With the advancement of photoelectric technology and computer image processing technology, the visual measurement method based on point clouds is gradually applied to the 3D measurement of large workpieces. Point cloud registration is a key step in 3D measurement, and its registration accuracy directly affects the accuracy of 3D measurements. In this study, we designed a novel MPCR-Net for multiple partial point cloud registration networks. First, an ideal point cloud was extracted from the CAD model of the workpiece and was used as the global template. Next, a deep neural network was used to search for the corresponding point groups between each partial point cloud and the global template point cloud. Then, the rigid body transformation matrix was learned according to these correspondence point groups to realize the registration of each partial point cloud. Finally, the iterative closest point algorithm was used to optimize the registration results to obtain a final point cloud model of the workpiece. We conducted point cloud registration experiments on untrained models and actual workpieces, and by comparing them with existing point cloud registration methods, we verified that the MPCR-Net could improve the accuracy and robustness of the 3D point cloud registration.

Performing predictive maintenance (PdM) is challenging for many reasons. Dealing with large datasets which may not contain run-to-failure data (R2F) complicates PdM even more. When no R2F data are available, identifying condition indicators (CIs), estimating the health index (HI), and thereafter, calculating a degradation model for predicting the remaining useful lifetime (RUL) are merely impossible using supervised learning. In this paper, a 3 dof delta robot used for pick and place task is studied. In the proposed method, autoencoders (AEs) are used to predict when maintenance is required based on the signal sequence distribution and anomaly detection, which is vital when no R2F data is available. Due to the sequential nature of the data, non-linearity of the system, and correlations between parameter time series, convolutional layers are used for feature extraction. Thereafter, a sigmoid function is used to predict the probability of having an anomaly given CIs acquired from AEs. This function can be manually tuned given the sensitivity of the system or optimized by solving a minimax problem. Moreover, the proposed architecture can be used for fault localization for the specified system. Additionally, the proposed method is capable of calculating RUL using Gaussian process (GP), as a degradation model, given HI values as its input.

Animal welfare is not only an ethically important consideration in good animal husbandry, but can also have a significant effect on an animal’s productivity. The aim of this paper is to show that a reduction in animal welfare, in the form of increased stress, can be identified in pigs from frontal images of the animals. We train a Convolutional Neural Network (CNN) using a leave-one-out design and show that it is able to discriminate between stressed and unstressed pigs with an accuracy of >90% in unseen animals. Grad-CAM is used to identify the animal regions used, and these support those used in manual assessments such as the Pig Grimace Scale. This innovative work paves the way for further work examining both positive and negative welfare states with a view to the development of an automated system that can be used in precision livestock farming to improve animal welfare.

A foundational model has been developed based on trends built from empirical data of space exploration and computing power through the first six plus decades of the Space Age which projects earliest possible launch dates for human-crewed missions from cis-lunar space to selected Solar System and interstellar destinations. The model uses computational power, expressed as transistors per microprocessor, as a key broadly limiting factor for deep space missions’ reach and complexity. The goal of this analysis is to provide a projected timeframe for humanity to become a multi-world species through off-world colonization, and in so doing all but guarantees the long-term survival of the human race from natural and human-caused calamities that could befall life on Earth. Be-ginning with the development and deployment of the first nuclear weapons near the end of World War II, humanity entered a ‘Window of Peril’ which will not be safely closed until robust off-world colonies become a reality. Our findings suggest the first human-crewed missions to land on Mars, selected Asteroid Belt objects, and selected moons of Jupiter and Saturn can occur before the end of the 21^st century. Launches of human-crewed interstellar missions to exoplanet destinations within roughly 40 lightyears of the Solar System are seen as possible during the 23^rd century and launch of intragalactic missions by the end of the 24^th century. An aggressive and sustained space exploration program, which includes colonization, is thus seen as critical to the long-term survival of the human race.

A method of direction-of-arrival (DoA) estimation for FMCW radars is presented. In addition to MUSIC and ESPRIT, which are well-known high-resolution DoA estimation algorithms, deep learning has recently emerged as a very promising alternative. It is proposed in this paper to use a 3D convolutional neural network (CNN) for DoA estimation. The 3D-CNN extracts from the radar data cube spectrum features of the region of interest (RoI) centered on the potential positions of the targets, thereby capturing the spectrum phase shift information, which corresponds to DoA, along the antenna axis. Finally, the results of simulations and field experiments are provided to demonstrate the superior performance, as well as the limitations, of the proposed 3D-CNN.

The world's growing population is highly dependent on animal agriculture. Animal products provide nutrient-packed meals that help to sustain individuals of all ages in communities across the globe. As the human demand for animal proteins grows, the agricultural industry must continue to advance its efficiency and quality of production. One of the most commonly farmed livestock is poultry and their significance is felt on a global scale. Current poultry farming practices result in the premature death and rejection of billions of chickens on an annual basis before they are processed for meat. This loss of life is concerning regarding animal welfare, agricultural efficiency, and economic impacts. The best way to prevent these losses is through the individualistic and/or group level assessment of animal on a continuous basis. On large-scale farms, such attention to detail was generally considered to be inaccurate and inefficient, but with the integration of Artificial Intelligence (AI) assisted technology individualized and per-herd assessments of livestock are possible and accurate. Various studies have shown cameras linked with specialized systems of AI can properly analyze flocks for health concerns, thus improving the survival rate and product quality of farmed poultry. Building on the recent advancements, this review explores the aspects of AI in the detection, counting and tracking of the poultry in commercial and research-based applications.

Phenotypes are driven by regulated gene expression, which in turn are mediated by complex interactions between diverse biological molecules. Protein-DNA interactions such as histone and transcription factor binding are well studied, along with RNA-RNA interactions in short RNA silencing of genes. In contrast, lncRNA-protein interaction (LPI) mechanisms are comparatively unknown, likely driven by the difficulties in studying LPI. However, LPI are emerging as key interactions in epigenetic mechanism, playing a role in development and disease. Their importance is further highlighted by their conservation across kingdoms. Hence, interest in LPI research is increasing. We therefore review the current state of the art in lncRNA-protein interactions. We specifically surveyed recent computational methods and databases which researchers can exploit for LPI investigation. We discovered that algorithm development is heavily reliant on a few generic databases containing curated LPI information. We show that early methods predict LPI using molecular docking, have limited scope and are slow, creating a data processing bottleneck. Recently, machine learning has become the strategy of choice in LPI prediction, likely due to the rapid growth in machine learning infrastructure and expertise. While many of these methods have notable limitations, machine learning is expected to be the basis of modern LPI prediction algorithms.

