Advancements in urban scene segmentation using deep learning and generative adversarial networks for accurate satellite image analysis.

In the urban scene segmentation, the "image-to-image translation issue" refers to the fundamental task of transforming input images into meaningful segmentation maps, which essentially involves translating the visual information present in the input image into semantic labels for different classes. When this translation process is inaccurate or incomplete, it can lead to failed segmentation results where the model struggles to correctly classify pixels into the appropriate semantic categories. The study proposed a conditional Generative Adversarial Network (cGAN), for creating high-resolution urban maps from satellite images. The method combines semantic and spatial data using cGAN framework to produce realistic urban scenes while maintaining crucial details. To assess the performance of the proposed method, extensive experiments are performed on benchmark datasets, the ISPRS Potsdam and Vaihingen datasets. Intersection over Union (IoU) and Pixel Accuracy are two quantitative metrics used to evaluate the segmentation accuracy of the produced maps. The proposed method outperforms traditional methods with an IoU of 87% and a Pixel Accuracy of 93%. The experimental findings show that the suggested cGAN-based method performs better than traditional techniques, attaining better segmentation accuracy and generating better urban maps with finely detailed information. The suggested approach provides a framework for resolving the image-to-image translation difficulties in urban scene segmentation, demonstrating the potential of cGANs for producing excellent urban maps from satellite data.

SIRT1/AMPK-mediated pathway: Ferulic acid from sugar beet pulp mitigating obesity-induced diabetes-linked complications and improving metabolic health.

Obesity-induced type 2 diabetes (T2D) increases the risk of metabolic syndrome due to the high calorie intake. The role of sugar beet pulp (SBP) in T2D and the mechanism of its action remain unclear, though it is abundant in phenolics and has antioxidant activity. In this study, we isolated and purified ferulic acid from SBP, referred to as SBP-E, and studied the underlying molecular mechanisms in the regulation of glucose and lipid metabolism developing high glucose/high fat diet-induced diabetic models in vitro and in vivo. SBP-E showed no cytotoxicity and reduced the oxidative stress by increasing glutathione (GSH) in human liver (HepG2) and rat skeletal muscle (L6) cells. It also decreased body weight gain, food intake, fasting blood glucose levels (FBGL), glucose intolerance, hepatic steatosis, and lipid accumulation. Additionally, SBP-E decreased the oxidative stress and improved the antioxidant enzyme levels in high-fat diet (HFD)-induced T2D mice. Further, SBP-E reduced plasma and liver advanced glycation end products (AGEs), malondialdehyde (MDA), and pro-inflammatory cytokines, and increased anti-inflammatory cytokines in HFD-fed mice. Importantly, SBP-E significantly elevated AMPK, glucose transporter, SIRT1 activity, and Nrf2 expression and decreased ACC activity and SREBP1 levels in diabetic models. Collectively, our study results suggest that SBP-E treatment can improve obesity-induced T2D by regulating glucose and lipid metabolism via SIRT1/AMPK signalling and the AMPK/SREBP1/ACC1 pathway.

Inclusion of Pseudomonas fluorescens into soil-like fraction from municipal solid waste management park to enhance plastic biodegradation.

