Image-based plant phenotyping has diverse applications, ranging from providing quantitative traits for genetic breeding to enhancing management practices for indoor and outdoor production systems. Misidentification of cell lines or ecotypes/varieties is a major problem across all biological research disciplines. With the 1000 Arabidopsis Genome Project facilitating the use of various ecotypes, it is crucial to verify the identity of ecotypes in discovery-based genetic screens involving hundreds of ecotypes. To address this issue, an RGB image analysis pipeline was established for the accurate recognition of different Arabidopsis thaliana ecotypes. In the developed pipeline, the most crucial aspects for accurately capturing traits and training deep learning models were identified as follows: (i) assessment of data complexity using spatial-temporal features of the RGB spectrum and data entropy, the latter defined as the variability within the dataset; (ii) data redefinition in instances of high data complexity; and (iii) data partitioning based on extracted morphological similarity among ecotype replicates. The pipeline includes several supervised deep learning models integrated into an auto-optimization subsystem. Extensive hyperparameter tuning was performed to identify the best-performing models for single-image and image-sequence ecotype classification. Two external datasets were evaluated to demonstrate the robustness of the pipeline, regardless of how they were collected. A graphical user interface is provided to prepare these images for input into the pipeline in cases of extreme variability. The pipeline can automatically verify ecotypes in large-scale studies and extract traits for further analysis and correlation, as needed, using datasets from a variety of sources.

Tracking dynamic changes in plant leaves using deep learning models represents a new approach to plant trait analysis. Combining deep learning techniques with botany and agronomy can be of great significance in the future. This indeed marks a crucial step towards addressing the increasingly prevalent problems in agriculture, especially considering that the issue of food scarcity represents a real problem we might face in the coming period. In this paper, we present an adaptation of the Speedy Measurement of Arabidopsis Rosette Traits (SMART) program - a robust, parameter-free system for plant image segmentation and trait extraction. Our goal was to optimize performance on a diverse dataset that differs significantly in characteristics from the one originally used to evaluate SMART. To this end, we replaced the traditional feature extraction methods with a custom-designed semantic segmentation approach. This modification enabled significantly improved results on our target dataset. Furthermore, the enhanced model offers promising potential for future applications, particularly in estimating plant developmental stages.

High-throughput plant phenotyping using RGB imaging offers a scalable and non-invasive solution for monitoring plant growth and extracting various traits. However, achieving accurate segmentation across experiments remains a challenging task due to image variability usually caused by shifts in pot positions. This study introduces a customized image stabilization method to align pots consistently across time-series images of Arabidopsis thaliana, enhancing spatial consistency. A large-scale RGB dataset was collected and prepared, with 4,000 manually annotated images used to train multiple encoder–decoder deep learning models. Various CNN-based encoders were paired with well-known decoders, including U-Net, $\mathbf{U}^{2}$-Net, PANet, and DeepLabv3. Stabilization significantly improved performance of models, with the $EffNetB1 +\mathbf{U}^{2}$-Net encoder-decoder combination achieving the highest precision score of 0.95 and Intersection over Union of 0.96. These results demonstrate the value of spatial consistency and offer a robust, scalable pipeline for automated plant segmentation in indoor phenotyping systems.

The precise detection of plant centres is important for growth monitoring, enabling the continuous tracking of plant development to discern the influence of diverse factors. It holds significance for automated systems like robotic harvesting, facilitating machines in locating and engaging with plants. In this paper, we explore the YOLOv4 (You Only Look Once) real-time neural network detector for plant centre detection. Our dataset, comprising over 12,000 images from 151 Arabidopsis thaliana accessions, is used to fine-tune the model. Evaluation of the dataset reveals the model's proficiency in centre detection across various accessions, boasting an mAP of 99.79% at a 50 % IoU threshold. The model demonstrates real-time processing capabilities, achieving a frame rate of approximately 50 FPS. This outcome underscores its rapid and efficient analysis of video or image data, showcasing practical utility in time-sensitive applications.

This paper presents a robust exploration of the capabilities of conditional Generative Adversarial Networks (GANs) in harnessing labeled data to produce high-quality labels for unlabeled samples. By leveraging conditional information, our approach guides the network to generate contextually relevant labels for specific time series data, accelerating the labeling process. A comprehensive evaluation of our model's performance, incorporating diverse metrics, visual representations, and his-tograms, illuminates the effectiveness of conditional GANs for the Assistive Label Generation (ALG) of time series Arabidopsis thaliana images. The Structural Similarity Index (SSIM) high-lights an average similarity of 98.89 % between the generated and manually labeled images. This innovative methodology holds the promise of significantly reducing labeling efforts.

