This paper proposes two max-pooling engines, named the RTB-MAXP engine and the CMB-MAXP engine, with a scalable window size parameter for FPGA-based convolutional neural network (CNN) implementation. The max-pooling operation for the CNN can be decomposed into two stages, i.e., a horizontal axis max-pooling operation and a vertical axis max-pooling operation. These two one-dimensional max-pooling operations are performed by tracking the rank of the values within the window in the RTB-MAXP engine and cascading the maximum operations of the values in CMB-MAXP engine. Both the RBM-MAXP engine and the CMB-MAXP engine were implemented using VHSIC Hardware Description Language (VHDL) and verified by simulations. They have been employed for and tested in our CNN accelerator targeting at the CNN model YOLOv4-CSP-S-Leaky for object detection.

Educational institutions must identify students who are academically struggling to provide them with necessary support to improve their performance. In this context, recommendation systems powered by deep learning techniques are vital for detecting and categorizing such students. These systems help students plan their future by uncovering patterns in their historical academic data. This study introduces a new deep learning model designed to classify academically underperforming students in educational settings. The model incorporates a Gated Recurrent Neural Network (GRU) and includes specific neural network features like a dense layer, max-pooling layer, and the ADAM optimization algorithm. The model's training and evaluation were conducted using a dataset comprising 15,165 student assessment records from various academic institutions. The performance of the developed GRU model was benchmarked against other educational recommendation systems, including Recurrent Neural Network models, AdaBoost, and the Artificial Immune Recognition System v2. The proposed GRU model demonstrated remarkable accuracy, achieving an overall rate of 99.70%.

Phenotypes are necessary for genomic evaluations and management. Sometimes genomics can be used to measure phenotypes when other methods are difficult or expensive. Prolificacy of bulls used in multiple-bull pastures for commercial beef production is an example. A retrospective study of 79 bulls aged 2-year-old and older used 141 times in 4-5 pastures across 4 years was used to estimate repeatability from variance components. Traits available before each season’s use were tested for predictive ability. Sires were matched to calves using individual genotypes and evaluating exclusions. A lower cost method of measuring prolificacy was simulated for 5 pastures using the bulls’ genotypes and pooled genotypes to estimate average allele frequencies of calves and of cows. Repeatability of prolificacy was 0.62 ± 0.09. A combination of age-class and scrotal circumference accounted for less than 5 % of variation. Simulated estimation of prolificacy by pooling DNA of calves was accurate. Adding pooling of cow DNA or actual genotypes both increased accuracy about the same. Knowing a bull’s prior prolificacy would help predict future prolificacy for management purposes and could be used in genomic evaluations and research with coordination of breeders and commercial beef producers.

