Conventional Identification Methods Research Articles

Comparison of the VITEK® 2 System with Conventional Methods for Species Identification and Antimicrobial Susceptibility Pattern of Staphylococcal Carrier Isolates

Staphylococcus aureus, an opportunistic pathogen that inhabits 20% to 70% of human anterior nares and can cause infections, ranging from mild, superficial infections of the skin and soft tissues to severe conditions like sepsis, necrotizing pneumonia and toxic shock syndrome. Healthcare workers are potential asymptomatic nasal carriers, contribute to major infection transmission. The emergence of multidrug-resistant strains necessitates advanced treatment approaches. The study aimed to identify staphylococcal nasal carriers among dental students, and to compare the results obtained from automated identification system, VITEK® 2 with conventional methods for identifying Staphylococcus species and determining antibiotic susceptibility patterns. Anterior nasal swabs were collected from 42 study participants were processed as per standard microbiological culture techniques. All the conventionally identified S. aureus isolates were subjected to a further analysis using an automated VITEK® 2 SYSTEM. Surprisingly, the automated identification system classified all conventionally proven S. aureus isolates as other Staphylococci species (S. epidermidis (60%), S. warneri, and S. lentus), raising concerns about potential misdiagnosis. Overall, there was a 97.5% categorical agreement between VITEK® 2 system and the reference method, with minimal errors (0.8% very major, 0.6% major, and 1.17% minor). These discrepancies underscore the importance of accurate species identification and highlight the necessity for advanced techniques in infection control strategies, emphasizing the potential impact on decolonization decisions.

Assessment of the Microbial Quality of Food Sold in Some Restaurants within Katsina Metropolis

Foods are substances that when consumed provide the body with nutrients for growth and development. Foods for consumption should be within the acceptable limit of microbial load, exceeding it may lead to food-borne intoxication and illness. This study aimed to determine the microbial quality of commonly sold foods in some restaurants within Katsina metropolis. Physiochemical properties of the food namely; pH, temperature, colour, and taste were determined using a pH meter, thermometer, and organoleptic approach respectively. Conventional methods of identification were used to identify the isolates and a modified method by Kirby Bauer was employed to determine antimicrobial assays of the identified isolates. The results obtained showed that the physiochemical parameters of pH and temperature range between 5.50 to 7.40, and 30.0 oC to 32.0 oC respectively with a normal taste and colour. Total bacterial (1.04 x107 CFU/g) and fungal (4.8 x106 CFU/g) counts of the samples fall within the unsatisfactory limits set by the International Commission on Microbiological Specifications for Food (ICMSF). A total of nine (9) bacteria and five (5) fungi were identified from fifteen (15) samples examined. E. coli (26.31%) was most prevalent followed by Enterobacter aerogens and Staphylococcus epidermis (15.78%), Bacillus subtilis, and Salmonella spp (10.52%) while Proteus mirabilis, Micrococcus luteus, Pseudomonas aeroginosa, and Clostridium spp. have the least occurrence (5.26%). Aspergillus flavus (45.45%) was most prevalent among the fungal isolates followed by Mucor (27.27%) and Botrytis, Alternaria, and Fusarium chlamydosporum (9.09%) have the least occurrence. The antimicrobial assay shows that Gentamycin, levofloxacin, Erythromycin, and Ciprofloxacin were effective against Micrococcus luteus, Staphylococcus spp., Clostridium spp., and Bacillus subtilis. Norfloxacin and Amoxicillin were resisted by Micrococcus luteus and Staphylococcus spp., Ketoconazole and Fluconazole inhibited Mucor and Aspergillus flavus but were resisted by Alternaria, Botrytis, and Fusarium chlamydosporum. It was concluded that foods sold in some restaurants within the Katsina metropolis fall within the unsatisfactory limits of ICMSF standards, thus, improved strict hygiene compliance is recommended.

