Counting Technique Research Articles

Detection and identification of centipedes based on deep learning.

The quantification of centipede populations is one of the key measures in achieving intelligent management of edible centipedes and promoting the upgrade of the rural centipede industry chain. However, current centipede counting techniques still face several challenges, including low detection accuracy, large model size, and difficulty in deployment on mobile devices. These challenges have limited existing network models to the experimental stage, preventing their practical application. To tackle the identified challenges, this study introduces a lightweight centipede detection model (FCM-YOLO), which enhances detection performance while ensuring fast processing and broad applicability. Based on the YOLOv5s framework, this model incorporates the C3FS module, resulting in fewer parameters and increased detection speed. Additionally, it integrates an attention module (CBAM) to suppress irrelevant information and improve target focus, thus enhancing detection accuracy. Furthermore, to enhance the precision of bounding box positioning, this study proposes a new loss function, CMPDIOU, for bounding box loss. Experimental results show that FCM-YOLO, while reducing parameter size, achieves an improved detection accuracy of 97.4% (2.7% higher than YOLOv5s) and reduces floating-point operations (FLOPs) to 11.5G (4.3G lower than YOLOv5s). In summary, this paper provides novel insights into the detection and enumeration of centipedes, contributing to the advancement of intelligent agricultural practices.

The grey wolf (Canis lupus) as a host of Echinococcus multilocularis, E. granulosus s.l. and other helminths – a new zoonotic threat in Poland

Abstract Introduction The aim of this study was to estimate the occurrence of Echinococcus spp. and other helminth infections in grey wolves in south-eastern Poland. Material and Methods Overall, 74 samples of wolf faeces were examined with a multiplex PCR and a system of real-time quantitative PCR methods to detect and identify Echinococcus spp. The faeces were additionally examined microscopically. Also, 20 samples of wolf intestines were examined with a sedimentation and counting technique (SCT). Results Echinococcus multilocularis DNA was detected in 6.8% and E. granulosus s.l. (identified as E. ortleppi) in 4.1% of faeces samples. Taenia spp. DNA was found in 43.2% and Mesocestoides in 4.1%. Examination of the intestines by SCT showed E. multilocularis worms in 10%, E. granulosus s.l. (E. ortleppi) in10%, Taenia spp. in 100%, hookworms in 30%, Alaria alata in 20%, Mesocestoides sp. in 10%, Trichuris vulpis in 15%, Molineus sp. in 5% and Euryhelmis sp. in 5%. By coproscopy, Capillariidae eggs were found in 59% of faeces samples. Genetic analysis of E. multilocularis worms showed the presence of two European haplotypes previously described in Poland in red foxes and pigs. Sequences of nad1 obtained from E. ortleppi worms shared full identity with a sequence from a human case in Poland. Conclusion The study showed the presence of E. multilocularis in wolves for the first time in Poland and confirmed our earlier observations on E. ortleppi. This double threat from Echinococcus in this wolf population should be taken into account when assessing the epidemiological risk. The study enriched the knowledge of other helminths found in wolves, also those (Euryhelmis) that were recorded for the first time in this species.

From Killer to Solution: Evaluating Bioremediation Strategies on Microbial Diversity in Crude Oil-Contaminated Soil over Three to Six Months in Port Harcourt, Nigeria

