasurfaces with expensive antibody functionalization. Due to their low cost and small size, aptamers should be promising to replace antibodies in plasmonic metasensing of exosomes. However, research on aptamer‐based plasmonic metasensing of exosomes is still unexplored. Here, the optical near‐field sensing mechanism of aptamer‐based plasmonic metasurface (APM) is investigated. Based on the study of the evanescent field of APM, using thiol‐modified aptamer boosts the utilization rate of resonance wavelength shift from 27.5% to 83.3% compared to biotinylated aptamers, attributed to a significant reduction in the near‐field occupation of the biofunction layer. Moreover, APM biosensors effectively detect clinical serum exosomes for breast cancer (BC) diagnosis and classification. The receiver operating characteristic analysis shows an area under the curve of 99.3% for APM diagnosis, surpassing the 79.1% for hematological tests of the conventional BC biomarker CA153. The results also indicate that APM biosensors can be a noninvasive tool for molecular classification of BC with great distinguishment of P < 0.0001. The research demonstrates that APM biosensors are enabling a reliable and convenient platform to facilitate clinical hematological tests of exosomes for auxiliary diagnosis of cancer.

Rapid discriminant analysis for the origin of specialty yam based on multispectral data fusion strategies

In order to achieve rapid and effective identification of Hebei yam, a qualitative discrimination model was constructed based on near infrared (NIR), mid infrared (MIR), and microscopic Raman spectra in combination with individual spectra and multispectral data fusion strategies. The results showed that the gray wolf optimizer-support vector machine (GWO-SVM) model constructed by mid-level fusion using the three feature spectra performed the best in distinguishing the geographic origin of the yam, with a prediction accuracy of 100.00% in both the training set and the test set, and an F1 score of 1.00. The results indicated that due to spectral complementarity, NIR, MIR and Raman combined with feature-level fusion can be used as a powerful, non-destructive, fast and feasible tool for geographic origin classification and brand protection of Hebei yam. This work is expected to be a potential method for origin identification analysis and quality monitoring in the food and pharmaceutical industries.

Functional Characterization of ABCA4 Missense Variants Aids Variant Interpretation and Phenotype Prediction in Patients With ABCA4-Retinal Dystrophies.

Biallelic pathogenic variants in the gene encoding the ATP-binding cassette transporter ABCA4 are the leading cause of irreversible vision loss in inherited retinal dystrophies (IRDs). Interpretation of ABCA4 variants is challenging, due to cis-modifying and hypomorphic variants. We have previously detected 10 missense variants of unknown significance (VUS) in patients with suspected ABCA4-retinal dystrophies (ABCA4-RDs) in Norway. In this study, we functionally characterized the VUS to aid interpretation of the variants and to determine if they are associated with the disease. The ABCA4 VUS were expressed in HEK293T cells and the ABCA4 expression level and ATPase activity were determined and correlated with the patients' phenotype. The functional data further used for reclassification of the VUS following the American College of Medical Genetics and Genomics (ACMG) guidelines. Of the 10 VUSs, 2 variants, Cys205Phe and Asn415Thr, were categorized as functionally severe. The age at presentation in the 2 patients carrying these variants was divergent and seemed to be driven by the patients' second pathogenic variants Gly1961Glu and c.5461-10T>C, respectively. Three variants, Val643Gly, Pro799Leu, and Val1433Ile were categorized as functionally moderate, and were found in patients with intermediate/late age at presentation. The remaining five variants were categorized as functionally normal/mild. Based on our data, c.614G>T p.(Cys205Phe), c.1244A>C p.(Asn415Thr), and c.2396C>T p.(Pro799Leu) were reclassified to (likely) pathogenic, while 4 of the functionally normal/mild variants could be reclassified to likely benign. Functional analyses of ABCA4 variants are a helpful tool in variant classification and enable us to better predict the disease severity in patients with ABCA4-RDs.

