Detection Step Research Articles

PROCEEDINGS IN UAS-ASSISTED BRIDGE INSPECTIONS: RTK-BASED PHOTOGRAMMETRIC RECONSTRUCTION AND SPATIAL FILTERING

Abstract. Traditional bridge inspections present considerable challenges in terms of efficiency and accuracy. However, recent advancements in Unmanned Aerial Systems (UASs) and deep learning for object detection have opened up new avenues for automatic bridge damage detection. We present a comprehensive framework leveraging these technologies for automated damage detection in UAS imagery, followed by accurate mapping of the damage predictions on photogrammetric models. In this work, we propose a photogrammetric procedure to retrieve geolocated bridge models solely based on Real-Time Kinematics (RTK) information. Within the damage detection step, we conduct extensive testing and optimization of model hyperparameters using YOLOv8 and Slicing Aided Hyper Interference (SAHI). Next, we map the predictions onto the 3D model using ray casting, allowing to group and filter the predictions by their area and position. Finally, a Graphical User Interface (GUI) allows bridge inspectors to identify false positive predictions, generate new training data, and directly measure damage dimensions in the images. Validation on a concrete box girder bridge resulted in a photogrammetric model with a mean error of 1.3 cm, negating the need for ground control points. Our model training process revealed substantial performance variations between training and test datasets, underscoring the importance of evaluating optimal hyperparameters on UAS inspection images rather than relying on the validation metrics. Lastly, we successfully map the detected damage and create new training data from the UAS inspection images. This framework significantly enhances bridge inspection accuracy and efficiency, providing a strong foundation for future developments in automated bridge inspections.

Selective miR-21 detection technology based on photocrosslinkable artificial nucleic acid-modified magnetic particles and hybridization chain reaction

Recently, microRNA (miRNA) detection in blood has attracted attention as a new early detection technology for cancer. The extraction of target miRNA is a necessary preliminary step for detection; however, currently, most extraction methods extract all RNA from the blood, which limits the detection selectivity. Therefore, a method for the selective extraction and detection of target miRNA from blood is very important. In this study, we utilized photocrosslinkable artificial nucleic acids and the hybridization chain reaction (HCR) in an attempt to improve upon the current standard method RT-qPCR, which is hampered by problems with primer design and enzymatic amplification. By introducing photocrosslinkable artificial nucleic acids to oligonucleotide probes modified with magnetic particles with a sequence complementary to that of the target miRNA and irradiating them with light, covalent bonds were formed between the target miRNA and the oligonucleotide probes. These tight covalent bonds enabled the capture of miRNA in blood, and intensive washing ensured that only the target miRNA were extracted. After extraction, two types of DNA (H1 and H2) modified with fluorescent dyes were added and the fluorescence signals were amplified by the HCR in the presence of the target miRNA bound to the photocrosslinkable artificial nucleic acids, allowing for isothermal and enzyme-free miRNA detection. The novel method is suitable for selective miRNA detection in real blood samples. Because the reaction proceeds isothermally and no specialized equipment is used for washing, this detection technology is simple and selective and suitable for application to point-of-care technology using microfluidic devices.

Abstract C109: Identifying implementation strategies to support cervical cancer screening programs in resource-limited countries through participatory action research