The study aimed to evaluate the efficacy of various bioremediation approaches on microbial diversity in crude oil-contaminated soil over three to six months in Port Harcourt, Nigeria. The objective was to assess the impact of different bioremediation strategies on microbial populations, particularly focusing on hydrocarbon-utilizing bacteria and fungi. Microbial populations were quantified using serial dilution and microbial count techniques. The vapor phase transfer mechanism was employed to estimate hydrocarbon-utilizing bacteria and fungi. Bacterial and fungal colonies were incubated for five days, followed by biochemical tests for isolate identification. Fungal pure cultures were observed under a microscope. The study observed a significant increase in microbial populations in soil free of crude oil pollution when bioremediators such as mushrooms and earthworms were introduced. Mushrooms exhibited a 50% increase in hydrocarbon-utilizing bacteria (HUB), while earthworms showed a 55% increase in HUB over the three to six-month period. The longer lifespan and nutrient absorption capabilities of earthworms facilitated faster growth. Furthermore, significant growth in the microbial population of hydrocarbon-utilizing bacteria and fungi was observed in crude oil-polluted soil after employing bioremediation, with the highest growth observed in soil treated with mushrooms at six months, followed by earthworms at six months. Conversely, the lowest microbial population was recorded in soil polluted with 10% crude oil and remediated with earthworms at three months. The results suggest that mushrooms and earthworms effectively increase microbial populations in crude oil-polluted soil. However, mushrooms demonstrated a higher microbial population increase compared to earthworms, especially in terms of promoting the growth of hydrocarbon-utilizing bacteria (HUB) and hydrocarbon-utilizing fungi (HUF). Based on the findings, it is recommended to prioritize using mushrooms as bioremediation agents in similar environmental restoration efforts due to their superior efficacy in increasing microbial populations, particularly HUB and HUF. This study underscores the potential of mushrooms and earthworms as effective bioremediation agents for restoring microbial diversity in crude oil-contaminated soil, offering insights for sustainable environmental restoration practices in oil-affected regions like Port Harcourt, Nigeria.

Differentiation of adsorption and degradation in steroid hormone micropollutants removal using electrochemical carbon nanotube membrane

The growing concern over micropollutants in aquatic ecosystems motivates the development of electrochemical membrane reactors (EMRs) as a sustainable water treatment solution. Nevertheless, the intricate interplay among adsorption/desorption, electrochemical reactions, and byproduct formation within EMR complicates the understanding of their mechanisms. Herein, the degradation of micropollutants using an EMR equipped with carbon nanotube membrane are investigated, employing isotope-labeled steroid hormone micropollutant. The integration of high-performance liquid chromatography with a flow scintillator analyzer and liquid scintillation counting techniques allows to differentiate hormone removal by concurrent adsorption and degradation. Pre-adsorption of hormone is found not to limit its subsequent degradation, attributed to the rapid adsorption kinetics and effective mass transfer of EMR. This analytical approach facilitates determining the limiting factors affecting the hormone degradation under variable conditions. Increasing the voltage from 0.6 to 1.2 V causes the degradation dynamics to transition from being controlled by electron transfer rates to an adsorption-rate-limited regime. These findings unravels some underlying mechanisms of EMR, providing valuable insights for designing electrochemical strategies for micropollutant control.

Monitoring of Bacillus spore-forming dynamics through flow cytometry.

The plate counting method is a traditional and widely accepted technique for live cell counting, often employed for Bacillus enumeration and spore forming rate calculations. However, this method requires at least 12 h to generate results, making it unsuitable for real-time monitoring of bacterial growth status and spore transformation rate. Bacillus thuringiensis crystals, produced during sporulation, are widely used as microbial pesticides, with high demand for industrial scale production. Variations in cultivation conditions and harvest timing during large-scale pore production of Bacillus thuringiensis significantly affect spore forming rate, impacting crystallization yield. Nevertheless, there is a lack of real-time monitoring methods for spore conversion rate. Flow cytometry (FCM), a well-established technique for single-cell analysis in eukaryotic cells, has been successfully applied in bacterial detection in environmental and food samples. In this study, we introduced a rapid flow cytometry-based method for determining spore forming rate of Bacillus thuringiensis, with two nucleic acid dyes, SYTO24 and LDS751. The method enables dynamic monitoring of spore, vegetative cell, and viable but non-culturable/dead cell proportions during the whole cultivation process, and spore forming rate could be gained within 30 min. Data of spore forming rate by FCM method is consistent with that by plate counting method, offering a faster and more efficient approach for assessing sporulation status in industrial Bacillus thuringiensis microbial pesticide production.

