Discriminative Approach Research Articles

Ejection of Real-Time Malicious Intrusion and Attacks in IoT Empowered Infrastructure

The project recognizes the pervasive threat of computer viruses, malware, and hostile attacks on computer networks, highlighting the critical role of intrusion detection as a proactive defense technology. The project introduces a novel approach based on deep learning to identify and mitigate cybersecurity vulnerabilities and breaches in IoT-driven cyber-physical systems, aiming for enhanced security measures. The project's objective is to elevate intrusion detection beyond the limitations of traditional systems by addressing issues like accuracy, detection effectiveness, and reducing false positives. This emphasizes the advancement and innovation in cybersecurity. To achieve the project's goals, the method employs a generative adversarial network, a cutting-edge deep learning technique. Additionally, it distinguishes itself by contrasting unsupervised and deep learning-based discriminative approaches, showcasing a comprehensive and effective approach to cybersecurity. In our project, we successfully implemented an ensemble method to boost predictive accuracy by integrating multiple individual models. Particularly noteworthy is the inclusion of a hybrid architecture, combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), denoted as CNN+LSTM. This hybrid model achieved an impressive accuracy of 99% when applied to the KDD-Cup dataset, underscoring the efficacy of our ensemble technique for intrusion detection in IoT- based cybersecurity infrastructures.

New approach for accurate discrimination and location of power transformers with different internal winding faults.

Power transformers are essential elements in power systems and thus their protection schemes have critical importance. In this paper, a scheme is proposed for accurate discrimination and location of internal faults in power transformers using conventional measuring devices attached to the transformer. Different types of internal winding faults are intensely considered: partial discharge, inter-disk faults, series and shunt short circuit faults and axial displacement. Depending on the transformer measured output voltage, input voltage and the input current, the construction of a locus diagram (ΔV-Iin) serves as an indicator for any physical modification to the winding. Using five suggested features extracted from the developed locus, an artificial neural network (ANN) technique is applied to accurately distinguish any deviation from the transformer healthy condition. The exact location of each fault inside the windings of power transformer is then determined. The obtained results validate the usefulness of the proposed scheme for different internal faults. The superiority of the proposed scheme is extensively examined by comparing its results with some published schemes.

Deep learning model with pathological knowledge for detection of colorectal neuroendocrine tumor

Colorectal neuroendocrine tumors (NETs) differ significantly from colorectal carcinoma (CRC) in terms of treatment strategy and prognosis, necessitating a cost-effective approach for accurate discrimination. Here, we propose an approach for distinguishing between colorectal NET and CRC based on pathological images by utilizing pathological prior information to facilitate the generation of robust slide-level features. By calculating the similarity between morphological descriptions and patches, our approach selects only 2% of the diagnostically relevant patches for both training and inference, achieving an area under the receiver operating characteristic curve (AUROC) of 0.9974 on the internal dataset, and AUROCs of 0.9724 and 0.9513 on two external datasets. Our model effectively identifies NETs from CRCs, reducing unnecessary immunohistochemical tests and enhancing the precise treatment for patients with colorectal tumors. Our approach also enables researchers to investigate methods with high accuracy and low computational complexity, thereby advancing the application of artificial intelligence in clinical settings.

Higher Microbial Abundance and Diversity in Bronchus-Associated Lymphoid Tissue (BALT) Lymphomas than in Non-Cancerous Lung Tissues.

It is well known that the majority of the extranodal marginal zone lymphomas of mucosa-associated lymphoid tissues (MALT lymphomas) are associated with microbiota, e.g., gastric MALT lymphoma with Helicobacter pylori. In general, they are very sensitive to low-dose radiotherapy and chemotherapeutic agents. The microbiota profile is not clearly elucidated in bronchus-associated lymphoid tissue (BALT) lymphoma, a rare type of MALT lymphoma in the lung. Thus, this study aimed to clarify the intratumor microbiome in BALT lymphoma using the third-generation NGS method. DNAs were extracted from 12 formalin-fixed paraffin-embedded (FFPE) tumor tissues obtained from BALT lymphoma patients diagnosed between 1990 and 2016. 16S rRNA gene was amplified by polymerase chain reaction. Amplicons were sequenced using a Nanopore platform. Next-generation sequencing analysis was performed to assess microbial profiles. For comparison, FFPE specimens from nine non-cancerous lung tissues were also analyzed. Specific bacterial families including Burkholderiaceae, Bacillaceae, and Microbacteriaceae were associated with BALT lymphoma by a linear discriminant analysis effect size approach. Although the number of specimens was limited, BALT lymphomas exhibited significantly higher microbial abundance and diversity with distinct microbial composition patterns and correlation networks than non-cancerous lung tissues. This study provides the first insight into intratumor microbiome in BALT lymphoma using the third-generation NGS method. A distinct microbial composition suggests the presence of a unique tumor microenvironment of BALT lymphoma.