Abstract Background: Improving the adoption and integration of cervical cancer screening programs in resource-limited countries requires engaging with many local health system actors. We hypothesize that participatory design workshops co-developed by researchers, health system practitioners, and policy makers, facilitate rapid engagement to identify context-specific priorities and tailor strategies to improve implementation processes. Methods: With the Peruvian Ministry of Health (MOH), we co-designed a week-long workshop with health system actors (planners, providers, lab technicians) from the North District of Lima city. Through facilitated dialogue, participants engaged in self-reflection to map the cervical cancer screening and follow-up system, visualize system barriers, and identify potential solutions. As research partners, we analyzed findings from the workshop using the Consolidated Framework for Implementation Research, a framework from implementation science that identifies multilevel contextual factors that influence program implementation and guides the tailoring of strategies for improvement. Results: We identified three key context-specific challenges including 1) power hierarchies between specialists and midwives that obstruct the efficiency of screening services, 2) the complexities around communicating screening results, appointments, and referrals, are burdensome for patients and cause loss to follow up, and 3) implementation plans are not adequately matched to resources and workforce capacity. We identified feasible implementation strategies to address these challenges including 1) develop relationships between midwives and specialists through facilitated discussions to surface assumptions and align screening goals, 2) co-create counseling tools to help patients understand results and follow up steps for early detection and treatment of precancerous lesion that also reduce patients’ burden, and 3) Apply design workshops with key actors to develop an implementation plans to guide processes, acceptable adaptations, clinical workflows, and planning (ordering tests, supplies, training human resources, etc.) to align goals to prevention objectives and resources. Conclusions: Engaging with health systems actors through participatory action research is a strategy that enables collective learning, identifying context-specific priorities, and developing tailored implementation strategies that are likely to accelerate integration of sustainable cervical cancer screening programs globally. Citation Format: Margarita Correa-Mendez. Identifying implementation strategies to support cervical cancer screening programs in resource-limited countries through participatory action research [abstract]. In: Proceedings of the 16th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2023 Sep 29-Oct 2;Orlando, FL. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2023;32(12 Suppl):Abstract nr C109.

Recent Progress in Mass Spectrometry-Based Single-Cell Metabolic Analysis.

Single-cell analysis enables the measurement of biomolecules at the level of individual cells, facilitating in-depth investigations into cellular heterogeneity and precise interpretation of the related biological mechanisms. Among these biomolecules, cellular metabolites exhibit remarkable sensitivity to environmental and biochemical changes, unveiling a hidden world underlying cellular heterogeneity and allowing for the determination of cell physiological states. However, the metabolic analysis of single cells is challenging due to the extremely low concentrations, substantial content variations, and rapid turnover rates of cellular metabolites. Mass spectrometry (MS), characterized by its high sensitivity, wide dynamic range, and excellent selectivity, is employed in single-cell metabolic analysis. This review focuses on recent advances and applications of MS-based single-cell metabolic analysis, encompassing three key steps of single-cell isolation, detection, and application. It is anticipated that MS will bring profound implications in biomedical practices, serving as advanced tools to depict the single-cell metabolic landscape.

Myelomatous Ascitis, a Rare Presenting Symptom of Multiple Myeloma

Abstract Introduction/Objective In 2022, plasma cell neoplasms accounted for approximately 1.8% of all new cancers in the United States with an estimated 34,470 new cases of multiple myeloma. Diagnosis is often straight forward in ~80% of cases by performing serum protein electrophoresis (SPEP), serum immunofixation (SIFE), and/or urine immunofixation (UIFE) with M-spike quantification. The diagnostic challange is in the remainder of asymptomatic myeloma cases (~20%) which are found incidentally. Specialized laboratory technicians are often the first step in identifying plasma cells in body fluids and/or peripheral blood smears. These incidental findings on routine labs, paired with the keen eye of a specialist, are one of the first steps in early detection of multiple myeloma. Methods/Case Report A 62 year-old male, originally from Cambodia, presented to an outside hospital emergency department with abdominal distention and pain. His past medical history was significant for dialysis-dependent end- stage renal disease and insulin-dependent diabetes mellitus type 2. Abdominal CT showed ascites with no other diagnostic findings. Cardiac, renal and hepatic etiologies of ascites were ruled out. Body fluid analysis of the ascites in the Clinical Pathology laboratory revealed numerous plasma cells. Cytologic examination, after consultation with Clinical Pathology, also revealed numerous plasma cells. Subsequent SPEP and SIFE disclosed an IgA lambda monoclonal protein. A diagnosis of multiple myeloma was confirmed by bone marrow biopsy with FISH studies. Results showed several high-risk abnormalities including translocations of 4::14, 14::16, and 14::20, denoting a “triple hit” multiple myeloma. Results (if a Case Study enter NA) NA Conclusion Plasmacytosis in ascites is an extremely rare initial presentation for multiple myeloma. With only a few cases reported in the literature, many technicians and pathologists might easily overlook plasma cells on routine cytology, especially with normal imaging and no previous diagnosis of myeloma. In this case, flagged peritoneal fluid by a skilled medical laboratory technician was key to making a diagnosis. Without any signs of a plasmacytoma or lytic bone lesions on imaging, a normal CBC with non-specific labs, and an unsuspecting surgical pathology report, multiple myeloma was not on the differential. Fast interdepartmental consultation, communication, and teamwork between surgical pathology and clinical pathology, lead to a rapid diagnosis and prompt treatment of this patient.