Since the launch of Protein Data Bank (PDB) in 1971, Cartesian coordinate system (CCS) has been the default approach to specify atomic positions in biomolecular experimental structures with X, Y and Z. In 2020, a local spherical coordinate system (LSCS) approach was proposed as an alternative to CCS, i.e., ρ, θ and φ. Recently, the continued application of deep learning technology in protein structure prediction (PSP) saw a leap forward in the accuracy of PSP, as evidenced by AlphaFold of Google’s DeepMind. However, there still is room for the improvement of the performances of PSP algorithms to date. Given that geometrically, CCS and LSCS are like the two sides of a coin, this short article puts forward a hypothesis that the time is now ripe to end the half-a-century burial of ρ, θ and φ in PDB, and use them as LSCS features for the design of novel PSP algorithms in future.

The analysis of microscopy images has always been an important yet time consuming process in in materials science. Convolutional Neural Networks (CNNs) have been very successfully used for a number of tasks, such as image segmentation. However, training a CNN requires a large amount of hand annotated data, which can be a problem for material science data. We present a procedure to generate synthetic data based on ad-hoc parametric data modelling for enhancing generalization of trained neural network models. Especially for situations where it is not possible to gather a lot of data, such an approach is beneficial and may enable to train a neural network reasonably. Furthermore, we show that targeted data generation by adaptively sampling the parameter space of the generative models gives superior results compared to generating random data points.

Substances that can modify the androgen receptor pathway in humans and animals are entering the environment and food chain with the proven ability to disrupt hormonal systems and leading to toxicity and adverse effects on reproduction, brain development, and prostate cancer, among others. State-of-the-art databases with experimental data of human, chimp, and rat effects by chemicals have been used to build machine learning classifiers and regressors and evaluate these on independent sets. Different featurizations, algorithms, and protein structures lead to dif- ferent results, with deep neural networks (DNNs) on user-defined physicochemically-relevant features developed for this work outperforming graph convolutional, random forest, and large featurizations. The results show that these user-provided structure-, ligand-, and statistically-based features and specific DNNs provided the best results as determined by AUC (0.87), MCC (0.47), and other metrics and by their interpretability and chemical meaning of the descriptors/features. In addition, the same features in the DNN method performed better than in a multivariate logistic model: validation MCC = 0.468 and training MCC = 0.868 for the present work compared to evalu- ation set MCC = 0.2036 and training set MCC = 0.5364 for the multivariate logistic regression on the full, unbalanced set. Techniques of this type may improve AR and toxicity description and predic- tion, improving assessment and design of compounds. Source code and data are available at https://github.com/AlfonsoTGarcia-Sosa/ML

For the Remotely Piloted Aircraft Systems (RPAS) market to continue its current growth rate, cost-effective "Detect and Avoid" systems that enable safe beyond visual line of sight (BVLOS) operations are critical. We propose an audio-based "Detect and Avoid" system, composed of microphones and an embedded computer, which performs real-time inferences using a sound event detection (SED) deep learning model. Two state-of-the-art SED models, YAMNet and VGGish, are fine-tuned using our dataset of aircraft sounds and their performances are compared for a wide range of configurations. YAMNet, whose MobileNet architecture is designed for embedded applications, outperformed VGGish both in terms of aircraft detection and computational performance. YAMNet's optimal configuration, with > 70% true positive rate and precision, results from combining data augmentation and undersampling with the highest available inference frequency (i.e. 10 Hz). While our proposed "Detect and Avoid" system already allows the detection of small aircraft from sound in real time, additional testing using multiple aircraft types is required. Finally, a larger training dataset, sensor fusion, or remote computations on cloud-based services could further improve system performance.

In cognitive radio systems, identifying spectrum opportunities is fundamental to efficiently use the spectrum. Spectrum occupancy prediction is a convenient way of revealing opportunities based on previous occupancies. Studies have demonstrated that usage of the spectrum has a high correlation over multidimensions which includes time, frequency, and space. Accordingly, recent literature uses tensor-based methods to exploit the multidimensional spectrum correlation. However, these methods share two main drawbacks. First, they are computationally complex. Second, they need to re-train the overall model when no information is received from any base station for any reason. Different than the existing works, this paper proposes a method for dividing the multidimensional correlation exploitation problem into a set of smaller sub-problems. This division is achieved through composite two-dimensional (2D)-long short-term memory (LSTM) models. Extensive experimental results reveal a high detection performance with more robustness and less complexity attained by the proposed method. The real-world measurements provided by one of the leading mobile network operators in Turkey validate these results.

UEDVT still remains an underdiagnosed entity due to a significant percentage of patients who remain asymptomatic. The etiology of UEDVT is overwhelmingly attributed to secondary causes including but not limited to central venous access devices and malignancy. Treatment modalities include anticoagulation, catheter directed thrombolysis, percutaneous mechanical thrombectomy or a multimodality approach along with the management of underlying etiology. We describe a case of a female with breast cancer, who came with left UEDVT and CVC malfunction and was successfully treated using the ClotTriever system to maintain continuous intravenous access.

Accurate and efficient traffic incident detection methods can effectively alleviate traffic congestion caused by traffic incidents, prevent secondary accidents and improve the safety of urban road traffic.Aiming at the problems that the traditional machine learning event detection method cannot fully extract the parameter characteristics of traffic flow and is not suitable formulti-dimensional and non-linear massive data, we propose a new traffic event detection method(CNN-XGBoost).This method combines the respective advantages of Convolution Neural Network(CNN) and Extreme Gradation Boosting (XGBoost). Firstly, we preprocessed the original freeway traffic incident detection data set by constructing initial variable set, data normalization, data balance processing and dimension reorganization. Secondly,we use CNN network to automatically extract the deep features of event detection data, and use XGBoost as a classifier to classify the extracted features for expressway traffic event detection.Finally, we use the data set of Hangzhou expressway microwave detector in China to carry out simulation experiments on CNN-XGBoost. The experimental results show that compared with XGBoost, CNN, Support Vector Machine (SVM) and Gradient Boosting Decision Tree (GBDT) and other methods, CNN-XGBoost method can effectively improve the accuracy of expressway traffic event detection and has better generalization ability.

The power converter is the significant device in a wind power system. Wind turbine will be shut down and off grid immediately with the occurrence of the IGBT module open-circuit fault of power converter, which will seriously impact the stability of grid and even threaten personal safety. However, in the existing diagnosis strategies of power converter, there are few single and double IGBT modules open-circuit fault diagnosis methods producing negative results including erroneous judgment, omissive judgment and low accuracy. In this paper, a novel method to diagnose the single and double IGBT modules open-circuit faults of the permanent magnet synchronous generator (PMSG) wind turbine grid-side converter (GSC) is proposed. Above all, collecting the three-phase current varying with wind speed of 22 failure states including a normal state of PMSG wind turbine GSC as the original signal data. Afterward, the original signal data are decomposed by using variational mode decomposition (VMD) to obtain the mode coefficient series, which are analyzed by the proposed method base on fault trend feature for extracting the trend feature vectors. Finally, the trend feature vectors are used as the input of deep belief network (DBN) for decision-making and obtaining the classification results. The simulation and experimental results show that the proposed method can diagnose the single and double IGBT modules open-circuit faults of GSC, and the accuracy is higher than the benchmark models.