Single-use facial masks which are predominantly made out of polypropylene is being used and littered in large quantities during post COVID-19 situation. Extensive researches on bioremediation of plastic pollution on soil led to the identification of numerous plastic degrading microorganisms. These organisms assimilate plastic polymers as their carbon source for synthesizing energy. Pseudomonas fluorescens (PF) is one among such microorganism which is being identified to biodegrade plastic polymers in controlled environment. The natural biodegradation of facial mask in soil-like fraction collected from municipal waste management site, bioaugmentation of the degradation process with Pseudomonas fluorescens, biostimulation of the soil with carbonless nutritional supplements and combined bioaugmentation with biostimulation process were studied in the present work. The study has been conducted both in controlled and in natural condition for a period of 12 months. The efficiency of the degradation was verified through FTIR analyses using carbonyl index, bond energy change, Loss in ignition (LOI) measurement along with CHNS analyses of residual substances. The analysis of results reported that carbonyl index (in terms of transmittance) was reduced to 46% of the control batch through the inclusion of PF in natural condition. The bioaugmented batch maintained in natural condition showed 33% reduction of LOI with respect to the control batch. The unburnt carbon content of the residual matter obtained from the furnace were analysed using CHNS analyser and indicated the lowest carbon content in the same bioaugmented batch. In this study, an attempt is made to verify the feasibility of enhancing biodegradation of single-use facial mask by bioaugmentation of soil-like fraction available in solid waste management park with Pseudomonas fluorescens under natural condition. CHNS and FTIR analysis assures the biodegradation of plastic waste in the soil-like fraction using Pseudomonas fluorescens under both controlled and natural environmental condition.

Solid Lipid Nanoparticles: A Potential Option for Enhancing Oral Bioavailability of Highly Soluble and Poorly Permeable (BCS Class III) Drugs.

Oral administration of drug is the most preferred one among the other routes for the majority of clinical applications. As compared to the parenteral method of administration, it has potential benefits such as increased patient compliance, fewer problems, and reduced treatment costs. Regardless of these factors, inadequate bioavailability owing to poor solubility or permeability limits the therapeutic effectiveness of orally given drugs. Though most current research focuses on BCS II (drugs with low solubility and high permeability), BCS III (drugs with high solubility and low permeability) also has poor oral bioavailability due to their limited permeability across lipid membranes and is usually administered through the parenteral route. The need for an oral alternative to parenteral administration has prompted a renewed focus on the development of innovative dosage forms that support the absorption of medicines that are poorly permeable through the intestinal epithelium. Because of their unique sizedependent feature in enhancing transmembrane permeability, ability to incorporate both lipophilic and hydrophilic drugs and biocompatible nature of components, the use of nanoparticles for improving drug bioavailability has been a focus of current study in the field of drug delivery in recent years. The lipidbased nanoparticle method presents a potential new avenue for manufacturing BCS Class III medicines with enhanced bioavailability, as poor permeability is the main issue for these agents. This research aims to assess the potential of lipid nanoparticles for improving the oral bioavailability of medicines with permeability-restricted oral absorption, such as pharmaceuticals in Biopharmaceutical Classification System (BCS) class III.

Design and Analysis of Multilayered Neural Network-Based Intrusion Detection System in the Internet of Things Network.

A large array of objects is networked together under the sophisticated concept known as the Internet of Things (IoT). These connected devices collect crucial information that could have a big impact on society, business, and the entire planet. In hostile settings like the internet, the IoT is particularly susceptible to multiple threats. Standard high-end security solutions are insufficient for safeguarding an IoT system due to the low processing power and storage capacity of IoT devices. This emphasizes the demand for scalable, distributed, and long-lasting smart security solutions. Deep learning excels at handling heterogeneous data of varying sizes. In this study, the transport layer of IoT networks is secured using a multilayered security approach based on deep learning. The created architecture uses the intrusion detection datasets from CIC-IDS-2018, BoT-IoT, and ToN-IoT to evaluate the suggested multi-layered approach. Finally, the new design outperformed the existing methods and obtained an accuracy of 98% based on the examined criteria.

Multiconvolutional Transfer Learning for 3D Brain Tumor Magnetic Resonance Images.