A quality assurance framework for routine monitoring of deep learning cardiac substructure computed tomography segmentation models in radiotherapy.

For autosegmentation models, the data used to train the model (e.g., public datasets and/or vendor-collected data) and the data on which the model is deployed in the clinic are typically not the same, potentially impacting the performance of these models by a process called domain shift. Tools to routinely monitor and predict segmentation performance are needed for quality assurance. Here, we develop an approach to perform such monitoring and performance prediction for cardiac substructure segmentation. To develop a quality assurance (QA) framework for routine or continuous monitoring of domain shift and the performance of cardiac substructure autosegmentation algorithms. A benchmark dataset consisting of computed tomography (CT) images along with manual cardiac substructure delineations of 241 breast cancer radiotherapy patients were collected, including one "normal" image domain of clean images and five "abnormal" domains containing images with artifact (metal, contrast), pathology, or quality variations due to scanner protocol differences (field of view, noise, reconstruction kernel, and slice thickness). The QA framework consisted of an image domain shift detector which operated on the input CT images and a shape quality detector on the output of an autosegmentation model, and a regression model for predicting autosegmentation model performance. The image domain shift detector was composed of a trained denoising autoencoder (DAE) and two hand-engineered image quality features to detect normal versus abnormal domains in the input CT images. The shape quality detector was a variational autoencoder (VAE) trained to estimate the shape quality of the auto-segmentation results. The output from the image domain shift and shape quality detectors was used to train a regression model to predict the per-patient segmentation accuracy, measured by Dice coefficient similarity (DSC) to physician contours. Different regression techniques were investigated including linear regression, Bagging, Gaussian process regression, random forest, and gradient boost regression. Of the 241 patients, 60 were used to train the autosegmentation models, 120 for training the QA framework, and the remaining 61 for testing the QA framework. A total of 19 autosegmentation models were used to evaluate QA framework performance, including 18 convolutional neural network (CNN)-based and one transformer-based model. When tested on the benchmark dataset, all abnormal domains resulted in a significant DSC decrease relative to the normal domain for CNN models ( ), but only for some domains for the transformer model. No significant relationship was found between the performance of an autosegmentation model and scanner protocol parameters ( ) except noise ( ). CNN-based autosegmentation models demonstrated a decreased DSC ranging from 0.07 to 0.41 with added noise, while the transformer-based model was not significantly affected (ANOVA, ). For the QA framework, linear regression models with bootstrap aggregation resulted in the highest mean absolute error (MAE) of , in predicted DSC (relative to true DSC between autosegmentation and physician). MAE was lowest when combining both input (image) detectors and output (shape) detectors compared to output detectors alone. A QA framework was able to predict cardiac substructure autosegmentation model performance for clinically anticipated "abnormal" domain shifts.