Forensic discrimination of fiber microspectrophotometry data by resampling and repeating two-sample hypothesis testing

Textile fibers are important forensic trace evidence in criminal investigations. Colored textile fibers are often analyzed using non-destructive microspectrophotometry. However, when the spectra of questioned and known samples are very similar, it is difficult to compare the spectra visually. Chemometric methods, such as principal component analysis and agglomerative hierarchical clustering, have been applied to microspectrophotometry data. In this study, we used two-sample hypothesis testing as a chemometric approach for discrimination of fiber samples without reducing or eliminating the dimensionality of the data. Cotton fibers dyed with vat dyes were analyzed by microspectrophotometry. We examined suitable data types and statistical methods for test fiber samples by resampling and repeating hypothesis testing. A combination of spectral data type and statistical method was identified that provided a good balance of type I (false exclusion) and type II (false inclusion) error rates in two-sample hypothesis testing of the fibers.The main advantage of our chemometric approach is that an appropriate method for samples can be selected by using the type I and II error rates. Furthermore, our method can use all the measured data for the calculation without reducing or eliminating the dimensionality of the data, so it is not necessary to reduce variables or smooth the spectrum. This statistical method also requires no training set. Therefore, two-sample hypothesis testing could be applied to fibers of different types, colors, or materials from those used in this study. Resampling and repeating two-sample hypothesis testing technique is promising as a new chemometric approach for comparing microspectrophotometry spectra.

Stochastic image spectroscopy: a discriminative generative approach to hyperspectral image modelling and classification

This paper introduces a new latent variable probabilistic framework for representing spectral data of high spatial and spectral dimensionality, such as hyperspectral images. We use a generative Bayesian model to represent the image formation process and provide interpretable and efficient inference and learning methods. Surprisingly, our approach can be implemented with simple tools and does not require extensive training data, detailed pixel-by-pixel labeling, or significant computational resources. Numerous experiments with simulated data and real benchmark scenarios show encouraging image classification performance. These results validate the unique ability of our framework to discriminate complex hyperspectral images, irrespective of the presence of highly discriminative spectral signatures.

A novel multi-layer discriminative dictionary learning approach for image classification

Discriminative dictionary learning (DDL) has been confirmed to be effective for image classification. However, existing DDL approaches often fail to extract deep hierarchical information due to the single-layer dictionary learning framework. Moreover, they overlook the atoms-label information in the dictionary, leading to reduced feature distinctiveness and lower classification accuracy. To overcome the above problem, a novel DDL method, called the Multi-layer local constraint and label embedding dictionary learning (M-LCLEDL), is proposed. Specifically, the novel multi-layer DDL framework, which is formed by stacking the DL process one by one, is designed to learn the deep hierarchical and nonlinear features. The layer-by-layer stacking of the DL process in the multi-layer DDL framework allows for the elimination of redundant and interfering features. This step-by-step elimination process enhances the stability and robustness of the framework. Additionally, to leverage the label information carried by the labeled training samples, atoms with label embedding and locality structure are introduced. The proposed approach includes a fast iteration strategy for efficient optimization. Experimental results demonstrate that the approach is relatively insensitive to dictionary size, achieving promising performance and greater stability compared to most DDL-based image classification approaches.

An integrated approach for discrimination of Magnoliae officinalis cortex before and after being processed by ginger juice combining LC/MS, GC/MS, intelligent sensors, and chemometrics.