As one of GEO-constellation for environmental monitoring in the next decade, Geostationary Environment Monitoring Spectrometer (GEMS) is designed to observe the Asia Pacific region to provide the information on the atmospheric chemicals, aerosol and cloud properties. For the continuous monitoring of the sensor performance after its launch in early 2020, here we suggest deep convective clouds (DCCs) as a possible target for the vicarious calibration of GEMS, the first UV/VIS hyperspectral sensor onboard a geostationary satellite. Tropospheric Monitoring Instrument (TROPOMI) and Ozone Monitoring Instrument (OMI) are used as a proxy of GEMS, and a conventional DCC detection approach applying the thermal threshold test is used for the DCC detection based on the collocations with Advance Himawari-8 Imager (AHI) onboard Himawari-8 geostationary satellite. DCCs are frequently detected over the GEMS observation area on average over 200 pixels in a single observation scene. Considering the spatial resolution of GEMS, 3.5 km×7 km which is similar to TROPOMI, and its temporal resolution (8 times a day), availability of DCCs for vicarious calibration of GEMS is expected to be sufficient. Inspection of the DCC reflectivity spectra estimated from the OMI and TROPOMI data also shows a promising result. Even though, their observation geometry and sensor characteristics are quite a different, the estimated DCC spectra agree quite a well within a known uncertainty range with comparable spectral features. When the DCC detection is further improved by applying both visible and infrared tests, the variability of DCC reflectivity from the TROPOMI data is reduced by half, from 10% to 5%. This is mainly due to the efficient screening of cold thin cirrus with the visible test and of bright warm clouds with the infrared test. The precise DCC detection is also expected to contribute to the accurate characterization of the cloud reflectivity, which will be further investigated.

An application of deep convolutional neural network and recurrence plot for financial market movement prediction is presented. Though it is challenging and subjective to interpret its information, the pattern formed by a recurrence plot provide a useful insight into the dy- namical system. We used a recurrence plot of seven financial time series to train a deep neural network for financial market movement predic- tion. Our approach is tested on our dataset and achieved an average of 53.25% classification accuracy. The result suggests that a well trained deep convolutional neural network can learn a recurrence plot and pre- dict a financial market direction.

Appropriate vaccine selection is crucial in the control of foot-and-mouth disease (FMD). Vaccination can prevent clinical disease and reduces viral shedding, but there is a lack of cross-protection between the seven serotypes and their sublineages, making the selection of an adequately protective vaccine difficult. Since the exact composition of their vaccines is not consistently disclosed by all manufacturers, incompatibility of the strains used for vaccination with regionally circulating strains can cause vaccination campaigns to fail. Here, we present a deep sequencing approach for polyvalent inactivated FMD vaccines that can identify all component strains by their genome sequences. The genomes of all strains of a commercial pentavalent FMD vaccine were de-novo assembled and the vaccine composition determined semi-quantitatively. The genome assembly required high stringency parameters to prevent misassemblies caused by conserved regions of the genome shared by related strains. In contrast, reference-guided assembly is only recommended in cases where the number of strains is previously known and appropriate reference sequences are available. The presented approach can be applied not only to any inactivated whole-virus FMD vaccine, but also to vaccine quality testing in general and allows for better decision-making for vaccines with unknown composition.

Although proposition of “Virtual Reality” (VR) and “Augment Reality” (AR) can be traced back to the 60s, both areas are actually blooming in recent decades. Thanks to the latest deep learning techniques, an enormous advance in computer vision research community has taken place. Since VR and AR are highly related to computer vision tasks, these areas have enjoyed the benefits as well. Yet there is no sufficient survey on such impact and new research areas arising from it. This paper mainly focuses on the latest research progress in ACM Symposium on Eye Tracking Research & Applications (ETRA) 2019, as well as several recent representative paper works. It aims to figure out the influence of deep learning techniques on latest VR/AR research. Meanwhile, new issues have popped up with the development of VR and AR technology, such as privacy and computation efficiency. This paper draws attention to such newly produced topics as well. In addition, this paper also investigates on the effect of latest VR and AR techniques on people, such as level of teamwork in collaborative tasks, assistance and treatment to patients and the disabled, etc.

The speech entailed in human voice comprises essentially para-linguistic information used in many voice-recognition applications. Gender voice-recognition is considered one of the pivotal parts to be detected from a given voice, a task that involves certain complications. In order to distinguish gender from a voice signal, a set of techniques have been employed to determine relevant features to be utilized for building a model from a training set. This model is useful for determining the gender (i.e, male or female) from a voice signal. The contributions are involved in two folds: (i) providing analysis information about well-known voice signal features using a prominent dataset, (ii) studying various machine learning models of different theoretical families to classify the voice gender, and (iii) using three prominent feature selection algorithms to find promisingly optimal features for improving classification models. Experimental results show the importance of sub-features over others, which are vital for enhancing the efficiency of classification models performance. Experimentation reveals that the best recall value is equal to 99.97%; 99.7% of two models of Deep Learning (DL) and Support Vector Machine (SVM) and with feature selection the best recall value is 100% for SVM techniques.

Polar mesocyclones (MCs) are small marine atmospheric vortices. The class of intense MCs, called polar lows, are accompanied by extremely strong surface winds and heat fluxes and thus largely influencing deep ocean water formation in the polar regions. Accurate detection of polar mesocyclones in high-resolution satellite data, while challenging, is a time-consuming task, when performed manually. Existing algorithms for the automatic detection of polar mesocyclones are based on the conventional analysis of patterns of cloudiness and involve different empirically defined thresholds of geophysical variables. As a result, various detection methods typically reveal very different results when applied to a single dataset. We develop a conceptually novel approach for the detection of MCs based on the use of deep convolutional neural networks (DCNNs). As a first step, we demonstrate that DCNN model is capable of performing binary classification of 500x500km patches of satellite images regarding MC patterns presence in it. The training dataset is based on the reference database of MCs manually tracked in the Southern Hemisphere from satellite mosaics. We use a subset of this database with MC diameters falling in the range of 200-400 km. This dataset is further used for testing several different DCNN setups, specifically, DCNN built “from scratch”, DCNN based on VGG16 pre-trained weights also engaging the Transfer Learning technique, and DCNN based on VGG16 with Fine Tuning technique. Each of these networks is further applied to both infrared (IR) and a combination of infrared and water vapor (IR+WV) satellite imagery. The best skills (97% in terms of the binary classification accuracy score) is achieved with the model that averages the estimates of the ensemble of different DCNNs. The algorithm can be further extended to the automatic identification and tracking numerical scheme and applied to other atmospheric phenomena characterized by a distinct signature in satellite imagery.