Image-based high-throughput plant phenotyping utilises various imaging techniques to automatically and non-invasively understand the growth of different plant species. These innovative imaging infrastructures are implemented to monitor plant development over time in indoor or outdoor environments. However, understanding the relationship between genotype and phenotype interactions under different environments remains challenging. This research study demonstrates superior extraction of leaf morphological features of different Arabidopsis thaliana ecotypes by analysing leaf geometry using a sequence of RGB images. Upon successful extraction of anatomical features, leaf length and area are converted into physical coordinates. Furthermore, considering these leaf features as 1D signals, the Fourier Spectrum is analysed, and most descriptive features are selected using PCA. Finally, leaf shape classification is established by training and testing five distinct ML models. A thorough evaluation of selected models demonstrates superiority in classifying two common leaf shapes of Arabidopsis plants.

ABSTRACT:Jennings, J, Štaka, Z, Wundersitz, DW, Sullivan, CJ, Cousins, SD, Čustović, E, and Kingsley, MI. Position-specific running and technical demands during male elite-junior and elite-senior Australian rules football match-play. J Strength Cond Res 37(7): 1449-1455, 2023-The aim of this study was to compare position-specific running and technical demands of elite-junior and elite-senior Australian rules football match-play to better inform practice and assist transition between the levels. Global positioning system and technical involvement data were collated from 12 Victorian U18 male NAB League ( n = 553) and 18 Australian Football League ( n = 702) teams competing in their respective 2019 seasons. Players were grouped by position as nomadic, fixed, or ruck, and data subsets were used for specific analyses. Relative total distance ( p = 0.635, trivial effect), high-speed running (HSR) distance ( p = 0.433, trivial effect), acceleration efforts ( p = 0.830, trivial effect), deceleration efforts ( p = 0.983, trivial effect), and efforts at >150 m·min -1 ( p = 0.229, trivial effect) and >200 m·min -1 ( p = 0.962, trivial effect) did not differ between elite-junior and elite-senior match-play. Elite juniors covered less total and HSR distance during peak periods (5 seconds-10 minutes) of demand ( p ≤ 0.022, small-moderate effects). Within both leagues, nomadic players had the greatest running demands followed by fixed position and then rucks. Relative disposals ( p = 0.330, trivial effect) and possessions ( p = 0.084, trivial effect) were comparable between the leagues. During peak periods (10 seconds to 2 minutes), elite juniors had less technical involvements than elite seniors ( p ≤ 0.001, small effects). Although relative running demands and positional differences were comparable between the leagues, elite juniors perform less running, HSR, and technical involvements during peak periods when compared with elite seniors. Therefore, coaching staff in elite-senior clubs should maintain intensity while progressively increasing the volume of training that recently drafted players undertake when they have transitioned from elite-junior leagues.

Our ability to interrogate and manipulate the genome far exceeds our capacity to measure the effects of genetic changes on plant traits. Much effort has been made recently by the plant science research community to address this imbalance. The responses of plants to environmental conditions can now be defined using a variety of imaging approaches. Hyperspectral imaging (HSI) has emerged as a promising approach to measure traits using a wide range of wavebands simultaneously in 3D to capture information in lab, glasshouse, or field settings. HSI has been applied to define abiotic, biotic, and quality traits for optimisation of crop management.

Epilepsy is a widely known neurological disease, causing atypical brain activity such as seizures. Apparently, it is critical to analyse possible triggers as well as establish appropriate medical treatment based on the seizure type. In general, diagnosis of epilepsy is usually conducted by applying various state-of-the-art algorithms to extract useful information from electroencephalography (EEG) signals. For effective real-time epilepsy diagnosis, the biomedical device integrated with the best performing machine learning algorithm is needed. Multilayer Perceptron (feed-forward) Artificial Neural Network (MLP-ANN) has proven to be a much better choice over traditional supervised machine learning algorithms in achieving high accuracy diagnosis. Challenges exist in handling extremely long data processing time in the case of many features in EEG signals plus complex MLP-ANN structure and computations. This research proposes the 5-12-3 MLP-ANN configuration to classify different types of epileptic seizures using Field Programmable Gate Array (FPGA) as a real-time embedded system