Background and purpose: Dynamic 18F-FDG PET-CT scanning can accurately quantify 18F-FDG uptake and has been successfully applied in diagnosing and evaluating therapeutic effects in various malignant tumors. There is no conclusion as to whether it can accurately distinguish benign and malignant lymph nodes in nasopharyngeal cancer. The main purpose of this study is to reveal the diagnostic value of dynamic PET-CT in cervical lymph node metastasis of nasopharyngeal cancer through analysis. Method: We first searched for cervical lymph nodes interested in static PET-CT, measured their SUV-Max values, and found the corresponding lymph nodes in magnetic resonance images before and after treatment. The valid or invalid groups were included according to the changes in lymph node size before and after treatment. Their Ki values were measured on dynamic PET-CT and compared under different conditions. Then, we conducted a correlation analysis between different factors and Ki values. Finally, diagnostic tests were conducted to compare the sensitivity and specificity of Ki and SUV-Max. Result: We included 67 cervical lymph nodes from different regions of 51 nasopharyngeal cancer patients and divided them into valid and invalid groups based on changes before treatment. The valid group includes 50 lymph nodes, while the invalid group includes 17. Significant differences (P<0.001) between the two groups in SUV-Max, Ki-Mean, and Ki-Max values. When the SUV-Max≤4.5, there was no significant difference in the Ki-Mean and Ki-Max between the two groups (P>0.05). When SUV-Max≤4.5 and pre-treatment lymph nodes<1.0cm, the valid group had significantly higher Ki-Mean (0.00910) and Ki-Maximum (0.01004) values than the invalid group (Ki-Mean=0.00716, Ki -Max=0.00767) (P<0.05). When SUV-Max≤4.5, pre-treatment lymph nodes<1.0cm, and EBV DNA replication was normal, Ki-Mean (0.01060) and Ki-Max (0.01149) in the valid group were still significantly higher than the invalid group (Ki-Mean=0.00670, Ki-Max=0.00719) (P<0.05). The correlation analysis between different factors (SUV-Max, T-stage, normal EB virus DNA replication, age, pre-treatment lymph node<1.0cm) and Ki value showed that SUV-Max and pre-treatment lymph node<1.0cm were related to Ki-Mean and Ki-Max. Diagnostic testing was conducted, the AUC value of the SUV-Max value was 0.8259 (95% confidence interval: 0.7296-0.9222), the AUC value of the Ki-Mean was 0.8759 (95% confidence interval: 0.7950-0.9567), and the AUC value of the Ki-Max was 0.8859 (95% confidence interval: 0.8089-0.9629). It was found that the sensitivity of SUV-Max was 88%, the specificity was 76%, the sensitivity of Ki-Mean was 88%, the specificity was 80%, the sensitivity of Ki-Max was 94%, the specificity was 76%, the specificity of Ki-Mean was better than SUV-Max, the sensitivity of Ki-Max was better than SUV-Max. Conclusion: Dynamic PET-CT has shown significant diagnostic value in diagnosing cervical lymph node metastasis of nasopharyngeal cancer, especially for the small SUV value, and lymph nodes do not meet the metastasis criteria before treatment, and EBV DNA replication is normal. Moreover, its sensitivity and accuracy are superior to static PET-CT.

Although monitoring and observing insect pest populations in the fields is essential in crop management, it is still a laborious and sometimes ineffective process. High infestation levels may diminish the photosynthetic activity of soybean plants, affecting their development and reducing the yield. An imprecise decision making in integrated pest management program may lead to an ineffective control in infested areas or the excessive use of insecticides. In order to reach a more efficient control of arthropods population it is important to evaluate the infestation in time to mitigate its negative effects on the crop and remote sensing is an important tool for monitoring. It was proposed that infested soybean areas could be identified, and the arthropods quantified from non-infested areas in a field by hyperspectral remote sensing. Thus, the goals of this study were to investigate and discriminate the reflectance characteristics of soybean non-infested and infested with Bemisia tabaci using hyperspectral remote sensing data. Therefore, samples of infested and non-infested soybean leaves were collected and transported to the laboratory to obtain the hyperspectral curves. The results obtained allowed to discriminate the different levels of infestation and to separate healthy from whitefly infested soybean leaves based on their reflectance.

We present a Deep Learning generative model specialized to work with graphs with a regular geometry. It is build on a Variational Autoencoder framework and employs Graph convolutional layers in both encoding and decoding phases. We also introduce a pooling technique (ReNN-Pool), used in the encoder, that allows to downsample graph nodes in a spatially uniform and highly interpretable way. In the decoder, a symmetrical un-pooling technique is used to retrieve the original dimensionality of graphs. Performance of the model are tested on the standard Sprite benchmark dataset, a set of 2D images of video game characters, adequately transforming images data into graphs, and on the more realistic use-case of a dataset of cylindrical-shaped graph data that describe the distributions of the energy deposited by a particle beam in a medium.

In this study, we address the formidable challenge of solving large-scale Max-Cut problems (MCP). We introduce a rapid computational procedure utilizing a hybrid 1-flip/r-flip local search heuristic. This innovative strategy significantly reduces the computational time required for MCP problems while consistently generating solutions of exceptional quality. The paper presents substantial computational insights, showcasing the effectiveness of our approach on very-large-scale Max-Cut instances with varying densities. Our proposed heuristic is rigorously evaluated by comparing its performance against a quantum annealing solver, leveraging a multi-start Tabu Search framework. The results underscore the potency of this unique combination as an efficient and effective solution for large-scale QUBO problems. Notably, our hybrid heuristic consistently delivers high-quality solutions within the stringent CPU time limits of 600 seconds, demonstrating its efficacy across Max-Cut instances ranging from 10,000 to 40,000 variables. This research contributes to advancing the state-of-the-art in large-scale QUBO problem-solving, offering a powerful and time-efficient approach with broad applicability.