Magnoliae officinalis cortex (MOC) is an important traditional Chinese medicine (TCM), and both raw and stir-fried MOC were commonly used in clinic. This study aimed to discriminate MOC and MOC stir-fried with ginger juice (MOCG) using an integrated approach combining liquid chromatography/mass spectrometry (LC/MS), gas chromatography/mass spectrometry (GC/MS), intelligent sensors, and chemometrics. The sensory characters of the samples were digitalized using intelligent sensors, i.e., colorimeter, electronic nose, and electronic tongue. Meanwhile, the chemical profiles of the samples were analyzed using LC/MS and GC/MS methods. Chemometric models were constructed to discriminate samples of MOC and MOCG based on not only the sensory data but also the chemical data. The differential sensory characters (L* and b* from colorimeter, ANS from electronic tongue, W1S and W2S from electronic nose) and the differential chemical compounds (26 and 11 compounds from LC/MS and GC/MS, respectively) were discovered between MOC and MOCG. Furthermore, twelve differential compounds showed good relations with differential sensory characters. Finally, artificial neural network models were established to discriminate samples of MOC and MOCG, in which W1S, W2S, ANS, b*, and 10 differential compounds were among the top 10 important variables, respectively. Samples of MOC and MOCG can be discriminated not only by the digitalized data of color, taste, and scent detected by intelligent sensors but also by chemical information obtained from LC/MS and GC/MS using chemometrics. The variations in sensory characters and chemical compounds between MOC and MOCG partially resulted from the Maillard reaction products and the oxidation of some compounds in the stir-frying process.

A Deep Learning Approach for Accurate Discrimination Between Optic Disc Drusen and Papilledema on Fundus Photographs.

Optic disc drusen (ODD) represent an important differential diagnosis of papilledema caused by intracranial hypertension, but their distinction may be difficult in clinical practice. The aim of this study was to train, validate, and test a dedicated deep learning system (DLS) for binary classification of ODD vs papilledema (including various subgroups within each category), on conventional mydriatic digital ocular fundus photographs collected in a large international multiethnic population. This retrospective study included 4,508 color fundus images in 2,180 patients from 30 neuro-ophthalmology centers (19 countries) participating in the Brain and Optic Nerve Study with Artificial Intelligence (BONSAI) Group. For training and internal validation, we used 857 ODD images and 3,230 papilledema images, in 1,959 patients. External testing was performed on an independent data set (221 patients), including 207 images with ODD (96 visible and 111 buried), provided by 3 centers of the Optic Disc Drusen Studies Consortium, and 214 images of papilledema (92 mild-to-moderate and 122 severe) from a previously validated study. The DLS could accurately distinguish between all ODD and papilledema (all severities included): area under the receiver operating characteristic curve (AUC) 0.97 (95% confidence interval [CI], 0.96-0.98), accuracy 90.5% (95% CI, 88.0%-92.9%), sensitivity 86.0% (95% CI, 82.1%-90.1%), and specificity 94.9% (95% CI, 92.3%-97.6%). The performance of the DLS remained high for discrimination of buried ODD from mild-to-moderate papilledema: AUC 0.93 (95% CI, 0.90-0.96), accuracy 84.2% (95% CI, 80.2%-88.6%), sensitivity 78.4% (95% CI, 72.2%-84.7%), and specificity 91.3% (95% CI, 87.0%-96.4%). A dedicated DLS can accurately distinguish between ODD and papilledema caused by intracranial hypertension, even when considering buried ODD vs mild-to-moderate papilledema.

Autistic traits are associated with differences in the perception of genuineness and approachability in emotional facial expressions, independently of alexithymia.