The difficulty or cost of obtaining data or labels in applications like medical imaging has progressed less quickly. If deep learning techniques can be implemented reliably, automated workflows and more sophisticated analysis may be possible in previously unexplored areas of medical imaging. In addition, numerous characteristics of medical images, such as their high resolution, three-dimensional nature, and anatomical detail across multiple size scales, can increase the complexity of their analysis. This study employs multiconvolutional transfer learning (MCTL) for applying deep learning to small medical imaging datasets in an effort to address these issues. Multiconvolutional transfer learning is a model based on transfer learning that enables deep learning with small datasets. In order to learn new features on a smaller target dataset, an initial baseline is used in the transfer learning process. In this study, 3D MRI images of brain tumors are classified using a convolutional autoencoder method. In order to use unenhanced Magnetic Resonance Imaging (MRI) for clinical diagnosis, expensive and invasive contrast-enhancing procedures must be performed. MCTL has been shown to increase accuracy by 1.5%, indicating that small targets are more easily detected with MCTL. This research can be applied to a wide range of medical imaging and diagnostic procedures, including improving the accuracy of brain tumor severity diagnosis through the use of MRI.

An Empirical Analysis of an Optimized Pretrained Deep Learning Model for COVID-19 Diagnosis.

As a result of the COVID-19 outbreak, which has put the world in an unprecedented predicament, thousands of people have died. Data from structured and unstructured sources are combined to create user-friendly platforms for clinicians and researchers in an integrated bioinformatics approach. The diagnosis and treatment of COVID-19 disease can be accelerated using AI-based platforms. In the battle against the virus, however, researchers and decision-makers must contend with an ever-increasing volume of data, referred to as "big data." VGG19 and ResNet152V2 pretrained deep learning architectures were used in this study. With these datasets, we could train and fine-tune our model on lung ultrasound frames from healthy people as well as from patients with COVID-19 and pneumonia. In two separate experiments, we evaluated two different classes of predictive models: one against pneumonia and the other against non-COVID-19. COVID-19 can be detected and diagnosed accurately and efficiently using these models, according to the findings. Therefore, the use of these inexpensive and affordable deep learning methods should be considered as a reliable method for the diagnosis of COVID-19.

Effective prediction of soil micronutrients using Additive Gaussian process with RAM augmentation.

In soil chemistry, the nutrients exhibit non-linear and complex relationships owing to their stochastic nature but mostly their similarity is a function of the distance between the data points. The similarity assessment using distance metrics is a popular technique employed by the regression, classification and feature selection algorithms. To enhance the precision of distance metric, the kernel trick is performed on the input space and the similarity is ascertained in the new high dimensional feature space. In Kernel Distance Metric Learning (KDML), the relevance of distance metrics is intensified to capture the precise similarity measure. In Hierarchical Kernel Learning (HKL) and Additive Gaussian Process (AGP) models, several orders of interactions among the subsets of predictors are emphasized while learning the kernel. In this paper a novel method, Restricted Additive Model (RAM) embedded in Additive Gaussian Process (AGP), to compute the distance in input space by adding selective weighted distances from the subset of predictors is proposed. RAM focuses on reusing the information content obtained while preprocessing the data and incorporate it while learning with the kernel. This can save a good amount of computational resources for high dimensional datasets. The proposed model is compared with HKL, AGP and a normal Gaussian Process (GP). The adjusted R2 and the Mean Absolute Error values showed that the proposed model showcased good accuracy reducing the computational time and resources. Further, the comparison of RAM with Automatic Relevance Determination of GP testified that the reusability of the information content turned to be effective in building a parsimonious model.

trans-ferulic acid attenuates hyperglycemia-induced oxidative stress and modulates glucose metabolism by activating AMPK signaling pathway in vitro.