Convolutional neural networks (CNNs) have proven to be a very efficient class of machine learning (ML) architectures for handling multidimensional data by maintaining data locality, especially in the field of computer vision. Data pooling, a major component of CNNs, plays a crucial role for extracting important features of the input data and downsampling its dimensionality. Multidimensional pooling, however, is not efficiently implemented in existing ML algorithms. In particular, quantum machine learning (QML) algorithms have a tendency to ignore data locality for higher dimensions by representing/flattening multidimensional data as simple one-dimensional data. In this work, we propose using the quantum Haar transform (QHT) and quantum partial measurement for performing generalized pooling operations on multidimensional data. We present the corresponding decoherence-optimized quantum circuits for the proposed techniques along with their theoretical circuit depth analysis. Our experimental work was conducted using multidimensional data, ranging from 1-D audio data, to 2-D image data, to 3-D hyperspectral data, to demonstrate the scalability of the proposed methods. In our experiments, we utilized both noisy and noise-free quantum simulations on a state-of-the-art quantum simulator from IBM Quantum. We also show the efficiency of our proposed techniques for multidimensional data by reporting the fidelity of results.

Three cohorts including the Fire Department of the City of New York (FDNY), the World Trade Center Health Registry (WTCHR), and the General Responder Cohort (GRC), each funded by the World Trade Center Health Program have reported associations between WTC-exposures and cancer. Results have generally been consistent with effect estimates for excess incidence for all cancers ranging from 6 to 14% above background rates. Pooling would increase sample size and de-duplicate cases between the cohorts. Pooling required time consuming steps: obtaining IRB approvals and legal agreements from entities involved; establishing an honest broker for managing the data; de-duplicating the pooled cohort files; applying to State Cancer Registries (SCRs) for matched cancer cases; and finalizing analysis data files. Obtaining SCR data use agreements ranged from 6.5 to 114.5 weeks with six states requiring >20 weeks. Records from FDNY (n=16,221), WTCHR (n=29,372), and GRC (n=33,427) were combined de-duplicated resulting in 69,102 unique individuals. Overall, 7,894 cancer tumors were matched to the pooled cohort, increasing the number cancers by as much as 58% compared to previous analyses. Pooling resulted in a coherent resource for future research for studies on rare cancers and mortality, with more representative of occupations and WTC- exposure.

In Los Angeles, at one point, the Covid-19 testing positivity rate was 6.25%, or one in sixteen. This translates to, on average, one in sixteen specimens testing positive and the vast majority testing negative. Usually, we run sixteen tests on sixteen specimens to identify the positive one(s). This process can be time consuming and expensive. Since a group of negative specimens pooled together for testing will produce a negative result, one single test could potentially eliminate many specimens. Only when the pooled specimen tests positive do we need further testing to identify the positive one(s). Based on this concept, we designed a strategy that will identify the positive specimen(s) efficiently. Assuming one in sixteen specimens is positive, we find that only four tests are needed. Furthermore, we can run them simultaneously, saving both resources and time. Although, in the real world, we cannot make the assumption of only one positive specimen, the same strategy works with slight modification and proves to be much more efficient than the conventional testing. Our strategy returns an answer 48% of the time in four tests and one time cycle. Overall, the average number of tests is seven or eight depending on the follow-up testing, and the average time cycle is about one and a half.

Alcoholism is attributed to regular or excessive drinking of alcohol and leads to the disturbance of the neuronal system in the human brain. This results in certain malfunctioning of neurons that can be detected by an electroencephalogram (EEG) using several electrodes on a human skull at appropriate positions. It is of great interest to be able to classify an EEG activity as that of a normal person or an alcoholic person using data from the minimum possible electrodes (or channels). Due to the complex nature of EEG signals, accurate classification of alcoholism using only a small data is a challenging task. Artificial neural networks, specifically convolutional neural networks (CNN), provide efficient and accurate results in various pattern-based classification problems. In this work, we apply CNN on raw EEG data, and demonstrate how we achieved 98% average accuracy by optimizing a baseline CNN model and outperforming its results in a range of performance evaluation metrics on the UCI-KDD EGG dataset. This article explains the step-wise improvement of the baseline model using the dropout, batch normalization, and kernel regularization techniques, and provides a comparison of the two models that can be beneficial for aspiring practitioners who aim to develop similar classification models in CNN. A performance comparison is also provided with other approaches using the same dataset.