Gastrointestinal parasites in free grazing goats from Ayacucho, Peru: prevalence and risk factors associated with infection in herds

This study assessed the prevalence and risk factors associated with gastrointestinal parasite infection in goats in Ayacucho, Peru. Fecal samples were collected from a total of 254 goats from four districts of Ayacucho: Ocaña (89), Colca (76), Pacaicasa (64), and Luricocha (25) during the dry season; recording the location, sex, and age of the animals. The fecal samples were analyzed using the flotation technique in salt and sugar solution, and modified McMaster egg counting techniques for eggs/oocysts (epg/opg) of gastrointestinal parasites. The associations between location, sex, and age with the prevalence of gastrointestinal parasites were analyzed using the chi-square test. Fecal samples showed an overall parasite prevalence of 87.80%. The identified parasites were Eimeria spp. (86.22%), Strongyle type eggs (STE) (65.75%), Skrjabinema spp. (7.87%), Trichuris spp. (3.15%) and Moniezia spp. (3.15%). There was a significant association between the location and the presence of parasites (p < 0.05); where STE was more prevalent in the district of Colca (98.68%); Trichuris spp. in Pacaycasa (9.38%); Skrjabinema spp. (48.00%), Moniezia spp. (12.00%) and Eimeria spp. (100%) were more prevalent in Luricocha. Sex had a significant association with the prevalence of Eimeria spp., Skrjabinema spp. and Moniezia spp. (p < 0.05); while age had a significant association with parasitosis only for Trichuris spp. and Moniezia spp. (p < 0.05). The epg/opg values revealed a higher parasite burden in goats from Colca compared to the other locations (p < 0.05). There was also no statistical relationship between fecal egg/oocyst counts and sex or age, nevertheless, there were moderate and high parasitic burdens. The high prevalence of parasites such as nematodes, cestodes, and coccidia suggests the need to implement strategic control and prevention programs in free-grazing goats. Location and sex were the most relevant risk factors for parasitosis in Ayacucho, Peru.

WATER INHABITING BIRDS OF MAIGANGA POST COAL MINING PONDS AND ARTIFICIAL WETLAND

Wetlands play a significant role in bird conservation and generally support biological diversity. Historically, bird community assessment has been employed in monitoring and identifying areas for conservation actions. In this study, we examined two post mining ponds and one artificial wetland in Maiganga Coal Mine, Gombe State for wetland avifauna. We focused on water birds (i.e. bird species that depend wholly or partially on water and wetland ecosystems for their survival). Survey was conducted during the onset of dry season in October 2021 to September 2022. Point count technique was used for the survey. A total of 626 individuals of 23 species from 19 genera, 10 families and 6 bird Order were recorded. The White-faced whistling duck was the most abundant bird species and was restricted to the active-mine pond (AMP). AMP was the most diverse of the three water bodies surveyed. However, some species were exclusive to either of the three sites. Similarly, AMP was the most abundant site with 426 individuals from 16 bird species, followed closely by the sedimentation pond with 147 individuals drawn from 15 bird species. The results suggest that water depth, age of establishment and surrounding vegetation structure could be a major determinant of bird species composition and abundance in the study area. The study highlights the importance of restorative actions aimed at recovering modified landscapes, through tree planting and creation of wetlands. This is evident in the presence of waterbirds in Maiganga, a location that was previously devoid of perennial water bodies and...

Temperature-dependent Rotational Dynamics of a 3-(benzo[d]Thiazol-2-yl)-7-diethylamino)-2H-chromen-2-one non-polar Probe in n-pentanol, n-nonanol, and n-decanol Solvents.

Rotational dynamics of non-polar probe 3-(benzo[d]thiazol-2-yl)-7-(diethylamino)-2H-chromen-2-one (3BT7D2H-one) and in n-pentanol, n-nonanol, and n-decanol alcohol solvents is studied using steady-state fluorescence depolarization and time-correlated single photon counting technique with varying temperature. Experimental observations indicate that 3BT7D2H-one rotates slowly in n-decanol solvent compared to other chosen solvents. Rotational motion is analyzed using the Stoke 's-Einstein-Debye (SED) model. 3BT7D2H-one solute rotational dynamics is satisfactorily described by the SED slip boundary limit in all three solvents.