Adenosine monophosphate-activated protein kinase (AMPK) is a potent metabolic regulator and an attractive target for antidiabetic activators. Here we report for the first that, trans-ferulic acid (TFA) is a potent dietary bioactive molecule of hydroxycinnamic acid derivative for the activation of AMPK with a maximum increase in phosphorylation (2.71/2.67 ± 0.10; p < .001 vs. high glucose [HG] control) in hyperglycemia-induced human liver cells (HepG2) and rat skeletal muscle cells (L6), where HG suppresses the AMPK pathway. It was also observed that TFA increased activation of AMPK in a dose- and time-dependent manner and also increased the phosphorylation of acetyl-CoA carboxylase (ACC), suggesting that it may promotes fatty acid oxidation; however, pretreatment with compound C reversed the effect. In addition, TFA reduced the level of intracellular reactive oxygen species (ROS) and nitric oxide (NO) induced by hyperglycemia and subsequently increased the level of glutathione. Interestingly, TFA also upregulated the glucose transporters, GLUT2 and GLUT4, and inhibited c-Jun N-terminal protein kinase (JNK1/2) by decreasing the phosphorylation level in tested cells under HG condition. Our studies provide critical insights into the mechanism of action of TFA as a potential natural activator of AMPK under hyperglycemia. PRACTICAL APPLICATIONS: Hydroxycinnamic acid derivatives possess various pharmacological properties and are found to be one of the most ubiquitous groups of plant metabolites in almost all dietary sources. However, the tissue-specific role and its mechanism under hyperglycemic condition remain largely unknown. The present study showed that TFA is a potent activator of AMPK under HG condition and it could be used as a therapeutic agent against hyperglycemia in type 2 diabetes.

Utility-Based Differentially Private Recommendation System.

The Recommendation system relies on feedback and personal information collected from users for effective recommendation. The success of a recommendation system is highly dependent on storing and managing sensitive customer information. Users refrain from using the application if there is a threat to user privacy. Several works that were performed to protect user privacy have paid little attention to utility. Hence, there is a need for a robust recommendation system with high accuracy and privacy. Model-based approaches are more prevalent and commonly used in recommendation. The proposed work improvises the existing private model-based collaborative filtering algorithm with high privacy and utility. We identified that data sparsity is the primary reason for most of the threats in a recommender framework through an extensive literature survey. Hence, our approach combines the l injection for imputing the missing ratings, which are deemed low, with differential privacy. We additionally introduce a random differential privacy approach to alternating least square (ALS) for improved utility. Experimental results on benchmarked datasets confirm that the performance of our private noisy Random ALS algorithm outperforms the non-noisy ALS for all datasets.

Deep neural network and model-based clustering technique for forensic electronic mail author attribution.

Electronic mail is the primary source of different cyber scams. Identifying the author of electronic mail is essential. It forms significant documentary evidence in the field of digital forensics. This paper presents a model for email author identification (or) attribution by utilizing deep neural networks and model-based clustering techniques. It is perceived that stylometry features in the authorship identification have gained a lot of importance as it enhances the author attribution task's accuracy. The experiments were performed on a publicly available benchmark Enron dataset, considering many authors. The proposed model achieves an accuracy of 94% on five authors, 90% on ten authors, 86% on 25 authors and 75% on the entire dataset for the Deep Neural Network technique, which is a good measure of accuracy on a highly imbalanced data. The second cluster-based technique yielded an excellent 86% accuracy on the entire dataset, considering the authors' number based on their contribution to the aggregate data.

Dataset on the assessment of water quality of ground water in Kalingarayan Canal, Erode district, Tamil Nadu, India.

This data article aimed to investigate the quality of ground water in Kalingarayan Canal for the analysis of pollution level, Tamil Nadu. In order to understand the pollution status of the canal, nine ground water samples (GW1- GW9) were collected from the downstream side of the canal during the period between January 2014 - December 2016. Nine stations were selected along the Kalingarayan Canal, and ground water samples were collected on a monthly basis from these stations. The parameters like pH, electrical conductivity (EC), total dissolved solids (TDS), chlorides, total hardness (TH) nitrates, sulphates, sodium, calcium and magnesium were analyzed to observe the current status of the groundwater quality. Also, the groundwater quality is expressed in terms of Water Quality index (WQI). The APHA method was applied to determine the physico chemical parameters of the water samples. From the investigation, WQI reflects a low quality of groundwater in sampling stations Kolathupalayam (GW3) and Perumparai (GW6) which is mainly contaminated with nitrate and the water is found to be very hard in nature. Also, it was observed that calcium and magnesium content in groundwater is very high at certain stations. Most of the groundwater from this place cannot be used for any kind of industrial processes and human consumption without proper treatment.