CAT-Seg: cascaded medical assistive tool integrating residual attention mechanisms and Squeeze-Net for 3D MRI biventricular segmentation

Cardiac image segmentation is a critical step in the early detection of cardiovascular disease. The segmentation of the biventricular is a prerequisite for evaluating cardiac function in cardiac magnetic resonance imaging (CMRI). In this paper, a cascaded model CAT-Seg is proposed for segmentation of 3D-CMRI volumes. CAT-Seg addresses the problem of biventricular confusion with other regions and localized the region of interest (ROI) to reduce the scope of processing. A modified DeepLabv3+ variant integrating SqueezeNet (SqueezeDeepLabv3+) is proposed as a part of CAT-Seg. SqueezeDeepLabv3+ handles the different shapes of the biventricular through the different cardiac phases, as the biventricular only accounts for small portion of the volume slices. Also, CAT-Seg presents a segmentation approach that integrates attention mechanisms into 3D Residual UNet architecture (3D-ResUNet) called 3D-ARU to improve the segmentation results of the three major structures (left ventricle (LV), Myocardium (Myo), and right ventricle (RV)). The integration of the spatial attention mechanism into ResUNet handles the fuzzy edges of the three structures. The proposed model achieves promising results in training and testing with the Automatic Cardiac Diagnosis Challenge (ACDC 2017) dataset and the external validation using MyoPs. CAT-Seg demonstrates competitive performance with state-of-the-art models. On ACDC 2017, CAT-Seg is able to segment LV, Myo, and RV with an average minimum dice symmetry coefficient (DSC) performance gap of 1.165%, 4.36%, and 3.115% respectively. The average maximum improvement in terms of DSC in segmenting LV, Myo and RV is 4.395%, 6.84% and 7.315% respectively. On MyoPs external validation, CAT-Seg outperformed the state-of-the-art in segmenting LV, Myo, and RV with an average minimum performance gap of 6.13%, 5.44%, and 2.912% respectively.

A derivative, integral, and proportional features extractor for fault detection in dynamic processes

Detecting faults in dynamic systems is challenging due to temporal dependencies and signal correlations. Feature extraction from time-series data is a common step in fault detection, which is usually performed according two main approaches: knowledge-based and statistical. Knowledge-based methods provide interpretable features but require significant design time; also, they usually lack generality. Statistical methods are faster but lead to dimensionality issues and lack of interpretability. To address these challenges, we propose an interpretable and automated feature extraction method. It combines the benefits of knowledge-based and statistical methods, offering a fast solution for extracting effective and interpretable indicators without requiring prior domain knowledge. Also, this method consistently computes a fixed set of interpretable features describing the process’s dynamic behavior.We extensively compare our approach with state-of-the-art methods considering nine open-source datasets spanning various domains. Our results show that classifiers trained on features extracted with the proposed method achieve performance comparable to those provided by state-of-the-art automatic features extractors, according to F1-score, true positive rate, and false positive rate. In addition, our approach proves to be more robust to dimensionality issues and enhances interpretability, extracting a reduced set of features effective at providing insight into the detected anomalies’ characteristics. Additionally, we demonstrate that the selected features maintain consistent performance across different classifiers, showcasing their versatility.

Discrimination of baru oil adulteration with soy oil using portable near infrared spectroscopy, Fourier-transform infrared spectroscopy and Partial Least-Squares Discriminant

Considered an important source of bioactive compounds and unsaturated fatty acids, Baru oil comes from the Brazilian Cerrado ecoregion and is sold with high value. Methods to detect tampering to certify the authenticity of this type of product are in great demand for quality control. Herein, this study used partial least squares for discriminant analysis (PLS-DA) combined with Fourier-transform infrared spectroscopy (FTIR) and portable near-infrared spectroscopy (NIR) for the detection of adulteration in Baru oil, using soybean oil as an adulterant. Adulteration concentrations were 10, 30, 50, 60, and 80% for analysis by NIR and 10, 30, 50, 60, 70, and 90% for FTIR. After the spectral range selection and pre-processing steps, discrimination models showed good discrimination, and the efficiency was confirmed from the figures of merit, which highlighted percentages above 99% with both techniques used. Anomalous samples were identified in discrimination models obtained with a portable NIR spectrometer in the outlier detection step. The methodology evaluated is direct, fast, and non-destructive, in which the PLS-DA models obtained from the sets of spectra by FTIR presented superior results than those evaluated with the portable NIR spectrometer; however, the latter was also efficient in discriminating as adulterated, reinforcing the feasibility of using spectroscopic techniques and chemometric tools.