Evaluating deep learning techniques for optimal neurons counting and characterization in complex neuronal cultures.

The counting and characterization of neurons in primary cultures have long been areas of significant scientific interest due to their multifaceted applications, ranging from neuronal viability assessment to the study of neuronal development. Traditional methods, often relying on fluorescence or colorimetric staining and manual segmentation, are time consuming, labor intensive, and prone to error, raising the need for the development of automated and reliable methods. This paper delves into the evaluation of three pivotal deep learning techniques: semantic segmentation, which allows for pixel-level classification and is solely suited for characterization; object detection, which focuses on counting and locating neurons; and instance segmentation, which amalgamates the features of the other two but employing more intricate structures. The goal of this research is to discern what technique or combination of those techniques yields the optimal results for automatic counting and characterization of neurons in images of neuronal cultures. Following rigorous experimentation, we conclude that instance segmentation stands out, providing superior outcomes for both challenges.

Liaisons Among Symbols

Biologic processes can be depicted as circular algorithms on a limited number of distinct elements. The concept deviates from the Sumerian tradition of using an unlimited number of identical units in a linear, noncircular fashion. We have uncovered relations between distinguishable elements that are constructed by using two natural numbers a, b (a, b ≤ 16, a ≤ b) that make up together one “Akkadian” unit. We propose to use the etalon collection of 136 units, each of which is a pair of a,b. (The collection consists of numeric values: {(1,1), (1,2), (1,3),…,(2,2), (2,3),…., (15,16), (16,16).}). We order and reorder the etalon collection by sorting and resorting it, paying attention to the cycles that appear during a resort, and to the certitude of coincidences appearing as a consequence of several cycles running parallel (like wheels of a Las Vegas machine). Reader is strongly advised to conduct a simple exercise of self-education, by ordering 12 books on their table, first in a sequence author – title, from which the reorder into the sequence title – author is the source of the self-education. Ordering and sorting are abilities that children learn sooner than at the age of 6 years, before the child learns the Sumerian concepts of what is a unit. The ability to recognize sorting procedures generating circular references has not been educated along with the ability to recognize multitudes made up of identical units. The terms ‘place’, ‘value’, ‘movement’, ‘time’, ‘coincidence’, ‘potential’, ‘information’, etc. are experienced anew, while doing the self-educating experiment with 12 books, based on the insights coming from deictic procedures, as one moves one’s books from their old place to their new place, ejecting other books in the process. We look at the books in transit. Elements that are in transit generate one distinct, their own logical class. There are rules pertaining to order and reorder, and to observe such, the best introduction is to use 12 random objects that are classified in 2 aspects. Because the entry to the thought system of circular order engages brain areas hitherto not trained, and because the basic concepts shift from “limitless, linear, unidentifiable” to “limited size, periodic/cyclic/circular, individuals”, the explanation of the discovery faces didactic difficulties. Reader is invited to overcome traditional eye-blinders and habitual blind spots, and to learn the particular techniques of periodic counting. The algorithms work in tandem with their well-known Sumerian counterparts and allow deep insights into Nature’s organizational principles.

Damage detection and localization in plate-like structures using sideband peak count (SPC) technique

This paper addresses the critical issue of detecting and localizing damage in plate-like structures, which are commonly encountered in aerospace, marine and other engineering applications. To address this challenge, the current study introduces the sideband peak count (SPC) technique as the foundation for diagnostic imaging for damage detection in plate structures. The proposed damage detection algorithm requires only a limited number of sensor responses, streamlining the detection process. It does not rely on a reference baseline, thereby enhancing its efficiency and accuracy. This approach enables rapid and precise identification of damage and its location within the plate structure. To validate the effectiveness and applicability of the proposed method, finite element simulation results are utilized. These results demonstrate the capability of the proposed technique to accurately detect and localize damage, providing a promising solution for enhancing the structural health monitoring of plate-like structures in various engineering domains.

Storehouse of Peculiar Supramolecular Architecture: Probing the Charge-Transfer Phenomenon and Effect of Altering the pH in a Meta-Oriented Single Donor-Double Acceptor Fluorophore.