Biotagging method for animal identification using dissolvable microneedle arrays prepared by customisable moulds

Properly handling animals and understanding their habits are crucial to establish a society where humans and animals coexist. Thus, identifying individual animals, including their possessions, and adequately managing each animal is necessary. Although several conventional identification methods exist, such as the use of ear punch, tattoos, and radio frequency (RF) chips, they require several processes and external apparatus. In this study, we proposed a new biotagging method using a microneedle array for animal identification. Our approach uses dissolvable microneedle arrays as a single patch to deliver dyes directly into the skin layer. Additionally, we developed a new fabrication method for customised female moulds to realise microneedle array patches (MAPs) with patterns of different characters and number. The characteristics and feasibility of the patterned MAPs were confirmed through basic evaluations and animal experiments. Moreover, we confirmed that patterns formed from biotagging using the developed patterned MAPs lasted over one month with clear readability. Finally, we confirmed that our patterned MAPs successfully realised biotagging on rat skin with the designated patterns including characters and number patterns. The proposed method is expected to enable minimally invasive tagging without external equipment or complex processes. In addition, the developed method could be used to embed various tags into the skin of animals and humans in the future.

Conventional and molecular diagnostics in onychomycosis-part2 : Molecular identification of causative dermatophytes by polymerase chain reaction and sequence analysis of the internal transcribed spacer region of ribosomal DNA

Dermatophyte identification using traditional methods such as optics-based direct fluorescence microscopy and culture is nowadays supplemented by molecular biological methods. The validity of dermatophyte DNA detection with direct uniplex-polymerase chain reaction-enzyme immunoassay (PCR-EIA) in nail samples was proven by sequence analysis of the ribosomal internal transcribed spacer (ITS) region. A total of 108dermatophytes, isolated from patients with onychomycosis, were positive for Trichophyton rubrum (TR) and Trichophyton interdigitale (TI) in culture and/or uniplex-PCR-EIA. Conventional methods for dermatophyte identification were complemented by direct uniplex-PCR-EIA and sequence analysis of the ribosomal ITS region (18S rRNA, ITS1, 5.8S rRNA, ITS2, 28S rRNA). Of 108 patients (average age62, median age 73), 56showed cultural growth with 31of them being identified as TR and23 as TI. There was high agreement with the sequence analysis. Surprisingly, the pathogen of asingle nail sample was identified as T.quinckeanum (formerly T.mentagrophytes sensu stricto), arare zoophilic dermatophyte in Germany. Asingle TI strain turned out to be amisidentified T.tonsurans based on the sequence analysis. In all, 34of the 52specimens lacking cultural growth were detected by PCR as TR, and 18specimens could be identified as TI. The results of dermatophyte identification of culture-negative nail samples were also in agreement with the results of sequence analysis. Molecular biological methods are well applicable, and they show high reliability for direct dermatophyte identification in nail samples without prior cultivation. Especially for nail samples without cultural growth, PCR-based dermatophyte identification was highly specific and sensitive.

Rapid identification of enteric bacteria from whole genome sequences using average nucleotide identity metrics.

Identification of enteric bacteria species by whole genome sequence (WGS) analysis requires a rapid and an easily standardized approach. We leveraged the principles of average nucleotide identity using MUMmer (ANIm) software, which calculates the percent bases aligned between two bacterial genomes and their corresponding ANI values, to set threshold values for determining species consistent with the conventional identification methods of known species. The performance of species identification was evaluated using two datasets: the Reference Genome Dataset v2 (RGDv2), consisting of 43 enteric genome assemblies representing 32 species, and the Test Genome Dataset (TGDv1), comprising 454 genome assemblies which is designed to represent all species needed to query for identification, as well as rare and closely related species. The RGDv2 contains six Campylobacter spp., three Escherichia/Shigella spp., one Grimontia hollisae, six Listeria spp., one Photobacterium damselae, two Salmonella spp., and thirteen Vibrio spp., while the TGDv1 contains 454 enteric bacterial genomes representing 42 different species. The analysis showed that, when a standard minimum of 70% genome bases alignment existed, the ANI threshold values determined for these species were ≥95 for Escherichia/Shigella and Vibrio species, ≥93% for Salmonella species, and ≥92% for Campylobacter and Listeria species. Using these metrics, the RGDv2 accurately classified all validation strains in TGDv1 at the species level, which is consistent with the classification based on previous gold standard methods.