Therapeutic evaluation of homeopathic treatment for canine oral papillomatosis.

AIM: A study was conducted to evaluate the ameliorative potential of homeopathic drugs in combination (Sulfur 30C, Thuja 30C, Graphites 30C, and Psorinum 30C) in 16 dogs affected with oral papillomatosis which was not undergone any previous treatment. MATERIALS AND METHODS: Dogs affected with oral papillomatosis, which have not undergone any initial treatment and fed with a regular diet. Dogs (total=16) were randomly divided into two groups, namely, homeopathic treatment group (n=8) and placebo control group (n=8). Random number table was used for allocation. Homeopathic combination of drugs and placebo drug (distilled water) was administered orally twice daily for 15 days. Clinical evaluation in both groups of dogs was performed by the same investigator throughout the period of study (12 months). Dogs were clinically scored for oral lesions on days 0, 5, 7, 10, 15, 20, 25, 30, 45, 60, 90, 120, and 150 after initiation of treatment. RESULTS: The homeopathic treatment group showed early recovery with a significant reduction in oral lesions reflected by clinical score (p<0.001) in comparison to placebo-treated group. Oral papillomatous lesions regressed in the homeopathic group between 7 and 15 days, whereas regression of papilloma in the placebo group occurred between 90 and 150 days. The homeopathic treated group was observed for 12 months post-treatment period and no recurrence of oral papilloma was observed. CONCLUSION: The current study proves that the combination of homeopathy drugs aids in fastening the regression of canine oral papilloma and proved to be safe and cost-effective.

SECNLP: A survey of embeddings in clinical natural language processing.

Distributed vector representations or embeddings map variable length text to dense fixed length vectors as well as capture prior knowledge which can transferred to downstream tasks. Even though embeddings have become de facto standard for text representation in deep learning based NLP tasks in both general and clinical domains, there is no survey paper which presents a detailed review of embeddings in Clinical Natural Language Processing. In this survey paper, we discuss various medical corpora and their characteristics, medical codes and present a brief overview as well as comparison of popular embeddings models. We classify clinical embeddings and discuss each embedding type in detail. We discuss various evaluation methods followed by possible solutions to various challenges in clinical embeddings. Finally, we conclude with some of the future directions which will advance research in clinical embeddings.

Validation and Clinical Application of Interferon-Gamma Release Assay for Diagnosis of Latent Tuberculosis Infection in Children.

BACKGROUND: India has the highest tuberculosis (TB) burden, accounting for one-fifth of the global incidence and two-third of the cases in Southeast Asia with an estimated 1.9 million new cases every year. Identifying and treating latent TB infection (LTBI) can reduce the risk of development of active disease by up to 90%, thereby decreasing a major burden to the prevalence of the disease, and thus reducing potential sources in future. AIM: Early diagnosis of LTBI by tuberculin skin test (TST) and a newer interferon-gamma release assay (IGRA). MATERIALS AND METHODS: Seventy-seven clinically asymptomatic household contacts (≤18 years) of confirmed pulmonary TB patients were enrolled to compare the performance of TST and IGRA to diagnose LTBI. At baseline, all participants underwent testing for IGRA and TST. RESULTS: TST showed positivity of 22%, while IGRA demonstrated positivity of 40% in the diagnosis of latent TB. Kappa value at 95% confidence interval was 0.4753, indicates a moderate agreement between the two tests. This indicates that IGRA is a better predictor of latent TB. Maximum positive percentage was in the age group of 16-18 years in both the tests followed by 1-5 years. AIM: Early diagnosis of LTBI by tuberculin skin test (TST) and a newer interferon-gamma release assay (IGRA).