Noninvasive imaging ranging from 400 to 2400 nm is used to define plant traits and link them to the abundant genomic data. The type of approach used depends on a number of factors and imaging methods can be combined to span broad scales. Platforms are broadly categorised by their adaption to field conditions or indoor settings. Field applications (including aerial and ground-based cameras and sensors attached to satellites, aeroplanes, unmanned aerial vehicles, drones, or tractors) provide remote sensing to estimate crop yield and monitor growing crops over large geographic areas. Indoor applications within greenhouses, controlled environment rooms, and laboratories use mostly fixed systems and handheld devices to measure plant growth rate, estimate biomass, detect crop stress, measure physiological and biochemical traits, study the viability of seeds, and characterise root systems for individual plants.

The magnitude of soft error rate (SER) of integrated circuits (ICs) utilized in space missions is jeopardized due to the inconsistent intensity of radiation exposure. To protect critical electronic elements and ensure desired system performance, it is necessary to establish the real-time detection of space particle events (SPE). This research study assesses eight supervised machine learning algorithms by varying history data length (3 to 24 hours) to predict the occurrence of SPE one hour ahead. Customized SPE hourly predictor based on logistic regression is chosen for hardware implementation owing to high prediction accuracy (96.35%) as well as simplicity. After that, the optimal prototype design of the logistic regression algorithm is implemented on Field Programmable Gate Array (FPGA) with affordable hardware footprint. Finally, the digital design tested on FPGA is simulated to generate an application-specific integrated circuit (ASIC) chip layout (industrial 130 nm) integrated with SPE hourly predictor.

Solar Particle Events (SPEs) generate cosmic radiation of different magnitude in a time span of several hours or even days. This contributes to an increased probability of higher magnitude Single-Event Upsets (SEUs) occurrence in space applications. It is critical to establish early detection of SEU rate or Soft Error Rate (SRE) changes to enable timely radiation hardening measures. This research paper focuses on the high-accuracy detection of SPEs using the manually collected space data. Additionally, the prediction of SRE increase or decrease was established with the seven widely used supervised machine learning algorithms. Excellent performance of 97.82%, including a high F1-score, was achieved during the presence of SPE using $k$ -Nearest Neighbor algorithms.

Staunton, CA, Stanger, JJ, Wundersitz, DW, Gordon, BA, Custovic, E, and Kingsley, MI. Criterion validity of a MARG sensor to assess countermovement jump performance in elite basketballers. J Strength Cond Res 35(3): 797-803, 2021-This study assessed the criterion validity of a magnetic, angular rate, and gravity (MARG) sensor to measure countermovement jump (CMJ) performance metrics, including CMJ kinetics before take-off, in elite basketballers. Fifty-four basketballers performed 2 CMJs on a force platform with data simultaneously recorded by a MARG sensor located centrally on the player's back. Vertical accelerations recorded from the MARG sensor were expressed relative to the direction of gravity. Jumps were analyzed by a blinded assessor and the best jump according to the force platform was used for comparison. Pearson correlation coefficients (r) and mean bias with 95% ratio limits of agreement (95% RLOA) were calculated between the MARG sensor and the force platform for jumps performed with correct technique (n = 44). The mean bias for all CMJ metrics was less than 3%. Ninety-five percent RLOA between MARG- and force platform-derived flight time and jump height were 1 +/- 7% and 1 +/- 15%, respectively. For CMJ performance metrics before takeoff, impulse displayed less random error (95% RLOA: 1 +/- 13%) when compared with mean concentric power and time to maximum force displayed (95% RLOA: 0 +/- 29% and 1 +/- 34%, respectively). Correlations between MARG and force platform were significant for all CMJ metrics and ranged from large for jump height (r = 0.65) to nearly perfect for mean concentric power (r = 0.95). Strong relationships, low mean bias, and low random error between MARG and force platform suggest that MARG sensors can provide a practical and inexpensive tool to measure impulse and flight time-derived CMJ performance metrics.

The application of serious games (SGs) has shown significant improvements in the education of both children without disorders and children with disorders such as autism. The major advantage of SGs over the traditional teaching approach is the possibility to boost motivation and engagement of children during the learning process. Currently, formal educational systems of many developed countries integrate SGs into primary and secondary schools. This re-search focuses on developing a 3D game called Colorful Classroom to enable children learn letters of the English alphabet, colors and numbers. The entire concept of the game is established using the Unity Engine, and all 3D models, including classroom and other objects, are modelled from scratch in Maya Autodesk. Evaluation of the game was conducted on two testing samples com-posed of typically developing, mentally delayed and autistic children. The findings show progressive learning of both tested groups and positive feed-back from teachers regarding the game design and logic. Finally, the game described in this research paper could be enhanced by designing more classes in different lessons.