MALDI-TOF MS analysis of Burkholderia pseudomallei and closely related species isolated from soils and water in Khon Kaen, Thailand

Melioidosis is caused by Burkholderia pseudomallei (Bp) acquired from the environment. Conventional identification methods for environmental Bp are challenging due to the presence of closely related species. Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) is accurate for bacterial identification, but has been little used to identify Bp from environmental samples. This study aims to evaluate MALDI-TOF MS for the identification of Bp and closely related species isolated from environmental samples in Thailand using whole-genome sequencing (WGS) as the gold standard, including determining the best sample preparation method for this purpose. We identified Bp (n = 22), Burkholderia spp. (n = 28), and other bacterial species (n = 32) using WGS. MALDI-TOF analysis of all Bp isolates yielded results consistent with WGS. A decision-tree algorithm identified 16 important variable peaks, using the protein extraction method (PEM), demonstrating distinct MALDI-TOF profiles for the three categories (Bp, Burkholderia spp. and “other bacterial species”). Three biomarker peaks (4060, 5196, and 6553 Da) could discriminate Bp from other Burkholderia and closely related species with 100% sensitivity and specificity. Hence, the MALDI-TOF technique has shown its potential as a species discriminatory tool, providing results comparable to WGS for classification and surveillance of environmental Bp.

Research on the Prediction of Tire Radial Load Based on 1D CNN and BiGRU

As an important indicator of vehicle systems, tire load is a key factor in the structural design and safety assessment of vehicles. Direct measurement methods for tire loads are expensive and complicated, while conventional load identification methods are limited by low accuracy and poor robustness. This study aimed to propose a radial load identification method for rubber-tired vehicles based on a one-dimensional convolutional neural network (1D CNN) and bidirectional gated recurrent unit (BiGRU). Considering a priori information of the radial load data of tires and based on the observability of the vehicle vibration system, the proposed method selected feature sets and then retained the effective feature subsets through feature selection to construct samples with multiple time steps as input and with a single time step as output for network training. In doing so, the load prediction results were obtained, and the theoretical model was modified by integrating prediction accuracy, generalization performance, and robustness. Compared with traditional algorithms, the proposed method could effectively reduce the error of load identification, improve adaptability under different operating conditions, and handle the measurement error of different noise levels, which are of practical application value in the engineering field.

Enhancing second-order blind identification for underdetermined operational modal analysis through bandlimited source separation

Blind source separation (BSS) has been demonstrated to be a promising method for operational modal analysis (OMA). However, the conventional BSS-based modal identification methods can only handle the determined or overdetermined identification where the number of sensors must equal or exceed that of active modes, limiting their wider application. Furthermore, the existing methods for underdetermined BSS require sparsity assumption of sources, optimization of model parameters, or structural prior information, undermining the non-parametric and “blind” properties of BSS. This paper proposes a novel method for underdetermined OMA. Firstly, the bandlimited source separation using sinc-dictionaries is performed to efficiently transform the underdetermined problem into several determined or overdetermined ones. An improved second-order blind identification (SOBI) involving Hilbert transform and random time-lagged covariances is then applied for each bandlimited signal to recover modal responses and mode shapes. To attenuate noise, an adaptive singular spectrum analysis (SSA) can be optionally applied to the recovered modal responses for the highly noisy systems. Finally, the natural frequencies and damping ratios are estimated by the single-degree-of-freedom (SDOF) fitting technique. Several numerical examples, an experimental frame case, and a field test of a pedestrian bridge are studied to verify the effectiveness of the proposed strategy.