The whitefly leads extensive damage to plants through direct feeding, honeydew secretion, plant physiological disorders, and vectoring plant viruses. This study aimed to evaluate the physiological characteristics of susceptible and resistant soybean cultivars to B. tabaci. The experiments were conducted in a greenhouse. Eleven soybean cultivars were selected and infested with 100 adults of B. tabaci at the V3 stage. The evaluation of photosynthetic parameters, such as photosynthetic rate, leaf transpiration, stomatal conductance, and internal CO2 concentration, revealed that B. tabaci infestation influenced gas exchange in soybean plants. The photosynthetic rate was higher in cultivars AS3810 and M8349 during the V6 stage. Infestations led to alterations in photosynthetic parameters, suggesting increased energy demand to maintain photosynthetic activity. However, the response to infestation varied among different cultivars, indicating varying levels of resistance and tolerance to the whitefly's damage. Additionally, the impact of infestation was more significant during the vegetative phenological. In conclusion, B. tabaci infestation affects soybean plants' physiology, leading to changes in gas exchange parameters and water use efficiency. The response to infestation varied among soybean cultivars, suggesting potential differences in resistance to the pest. The study highlights the importance of evaluating the physiological impact of whitefly infestations on soybean.

Polyploidy induction is recognized as one of the major evolutionary processes presenting remark-able morphological, physiological, and genetic variations in plants. Soybean (Glycine max L.), also known as soja bean or soya bean, is an annual leguminous crop of the pea family (Fabaceae) that shares a paleopolypoidy history, dating back to approximately 56.5 million years ago with other leguminous crops such as cowpea and other Glycine specific polyploids. This crop has been documented as one of the polyploid complex species among legumes whose gene evolution and result-ant adaptive growth characteristics, following induced polyploidization has not been fully explored. Furthermore, there are no successfully established in vivo or in vitro based polyploidy in-duction protocols that have been reported so far, particularly, with the intention to develop mutant plants showing strong resistance to abiotic salinity stress. This review, therefore, describes the role of synthetic polyploid plant production in soybean for the mitigation against high soil salt stress levels, and how this evolving approach could be used to further enhance nutritional, pharmaceutical and economic industrial value of soybeans, including addressing challenges involved during the polyploidization process.

Soybean (Glycine max L.) is an important crop that serves as a source of edible oil and protein. However, little is known about its molecular mechanism of adaptation to extreme environmental conditions. Based on the Arabidopsis thaliana sequence database and Phytozome, a soybean gene that was highly homogenous with the reduced induction of the non-photochemical quenching2 (AtRIQ2) gene, GmRIQ2-like (accession NO.: Glyma.04G174400), was identified in this study. The gene structure analysis revealed that GmRIQ2-like encoded a transmembrane protein. Elements of the promoter analysis indicated that GmRIQ2-like participated in the photosynthesis and abiotic stress pathways. The subcellular localization results revealed that the protein encoded by GmRIQ2-like was located in chloroplasts. The quantitative real-time (qRT)-PCR results revealed that GmRIQ2-like-overexpression (OE) and -knock-out (KO) transgenic soybean seedlings were cultivated successfully. The relative chlorophyll (Chl) and zeaxanthin contents and Chl fluorescence kinetic parameters demonstrated that GmRIQ2-like dissipated excess light energy by enhancing the non-photochemical quenching (NPQ) and reduced plant photoinhibition. These results suggested that GmRIQ2-like was induced in response to strong light and depressed Chl production involved in soybean stress tolerance. These findings indicate that the transgenic seedlings of GmRIQ2-like could be used to enhance strong light stress tolerance and protect soybean plants from photoinhibition damage. This study will serve as a reference for studying crop photoprotection regulation mechanisms and benefits the research and development of new cultivars.