Adaptive frequency-domain filtering for neural signal preprocessing

Electrical interference from various sources is a common issue for experimental extracellular electrophysiology recordings collected using multi-electrode array neural recording systems. This interference deteriorates the signal-to-noise ratio (SNR) of the raw electrophysiology signals and hampers the accuracy of data post-processing using techniques such as spike-sorting. Traditional signal processing methods to digitally remove electrical interference during post-processing include bandpass filtering to limit the signal to the relevant spectral range of the biological data, e.g., the spikes band (300 Hz - 7 kHz), targeted notch filtering to remove power line interference from standard alternating current mains electricity and common reference removal to minimize noise common to all electrodes. These methods require a priori knowledge of the frequency of the interfering signal source to address the unique electromagnetic interference environment of each experimental setup. We discuss an adaptive method for automatically removing narrow-band electrical interference through a spectral peak detection and removal (SPDR) step that can be applied during post-processing of the recorded data, based on the intuition that tall, narrowband signals localized in the signal spectrum correspond to interference, rather than the activity of neurons. A spectral peak prominence (SPP) threshold is used to detect these peaks in the frequency domain, which will then be removed via notch filtering. We applied this method to simulated waveforms and also experimental electrophysiology data collected from cerebral organoids to demonstrate its effectiveness for removing unwanted interference without significantly distorting the neural signals. We discuss that proper selection of the SPP threshold is required to avoid over-filtering, which can result in distortion of the electrophysiology data. We also compare the firing-rate activity in the filtered electrophysiology with fluorescence calcium imaging, a secondary cellular activity marker, to quantify signal distortion and provide bounds on SNR-based optimization of the SPP threshold. The adaptive filtering technique demonstrated in this paper is a powerful method that can automatically detect and remove interband interference in recorded neural signals, potentially enabling data collection in more naturalistic settings where external interference signals are difficult to eliminate.

Impact of Various Risk Factors on the Positive Fecal Immunochemical Test for Colorectal Cancer in the Iranian Population.

Background: Colorectal cancer (CRC) is the most prevalent cancer with high mortality worldwide. We aimed to evaluate the incidence of CRC based on the positive fecal immunochemical test (FIT) result in the Iranian population. Methods: The present study was conducted on the health assessment data recorded in the SINA (Integrated Health Information System) in 2018 and 2019 from individuals who had participated in the national program, including asymptomatic people aged 50-69 years or had risk factors of CRC such as family or past personal history of CRC as well as symptomatic individuals, for the early detection and prevention of CRC in Mashhad, Iran. Results: The study participants included 140,463 eligible individuals, of whom 8258 (5.88%) and 145 (2.21%) were positive for FIT and diagnosed with colon cancer, respectively. Unfortunately, only 654 people had undergone colonoscopy. Our results indicated that age, fast food intake (≥two units per day), family history of CRC in first or second-degree relatives, some gastrointestinal diseases such as inflammatory bowel disease (IBD) and CRC, as well as bleeding per anus, constipation, abdominal cramp, and losing body weight were associated with increased risk of positive FIT. However, some other factors, including having a hard job, physical activity, and Iranian nationality (compared to non-Iranians), were associated with a low risk of positive FIT screening tests for CRC. Conclusion: A high number of high-risk persons in Mashhad were positive for the FIT test in 2018-2019, and many of them were diagnosed with CRC, according to the colonoscopy results. Therefore, screening is highly recommended as the first step in the early detection of CRC.