Preliminaries Convolutional Neural Network (CNN) applications have recently emerged in Structural Health Monitoring (SHM) systems focusing mostly on vibration analysis. However, the SHM literature shows clearly that there is a lack of application regarding the combination of PZT (Lead Zirconate Titanate) based method and CNN. Likewise, applications using CNN along with the Electromechanical Impedance (EMI) technique applied to SHM systems are rare. To encourage this combination, an innovative SHM solution through the combination of the EMI-PZT and CNN is presented here. To accomplish this, the EMI signature is split into several parts followed by computing the Euclidean distances among them to form a RGB (red, green and blue) frame. As a result, we introduce a dataset formed from the EMI-PZT signals of 720 frames, encompassing a total of 4 types of structural conditions for each PZT. In a case study, the CNN-based method was experimentally evaluated using three PZTs glued onto an aluminum plate. The results reveal an effective pattern classification; yielding a 100% hit rate which outperforms other SHM approaches. Furthermore, the method needs only a small dataset for training the CNN, providing several advantages for industrial applications.

Oscillometric blood pressure (BP) devices currently estimate a single point but do not identify fluctuations in BP or distinguish them from variations in response to physiological properties. In this paper, to analyze BP normality based on oscillometric measurements, we use statistical approaches including kurtosis, skewness, Kolmogorov-Smirnov, and correlation tests. Then, to mitigate uncertainties, we use a deep neural network (DNN) to determine the confidence limits (CLs) of BP measurements based on their normality. The proposed DNN regression model decreases the standard deviation of error (SDE) of the mean error (ME) and the mean absolute error (MAE) and reduces the uncertainty of the CLs and SDEs of the proposed technique. We validate the normality of the distribution of the BP estimation distribution which fits the Gaussian distribution very well. We use a rank test in the DNN regression model to demonstrate the independence of the artificial SBP and DBP estimations. First, we perform statistical tests to verify the normality of the BP measurements for individual subjects. The proposed methodology provides accurate BP estimations and reduces the uncertainties associated with the CLs and SDEs based on the DNN regression estimator.

The enantioselective alpha-amination of 1,3-dicarbonyl compounds has been performed using a catalytic system based on deep eutectic solvents (DES) and chiral 2-amino benzimidazole-derived organocatalysts. This procedure avoids the use of toxic volatile organic compounds (VOCs) as a reaction medium, providing access to highly functionalized chiral molecules, which are important intermediates for the natural product synthesis, in a selective and efficient manner. Furthermore, the reaction can be performed on a large scale and recycling the catalytic system is possible for at least five times, leading to a clean, cheap, simple, and scalable procedure that meets most of the criteria required to be a green and sustainable process.

Mice are not natural hosts for influenza A viruses (IAVs), but they are useful models for studying antiviral immune responses and pathogenesis. Serial passage of IAV in mice invariably causes the emergence of adaptive mutations and increased virulence. Typically, mouse-adaptation studies are conducted in inbred laboratory strains BALB/c and C57BL/6, which have defects in the antiviral Mx1 gene that results in increased susceptibility to infection and disease severity. Here, we report the adaptation of IAV reference strain A/California/07/2009(H1N1) (a.k.a. CA/07) in outbred Swiss Webster mice. Serial passage led to increased virulence and lung titers, and dissemination of the virus to brains. We adapted a deep-sequencing protocol to identify and enumerate adaptive mutations across all genome segments. Among mutations that emerged during mouse-adaptation, we focused on amino acid substitutions in polymerase subunits: polymerase basic-1 (PB1) T156A and F740L, and polymerase acidic (PA) E349G. These mutations were evaluated singly and in combination in minigenome replicon assays, which revealed that PA E349G increased polymerase activity. By selectively engineering these three adaptive PB1 and PA mutations into the parental CA/07 strain, we demonstrated that adaptive mutations in polymerase subunits decreased the production of defective viral genome segments with internal deletions, and dramatically increased the release of infectious virions from mouse cells. Together, these findings increase our understanding of the contribution of polymerase subunits to successful host adaptation.

Phosphorylation reactions of glycerol were studied using different inorganic phosphates such as sodium phosphate, trimetaphosphate (a condensed phosphate), and struvite. The reactions were carried out in two non-aqueous solvents: formamide and a eutectic solvent consisting of choline chloride and glycerol in a ratio of 1:2.5. The glycerol reacted in formamide and in the eutectic solvent with phosphate to yield its phosphorylated derivatives in the presence of silicates such as quartz sand and kaolinite clay. The reactions were carried out by heating glycerol with a phosphate source at 85 °C for one week and were analyzed by 31P nuclear magnetic resonance (NMR) spectroscopy and mass spectrometry (MS). The yield of the phosphorylated glycerol was improved by the presence of silicates, and reached 90% in some experiments. Our findings further support the proposal that non-aqueous solvents are advantageous for the prebiotic synthesis of biomolecules, and suggest that silicates may have aided in the formation of organophosphates on the prebiotic earth.

Face verification for unrestricted faces in the wild is a challenging task. This paper proposes a method based on two deep convolutional neural networks(CNN) for face verification. In this work, we explore to use identification signal to supervise one CNN and the combination of semi-verification and identification to train the other one. In order to estimate semi-verification loss at a low computation cost, a circle, which is composed of all faces, is used for selecting face pairs from pairwise samples. In the process of face normalization, we propose to use different landmarks of faces to solve the problems caused by poses. And the final face representation is formed by the concatenating feature of each deep CNN after PCA reduction. What's more, each feature is a combination of multi-scale representations through making use of auxiliary classifiers. For the final verification, we only adopt the face representation of one region and one resolution of a face jointing Joint Bayesian classifier. Experiments show that our method can extract effective face representation with a small training dataset and our algorithm achieves 99.71% verification accuracy on LFW dataset.

As UAVs are increasingly employed across various industries, the demand for robust and accurate detection has become crucial. LiDAR has developed as a vital sensor technology because to its ability to offer rich 3D spatial information, particularly in applications such as security and airspace monitoring. This review systematically explores recent innovations in LiDAR-based drone detection, deeply focusing on the principle and components of LiDAR sensor, its classifications based on different parameters and scanning mechanisms, as well as the approaches for processing LiDAR data. The review briefly compares several deep learning approaches, including point-based, voxel-based, and hybrid models, that have improved drone detection, tracking, and classification. We also explore the integration of multi-modal sensor fusion, which combines LiDAR data with other complimentary modalities to improve UAV detection and tracking in complex environments such as GNSS-denied zones.