Water stress (WS) and heat stress (HS) have a negative effect on soybean plant growth and crop productivity. During WS, soybean plants opt for survival through ion homeostasis and the conformations of proteins are disconcerted as plant cells lose water while HS leads to difficulties in flowering and fruiting. Some of these changes include oxidative stress leading to the destruction of photosynthetic apparatus, macromolecules within cells and the onset of complex signaling cascades. Changes in the physiological characteristics, proteome, and certain metabolites investigated on molecular and cellular functions were studied in two soybean cultivars exposed to different heat and water stress conditions independently and in combination. Leaf protein composition was studied using 2-DE and complemented with MALDI TOF mass spectrometry. While two cultivars displayed genetic variation in response to water and heat stress, thirty-nine proteins were significantly altered in their relative abundance in response to WS, HS and combined WS+HS in both cultivars; a majority of them involved in metabolism, response to heat and photosynthesis showing significant cross-tolerance mechanisms. Functional analysis revealing a majority of heat responsive-proteins were more abundant during HS and combined stress (WS+HS) whereas these proteins were low to WS in cultivar PI 471938 and heat shock proteins were in low abundance to water, heat and combined stresses in cultivar R95-1705. Most protein abundances were not correlated with their expression at mRNA levels in PI cultivar, however, in cultivar R 95, the expression levels of transcript follow their relative abundance in proteins. Our systems bioinformatics analyses revealed that MED37C, a probable mediator of RNA polymerase transcription II protein showed potential interacting partners in Arabidopsis and our studies signifies the marked impact of this protein in PI cultivar. Elevated activities in antioxidant enzymes indicate that the PI-371938 cultivar has the ability to restore the oxidation levels and sustain the plant during the stress. Our study hypothesizes the plant’s development of cross-stress tolerance which will help foster the ongoing ventures in genetic modifications in stress tolerance.

The purpose of this study was to investigate the effect that Glycine max hydrolyzed with enzymes from Bacillus velezensis KMU01 has on dextran sulfate sodium (DSS)-induced colitis in mice. Hydrolysis improves functional health through the bioconversion of raw materials and increase in intestinal absorption rate and antioxidants. Therefore, G. max was hydrolyzed in this study using a food-derived microorganism, and its anti-inflammatory effect observed. Enzymatically hydrolyzed G. max (EHG) was orally administered once daily for four weeks before DSS treatment. Colitis was induced in mice through consumption of 5% (w/v) DSS in drinking water for eight days. Results showed that EHG treatment significantly alleviated DSS-induced body weight loss and decreased the disease activity index and colon length. In addition, EHG markedly reduced tumor necrosis factor-a, interleukin (IL)-1b, and IL-6 production, and increased that of IL-10. EHG improved DSS-induced histological changes and intestinal epithelial barrier integrity in mice. Moreover, we found that the abundance of 15 microorganisms changed significantly; that of Proteobacteria and Escherichia coli, which are upregulated in patients with Crohn’s disease and ulcerative colitis, decreased after EHG treatment. These results suggest that EHG has a protective effect against DSS-induced colitis and is a potential candidate for colitis treatment.

This paper focuses on robust multi-criteria traffic network equilibrium problems with path capacity constraints. The concepts of robust vector equilibrium and robust vector equilibrium with respect to worst case are introduced, respectively. To generate a subset of robust vector equilibrium, an equivalent min-max optimization problem is constructed. In addition, a direct search algorithm, in which the step size without derivatives and redundant parameters, for solving this min-max problem is proposed. To find a subset of robust vector equilibrium with respect to worst case, an equivalent smoothing optimization problem based on a variant version of ReLU activation function is established. Numerical experiments are also presented to expound the advantages of the algorithms.