A prospective approach to detect advanced persistent threats: Utilizing hybrid optimization technique

Advanced Persistent Threat (APT) attacks pose significant challenges for AI models in detecting and mitigating sophisticated and highly effective cyber threats. This research introduces a novel concept called Hybrid HHOSSA which is the grouping of Harris Hawk Optimization (HHO) and Sparrow Search Algorithm (SSA) characteristics for optimizing the feature selection and data balancing in the context of APT detection. In addition, the light GBM as well as the weighted average Bi-LSTM are optimized by the proposed hybrid HHOSSA optimization. The HHOSSA-based attribute selection is used to choose the most important attributes from the provided dataset in the early step of the quasi-identifier detection. The HHOSSA-SMOTE algorithm effectively balances the unbalanced data, such as the lateral movements and the data exfiltration in the DAPT 2020 database, which further improves the classifier performance. The light GBM and the Bi-LSTM classifier hyperparameters are well attuned and classified by the HHOSSA optimization for the precise classification of the attacks. The outcome of both the optimized light GBM and the Bi-LSTM classifier generates the final prediction of the attacks existing in the network. According to the research findings, the HHOSSA-hybrid classifier achieves high accuracy in detecting attacks, with an accuracy rate of 94.468 %, a sensitivity of 94.650 %, and a specificity of 95.230 % with a K-fold value of 10. Also, the HHOSSA-hybrid classifier achieves the highest AUC percentage of 97.032, highlighting its exceptional performance in detecting APT attacks.

Thresholding-accelerated convolutional neural network for aeroengine turbine blade segmentation

Turbine blades can only be detected nondestructively and precisely using industrial computed tomography (CT). The accuracy of CT image segmentation, which is a key step in CT detection, significantly affects CT detection precision. However, CT images of turbine blades cannot be segmented precisely because they contain inhomogeneity, noise, artifacts, and low-contrast areas. In addition, it is crucial to consider both efficiency and precision in industrial applications. Unfortunately, large-size networks often tend to be inefficient, while lightweight networks lack the necessary accuracy. To address these issues, we propose an innovative approach utilizing an ultra-lightweight neural network that fuses a threshold-based segmentation algorithm with a convolutional neural network for acceleration. The integrated thresholding algorithm was developed through the convolution of the Phansakar method. The convolutional neural network was designed with a simplified multichannel convolution operation to minimize computational cost. Notably, the proposed neural network utilizes only 0.11 M learnable parameters, which is significantly less than the number utilized by most classical deep neural networks. Experimental results for CFM56-7BE and Pratt & Whitney F100 aeroengine hollow turbine blade CT images demonstrate that compared to state-of-the-art algorithms, our proposed network can achieve 0.44 % mean intersection over union and 0.23 % mean Dive similarity coefficient improvements on testing datasets with significantly reduced computational cost. Therefore, the proposed method has high practical application significance and can achieve real-time detection.

Nonlinear directed acyclic graph estimation based on the kernel partial correlation coefficient

Directed acyclic graphs (DAGs) are powerful tools for detecting causality among variables and thus, they have attracted increasing interest in recent years. In most previous studies, DAGs were estimated under the assumption of linearity between variables; however, this assumption is not usually true in real-world applications. Therefore, developing DAG estimation methods for nonlinear scenarios is of great interest. In this work, we propose a DAG estimation method based on the kernel partial correlation (KPC) coefficient to identify nonlinear interactions among variables. The method consists of three steps: neighborhood selection, skeleton estimation and direction detection. While all the steps are grounded on the KPC coefficient, we develop a threshold-based criterion to address the falsely discovered edges in the skeleton estimation step and utilize the asymmetric property of the KPC coefficient in the direction detection step. Numerical simulations demonstrate the advantages of the proposed method over various competing methods. Finally, we apply the proposed method to construct networks in three real-world structural equation modeling examples in the social sciences and on one DNA binding site dataset to demonstrate its effectiveness.