The application of deep learning convolutional neural networks (CNNs) for rock image characterization has become a prominent method in petroleum geology both nationally and internationally. Precise and automated segmentation of rock sheet images is essential for effective analytical studies. This research addresses the limitations of traditional image segmentation methods, which suffer from low accuracy and high costs in analyzing reservoir rock flakes. We propose an advanced model based on the U-Net architecture, incorporating both attention mechanisms and residual networks. The inclusion of residual modules enhances the network's depth, while the Convolutional Block Attention Module (CBAM) improves feature representation by adjusting the weighting of learned information. Extensive experimental results demonstrate that this approach delivers superior segmentation performance, marking a significant advancement in the field of reservoir rock image analysis.

Fundus vascular images are essential for diagnosing various ophthalmic diseases. With deep learning and image processing development, fundus image segmentation methods based on computer vision have become more common. However, the UNet model faces challenges such as the loss of spatial resolution during downsampling and difficulties in simultaneously capturing global context and local details, especially for small objects and complex boundaries. We propose the Detail Enhanced Temporal Fusion Network (DETF-Net) to overcome these issues. This network incorporates a detail feature enhancement module (DFEM) to preserve boundary features and a dynamic temporal fusion module (DTFM) to improve robustness across different scales. The DFEM uses median pooling, spatial attention, and hybrid convolution to retain detail, while the DTFM extracts local and global features and adapts to dynamic changes in blood vessel structures. Evaluation on DRIVE, CHASE_DB1, and STARE datasets shows that DETF-Net achieves accuracy of 0.9865, 0.9877, and 0.9878, and specificity of 0.9865, 0.9870, and 0.9875, respectively, outperforming existing models. These results demonstrate DETF-Net's effectiveness in fundus image segmentation.

Liver disease can significantly impact life expectancy, making early diagnosis and therapeutic intervention critical challenges in medical care. Imaging diagnostics play a crucial role in diagnosing and managing liver diseases. Recently, the application of artificial intelligence (AI) in medical imaging analysis has become indispensable for healthcare. AI, trained on vast datasets of medical images, has sometimes demonstrated diagnostic accuracy that surpasses human experts. AI-assisted imaging diagnostics are expected to contribute significantly to the standardization of diagnostic quality. Furthermore, AI has the potential to identify image features imperceptible to humans, thereby playing an essential role in clinical decision-making. This capability enables physicians to formulate more accurate diagnoses and develop effective treatment strategies, ultimately improving patient outcomes. Additionally, AI is anticipated to become a powerful tool in personalized medicine. By integrating individual patient imaging data with clinical information, AI can propose optimal treatment plans, making it an essential component in providing the most appropriate care for each patient. Current reports highlight the advantages of AI in managing liver diseases. As AI technology continues to evolve, it is expected to further advance personalized diagnostics and treatments, contributing to overall improvements in healthcare quality.

Machine unlearning, the process of removing the influence of specific data points from trained machine learning models, has become increasingly important in light of modern data privacy regulations, such as the GDPR and the "right to be forgotten." This paper explores the challenges and solutions associated with implementing machine unlearning in three widely used neural network architectures: Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), and Graph Neural Networks (GNNs). Each of these networks presents unique challenges due to their distinct architectures and learning processes. Techniques such as selective retraining, influence functions, and knowledge distillation have been proposed to address these challenges. The paper also introduces the concept of full parameter unlearning, which adjusts all trainable parameters using two key techniques: gradient ascent based on first-order information and Fisher information based on second-order information. These methods ensure comprehensive unlearning, but also introduce computational complexity. We discuss examples, potential solutions, and future research directions to make full parameter unlearning more scalable and efficient, thus providing a framework for balancing data privacy with model performance.

Stock price prediction is of great significance but faces numerous challenges. In this study, a hybrid CNN-LSTM model was utilized. The stock data were processed and feature engineering was conducted. The model architecture and training strategies were expounded. Experimental results demonstrated that this model outperformed traditional methods and benchmark models on the test set, featuring strong capabilities in feature extraction and handling long-term dependencies. Key roles of data preprocessing, hyperparameter adjustment, and model fusion were also summarized, providing valuable references for stock price prediction.

To enhance the peak-shaving capability of the boiler, a mathematical model of hydrodynamic and wall temperature characteristics for the water-cooled wall of a 1000 MW boiler was established. The attributes pertaining to the mass flow distribution, the temperature of the effluent working fluid, pressure drop, and the thermal distribution across the wall surfaces at 30% of the boiler's maximum continuous rating (BMCR) were meticulously computed and subjected to a thorough analytical review. The findings suggest that, under the operation at 30% BMCR load, there is a substantial equilibrium in the flow distribution across the quartet of walls that constitute the water-cooled wall assembly. The maximum mass flow rate deviations in the helical and vertical sections are 1.95% and 3.47%, respectively, showing small flow deviations and reasonable distribution. The temperature deviation in the helical section is 0.3 °C, reflecting the characteristic low thermal deviation in helical tubes. While the temperature deviation at the outlet of the vertical section is higher, it remains within safe limits. The pressure loss across the water-cooled wall system amounts to 0.4 MPa. The peak wall temperature reaches 337.5°C, remaining within the material's permissible safety limits. In-depth performance analysis ensures the safe operating conditions of the water-cooled wall during low load conditions.

Information dissemination and preservation are crucial for societal progress, especially in the technological age. While technology fosters knowledge sharing, it also risks spreading misinformation. Audio deep fakes, convincingly fabricated audio using Artificial intelligence (AI), exacerbate this issue. We present Sonic Sleuth, an AI model for detecting audio deepfakes. Our approach leverages Deep Learning (DL) for a robust detection model. Meticulous data preprocessing and rigorous experimentation with various models led to the implementation of the most effective solution with a custom CNN model. Our comprehensive testing resulted in a highly accurate model (98.27% accuracy, 0.016 EER) trained on a substantial dataset of real and synthetic audio. In addition to an 84.92% accuracy and 0.085 EER on an external dataset, these results demonstrate Sonic Sleuth’s potential as a powerful tool against audio misinformation.