X-Ray Source Classification Using Machine Learning: A Study with EP-WXT Pathfinder LEIA

X-ray observations play a crucial role in time-domain astronomy. The Einstein Probe (EP), a recently launched X-ray astronomical satellite, emerges as a forefront player in the field of time-domain astronomy and high-energy astrophysics. With a focus on systematic surveys in the soft X-ray band, EP aims to discover high-energy transients and monitor variable sources in the universe. To achieve these objectives, a quick and reliable classification of observed sources is essential. In this study, we developed a machine learning classifier for autonomous source classification using data from the EP-WXT Pathfinder—Lobster Eye Imager for Astronomy (LEIA) and EP-WXT simulations. The proposed Random Forest classifier, built on selected features derived from light curves, energy spectra, and location information, achieves an accuracy of approximately 95% on EP simulation data and 98% on LEIA observational data. The classifier is integrated into the LEIA data processing pipeline, serving as a tool for manual validation and rapid classification during observations. This paper presents an efficient method for the classification of X-ray sources based on single observations, along with implications of most effective features for the task. This work facilitates rapid source classification for the EP mission and also provides valuable insights into feature selection and classification techniques for enhancing the efficiency and accuracy of X-ray source classification that can be adapted to other X-ray telescope data.

Capsize criteria in beam seas: Melnikov analysis vs. safe basin erosion

We study the problem of capsizing of a rolling ship in harmonic and random beam seas, by means of the Melnikov method and safe basin calculations. In the random excitation case, we consider an integro-differential Cummins-type model equation that takes into account the hydrodynamic memory. The non-linear restoring moment is modeled by a high-order polynomial and the Melnikov criteria are evaluated numerically. We also examine a variant of the classical Melnikov method in which the damping terms are incorporated into the unperturbed system and the perturbation takes a modified form. We compare the theoretical predictions with direct (Monte-Carlo) simulations of the safe basins for two existing ships. In the random excitation case, we quantify the erosion by means of a mean integrity index. For weak damping, the classical and modified Melnikov curves coincide and are in good agreement with the onset of the safe basin erosion. As damping increases the Melnikov curves become less and less conservative with respect to the onset of erosion. Finally, the potential of the Melnikov method to provide a ship classification tool is discussed.

Seismic Damage Prediction and Classification tool: Utilizing Adaptive Neuro-Fuzzy Inference System (ANFIS) and Geographic Information System (GIS)

Seismic damage prediction of wide range of buildings is an important prioritization and classification tool for implementation of seismic risk and vulnerability assessment. This study has developed a rapid visual screening (RVS) tool using Adaptive Neuro-Fuzzy Inference System (ANFIS) model and Geographic Information System (GIS). Hospital an d public-school buildings located in districts 5 and 6 have been selected for assessment. Technical calculation basis in the development of FEMA P- 154 was followed in formulating the model using the neuro-fuzzy tool package in MATLAB. Six (6) building para meters and their resulting output (final score) were inputted for training. Sub-clustering FIS model showed the lowest RMSE and R2 result out of the five (5) FIS models compared. The model showed effective performance in classifying the buildings’ damage grades having 0.2908, 0.8073 and 0.948 for RMSE, and for testing and overall coefficient of determination (R2) values, respectively. Performance me trics from the developed confusion matrix showed high range of values for sensitivity, specificity, precision, and accuracy, with maximum error rate and false positive rate of 0.11 and 0.25, respectively, in classifying the buildings’ damage grade. These validate the model’s performance and ability in classifying the damage grade of the buildings observed. The results were used to develop a digital mapping of the damage grade distribution of the selected buildings in the area using ArcGIS.

Reappraisal of bone and soft tissue cytopathology classification using the modified Milan system.