In this article, we aim to show the capabilities, benefits, as well as restrictions, of three different air quality-related information sources, namely the Sentinel-5Precursor TROPOspheric Monitoring Instrument (TROPOMI) space-born observations, the Multi-Axis Differential Optical Absorption Spectroscopy (MAX-DOAS) ground-based measurements and the LOng Term Ozone Simulation – EURopean Operational Smog (LOTOS-EUROS) chemical transport modelling system simulations. The tropospheric NO2 concentrations between 2018 and 2021 are discussed as air quality indicators for the Greek cities of Thessaloniki and Ioannina. Each dataset was analysed in an autonomous manner and, without disregarding their differences, the common air quality picture that they provide is revealed. All three systems report a clear seasonal pattern, with high NO2 levels during winter-time and lower NO2 levels during summer-time, reflecting the importance of photochemistry in the abatement of this air pollutant. The spatial patterns of the NO2 load also showed, in both space-born observations and model simulations, the undeniable variability of the NO2 load within the urban agglomerations. The diurnal variability was furthermore clearly identified by the ground-based measurements, which also unquestionably revealed a Sunday minimum NO2 load effect, alongside the rest of the sources of air quality information. Within their individual strengths and limitations, the space-born observations, the ground-based measurements and the chemical transport modelling simulations, demonstrate unequivocally their ability to report on the air quality situation in urban locations.

Colletotrichum is one of the most important plant pathogenic genera of fungi due to its scientific and economic impact. Colletotrichum spp. can infect a wide range of hosts, causing losses in crops of major importance worldwide, such as soybean. In the past, soybean anthracnose was mainly caused by C. truncatum, but during the last decade, other species have been identified at an increasing rate, becoming one of the most important limiting factors to soybean production in several regions. To gain a better understanding of the evolutionary origin of soybean anthracnose, we compared the repertoire of effector candidates of four Colletotrichum species pathogenic to soybean and eight pathogens of other hosts. Our results show that the four species infecting soybean belong to two lineages and do not share any of the lineage specific effector candidates identified. These results strongly suggest that two Colletotrichum lineages have acquired the capability to infect soybean independently. This study also provides, for each lineage, a set of candidate effectors encoding genes that may have important roles in pathogenicity towards soybean offering a new resource useful for further research on soybean anthracnose management.

In considering knowledge graphs in a diverse range of domains of interest, graph neural networks have demonstrated significant improvements in node classification and prediction when applied to graph representation with learning node embedding to effectively represent hierarchical properties of graphs. DiffPool is a deep-learning approach using a differentiable graph pooling technique that generates hierarchical representations of graphs. In operation DiffPool is a differentiable graph pooling technique that generates hierarchical representations of graphs. DiffPool learns a differentiable soft cluster assignment for nodes at each layer of a deep graph neural network with nodes mapped sets of clusters. However, control of the learning process is difficult given the complexity and large number of parameters on an `end-to-end’ model. To address this difficulty we propose an novel approach termed FPool which is predicated on the basic approach adopted in DiffPool (where pooling is applied directly to node representations). Methods designed to enhance data classification have been developed and evaluated using a number popular and publicly available sensor data sets. Experimental results for FPool demonstrate improved classification and prediction performance when compared to alternative methods. Moreover, FPool shows an important reduction in the training time over the basic DiffPool framework.

Among the first discovered and most prominent cellular oncogenes is MYC, which encodes a bHLH-ZIP transcription factor (Myc) that both activates and suppresses numerous genes involved in proliferation, energy production, metabolism and translation. Myc belongs to a small group of bHLH-ZIP transcriptional regulators (the Myc Network) that includes its obligate heterodimerization partner Max and six “Mxd proteins” (Mxd1-4, Mnt and Mga) each of which heterodimerizes with Max and largely oppose Myc’s functions. More recently, a second group of bHLH-ZIP proteins (the Mlx Network) has emerged. It is comprised of the Myc-like factors ChREBP and MondoA, which, in association with the Max-like member Mlx, regulate smaller and more functionally restricted sets of target genes, some of which are shared with Myc. Opposing ChREBP and MondoA are heterodimers comprised of Mlx and Mxd1, Mxd4 and Mnt, which also structurally and operationally link the two Networks. We discuss here the functions of these “Extended Myc Network” members with particular emphasis on the roles played by Max, Mlx and Mxd proteins in suppressing normal and neoplastic growth. These roles are complex due to the temporally- and tissue-restricted expression of Extended Myc Network proteins in normal cells, their regulation of both common and unique target genes and, in some cases, their functional redundancy.