Comparison of Residual-based Methods on Fault Detection

An important initial step in fault detection for complex industrial systems is gaining an understanding of their health condition. Subsequently, continuous monitoring of this health condition becomes crucial to observe its evolution, track changes over time, and isolate faults. As faults are typically rare occurrences, it is essential to perform this monitoring in an unsupervised manner. Various approaches have been proposed not only to detect faults in an unsupervised manner but also to distinguish between different potential fault types. In this study, we perform a comprehensive comparison between two residual-based approaches: autoencoders, and theinput-output models that establish a mapping between operating conditions and sensor readings. We explore the sensorwise residuals and aggregated residuals for the entire system in both methods. The performance evaluation focuses on three tasks: health indicator construction, fault detection, and health indicator interpretation. To perform the comparison, we utilize the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dynamical model, specifically a subset of the turbofan engine dataset containing three different fault types. All models are trained exclusively on healthy data. Fault detection is achieved by applying a threshold that is determined based on the healthy condition. The detection results reveal that both models are capable of detecting faults with an average delay of around 20 cycles and maintain a low false positive rate. While the fault detection performance is similar for both models, the input-output model provides better interpretability regarding potential fault types and the possible faulty components.

Computer-Aided Visual Inspection of Glass-Coated Tableware Ceramics for Multi-Class Defect Detection

Quality control procedures in the manufacturing of tableware ceramics require a demanding, monotonous, subjective, and faulty human manual inspection. This paper presents two machine learning strategies and the results of a semi-automated visual inspection of ceramics tableware applied to a private dataset acquired during the VAICeramics project. In one method, an anomaly detection step was integrated to pre-select possible defective patches before passing through an object detector and defects classifier. In the alternative one, all patches are directly provided to the object detector and then go through the classification phase. Contrary to expectations, the inclusion of the anomaly detector demonstrated a slight reduction in the performance of the pipeline, which may result from error propagation. Regarding the proposed methodology for defect detection, it exhibits average performance in monochromatic images with more than 600 real defects in total, efficiently identifying the most common defect classes in highly reflective surfaces. However, when applied to newly acquired images, the pipeline encounters challenges revealing a lack of generalization ability and experiencing limitations in detecting specific defect classes, due to their appearance and limited available samples used for training. Only two defect types presented high classification performance, namely Dots and Cracked defects.

Study of Non-Carcinogenic Risk to Public Health from Oral Consumption of Substandard Groundwater in the Nizhnevolzhsky Basin

The analysis of non-carcinogenic health risks associated with oral intake of toxicants is a relevant approach for the identification of endemic ecologically dependent diseases. It is based on the assessment of chronic exposure to various chemicals having a unidirectional mechanism of toxic effect. Main goal of the study is the sanitary and environmental assessment of drinking water from underground water supply sources of the Nizhnevolzhsky basin of the Volgograd region based on a step-by-step procedure for public health risk assessing. Study area GIS-data analysis was performed at the stage of hazard detection step (selection of a list of priority pollutants); a laboratory analysis of the chemical composition of water was carried out; the calculation of the dose of toxicants entering the body with drinking water was performed. For the first time for the territory of the Volgograd region, we calculated non-carcinogenic risks associated with oral intake of toxicants, revealed critical system and organs, mostly susceptible for the development of non-carcinogenic phenomena. An analysis of the literary sources devoted to the problems of the formation of substandard groundwater for drinking purposes and the health risks associated with this phenomenon was carried out according to the list of priority pollutants determined in the current study. It is possible to use the results of the study to adjust measures in the organization of water treatment and procedures for improving the social and hygienic monitoring of the health of water users of the Nizhnevolzhsky underground basin.