New barium, strontium and strontium-doped barium squarates: synthesis, crystal structures and DNA/BSA binding, antioxidant and in vitro cytotoxicity studies.

A new set of differently hydrated barium and strontium squarates, namely poly[[triaqua(µ-1,2-dioxocyclobut-3-ene-1,2-diolato)barium] monohydrate], {[Ba(C4O4)(H2O)3]·H2O}n (1), poly[[diaqua(µ-1,2-dioxocyclobut-3-ene-1,2-diolato)strontium] monohydrate], {[Sr(C4O4)(H2O)2]·H2O}n (2), and poly[[triaqua(µ-1,2-dioxocyclobut-3-ene-1,2-diolato)barium/strontium(0.85/0.15)] monohydrate], {[Ba0.85Sr0.15(C4O4)(H2O)3]·H2O}n (3), is reported. The study of their crystal structures indicates that all the complexes crystallize in the triclinic space group P-1. Complexes 1 and 3 have a rare combination of squarate units coordinated through monodentate O atoms to two different metal atoms and through two bidentate O atoms to three different metal atoms. Furthermore, they have three coordinated water molecules to give a coordination number of nine. The squarate ligands in complex 2 exhibit two different coordination modes: (i) monodentate O atoms coordinated to four different Sr atoms and (ii) two monodentate O atoms coordinated to two different metal atoms with the other two O atoms bidentate to four different Sr atoms. All the compounds decompose to give the respective carbonates when heated to 800 °C, as evidenced by thermogravimetry/differential thermal analysis (TG-DTA), which are clusters of nanoparticles. Complexes 1 and 3 show additional endothermic peaks at 811 and 820 °C, respectively, indicating the phase transition of BaCO3 from an orthorhombic (α-Pmcn) to a trigonal phase (ß-R3m). All three complexes have significant DNA-binding constants, ranging from 2.45 × 104 to 9.41 × 104 M-1 against EB-CT (ethidium bromide-calf thymus) DNA and protein binding constants ranging from 1.1 × 105 to 8.6 × 105 with bovine serum albumin. The in vitro cytotoxicity of the complexes is indicated by the IC50 values, which range from 128.8 to 261.3 µg ml-1. Complex 3 shows better BSA binding, antioxidant activity against the DPPH radical and cytotoxicity than complexes 1 and 2.

Immunomodulatory basis of antioxidant therapy and its future prospects: an appraisal.

Antioxidants are agents which can modulate oxidant-antioxidant profile of body system by neutralizing pro-oxidant molecules. The current scientific knowledge on mechanisms of antioxidant activity of biomolecules was critically reviewed with a special emphasis on immunomodulation. The immuno-oxidative wreckage of animals in various disease conditions and the role of biomodulators in curbing the oxidative stress through immune pathways were analyzed. The critical role of immunomodulatory mechanisms in controlling oxidative damage was identified. Selection of antioxidant therapy considering the immunopharmacology of the drug as well as immunological basis of disease may reduce treatment failure and adverse health effects. Hence, it is suggested that future studies on antioxidants may focus on the immuno-oxidative pathobiology to better understand its clinical effects and effective disease management.

One-pot synthesis of glycyrrhetic acid polyglycosides based on grafting-from method using cyclic sulfite.

Glycyrrhetic acid polyglycosides were synthesized in one-pot via cationic ring-opening condensation polymerization of cyclic sulfite (4) initiated by glycyrrhetic acid as an aglycon. Sulfite 4 worked as a practical monomer for the preparation of (1 â†’ 2)-linked polysaccharide skeletons. The chemical stability of 4 was evaluated by the comparison of thermodynamic parameters with those of conventional epoxide (2). The grafting reaction of 4 from glycyrrhetic acid (5) was performed in the presence of TfOH and MS 3A in CH2Cl2 at room temperature. The polymerization degree was moderately controllable by the change of feed ratio of initiator.