MXenes are two-dimensional nanomaterials isolated from MAX phases by the selective extraction of the A component —a p-block element. The MAX phase exfoliation energy, Eexf, is regarded as a chemical descriptor of the MXene synthesizability. Here we show, by density functional theory estimations of the Eexf values for 486 different MAX phases, that Eexf decreases i) when MAX is a nitride, ii) when going along a d series of the metal M component, iii) when going down a group of the p-block A element, as well as iv) when having thicker MXene phases. Furthermore, Eexf is found to bias, even to govern, the surface chemical activity, as evaluated here on the CO2 adsorption strength, so that more unstable MXenes, displaying larger Eexf values, display a stronger attachment of species upon.

Building deep learning models proposed by third parties can become a simple task when specialized libraries are used. However, a great deal of mystery still surrounds the design of new models or the modification of existing ones. These tasks require in-depth knowledge of the different components or building blocks as well as their dimensions. This information is limited and broken up in different literature. In this article, we collect and explain in-depth the building blocks to design deep learning models, starting from the artificial neuron to the concepts involved in building deep neural networks. Furthermore, the implementation of each building block is exemplified using the Keras library.

Abstract: This study aimed to evaluate the application of chemical defensives and long-life inoculant, in mixtures or not, under the nodulation process of plants and the quality of soy seeds during storage. The first was carried out in a greenhouse and completely randomized design was used, in an 8 x 2 factorial scheme, with three replications, and the treatments consisted of applications of seed treatments via industrial: (T1 - control; T2 - MaximAdvanced; T3 - Fortenza; T4 - long-life inoculant; T5 - MaximAdvanced + Fortenza); T6 - MaximAdvanced + long-life inoculant; T7 - Fortenza + long-life inoculant; T8 - MaximAdvanced + Fortenza + long-life inoculant), which were sown in pots containing soils from two cultivation areas; the second in the laboratory, using a completely randomized design, in a factorial scheme 8 x 7, with four replications, with treatments consisting of eight combinations of industrial seed treatment in the greenhouse, stored for two months. That seed treatment industrial with fungicide/insecticide/inoculant, applied in isolation or not, does not influence the soy nodulation process. Soy seeds, regardless of the type of treatment received with fungicide/insecticide/long-life inoculant products, in mixtures or in isolation, may be stored for a period of 40 days for commercial purposes.

Soybean maturity is a trait of critical importance for the development of new soybean cultivars, nevertheless, its characterization based on visual ratings has many challenges. Unmanned aerial vehicles (UAVs) imagery-based high-throughput phenotyping methodologies have been proposed as an alternative to the traditional visual ratings of pod senescence. However, the lack of scalable and accurate methods to extract the desired information from the images remains a significant bottleneck in breeding programs. The objective of this study was to develop an image-based high-throughput phenotyping system for evaluating soybean maturity in breeding programs. Images were acquired twice a week, starting when the earlier lines began maturation until the latest ones were mature. Two complementary convolutional neural networks (CNN) were developed to predict the maturity date. The first using a single date and the second using the five best image dates identified by the first model. The proposed CNN architecture was validated using more than 15,000 ground truth observations from five trials, including data from three growing seasons and two countries. The trained model showed good generalization capability with a root mean squared error lower than two days in four out of five trials. Four methods of estimating prediction uncertainty showed potential at identifying different sources of errors in the maturity date predictions. The architecture used solves limitations of previous research and can be used at scale in commercial breeding programs.

Music-domain visual programming languages (VPLs) have shown to be Turing complete. However, the common lack of built-in flow control structures can obstruct using VPLs implementing general-purpose algorithms, which harms the direct use of algorithms and algorithm theory in art creation processes using VPLs. In this article, we show how to systematically implement general-purpose algorithms in music-domain visual languages by using the Finite State Machines with Datapath computation model. The results expose a finite state machine and a set of internal state variables that walk paths whose speed can be controlled using a metronome ticks and whose path depends on the initial conditions of the algorithm. These elements can be further mapped to music elements according to the musician's intentions. We demonstrate this technique by implementing Euclid's Greatest Common Divider algorithm and using it to control high-level music elements in an implementation of Terry Riley's In C, and to control audio synthesis parameters in a FM synthesizer.