Optimization Objective Function Corona Discharge Acoustic Using Fuzzy c-Means (FcM )

In many electrical networks in Indonesia, insulation failure due to high voltage phenomena like Corona Discharge (CD) still happens. This is a result of our inability to perform early Corona Discharge (CD) identification. This study’s objective is to optimalize the sound properties of Corona Discharge (CD) as a first step throught the early identification of insulation failure in the form of clustering 20 kV cubicle. Based on observations on the needle-rod electrode 3 cm apart, the smallest breakdown was obtained at 34.3 kV. So that the classification of CD sound by 3 clusters starting 20 kV cubicle voltage until before the failure occurs on 33 kV. The temperature in the cubical is between 27.5℃ - 35.3℃ and humidity ranges from 70% - 95%. It was stated in the study that the FcM method was the most widely used and successful method. In this case, FcM can obtain more flexible results that classify data into clusters easily. This research will be carried out using the Fuzzy c-Means (FcM) method. Feature extraction with linear predictive coding (LPC) method, then optimization by using the Fuzzy c-Means (FcM) method which is expected to be used as an initial step for early detection of insulation failure.

Combinatorial fluorescent labeling of live anaerobic bacteria via the incorporation of azide-modified sugars into newly synthesized macromolecules.

The human gut microbiome modulates physiological functions and pathologies; however, a mechanistic understanding of microbe-host and microbe-microbe interactions remains elusive owing to a lack of suitable approaches to monitor obligate anaerobic bacterial populations. Common genetically encoded fluorescent protein reporters, derived from the green fluorescent protein, require an oxidation step for fluorescent light emission and therefore are not suitable for use in anaerobic microbes residing in the intestine. Fluorescence in situ hybridization is a useful alternative to visualize bacterial communities in their natural niche; however, it requires tissue fixation. We therefore developed an approach for the real-time detection and monitoring of live communities of anaerobic gut commensals in their natural environment. We leverage the bacterial cells' reliance on sugars for macromolecule synthesis in combinatorial click chemistry labeling, where the addition of azide-modified sugars to the culturing media enables the fluorescence labeling of newly synthesized molecules via the addition of combinations of exogenous fluorophores conjugated to cyclooctynes. This process is suitable for labeling communities of live anaerobic gut bacteria with combinations of fluorophores that do not require oxygen to mature and fluoresce, and that can be detected over time in their natural environments. The labeling procedure requires 4-9 d, depending on the varying growth rates of different bacterial strains, and an additional 1-2 d for the detection and monitoring steps. The protocol can be completed by users with basic expertise in bacterial culturing.

Dual-discriminator conditional generative adversarial network optimized with hybrid manta ray foraging optimization and volcano eruption algorithm for hyperspectral anomaly detection

A significant task on remote sensing field is anomaly detection in hyperspectral images (HSI). Many scientists have created several relevant techniques developing deep network-based ways for hyperspectral anomaly detection (HAD) in the recent years. Dual-discriminator conditional generative adversarial network (DcGAN) optimized with hybrid Manta ray foraging optimization algorithm and Volcano eruption algorithm (Hyb-MRF-VEA) is proposed for anomaly identification in Hyperspectral images (DcGAN-HAD) in this manuscript. The three steps of the proposed methodology are data preparation, reconstruction, and detection. Background purification is a stage in the data preparation process that trains the deep network unsupervised. In the reconstruction step, DcGAN method is executed in spatial, spectral, combined spectral-spatial domains. The novelty of DcGAN method is to produce the hyper spectral images (HSIs) that are closer to real ones. Among original and image pixels the reconstruction error map (REM) is computed. The pixel weights are obtained with respect to REM at the detection step. Finally, to obtain the final detection map, the original with reconstructed image is subject to spatial and spectral joint anomaly detector. For scaling the optimal parameters and make sure exact detection, DcGAN approach not exposes any optimization techniques adoption. Therefore, in this work, a Hyb-MRF-VEA with optimize DcGAN weight parameters. The proposed DcGAN-HAD system is done in PyTorch and its efficacy is calculated with certain performances metrics, like, area under ROC curve (AUC) metric, precision, computation time, accuracy. For hyper spectral remote sensing scenes dataset of PAVIA CENTER ANDUNIVERSITY, the proposed DcGAN-HAD method attains 22.15%, 58.97% and 34.29% higher accuracy compared with the existing methods.