Presence of blaCTXM-1, blaCTXM-9, and blaTEM-1 Genes in Extended-spectrum β-lactamase-producing Escherichia coli Isolates from Hospital Wastewater

BACKGROUND: Extended-spectrum β-lactamase-producing Escherichia coli (ESBL-EC) are selectively proliferated in the human gut, excreted through feces, and deposited through wastewater lines, with hospital wastewater acting as a major reservoir of antibiotic resistance genes and resistant bacteria, thus pose adverse effects to human health. This study aimed to determine the presence of blaCTXM-1, blaCTXM-9, blaTEM-1, and blaSHV-1 genes in ESBL-EC in wastewater from selected hospitals in Manila and Quezon City, the Philippines.METHODS: Influent and effluent in twelve hospital wastewater treatment plants were collected, screened for cefotaxime-resistant E. coli, and examined for the ESBL production through phenotypic characterization using conventional bacterial identification, disk diffusion method, and VITEK® 2 Compact system and genotypic identification of ESBL-EC blaCTXM-1, blaCTXM-9, blaTEM-1, blaSHV-1 genes using multiplex polymerase chain reaction (PCR).RESULTS: Conventional bacterial identification methods and the VITEK® 2 Compact system results showed that both influent and effluent samples were positive for ESBL-EC at 33.3% and 16.7%, respectively. Multiplex PCR results revealed that various E. coli isolates were of ESBL-EC blaCTXM-1, blaCTXM-9, and blaTEM-1 genes. Multi-drug resistance was observed among all ESBL-EC isolates with resistance being highest against ampicillin, cefuroxime, ceftazidime, ceftriaxone, cefepime, piperacillin, and aztreonam.CONCLUSION: As the study revealed the presence of ESBL-producing bacteria, efforts must be made to ensure the prudent antimicrobial use with possible emphasis on antibiotic rotation accompanied by intensified infection prevention and control in hospital settings.KEYWORDS: antimicrobial resistance, beta-lactams, blaCTXM, blaTEM, extended-spectrum beta-lactamase, E. coli, hospital wastewater

Fluid identification and tight oil layer classification for the southwestern Mahu Sag, Junggar Basin using NMR logging-based spectrum decomposition

The intricate distribution of oil and water in tight rocks makes pinpointing oil layers challenging. While conventional identification methods offer potential solutions, their limited accuracy precludes them from being effective in their applications to unconventional reservoirs. This study employed nuclear magnetic resonance (NMR) spectrum decomposition to dissect the NMR T2 spectrum into multiple sub-spectra. Furthermore, it employed laboratory NMR experiments to ascertain the fluid properties of these sub-spectra, aiming to enhance identification accuracy. The findings indicate that fluids of distinct properties overlap in the T2 spectra, with bound water, movable water, bound oil, and movable oil appearing sequentially from the low-value zone to the high-value zone. Consequently, an oil layer classification scheme was proposed, which considers the physical properties of reservoirs, oil-bearing capacity, and the characteristics of both mobility and the oil-water two-phase flow. When applied to tight oil layer identification, the scheme's outcomes align closely with actual test results. A horizontal well, deployed based on these findings, has produced high-yield industrial oil flow, underscoring the precision and dependability of this new approach.

Duct modal identification considering statistical dependency via the Boltzmann machine

The fan noise is the primary component of aero-engine noise. Duct acoustic modal identification is essential for analyzing the mechanism of fan noise generation and propagation. The acoustic modal in the duct can be identified by the measurement of the microphone array mounted on the duct wall. It is generally assumed in the conventional modal identification methods that the modal coefficients are independent of each other. However, the realistic duct acoustic modal coefficients exhibit significant statistical dependence. A Boltzmann machine(BM) model considering the statistical dependence between modal coefficients is proposed for recovering the modal coefficients in this paper. The modal coefficients are estimated using a block coordinate optimization method in a Bayesian framework. Moreover, the modal Boltzmann parameters can be learned iteratively by the BM. The effectiveness of the proposed method is verified by numerical simulations and experimental tests. It turns out that the modal coefficients can be accurately identified by the proposed method, and a more significant sparsity is shown by the results. In addition, the statistical dependence between the modal coefficients can be captured by the BM.