The investigation of excited-state intramolecular charge transfer (ESICT) has been a fascinating area of research. Although the ESICT events have been studied mostly for para-disubstituted donor-acceptor type molecules, the meta-oriented donor-acceptor type molecules have also shown tremendous potential as ESICT active molecules. In the current work, a small fluorescent probe diethyl 5-amino isophthalate (DE-5A-IPA) was investigated as a potential model to investigate ESICT events in the solution as well as solid phase. DE-5A-IPA was synthesized easily starting from commercially available 5-amino isophthalic acid in excellent yield. In the solid state, differing extents of CH···π-type binding led to formation of fully planar and puckered "cyclobutane" mimic supramolecular architecture, as evidenced from the crystal structure analysis. In addition, the single crystal structure of DE-5A-IPA shows that the donor (-NH2) and acceptor (-CO2Et) are situated in the same plane, thereby assuring the prerequisites of a through-space charge transfer. DE-5A-IPA undergoes noticeable Stokes shift (in cm-1) when the polarity of the medium was changed (4820 cm-1 in hexane; 9375 cm-1 in water). The excited-state dipole moment (μe) was calculated to be 4.0 units higher than the ground-state dipole moment (μg). DE-5A-IPA had an appreciable quantum yield (0.10 ± 0.03 to 0.27 ± 0.04). The ESICT phenomenon was also investigated by ground- and excited-state structural calculations using Gaussian 16 software. The excited-state lifetime measured by the time correlated single photon counting technique was found to vary with the polarity of the solvent, thereby providing further support to the ESICT phenomenon being operative in DE-5A-IPA. Taking advantage of the -NH2 group (which is susceptible to protonation) in DE-5A-IPA, steady state and time-resolved photodynamics were investigated in solutions of varying pH values. Interestingly, the emission quantum yields as well as the emission lifetime increase with an increase in pH value, thereby establishing DE-5A-IPA as a pH-sensitive probe. The current findings shall boost the understanding of meta-oriented ESICT enabled compounds in terms of their excited-state photophysics.

Impact of Gold Nanoparticles Intraperitoneal Injection on Mice's Erythrocytes and Renal Tissue.

The purpose of this study was to investigate the effects of two different types of gold nanoparticles (AuNPs) delivered by intraperitoneal (IP) injection on blood and kidney tissue changes in a mouse model. Three groups of fifteen adult male BALB/c healthy mice, weighing approximately 25-30 g, were used for the experiment and designated G1, G2, and G3, respectively. G1 mice received vehicle, whereas G2 and G3 received an IP injection of 10 mg/kg body weight of methoxy poly ethylene glycol gold nanoparticles (PEG-AuNPs) and fluorescently dye labeled gold nanoparticles (Dye-AuNPs), respectively. Hematological parameters were measured based on the standard complete blood cell count (CBC) technique. The two nanoparticles, i.e., PEG-AuNPs and Dye-AuNPs, significantly reduced most red blood cell (RBC) parameters in the groups with the exception of a nonsignificant effect on hemoglobin (HBG) levels. Both gold nanoparticles, i.e., PEG-AuNPs and Dye-AuNPs, led to a reduced RBC count, mean corpuscular volume (MCV), and mean corpuscular hemoglobin (MCH) level when compared with the control. Notably, Dye-AuNPs and PEG-AuNPs resulted in a considerably higher RBC distribution RDW-(CV % and SD fL). Glomerular injury was suggested based on the development of hydropic degeneration and the presence of a protein-rich fluid inside the tubules. Renal tissue and blood indices changed significantly in response to the two nanoparticles, suggesting possible organ injury.