People with autism and higher levels of autistic traits often have difficulty interpreting facial emotion. Research has commonly investigated the association between autistic traits and expression labeling ability. Here, we investigated the association between two relatively understudied abilities, namely, judging whether expressions reflect genuine emotion, and using expressions to make social approach judgements, in a nonclinical sample of undergraduates at an Australian university (N = 149; data collected during 2018). Autistic traits were associated with more difficulty discriminating genuineness and less typical social approach judgements. Importantly, we also investigated whether these associations could be explained by the co-occurring personality trait alexithymia, which describes a difficulty interpreting one's own emotions. Alexithymia is hypothesized to be the source of many emotional difficulties experienced by autistic people and often accounts for expression labeling difficulties associated with autism and autistic traits. In contrast, the current results provided no evidence that alexithymia is associated with differences in genuineness discrimination and social approach judgements. Rather, differences varied as a function of individual differences in specific domains of autistic traits. More autistic-like social skills and communication predicted greater difficulty in genuineness discrimination, and more autistic-like social skills and attention to details and patterns predicted differences in approach judgements. These findings suggest that difficulties in these areas are likely to be better understood as features of the autism phenotype than of alexithymia. Finally, results highlight the importance of considering the authenticity of emotional expressions, with associations between differences in approach judgements being more pronounced for genuine emotional expressions. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Characterization of EJ-270 and Ce-doped LiCAF scintillators for the development of high-rate neutron reflectometer detectors

The Second Target Station of the Spallation Neutron Source at Oak Ridge National Laboratory is anticipated to provide a neutron source with ∼20 times increase in peak brightness than the First Target Station. The neutron reflectometers currently in operation at the First Target Station need to be upgraded due to the increased neutron flux. A prototype neutron detector module based upon a pixelated scintillator array readout by silicon photomultipliers is being developed to address the high-rate challenge faced with future neutron reflectometer instruments at the Second Target Station. Two types of scintillator materials were considered for this detector development, i.e., 6Li-loaded EJ-270 plastic scintillator and Ce-doped LiCAF single crystal. This paper reports the scintillator characterization results, including light yield, pulse shape discrimination performance, capability to detect thermal neutrons in a high γ-ray field, and γ-ray sensitivity. The number of photons produced per neutron capture by EJ-270 and LiCAF:Ce was measured to be 2176 ± 91 and 2651 ± 108, respectively. EJ-270 demonstrated a good capability to discriminate between neutrons and γ-rays by employing the commonly used charge comparison method (figure-of-merit: 1.13 ± 0.01 for an energy cut of 292–426 keVee) and a reasonable performance when using the time-over-threshold techniques; however, no discrimination was observed from LiCAF:Ce regardless of the pulse shape discrimination approaches utilized, making pulse height discrimination necessary for LiCAF:Ce to differentiate between neutrons and γ-rays. Both EJ-270 and LiCAF:Ce exhibited an acceptable capacity to detect thermal neutrons at high exposure rates up to approximately 584 mR/h. The γ-ray sensitivities measured with a60Co source at an exposure rate of around 1145 mR/h were determined to be (6.11 ± 0.87) × 10−6 and (7.64 ± 1.08) × 10−7 for EJ-270 and LiCAF:Ce, respectively.

Polyoxometalate-based peroxidase-mimicking sensors for colorimetric detection and discrimination of phenolic pollutants

Phenol and its derivatives represent a kind of significant hazards to both human health and the integrity of ecological systems. Exploring an efficient detection and discrimination approach for them is urgent. Herein, a kind of polyoxometalate-based peroxidase-mimicking crystalline colorimetric sensors were developed by integrating dual active sites of Keggin-type polyoxoanions and coordination unsaturated copper centers, for which the formulas are [Cu(dppeo)3]2[Cu(dppeo)2(H2O)](dppeo)0.75[PMo12O40]2·9H2O (1), [Cu(dppeo)2(H2O)]2 [SiW12O40]·6H2O (2), [Cu(dppeo)2]3[PW12O40]2·12H2O (3), (dppeo = 1,2-bis(diphenylphosphino)ethane dioxide). Structural analysis revealed that these compounds exhibit 0-D supramolecular architecture formed through the interplay of electrostatic forces and hydrogen bonding interactions between Keggin-type polyoxoanions and dppeo-chelated copper-organic cationic fragments. Sensors 1–3 exhibit favorable peroxidase-mimicking catalytic activities, which expedite the reaction involving phenol, 4-aminoantipyrine and hydrogen peroxide (H2O2), resulting in a pronounced color change for indicating the target concentration levels. These crystalline sensors responded linearly to phenol concentration within 0.01–1.0 mM, affording low detection limits of 1.19, 1.59 and 3.78 μM for 1–3. These sensors demonstrate exceptional anti-interference capabilities and exhibit excellent applicability in real water samples, ensuring high recovery rates. By incorporating a colorimetric array with principal component analysis, the sensors effectively discriminate between common phenolic compounds. This research presents an innovative methodology for the design of crystalline sensor materials, paving the way for the detection and differentiation of phenolic pollutants within environmental applications.