Inherited retinal diseases (IRDs) are clinically complex and genetically heterogeneous visual impairment disorders with varying penetrance and severity. Disease-causing variants in at least 289 nuclear and mitochondrial genes have been implicated in their pathogenesis. In the current study, we performed exome sequencing on a 51 years-old Ashkenazi Jewish patient with non-syndromic retinitis pigmentosa (RP) and identified compound heterozygous variants in the CLRN1 gene: a known pathogenic missense [p.(N48K)] and a novel deep intronic variant c.254-643G>T. A minigene splicing assay that was performed aiming to study the effect of the c.254-643G>T variant on CLRN1 pre mRNA splicing revealed the inclusion of a pseudo-exon that was also reported to be included in the transcript due to an adjacent variant, c.254-649T>G. However, unlike the reported c.254-649T>G variant, c.254-643G>T showed aberrant splicing in a leaky manner, implying that the identified variant is not totally penetrant. The non-syndromic phenotype observed in this index case may be attributed to the leaky nature of this variant, which is causing some normal transcripts to be produced. To conclude, we report on a novel deep intronic variant in CLRN1 causing non-syndromic RP.

Energy consumption is a critical issue in the energy sector, and recent events such as the global energy crisis, costs, the need to reduce greenhouse emissions, and extreme weather conditions have increased the demand for energy efficiency. Accurately predicting energy consumption is one of the key steps to addressing inefficiency in energy consumption, and its optimization. In this regard, accurate predictions of energy consumption would not only help to minimize wastage, but also to save cost. In this article, we propose intelligent models using an ensemble of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) neural networks for predicting energy consumption in smart buildings. The proposed model outperforms other state-of-the-art deep learning models for predicting minute energy consumption, with a mean square error of 0.109. The proposed model also accurately captures latent trends in the data that other models struggle to capture. The results highlight the potential of using hybrid deep learning models for improved energy efficiency management in smart buildings.

Despite the technological advancements of 3-D city models, the 3-D shape abstraction methods for urban vegetation are recent and still limited to support spatial analysis of individual or groups of trees and forest patches. In this paper, a scheme for individual urban tree abstraction, which retains the semantic complexity of the object, is proposed. Our contribution is three-fold. First, an initial tree structure based on a new 3-D aggregation operator is proposed. Second, we developed Gestalt rules for 3-D urban vegetation mapping. Third, current state-of-the-art deep learning is adapted for the abstraction of individual urban trees. Quantitative and qualitative results show the effectiveness of our proposed approach in accurately reducing the spatial density of trees and the degree of fragmentation of the total green area, which can access information about the location, size, and spatial distribution of mapped urban trees.

Oral drug absorption is the primary route for drug administration. However, this process hinges on multiple factors, including the drug’s physicochemical properties, formulation characteristics, and gastrointestinal physiology. Given its intricacy and the exorbitant costs associated with experimentation, the trial-and-error method proves prohibitively expensive. Theoretical models have emerged as a cost-effective alternative by assimilating data from diverse experiments and theoretical considerations. These models fall into three categories: data-driven models, encompassing classical pharmacokinetics, quantitative-structure models (QSAR), and machine/deep learning. Mechanism-based models include quasi-equilibrium, steady-state, and physiologically based pharmacokinetics, alongside first principles such as molecular dynamics and continuum models. This review provides an overview of recent modeling endeavors across these categories, evaluating their respective advantages and limitations. Additionally, a primer on partial differential equations and their numerical solutions is included in the supplementary materials, recognizing their utility in modeling physiological systems despite their mathematical complexity limiting their widespread application in this field.

To enhance the accuracy and efficiency of address parsing in traffic accident handling, this study designs a deep address parsing model based on BERT, named ASSPM. This model effectively addresses the limitations of existing deep learning models in Chinese address parsing tasks by integrating address spatial semantics. First, a lexicon-enhancement method based on hybrid representation is employed, transforming the spatial semantics extracted by the Address Spatial Semantics Extractor (ASSE) into a symbolic semantic space that can be integrated with the feature vector space of the deep model. This achieves effective fusion of spatial semantics and the deep model at the model level. Second, a lexicon adapter enhanced with spatial semantics is utilized to integrate spatial semantics into the Transformer layers of the BERT model, achieving semantic fusion at the BERT level. Finally, comparative experiments on a custom address dataset and a public Chinese address dataset validate the proposed method’s superior performance over other baseline methods. This research provides robust support for the application of deep address parsing models integrating address spatial semantics in traffic accident handling, promising to improve the efficiency and accuracy of traffic accident management.

The high penetration of distributed energy resources poses significant challenges to the dispatch and operation of power systems. Improving the accuracy of short-term load forecasting (STLF) can optimize grid management, leading to increased economic and social benefits. Currently, some simple AI and hybrid models has issues to deal with and struggle with multivariate dependencies, long-term dependencies, and non-linear relationships. This paper proposes a novel hybrid model for short-term load forecasting (STLF) that integrates multiple AI models with Lasso regression using the stacking technique. The base learners include ANN, XgBoost, LSTM, Stacked LSTM, and Bi-LSTM, while Lasso regression serves as the meta-learner. By considering factors such as temperature, rainfall, and daily electricity prices, the model aims to more accurately reflect real-world conditions and enhance predictive accuracy. Empirical analyses on real-world datasets from Australia and Spain show significant improvements in forecasting accuracy, with a substantial reduction in Mean Absolute Percentage Error (MAPE) compared to existing hybrid models and individual AI models. This research highlights the efficiency of the stacking technique in improving STLF accuracy, suggesting potential operational efficiency benefits for the power industry.

Focusing on the problem of identifying and classifying aero-engine models, this paper measures the infrared spectrum data of aero-engine hot jets using a telemetry Fourier transform infrared spectrometer. Simultaneously, infrared spectral data sets with the six different types of aero-engines are created. For the purpose of classifying and identifying infrared spectral data, a CNN architecture based on the continuous wavelet transform peak seeking attention mechanism (CWT-AM-CNN) is suggested. This method calculates the peak value of middle wave band by continuous wavelet transform, and the peak data is extracted by the statistics of the wave number locations with high frequency. Attention mechanism is used for the peak data, and the attention mechanism is weighted to the feature map of the feature extraction block. The training set, vali-dation set and prediction set are divided in the ratio of 8:1:1 for the infrared spectral data sets. For three different data sets, CWT-AM-CNN proposed in this paper is compared with the classical classifier algorithm based on CO2 feature vector and the popular AE, RNN and LSTM spectral processing networks. The prediction accuracy of the proposed algorithm in the three data sets is as high as 97%, and the lightweight network structure design not only guarantees high precision, but also has a fast running speed, which can realize the rapid and high-precision classification of the infrared spectral data of the aero-engine hot jets.