The use of low-frequency current fluctuations in measuring the mobility of holes in the MEH-PPV polymer

A diagnostic method based on the evaluation of low-frequency current fluctuation spectra is presented. When measuring the current through a p-type MEH-PPV sample, the occurrence of fluctuation is observable which can be measured with an AC amplifier. A model has been proposed that proves that the fluctuations originate from the interaction between the valence band and the band gap traps. The mean value of the amplitudes of these fluctuations increases linearly with decreasing frequency with a slope from which the product of mobility and lifetime of current carriers µpτp= (9 ± 3) × 10−15 cm2V−1 was obtained. The hole lifetime of (0.27 ± 0.01) ns was evaluated from the luminescence relaxation using the time-correlated single photon counting (TCSPC) technique. The mobility value (3 ± 1) × 10−5 cm2 V−1s−1 calculated using the above methods was compared with the mobility 1.8 × 10−5 cm2 V−1s−1 determined by the CELIV method (Charge extraction by linearly increasing voltage) and good agreement was obtained.

Quantitative analysis of transferrin uptake into living cells at single-molecule level

Endocytosis, apart from providing a mechanism for cells to take up nutrients, is the principal route of entry for many nanomedicines. The evaluation of therapeutic delivery efficiency without providing quantitative parameters, like the number of molecules entering the cell and the time of their entry, is very limited. Despite advances in single-molecule methods for in-cell quantitative measurements, they have not become widely used in the study of endocytosis. Their application, however, is challenging owing to the appropriate experimental design and applicable analysis methods. Here, by using an integrated approach based on the multidimensional time-correlated single-photon counting (TCSPC) technique, we demonstrate the quantitative method to measure the time- and concentration-dependent uptake of TRITC-transferrin into living cells with single-molecule sensitivity. The methodology opens possibilities for quantitatively assessing the delivery efficiency of fluorescent molecules into living cells.

Topology of quasi divisor graphs associated with non-associative algebra

The visualization of graphs representing algebraic structures has increasingly gained traction in chemical engineering research, emerging as a significant scientific challenge in contemporary studies. Due to their practical applications, graphs associated with groups and various algebraic systems have garnered significant interest in academic literature. Chemical graph theory employs graphs to illustrate molecular structures, where vertices symbolize atoms and edges represent bonds. The structure of quasi divisor graphs linked to non-associative algebra, including quasigroups and loops, presents numerous potential implications and wider applications. These applications span multiple disciplines, such as algebra, combinatorics, computer science, and network theory. Latin squares are tabular representations of quasigroups, generalizations of group structure. Numerous classifications of quasigroups exist in academic literature, such as Moufang quasigroups, Bol quasigroups, and alternative quasigroups. However, the structural characteristics of quasigroups exhibiting the weak inverse property closely resemble those of groups. The overall purpose of this study is to see the interrelationship between non-isomorphic quasi divisor graphs and a particular class of G-loops. To achieve our results, we employ a variety of methods, including a combinatorial approach, degree counting techniques, vertex and edge partitioning methods, as well as graph-theoretical tools and analytical procedures. In this paper, we compute a few topological indices based on degree, distance, and degree-distance using the structural aspects of quasi divisor graphs of orders 2φ,22ϕ,23ϕ and 4ϕ1ϕ2 where φ is a positive integer and ϕ1,ϕ2 are odd primes with ϕ1<ϕ2. This work also includes polynomial forms and their geometrical interpretations connected to linear, quadratic and higher degree topological indices of quasi divisor graphs associated with a class of non-commutative weak inverse property quasigroups.

Quantification of nanoscale precipitation in AA7050 using X-ray scattering, electron microscopy and automated particle counting techniques

Material strength is dependent on several factors, including precipitation strengthening, which is the main strengthening mechanism in AA7050 aluminum alloys. These alloys contain numerous nanometer-scale precipitates that occur throughout grains and along grain boundaries when subjected to a range of heat treatment conditions. In this study, three different characterization methods were used to characterize these nanoscale precipitates: conventional scanning transmission electron microscopy (STEM); laboratory-based small-angle X-ray scattering (SAXS); and a new software analysis tool developed by Thermo Fisher Scientific: automated particle workflow (APW). Each method was used to determine average precipitate size and volume fraction of precipitation in AA7050-T7451 specimens with variable post-T7 heat treatment procedures. STEM techniques measured the average particle size as ranging from 7.6 to 17.6 nm, compared to 6.3–10.7 nm for SAXS, and 7.4–10.8 nm for APW. Volume fraction determinations varied from 0.23 to 16 %, depending on method, and were the most difficult to quantify. Significant outcomes of the current study are that SAXS and APW are the most accurate methods for determining average particle size and that future work is needed to effectively analyze precipitate volume fraction.