A unified approach for breast cancer discrimination using metasurface-based microwave technology

Multifocal (MF) and multicentric (MC) breast cancers are more likely to be aggressive than unifocal (UF) breast tumors, and they are linked to high recurrence probability, lymph node metastases, and low survival rates. Metastasis is the process through which cancer cells spread to different body areas. Although the longevity of patients with metastatic breast cancer is high, it is restricted by the growth of brain metastases. Medical imaging techniques have inherent limits. Hence, a precise and sensitive substitution is required. Because microwave imaging is portable, non-ionizing, and affordable, it has become a viable method for the detection of breast cancer. As far as we know, this is the first research aiming at discriminating MF and MC breast cancers from UF ones. This proposal presents a 2×2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$2\ imes 2$$\\end{document} planar metasurface-based array antenna in the Industrial Scientific Medical frequency band at 2.4 GHz. The proposed array configuration significantly enhanced the gain to 4 dBi rather than a single element at 50 Ω. The geometric arrangement of the four antenna elements is optimized to discriminate the critical stage of breast cancers (UF, MF, or MC). As the proposed structure does not surround the breast, it contributes to a higher degree of comfort than the conventional antenna configurations. The magnitude and phase of S-parameters of the backscattered signals are analyzed in this research.

Comprehensive profiling and authentication of porcine, bovine, and goat bone gelatins through UHPLC-HRMS metabolomics and chemometric strategies

Gelatin is a derivative that can be obtained from the bones of animals such as bovine, goat, and porcine. Ensuring the halal status of gelatin is crucial due to the combination of gelatin derived from bovines and goats mixed with porcine gelatin in order to enhance the stability of its physico-chemical properties for application in food and cosmetic applications. This study aims to authenticate the halal status of gelatin by utilizing the metabolomics analysis approach using UHPLC-HRMS in combination with chemometrics. The study's findings showed that PCA analysis clearly distinguished the metabolite profiles of bone gelatins obtained from porcine, bovine, and goat sources. Cluster analysis identified distinct metabolic characteristics in bone gelatins derived from bovine, goat, and porcine. Fifteen potential metabolites were identified by PLS-DA for the halal authentication of gelatin. These metabolites include terephthalic acid, 5,5'-[(6Z)-6-Tetradecene-1,14-diyl]bis (1,3-benzenediol), 1,2-Cyclohexane dicarboxylic acid diisononyl ester, 5-Hydroxymethyl-2-furaldehyde, D-(+)-Pyroglutamic acid, 4-Hydroxybenzaldehyde, Dodecyl sulfate, Bis(2-ethylhexyl)phthalate, Nicotinamide, dl-Malic acid, NP-011548, 4-Nitrocatechol, 1-Linoleoyl glycerol, Olomoucine, and Myristyl sulfate. The study findings indicated that bone gelatins derived from bovine, goat, and porcine sources exhibit distinct profiles of metabolites. Metabolomics, when paired with chemometrics, is a discriminative approach for determining the halal status of gelatin.

In-silico approaches for discrimination of Curcuma species and their closely related family using the novel technique of DNA Barcoding