3D reality capturing has demonstrated increased efficiency and consistently accurate outcomes in architectural digitisation. Nevertheless, despite advancements in data collecting, 3D reality capturing still lacks full automation, especially in the post-processing and modelling phase. Artificial intelligence (AI) has been a significant focus, especially in computer vision, and tasks such as image classification and object recognition might be beneficial to the digitisation process and its subsequent utilisation. This article aims to examine the potential outcomes of integrating AI technology into the field of 3D reality-capturing, with a particular focus on its use in architectural scenarios. The main methods used for data collection are laser scanning (static or mobile) and photogrammetry. As a result, image data including RGB-D data (files containing both RGB colours and Depth information) and point clouds have become the most common raw datasets available for object mapping. The study comprehensively analyses the current use of 2D and 3D deep learning techniques in documentation tasks, particularly downstream applications. It also highlights the ongoing research efforts in developing real-time applications with the ultimate objective of achieving generalisation and improved accuracy.

Surface water plays a crucial role in climate change, human production, and life, making accurate monitoring and observation of surface water particularly important. However, due to the significant diversity and complexity of water distribution in surface space, accurate mapping of surface water faces considerable challenges. When extracting water bodies from medium-resolution satellite remote sensing images, CNN methods may suffer from limitations in receptive fields and insufficient context modeling capabilities, leading to the loss of water body boundary details and poor fusion of multiscale features. Currently, there is relatively little research on this issue; therefore, it is necessary to explore new combinations of deep learning networks to address these challenges. The purpose of this study is to address the above issues. We propose a new combination of deep learning networks that fully utilize multiscale information to enhance water features. Specifically, we first combine deformable convolutions with the Swin Transformer to increase effective receptive fields while better integrating global semantic information. This combination can capture features of water bodies at different scales, improve the accuracy and integrity of water extraction, and provide reliable technical support for detailed water body extraction. We tested the newly constructed model using Sentinel-2 satellite images. Our model achieved results of over 90%, with an average accuracy of 97.89%, average precision of 94.98%, average recall of 90.05%, and an average F1 score of 92.33%. In addition, our model achieved an accuracy of 98.03% in mountainous areas. Our experiments and results validate the potential of combining the Swin Transformer and deformable convolutions in detailed water body extraction.

Recent advancements in deep learning have spurred the development of numerous novel semantic segmentation models for land cover mapping, showcasing exceptional performance in delineating precise boundaries and producing highly accurate land cover maps. However, to date, no systematic literature review has comprehensively examined semantic segmentation models in the context of land cover mapping. This paper addresses this gap by synthesizing recent advancements in semantic segmentation models for land cover mapping from 2017 to 2023, drawing insights on trends, data sources, model structures, and performance metrics based on a review of 106 extracted articles. Our analysis identifies top journals in the field, including MDPI Remote Sensing, IEEE Journal of Selected Topics in Earth Science, and IEEE Transactions on Geoscience and Remote Sensing, IEEE Geoscience and Remote Sensing Letters, ISPRS Journal Of Photogrammetry And Remote Sensing as the leading journals. We find that research predominantly focuses on land cover, urban areas, precision agriculture, environment, coastal areas, and forests. Geographically, 35.29% of the study areas are located in China, followed by USA (11.76%), France (5.88 %), Spain (4%) and others. Sentinel-2, Sentinel-1, and Landsat satellites emerge as the most commonly used data sources. Benchmark datasets such as ISPRS Vaihingen & Potsdam, LandCover.ai, DeepGlobe, and GID datasets are frequently employed. Model architectures predominantly utilize encoder-decoder, and hybrid convolutional neural network-based structures because of their impressive performances, with limited adoption of transformer-based architectures due to its computational complexity issue, and slow convergence speed. Lastly, this paper highlights existing key research gaps in the field to guide future research directions.

Ensuring precise segmentation of colorectal polyps holds critical importance in the early diagnosis and treatment of colorectal cancer. Nevertheless, existing deep learning-based segmentation methods are fully-supervised, requiring extensive precise manual pixel-level annotation data, which leads to high annotation costs. Additionally, it remains challenging to train large-scale segmentation models when confronted with limited colonoscopy data. To address these issues, we introduce the general segmentation foundation model—Segment Anything Model (SAM) into the field of medical image segmentation. Fine-tuning the foundation model is an effective approach to tackle sample scarcity. However, current SAM fine-tuning techniques still rely on precise annotations. To overcome this limitation, we propose WSPoly-SAM, a novel weakly-supervised approach for colonoscopy polyp segmentation. WSPoly-SAM utilizes weak annotations to guide SAM in generating segmentation masks, which are then treated as pseudo-labels to guide the fine-tuning of SAM, thereby reducing the dependence on precise annotations data. To improve the reliability and accuracy of pseudo-labels, we have designed a series of enhancement strategies to improve the quality of pseudo-labels and mitigate the negative impact of low-quality pseudo-labels. Experimental results on five medical image datasets demonstrate that WSPoly-SAM outperforms current fully-supervised mainstream polyp segmentation networks on the Kvasir-SEG, ColonDB, CVC-300, and ETIS datasets. Furthermore, by using different amounts of training data in weakly-supervised and fully-supervised experiments, it is found that weakly-supervised fine-tuning can save 70% to 73% of annotation time costs compared to fully-supervised fine-tuning. This study provides a new perspective on the combination of weakly-supervised learning and SAM models, significantly reducing annotation time and offering insights for further development in the field of colonoscopy polyp segmentation.

Soil water content (SWC) and soil organic carbon (SOC) are two important factors to consider when revegetation in degraded land of arid and semiarid areas. Knowing the response of SWC and SOC to vegetation restoration as well as their coupling interaction is important for sustainability of vegetation restoration. In this study, three common plantations of the same recovery years were selected on China’s Loess Plateau, which included Pinus sylvestris, Pinus tabuliformis and Populus simonii, to evaluate the response of SWC and SOC to vegetation restoration as well as their interactions, and then revealed the influencing factors of SWC and SOC variations. Results showed that compared to the grassland, three plantations all exacerbated the deficit of deep soil water, but Populus simonii increased the SOC, while the rest all decreased the SOC. And tradeoff of Populus simonii had the lowest root mean squared error (RMSD). Therefore, Populus simonii was identified as representing a suitable revegetation technique for this region. There was strong interaction between SWC and SOC for shallow soil layers. Land use type (LUT) has an important effect on deep SOC variations, while SOC and soil texture for deep SWC variations. The results were helpful to the sustainable development of artificial forests in this region as well as other similar arid and semiarid areas.

Proteins need to be located in appropriate spatiotemporal contexts to carry out their diverse biological functions. Mislocalized proteins may lead to a broad range of diseases, such as cancer and Alzheimer’s disease. Knowing where a target protein resides within a cell will give insights into tailored drug design for a disease. As the gold validation standard, the conventional wet lab uses fluorescent microscopy imaging, immunoelectron microscopy, and fluorescent biomarker tags for protein subcellular location identification. However, the booming era of proteomics and high-throughput sequencing generates tons of newly discovered proteins, making protein subcel-lular localization by wet-lab experiments a mission impossible. To tackle this concern, in the past decades, artificial intelligence (AI) and machine learning (ML), especially deep learning methods, have made significant progress in this research area. In this article, we review the latest advances in AI-based method development in three typical types of approaches, including sequence-based, knowledge-based, and image-based methods. We also elaborately discuss existing challenges and future directions in AI-based method development in this research field.