Arthropod Taxonomy Orders Object Detection in ArTaxOr dataset using YOLOX

The detection and classification of insect species represent challenging computer vision tasks that have significant applications in zoology and agriculture. Fortunately, biologists and taxonomists have developed a systematic approach to organizing organisms, which results in a hierarchical classification system. Insect classification employs a hierarchical structure that includes object detection at the order level, family classification, and species classification. However, the conventional insect identification method is time-consuming and requires the expertise of highly skilled taxonomists to identify insects accurately based on morphological characteristics. This paper presents a pioneering study on the automatic detection and classification of Arthropod Taxonomy Orders using an enhanced variant of the You Only Look Once (YOLOX) framework along with the Arthropod Taxonomy Orders Object Detection (ArTaxOr) Dataset. The proposed ArTaxOr dataset encompasses diverse arthropod species such as insects, spiders, crustaceans, centipedes, millipedes, and isopods. Moreover, some images within this dataset depict multiple species with varying sizes, shapes, and colors. Accordingly, all images are resized to 640 times 640 to ensure compliance with the requisite input image size for YOLOX. Further, mosaic augmentation is employed to enhance the model’s accuracy in recognizing small objects. Inspite of natural complexity in a majority of dataset images, the proposed YOLOX-based model attained superior mean average precision. The outcomes of this study could act as a standard against which forthcoming research in this domain could be compared or judged.

Localization of cyclostationary acoustic sources via cyclostationary beamforming and its high spatial resolution implementation

The localization of cyclostationary sound sources is important for rotating machinery noise source identification and fault diagnosis. Cyclostationary sound sources are a special class of nonstationary sound sources, which exhibit periodic changes in statistics. Most of the conventional sound source identification methods are based on the stationary sound source assumption, which do not consider the cyclostationarity of the radiated sound field by rotating machinery. Thus, they are hard to localize the acoustic sources with different cyclic frequencies. In this paper, a novel technique of localizing the cyclostationary acoustic sources with different cyclic frequencies is proposed. First, the cyclostationary conventional beamforming (CSCBF) method is deviated. In CSCBF, the cyclic-cross-spectral matrix (CCSM) is defined considering all the cross cyclic spectral correlation (CSC) between different microphones in the array. The left steering vector and right steering vector are constructed to focus the CCSM on each scanning grid point at a given combination of cyclic frequency and spectral frequency. Then, the high resolution cyclostationary beamforming (HR-CSBF) is further developed to improve the spatial resolution of CSCBF. In HR-CSBF, two linear equations according to the property of CSC is established as the acoustic inverse problems. With the sparse distribution of the cyclostationary sources in the space as the prior knowledge, the iterated Bayesian focusing (IBF) is utilized to obtain a robust and sparse solution in HR-CSBF. Numerical simulations and experiments are conducted to validate the proposed methods. To explore the potential applications of the proposed methods, the localization of high pressure pump (HPP) and rolling bearing with outer-race failure are also used to evaluate the effectiveness of the proposed methods. It turns out that both CSCBF and HR-CSBF can localize the cyclostationary sources with different cyclic frequencies. Compared with CSCBF, HR-CSBF can achieve a higher spatial resolution in the obtained acoustic map.