In this study, we have discriminated and identified the Genus of Curcuma and related species Zingiberaceae using rbcL and trnL DNA barcode primers. Curcuma genus related to the family Zingiberaceae comprises a significant number of medicinal plants renowned for their use in ethnomedicine, playing a pivotal role in the medical, health, and pharmaceutical sectors. Traditionally, morphological methods alone have proven insufficient for accurately identifying species within this family. However, DNA barcoding technology provides a contemporary solution by utilizing plant DNA sequences for species identification, thus enabling effective conservation efforts. We used DNA barcoding techniques and for analysis used the Maximum Parsimony tree in MEGA 11 with the Kimura 2-parameter (KP model) to analyse the genetic relationships between species. Out of the 13 accessions that were studied, 12 accessions belonged to Curcuma caesia and 1 accession belonged to Curcuma aeruginosa. The genetic relationships observed were correlated with the geographical distributions of these species. It was determined that C. aeruginosa is a mutated species of C. caesia. Additionally, 1 specimen of Alpinia galanga, a plant species related to the Zingiberaceae. Barcode primer trnL primer demonstrated a 92% efficiency during the investigation. The rbcL and trnL loci are recommended as potential barcode markers for discriminating between different plant species. This study developed a comprehensive DNA barcoding database that can confidently differentiate between species by combining morphological and molecular data. This database has the potential to identify adulteration in herbal products, combat illegal trade and adulteration of plant species, and assist in germplasm conservation efforts.

19F NMR Probes: Molecular Logic Material Implications for the Anion Discrimination and Chemodosimetric Approach for Selective Detection of H2O2.

Detection and discrimination of similar solvation energies of bioanalytes are vital in medical and practical applications. Currently, various advanced techniques are equipped to recognize these crucial bioanalytes. Each strategy has its own benefits and limitations. One-dimensional response, lack of discrimination power for anions, and reactive oxygen species (ROS) generally limit the utilized fluorescent probe. Therefore, a cutting-edge, refined method is expected to conquer these limitations. The use of 19F NMR spectroscopy for detecting and discriminating essential analytes in practical applications is an emerging technique. As an alternative strategy, we report two fluorinated boronic acid-appended pyridinium salts 5-F-o-BBBpy (1) and 5-CF3-o-BBBpy (2). Probe (1) acts as a chemosensor for identifying and discriminating inorganic anions with similar solvation energies with strong bidirectional 19F shifts in the lower ppm range. Probe (2) turns as a chemo dosimeter for the selective detection and precise quantification of hydrogen peroxide (H2O2) among other competing ROS. To demonstrate real-life applicability, we successfully quantified H2O2 via probe (2) in different pharmaceutical, dental, and cosmetic samples. We found that tuning the -F/-CF3 moiety to the arene boronic acid enables the π-conjugation, a crucial prerequisite for the discrimination of anions and H2O2. Characteristic 19F NMR fingerprints in the presence of anions revealed a complementary implication (IMP)/not implication (NIMP) logic function. Finally, the 16 distinct binary Boolean operations on two logic values are defined for "functional completeness" using the special property of the IMP gate. Boolean logic's ability to handle information by utilizing characteristic 19F NMR fingerprints has not been seen previously in a single chemical platform for detecting and differentiating such anions.

Body shape divergence of paradise thread fish (Polynemus paradiseus) collected from different coastal habitats of southern Bangladesh: A multivariate approach for population discrimination

The paradise thread fish (Polynemus paradiseus) is a commercially and ecologically important euryhaline fish that primarily lives in diversified coastal and estuarine habitats. A comprehensive understanding of the divergence in body shape and discrimination in population parameters related to habitats is crucial for fisheries management and conservation endeavours. To test whether significant morphological differences exist between P. paradiseus populations inhabiting different coastal environments, a total of 366 individuals (198 male and 168 female) were collected from five distant places over three zones- Cox's Bazar (Bakkhali River) and Chattogram (Karnaphuli River) in the southeast coastal regions, Noakhali (lower Meghna River) in the southcentral zone, and Khulna (Shibsa River) and Borguna (Bishkhali River) in the southwest zones adjacent to the Bay of Bengal, Bangladesh in November 2022. The truss networking and geometric morphometric analysis (GMA) indicated variations in body shape among P. paradiseus individuals induced by sexual dimorphism. Wireframe graphs demonstrated that female individuals had wider dorsal-abdominal parts than males. Using the truss networking dataset for five coastal habitats, multivariate analyses revealed two overlapping clusters: southwest (Borguna and Khulna) populations in one cluster, while central (Noakhali) and southeast (Chattogram and Cox's Bazar) populations form separate clusters. The GMA also illustrated that the Khulna-Borguna population was located near the opposite end of the Chattogram-Cox's Bazar population axis, and the Noakhali populations were somewhat in the middle, with a high degree of overlap. Wireframe graphs displayed a significant body shape variations among populations, mainly in the snout shape, the width of the dorsal-abdominal part, the tail shape, and the head shape. The Discriminant Function Analysis revealed that there were pronounced variations in body shape between two populations located in distant regions, while there were minimum variations between two populations located close to each other. This study underscores the effectiveness of landmark-based truss networking and geometric morphometrics in discerning morphological variations across different habitats. These variations likely hold adaptive significance and are critical for informed population management and conservation strategies in the population structure of euryhaline P. paradisus.