Owing to the significant increase of tobacco products, smoking becomes the most common risk factor responsible for causing chronic disease such as lung cancer, pulmonary and coronary artery diseases. This research study focuses on extensive data analysis throughout four different hypotheses regarding tobacco consumption among different age groups and professions. Before hypotheses testing, an online survey is made to collect raw data about cigarette smoking. Afterwards, the final processed dataset is created, and some useful probability statements are derived and calculated by applying well-known statistical methods. Finally, the first three hypotheses are tested using IBM SPSS software environment including one-way Analysis of Variance (ANOVA) tool and Two-Tailed t-test. The final hypothesis is examined using the correlation matrix and developing a regression data model based on a linear correlation between independent variables of interest.

The paper aims to apply a decision tree based machine learning algorithm to predict possible alcohol addicts among high school students. The data mining process is performed on the real-world data collected in two high schools in Portugal. The dataset is originally designed for the estimation of high school student’s performance where alcohol consumption is used as one of the parameters. In the implementation phase, KNIME analytics platform is applied to test the model. The significant part represents preprocessing of data where the new attributes are derived including class attribute labeled using alcohol addict matrix. Afterwards, the linear correlation is used to reduce the number of features. Data processing consists of dividing the dataset into training and test data, making artificial data for training phase and lastly analyzing the outputs of decision tree learner and predictor. Constructed decision tree determines the connections between certain attributes and student alcohol consumption. Finally, the overall accuracy of the model is measured using a confusion matrix.

Assessment of skeletal maturity is typical strategy applied in clinical pediatrics today. The main goal of a Bone Age Assessment (BAA) is to determine endocrinology and growth disorders by comparing the bone and chronological age of the patient. Several methods are developed to determine skeletal maturity, but Greulich-Pyle and Tanner-Whitehouse represent the two most common methods that involve left hand and wrist radiographs. However, these methods are extremely time-dependent and rely on an experienced radiologist, who further evaluates bone age using hand atlas as a reference. In this paper, VGG-16 and ResNet50 are two Deep Convolutional Neural Network (DCNN) models applied with ImageNet pre-trained weights in order to estimate correct bone age and achieve high accuracy of gender prediction using public RSNA dataset that includes 12611 radiographs. The experimental results show month discrepancy of approximately eight months and 82% accuracy during the process of gender classification.

The parametric identification is the primary consideration in developing a sophisticated automated control system. However, most tuning and system identification methods require the use of non-standard equipment such as relay which could cause a significant error and in turn affect the accuracy of the entire industrial process. The novel approach to the system identification in closed-loop feedback is similar to old Ziegler-Nichols (ZN) experiment, but it does not include any additional equipment while identifying the points in three quadrants in the Nyquist diagram. After applying this method to identify one complex object i.e. servomechanism with only damped oscillations, it is necessary to validate the correctness of the obtained model. Conducting the laboratory experiment in the open-loop loop represents the best way of verifying stated approach, since the transfer function including the Nyquist diagram of the model may provide enough data for further analysis. The verification laboratory experiments confirmed applicability together with the effectiveness of the new method in considerably less idealized conditions compared to computer-based simulations.

The process of experimental identification refers to a challenging task since most of the closed-loop identification methods depend on some existing knowledge of the controlled object. Although various identification methods have been described and implemented in the past, the common issue refers to the use of nonlinear equipment such as relays that may cause an undesirable error and consequently affect the accuracy of the controlled object. The main aim of this research is to conduct experimental verification of a novel approach to linear system identification in the closed-loop feedback system. The novel approach represents an extension to the Ziegler-Nichols experiment performed in the closed-loop feedback system, but without using any additional equipment. One servomechanism composed of two motors is used as an object of identification where data acquisition is performed using a dSPACE embedded module allowing real-time reading of measurement results. The conducted experiment succeeds in locating a representative number of points in the Nyquist plot bringing only damped oscillations. Finally, the considered motor is identified as a first-order object due to the dynamic of available mechanical as well as electrical subsystems.