A standardized reporting system for bone and soft tissue tumor cytopathology has not yet been established. The objective of this study was to explore the potential utility of a classification modified from the Milan System for Salivary Gland Cytopathology and compared it with the upcoming World Health Organization (WHO) system for fine-needle aspiration of soft tissue lesions. The authors reviewed 285 cytology cases of bone/joint (n=173) and soft tissue (n=112) lesions, scoring each within diagnostic categories. The results were compared with histologic diagnoses and the risk of malignancy (ROM) for each category, and diagnostic reliability was analyzed. All 285 cases were successfully classified into one of the following categories: nondiagnostic (6.3%), non-neoplastic (11.9%), atypia of uncertain significance (11.9%), benign neoplasm (5.6%), bone and soft tissue neoplasm of uncertain malignant potential (25.3%), suspicious for malignancy (1.4%), and malignant (37.5%). The ROM was 44.4% (eight of /18 cases) in nondiagnostic, 0% (zero of 34 cases) in non-neoplastic, 32.4% (11 of 34 cases) in atypia of uncertain significance, 0% (zero of 16 cases) in benign neoplasm, 16.7% (12 of 72 cases) in bone and soft tissue neoplasm of uncertain malignant potential, 75.0% (three of four cases) in suspicious for malignancy, and 100% (107 of 107 cases) in malignant categories. Using the WHO system, the proportion and ROM of the benign category (non-neoplastic and benign neoplasm) was 17.5% and 0%, respectively. Among benign and malignant lesions, the diagnostic accuracy, sensitivity, and specificity for detecting malignancy were 99.4%, 100%, and 98.0%, respectively. The modified Milan system as well as the WHO system may be a useful cytopathologic classification tool for both bone and soft tissue lesions.

A machine learning algorithm for the automatic classification of Phytophthora infestans genotypes into clonal lineages

AbstractPremiseThe prompt categorization of Phytophthora infestans isolates into described clonal lineages is a key tool for the management of its associated disease, potato late blight. New isolates of this pathogen are currently classified by comparing their microsatellite genotypes with characterized clonal lineages, but an automated classification tool would greatly improve this process. Here, we developed a flexible machine learning–based classifier for P. infestans genotypes.MethodsThe performance of different machine learning algorithms in classifying P. infestans genotypes into its clonal lineages was preliminarily evaluated with decreasing amounts of training data. The four best algorithms were then evaluated using all collected genotypes.ResultsmlpML, cforest, nnet, and AdaBag performed best in the preliminary test, correctly classifying almost 100% of the genotypes. AdaBag performed significantly better than the others when tested using the complete data set (Tukey HSD P < 0.001). This algorithm was then implemented in a web application for the automated classification of P. infestans genotypes, which is freely available at https://github.com/cpatarroyo/genotypeclas.DiscussionWe developed a gradient boosting–based tool to automatically classify P. infestans genotypes into its clonal lineages. This could become a valuable resource for the prompt identification of clonal lineages spreading into new regions.

Non-Invasive Quality Control of Organoid Cultures Using Mesofluidic CSTR Bioreactors and High-Content Imaging.

Human brain organoids produce anatomically relevant cellular structures and recapitulate key aspects of in vivo brain function, which holds great potential to model neurological diseases and screen therapeutics. However, the long growth time of 3D systems complicates the culturing of brain organoids and results in heterogeneity across samples hampering their applications. We developed an integrated platform to enable robust and long-term culturing of 3D brain organoids. We designed a mesofluidic bioreactor device based on a reaction-diffusion scaling theory, which achieves robust media exchange for sufficient nutrient delivery in long-term culture. We integrated this device with longitudinal tracking and machine learning-based classification tools to enable non-invasive quality control of live organoids. This integrated platform allows for sample pre-selection for downstream molecular analysis. Transcriptome analyses of organoids revealed that our mesofluidic bioreactor promoted organoid development while reducing cell death. Our platform thus offers a generalizable tool to establish reproducible culture standards for 3D cellular systems for a variety of applications beyond brain organoids.