AgriGAN: unpaired image dehazing via a cycle-consistent generative adversarial network for the agricultural plant phenotype

Artificially extracted agricultural phenotype information exhibits high subjectivity and low accuracy, while the utilization of image extraction information is susceptible to interference from haze. Furthermore, the effectiveness of the agricultural image dehazing method used for extracting such information is limited due to unclear texture details and color representation in the images. To address these limitations, we propose AgriGAN (unpaired image dehazing via a cycle-consistent generative adversarial network) for enhancing the dehazing performance in agricultural plant phenotyping. The algorithm incorporates an atmospheric scattering model to improve the discriminator model and employs a whole-detail consistent discrimination approach to enhance discriminator efficiency, thereby accelerating convergence towards Nash equilibrium state within the adversarial network. Finally, by training with network adversarial loss + cycle consistent loss, clear images are obtained after dehazing process. Experimental evaluations and comparative analysis were conducted to assess this algorithm's performance, demonstrating improved accuracy in dehazing agricultural images while preserving detailed texture information and mitigating color deviation issues.

Is ward-level calculation of urban green space availability important?—A case study on Vellore city, India, using the histogram-based spectral discrimination approach

How much green space is available for individuals is a major question that city planners are generally interested in, and the present study aimed to address this issue in the context of Vellore, India, through two approaches, namely, the per capita and the geographical area approach. In existing studies, urban green space (UGS) was only calculated at the macro level, i.e., for the city as a whole. Micro-or ward-level analysis was not attempted before, and the present study carried out the same to get a clear picture of the amount of greenery available in each ward of a city. For this purpose, a two-step approach was proposed where the histograms of Google Earth (GE) images were analyzed first to check whether the green cover types such as trees, shrubs/grassland, and cropland were spectrally different. Then, classification techniques such as ISODATA, maximum likelihood, support vector machine (SVM), and object-based methods were applied to the GE images. It was found that SVM performed well in extracting different green cover types with the highest overall accuracy of 93% and Kappa coefficient of 0.881. It was found that when considering the city as a whole, the amount of UGS available is 42% of the total area, which is more than the recommended range of 20–40%. Similarly, the available UGS per person is 97.84 m2, which is far above the recommended 12 m2/person. However, the micro-level analysis revealed that some of the wards have not satisfied the criteria of per capita and percentage area, though the city as a whole has satisfied both the criteria. Thus, the results indicate the importance of calculating the urban green space availability at the ward level rather than the city level as the former gives a closer look at the surplus and deficit areas. The results of terrestrial LiDAR survey at individual tree level revealed that if trees are located adjacent to buildings or roads, it results in fewer heat islands compared to the case where there are no trees.

Advancing livestock and poultry disease diagnosis with high-resolution melt curve analysis

High-Resolution Melting (HRM) is a sensitive polymerase chain reaction-based molecular assay used to detect, single nuclear polymorphisms, mutations, and variations in genotypes of pathogens. HRM analysis is more convenient than other detection and discrimination approaches since it is a closed-tube method, that is the polymerase chain reaction amplification and subsequent analysis are carried out sequentially in the well. It finds application in various veterinary diagnoses and discrimination of genotypes of the microorganisms. Numerous public health organizations have recommended increased monitoring activities to support current surveillance programs in response to the threat of bioterrorism and emerging infectious diseases. HRM assay will be an efficient, cost-effective disease diagnostic and genotype of circulating pathogen identification method thereby aiding in disease surveillance which is important for monitoring the spread of infectious diseases. This review emphasizes the application of HRM in livestock, poultry, and companion animals in recent times carried out all over the world for determining the genotype, strain, and breed differentiation including pathogens classification.