Load variations in any power system result in losses escalation and voltage drops. With the sensible and optimal allocation of distributed generators (DGs), these problems could be considerably mitigated. It has been seen in the priorly existing methods that ideally allocation of DGs has been carried out during fixed loads and constant power requirements. However, in real scenarios the loads are always variable and allocation of DGs must be done in accordance to the variations of the connected load. Therefore, the current paper addressed the aforementioned problem by distinctive optimal allocation of DGs for each variability of 24hour load horizon. However, the single exclusive solution is considered among all allocations of 24 hours. The min-max regret concept has been utilized in order to deal with such methodology. Altogether, 24 scenarios are analyzed wherein each scenario corresponds to a specific hour of the respective day. The optimal allocation of DGs in terms of their optimal sizing and placement has been carried out by using three algorithms including battle royal optimization (BRO), accelerated particle swarm optimization (APSO) and genetic algorithm (GA). The multi-objective optimization problem is evaluated on the basis of minimum value criterion of the multi-objective index (MO). MO comprises of active and reactive power losses and voltage deviation. Hence, in order to find robustness of proposed technique, Conseil international des grands réseaux electriques (CIGRE’s) MV benchmark model incorporating 14 buses has been considerably used as a test network. In the end the results of three proposed algorithms have been compared.

Improving air quality and reducing human exposure to unhealthy levels of airborne chemicals are important global missions, particularly in China. Satellite remote sensing offers a powerful tool to examine regional trends in NO2, thus providing a direct measure of key parameters that strongly affect surface air quality. To accurately resolve spatial gradients in NO2 concentration using satellite observations and thus understand local and regional aspects of air quality, a priori input data at sufficiently high spatial and temporal resolution to account for pixel-to-pixel variability in the characteristics of the land and atmosphere are required. In this paper, we adapt the Berkeley High Resolution product (BEHR v3.0A, v3.0B and v3.0C) and meteorological outputs from the Weather Research and Forecasting (WRF) model to describe column NO2 in southern China. The BEHR approach is particularly useful for places with large spatial variabilities and terrain height differences such as China. We retrieved tropospheric NO2 vertical column density (TVCD) within part of southern China, for four seasons of 2015, based upon satellite datasets from Ozone Monitoring Instrument (OMI). Retrieval results are validated by comparing with MAX-DOAS tropospheric column measurements conducted in Guangzhou. BEHR retrieval algorithms are more consistent with MAX-DOAS measurements than OMI-NASA retrieval, opening new windows into research questions that require high spatial resolution, for example retrieving NO2 vertical column and ground pollutant concentration in China and other countries.

Market turbulence with fiscal investment influences has altered IT infrastructure performance as business pursue extravagant new technology adoption. Yet, few studies have examined how shareware solution goes beyond Medium Size Enterprise that pushes efficiency and sustainability. This PLS-SEM integrated with dual primary compilation approach lessens shallow perceptions coupled with outlooks that streamline each phenomenal activity that is worthy of the necessity for competitive innovation. This unified model was applied to sampling respondents and analyzed using an ordinal regression relationship that generates a robust association that triggers the hypothesis acceptance. The adopting of BOINC shareware mesh network towards unified processing designs that were employed to build the yield by promising financial possibility using coordinated interworks hence improved group accomplishment and establishing greater esteem. This paper showcases a flexible inner IT infrastructure alongside the economic uncertainty with the framework advancement for Exostructure as a Service. Associated theoretical and practical implications were discussed.

The SARS-CoV-2 virus that causes the COVID-19 disease has wreaked havoc on the world community in terms of every imaginable parameter. The research output on COVID-19 has been nothing short of phenomenal, especially in the medical and biomedical sciences, where the search for a potential vaccine is being conducted in earnest. Much of the advanced research has been distributed in the leading medical journals, including the Journal of the American Medical Association (JAMA), where the latest research is distributed on a daily basis. The purpose of this paper is to provide some perspectives on 44 interesting and highly topical research papers that have been published in JAMA, at the time of writing, within the past two weeks. The diverse topics include public health, general medicine, internal medicine, oncology, paediatrics, geriatrics, and biostatistics.