SENTIMENT ANALYSIS OF YOUTUBE COMMENTS ON WISH 107.5 VIDEOS USING NATURAL LANGUAGE PROCESSING (NLP)

Wish 107.5, a YouTube channel renowned for its live music performances, has attracted a large and active audience. Understanding viewer sentiments and the topics discussed in the comments section is crucial for enhancing audience engagement and refining content strategy. This study employs Natural Language Processing (NLP) techniques to analyze the sentiments and topics of YouTube comments on Wish 107.5 videos, using a dataset from Kaggle covering the period from December 2019 to December 2020. Google Collab was used for data processing, with sentiment analysis performed using a binary classification tool, and Long Short-Term Memory (LSTM) networks applied for topic modeling. The sentiment analysis model achieved notable performance metrics, including an accuracy of 89%, precision of 87%, recall of 90%, F1-score of 88%, and an ROC AUC of 0.92, demonstrating its effectiveness in classifying YouTube comments. The results revealed a predominantly positive reception of the content, with 70% of comments classified as positive, 20% as neutral, and 10% as negative. Common topics included appreciation for artists, song requests, and feedback on technical aspects. While the model exhibited a training accuracy nearing 1.0, the validation accuracy was 0.78, indicating some overfitting. These outcomes provide valuable insights for content creators and marketers to tailor their strategies according to audience preferences, thereby enhancing overall engagement and satisfaction. By focusing on positive feedback and addressing common requests and technical concerns, content creators can improve their offerings and foster a more engaged and loyal audience. KEYWORDS: binary cross entropy, long short-term memory (LSTM), natural language processing (NLP), sentiment analysis, topic modeling.

A [formula omitted] adic approach to the TSPO gene

TSPO protein is known to be involved in various cellular functions and dysregulations of TSPO expression has been found to be associated with pathologies of different human diseases, including cardiovascular disease, cancer, neuroinflammatory, neurodegenerative, neoplastic disorders. However, there are limited studies in the literature on the effects of sequence variations in the TSPO gene on the function of the protein and their relationship with human diseases. Evaluating the pathogenicity of genetic variants is crucial in terms of prioritizing the functional importance and clinical use. Therefore, various in-silico prediction tools have been developed that combine different algorithms to predict the effects of sequence variations on protein functions or gene regulation. In this study, the p-adic distance approach in modeling the genetic code, proposed and developed by Dragovich and Dragovich, was discussed in order to obtain an alternative to the existing in-silico prediction tools. Dragovichs’ approach is expressed as follows: A 5-adic space of codons is constructed and 5-adic and 2-adic distances between codons are taken into account. As a result, two codons with the smallest value of 5-adic and 2-adic distances are obtained, encoded for the same amino acid and stop signal. This model describes well the degeneration of the genetic code. This study combined the data obtained from in-silico prediction tools and used a bioinformatics approach to determine the functional relevance of coding SNPs in the TSPO. Overall, we evaluate the potential utility of Dragovichs’ approach by comparing it with other existing prediction tools for variant classification and prioritization.

Enhancing Radar Image Classification with Autoencoder-CNN Hybrid System

The tracking, analysis, and classification of human movements can be crucial, particularly in areas such as elderly care, healthcare, and infant care. Typically, such tracking is done remotely with cameras. However, radar systems have emerged as significant methods and tools for these tasks due to their advantages such as privacy, wireless operation, and the ability to work through walls. By converting reflected radar signals from targets into images, human activities can be classified using powerful classification tools like deep learning. In this study, range-Doppler images of behind-the-wall human movements obtained with a radar system consisting of one transmitter and four receiver antennas were classified. Since the data collected from the four receiver antennas are in different positions, the collected reflection signals also differ. The signals collected with the range-time matrix content were divided into positive and negative parts, resulting in eight images from the four antennas. Instead of using all the data in CNN training, the images were first subjected to a reconstruction process with an autoencoder to reduce differences. As a result, it was observed that reconstructing the images with an autoencoder before classification with CNN increased the classification success. In conclusion, it was observed that the classification success of radar images can be increased by using a hybrid system with an autoencoder to reconstruct the images before classification with CNN.