РАЗРАБОТКА ПРОГРАММЫ РАСЧЕТА ПАРАМЕТРОВ СХЕМЫ ЗАМЕЩЕНИЯ ТРЕХФАЗНОГО АСИНХРОННОГО ЭЛЕКТРОДВИГАТЕЛЯ

The article is devoted to developing a program for calculating the parameters of a T-shaped equivalent circuit of three-phase asynchronous electric motors. The relevance of this work is due to the need to obtain reliable results of computer simulation modelling of electric drive systems in software packages. The aim of the study is to implement in a convenient software interface an analytical technique for calculating the parameters of an asynchronous motor equivalent circuit with minimal deviations from the catalogue data. For the software calculation of the equivalent circuit parameters the paper considers analytical approximation and iterative counting techniques, since they do not require experiments on industrial electrical equipment. A comparative analysis of such techniques is performed using the example of a three-phase asynchronous motor brand BA280S4 with a power of 110 kW. The results of the compar-ative analysis show that the highest reliability of the mechanical and electromechanical characteristics is achieved in the case of using the iterative counting technique with minimizing the objective function of the sum of the weighted squares of the deviations of the control point values from the catalogue data. The authors implement the program for calculating the equivalent circuit parameters according to the selected calculation method in the Embarcadero Delphi environment. The reliable values of the electric motor parameters calculated by the program will allow for computer to model electric drive systems that best matches real objects.

Shrimp Larvae Counting Based on Improved YOLOv5 Model with Regional Segmentation

Counting shrimp larvae is an essential part of shrimp farming. Due to their tiny size and high density, this task is exceedingly difficult. Thus, we introduce an algorithm for counting densely packed shrimp larvae utilizing an enhanced You Only Look Once version 5 (YOLOv5) model through a regional segmentation approach. First, the C2f and convolutional block attention modules are used to improve the capabilities of YOLOv5 in recognizing the small shrimp. Moreover, employing a regional segmentation technique can decrease the receptive field area, thereby enhancing the shrimp counter’s detection performance. Finally, a strategy for stitching and deduplication is implemented to tackle the problem of double counting across various segments. The findings from the experiments indicate that the suggested algorithm surpasses several other shrimp counting techniques in terms of accuracy. Notably, for high-density shrimp larvae in large quantities, this algorithm attained an accuracy exceeding 98%.

Accurate crowd counting for intelligent video surveillance systems

The paper presents a novel deep learning approach for crowd counting in intelligent video surveillance systems, addressing the growing need for accurate monitoring of public spaces in urban environments. The demand for precise crowd estimation arises from challenges related to security, public safety, and efficiency in urban areas, particularly during large public events. Existing crowd counting techniques, including feature-based object detection and regression-based methods, face limitations in high-density environments due to occlusions, lighting variations, and diverse human figures. To overcome these challenges, the authors propose a new deep encoder-decoder architecture based on VGG16, which incorporates hierarchical feature extraction with spatial and channel attention mechanisms. This architecture enhances the model’s ability to manage variations in crowd density, leveraging adaptive pooling and dilated convolutions to extract meaningful features from dense crowds. The model’s decoder is further refined to handle sparse and crowded scenes through separate density maps, improving its adaptability and accuracy. Evaluations of the proposed model on benchmark datasets, including Shanghai Tech and UCF CC 50, demonstrate superior performance over state-of-the-art methods, with significant improvements in mean absolute error and mean squared error metrics. The paper emphasizes the importance of addressing environmental variability and scale differences in crowded environments and shows that the proposed model is effective in both sparse and dense crowd conditions. This research contributes to the advancement of intelligent video surveillance systems by providing a more accurate and efficient method for crowd counting, with potential applications in public safety, transportation management, and urban planning.