Evaluation of conventional methods for species identification of Staphylococcus aureus using MALDI-TOF MS, protein identification and quantification

Objectives: This study aimed to evaluate conventional methods for species identification of Staphylococcus aureus by MALDI-TOF MS. Additionally, the representatives of different species were used to analyze protein expression. Materials and methods: A total of 185 non-duplicated clinical S. aureus identified using the conventional method (colony morphology, Gram’s stain, slide coagulase test, tube coagulase test, catalase test, and mannitol fermentation) was confirmed the identification by MALDI-TOF MS and analyzed by Mass spectral profiling (MSP) and Principal component analysis (PCA). The representatives of different species reported by both methods were confirmed using 16SrRNA sequence and analyzed proteins expression by timsTOF MS. Results: All S. aureus suspected isolates could discriminate among species by MALDI-TOF MS including S. aureus (N=151, 81.6%), S. argenteus (N=32, 17.3%), S. hominis (N=1, 0.5%), and S. haemolyticus (N=1, 0.5%). Using 16S rRNA genebased analysis, S. aureus and S. argenteus could not differentiate from each other. Protein expression of S. aureus was similar to S. argenteus. These genes including rpsT, Huti, pyrF, atpD.1, cpfC, SAUA300_0786, atl.1, and MW2416 showed higher expression in S. aureus (MS076) than S. argenteus (MS060), S. haemolyticus (MS095) and S. hominis (MS060). Conclusion: MALDI-TOF MS provides an excellent tool for accurately species identification of staphylococci. S. aureus expressed protein analyzed higher than the other 3 species. The highest protein expression in S. aureus implies the most virulence of this strain.

A Multilabel Approach for Fault Detection and Classification of Transmission Lines using Binary Relevance

In Contemporary automation systems, Fault detection and classification of electrical transmission lines in grid systems are given top priority. The broad application of Machine Learning (ML) methods has enabled the substitute of conventional methods of fault identification and classification. These methods are more effective ones that can identify faults early on using a significant quantity of sensory data. So detecting simultaneous failures is difficult in the context of distracting the noise and several faults in the transmission lines. This study contributes by offering a unique way for concurrently detecting and classifying several faults using a multilabel classification approach based on binary relevance classifiers. The proposed binary relevance multilabel detection and classification models’ performances are examined. Under both ideal and problematic circumstances, faults in the dataset are collected. A variety of multilabel fault types detection and classification determines the suggested method’s effectiveness.

Adaptive identification method of new energy grid operation risk based on linear decision function

The current conventional risk identification method of new energy grid operation mainly achieves risk identification by mining equipment status information, which leads to poor identification effect due to the lack of effective extraction of abnormal data features. In this regard, a linear decision function-based adaptive risk identification method for new energy grid operation is proposed. The data flow model is constructed by combining the linear decision function, and the features of interval abnormal data and fluctuating abnormal data are extracted. A sliding window model is constructed, and the unsupervised model is used to realize the effective update of new energy grid operation data. In the experiments, the proposed method is verified for recognition accuracy. The experimental results show that when the proposed method is used to identify the risk of grid operation, the effective data mis-deletion rate of the algorithm is low and has a more desirable identification effect.

PURE: Passive Multi-Person Identification via Footstep for Mobile Service Networks

Recently, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">passive behavioral biometrics</i> (e.g., gesture or footstep) acquired from wireless networks or mobile services have become promising complements to conventional user identification methods (e.g., face or fingerprint) under special situations, yet existing sensing technologies require lengthy measurement traces and cannot identify multiple users at the same time. To this end, we propose PURE as a passive multi-person identification system leveraging deep learning enabled footstep separation and recognition. PURE passively identifies a user by identifying the unique “footprints” in its footstep. Different from existing gait-enabled recognition systems incurring a long sensing delay to acquire many footsteps, PURE can recognize a person by as few as only one step, substantially cutting the identification latency. To make PURE adaptive to walking pace variations, environmental dynamics, and even unseen targets, we apply an adversarial learning technique to improve its domain generalisability and identification accuracy. Finally, PURE is robust against replay attack, enabled by the richness of footstep and spatial awareness. We implement a PURE prototype using commodity hardware and evaluate it in typical indoor settings. Evaluation results demonstrate a cross-domain identification accuracy of over 90%.

Identification of the blasting vibration characteristics of groundwater-sealed tunnel

Blasting is widely used in mining, subway, demolition and groundwater-sealed tunnel, among them, the last one is widely concerned because of its many adjacent tunnels, high anti-seepage requirements, strict blasting control, etc. The identification of blasting characteristics is of great significance to the blasting construction and the safety evaluation of the groundwater-sealed tunnel. In view of the problem that conventional feature identification methods are less explored in groundwater-sealed tunnel, a complementary ensemble empirical mode decomposition with adaptive noise and multiscale permutation entropy and Hilbert–Huang transform (HHT) method was proposed. Then, the proposed method was verified by the numerical simulation and the Huangdao groundwater-sealed tunnel engineering. The results show that the proposed method can suppress modal aliasing and signal noise and identify the blasting characteristics of groundwater-sealed tunnel effectively. In addition, the blasting vibration energy which accounts for 94.7% in the frequency range of 0–200 Hz, 72.5% of 0–50 Hz was summarized. Furthermore, the safety status of each monitoring point was evaluated through HHT and the feasibility of millisecond blasting was identified. The method proposed can identify the vibration characteristics and safety status of groundwater-sealed tunnel from the perspective of time–frequency and energy effectively.

Baseline-free structural damage detection using PCA- Hilbert transform with limited sensors

Conventional vibration-based damage identification methods need a large number of sensors on the bridge to identify the structural modal information and rely on the response data of bridges under a non-damage state for comparison, which restricts their implementations in the health monitoring of bridge structures in service. This paper proposes a baseline-free structural damage detection method based on limited sensor information. The proposed method uses the Hilbert transform combined with principal component analysis (PCA) to locate the damage. Firstly, PCA is performed on the displacement response data matrix of the bridge under a moving load to obtain the principal component matrix. According to the physical interpretation of PCA of the responses of a beam-like bridge under a moving load, each column of the principal component matrix, namely the principal component, composes of a mode shape and the dynamic information at this modal frequency of the bridge. The dynamic information of the modal frequency is indirectly obtained by filtering out the mode shape by low pass filter. Then the Hilbert transform is used to process the dynamic component information to receive the instantaneous frequency which is regarded as the damage index. When the structure is damaged, the first instantaneous frequency at the damaged location changes abruptly. To demonstrate the effectiveness and performance of the proposed method, numerical simulations and experimental validations on beam bridge models are conducted. The results show that the method is free from the requirement of the information of bridges under the undamaged state, and only limited sensors are needed to locate the damage.

Soil-MobiNet: A Convolutional Neural Network Model Base Soil Classification to Determine Soil Morphology and Its Geospatial Location.

Scholars have classified soil to understand its complex and diverse characteristics. The current trend of precision agricultural technology demands a change in conventional soil identification methods. For example, soil color observed using Munsell color charts is subjective and lacks consistency among observers. Soil classification is essential for soil management and sustainable land utilization, thereby facilitating communication between different groups, such as farmers and pedologists. Misclassified soil can mislead processes; for example, it can hinder fertilizer delivery, affecting crop yield. On the other hand, deep learning approaches have facilitated computer vision technology, where machine-learning algorithms trained for image recognition, comparison, and pattern identification can classify soil better than or equal to human eyes. Moreover, the learning algorithm can contrast the current observation with previously examined data. In this regard, this study implements a convolutional neural network (CNN) model called Soil-MobiNet to classify soils. The Soil-MobiNet model implements the same pointwise and depthwise convolutions of the MobileNet, except the model uses the weight of the pointwise and depthwise separable convolutions plus an additional three dense layers for feature extraction. The model classified the Vellore Institute of Technology Soil (VITSoil) dataset, which is made up of 4864 soil images belonging to nine categories. The VITSoil dataset samples for Soil-MobiNet classification were collected over the Indian states and it is made up of nine major Indian soil types prepared by experts in soil science. With a training and validation accuracy of 98.47% and an average testing accuracy of 93%, Soil-MobiNet showed outstanding performance in categorizing the VITSoil dataset. In particular, the proposed Soil-MobiNet model can be used for real-time soil classification on mobile phones since the proposed system is small and portable.