Predicting human trajectories poses a significant challenge due to the complex interplay of pedestrian behavior, which is influenced by environmental layout and interpersonal dynamics. This complexity is further compounded by variations in scene density. To address this, we introduce a novel dataset from the Festival of Lights in Lyon 2022, characterized by a wide range of densities (0.2-2.2 ped/m2). Our analysis demonstrates that density-based classification of data can significantly enhance the accuracy of predictive algorithms. We propose an innovative two-stage processing approach, surpassing current state-of-the-art methods in performance. Additionally, we utilize a collision-based error metric to better account for collisions in trajectory predictions. Our findings indicate that the effectiveness of this error metric is density-dependent, offering prediction insights. This study not only advances our understanding of human trajectory prediction in dense environments but also presents a methodological framework for integrating density considerations into predictive modeling, thereby improving algorithmic performance and collision avoidance.

The boosted interest in the use of rare earth elements (REEs) in modern technologies had also increase the necessity of their recovery from various sources, including raw materials and wastes. Though Hydrometallurgy plays a key role in these recovery processes, some drawbacks (apparent or not) of these processes, had led to the development of a more environmental friendship subclass named Solvometallurgy, in which non-aqueous solvents substituted to the aqueous media of the hydrometallurgical processing. The non-aqueous solvents chosen for these usages are, besides ionic liquids (ILs), the so-named Deep Eutectic Solvents (DEEs). The utilization of DEEs included the leaching of REEs from the different sources containing them, and also in the separation-purification steps necessary for the yielding of these elements, normally as oxides or salts, in the most purified form. This work reviewed the most recent literature (2023 year) about the utilization of deep eutectic solvents in the recovery of REEs from various sources, and in the coupling of these two (DESs and REEs) to derived compounds to be used in other fields.

Yield calculation is an important link in modern precision agriculture, which is an effective means to improve breeding efficiency, and adjust planting and marketing plans. With the continuous progress of artificial intelligence and sensing technology, yield calculation schemes based on image processing technology have many advantages such as high accuracy, low cost, and non-destructive calculation, and have been favored by a large number of researchers. This article reviews the research progress of crop yield calculation based on remote sensing images and visible light images, describes the technical characteristics and applicable objects of different schemes, and focuses on detailed explanations of data acquisition, independent variable screening, algorithm selection and optimization. Common issues are also discussed and summarized. Finally, solutions are proposed for the main problems that have arisen so far, and future research directions are predicted, with the aim of achieving more progress and wider popularization of yield calculation solutions based on image technology.

Infrared small target detection (ISTD) plays a crucial role in both civilian and military applications. The detection of small targets against dense cluttered backgrounds remains a challenging task, requiring the collaboration of false alarm source elimination and target detection. Existing approaches primarily focus on modeling targets while often neglecting false alarm sources. To address this limitation, we propose a Target and False Alarm Collaborative Detection Network to leverage the information provided by false alarm sources and the background. Firstly, we introduce a False Alarm Source Estimation Block (FEB) that estimates potential interferences present in the background by extracting features on multiple scales and employing stepwise upsampling for feature fusion. Subsequently, we propose a framework that employs multiple FEBs to eliminate false alarm sources across multiple scales. Finally, a Target Segmentation Block (TSB) is introduced to accurately segment the targets to produce the final detection result. Experiments on public datasets demonstrate that, compared to other methods, our model achieves high accuracy in segmenting targets while being able to extract false alarm sources which can be used for further studies.

This study presents a novel approach for automating the body condition scoring of dairy cows, leveraging advancements in 3D imaging technology and deep neural networks. The primary objective was to design and implement a system capable of accurately and efficiently assessing the body condition of dairy cows, a critical metric in livestock management for optimizing health and productivity. To achieve this, a 3D camera was employed to capture detailed point cloud data, reconstructing the three-dimensional morphology of individual cows. The obtained data were then fed into a deep neural network, specifically tailored for the task of ranking body condition. The neural network was trained on a diverse dataset of annotated body condition score representing varying degrees of body condition, ensuring robust performance across different physiological states. The results demonstrate the efficacy of the proposed system in automatically and objectively scoring the body condition of dairy cows. The automated process not only expedites the assessment but also reduces the subjectivity associated with manual scoring methods. This innovative approach holds promise for improving the efficiency of dairy farm management by providing timely and accurate body condition assessments. The integration of 3D imaging and deep learning techniques paves the way for future advancements in precision livestock farming, contributing to enhanced animal welfare, optimized production, and sustainable agriculture practices.

The advent of AI in medicine has transformed various medical specialties, including orthodontics. AI has shown promising results in enhancing the accuracy of diagnoses, treatment planning, and predicting treatment outcomes. With the growing number of AI applications and commercially available tools, there is an increase in their usage in orthodontic practices worldwide. This review aims to explore the principles of artificial intelligence (AI), its applications in the diagnostic process of modern orthodontic practices, and concerns associated with the implementation of AI algorithms in clinical practice. A comprehensive review of the literature was conducted, focusing on five categories where AI has been applied in orthodontics: dental diagnostics, cephalometric evaluation, skeletal age determination, temporomandibular joint (TMJ) evaluation, and extraction decision making. AI has demonstrated high efficacy in all those fields. However, variations in performance and the necessity of manual supervision indicate that AI should be used cautiously in clinical settings. Nevertheless, the high complexity and potential unpredictability of AI algorithms call for cautious implementation and regular manual validation of results. Continuous AI learning, proper governance, and addressing privacy and ethical concerns are crucial for the successful integration of AI into orthodontic practice.

Abstract: Botnets pose a grave cybersecurity threat, enabling widescale malicious activities through networks of compromised devices. Detecting botnets is challenging given their frequent use of evasion techniques like encryption. Traditional signature-based methods fail against modern botnets capable of zero-day attacks. This paper surveys recent advances applying machine learning for botnet detection based on analysis of network traffic payloads, flows, DNS data, and hybrid feature fusion. Core machine learning models include support vector machines, neural networks, random forests, and deep learning architectures, which extract patterns to separate benign and botnet behaviors automatically. Results demonstrate machine learning's capabilities in identifying heterogeneous botnets using artefacts in network streams. However, challenges remain around limited labeled data, real-time streaming, adversarial evasion, and model interpretability. Promising directions involve semi-supervised learning, adversarial training, scalable analytics, and explainable AI to address these gaps. Beyond the technical aspects, responsible development and deployment of botnet detection systems raise ethical considerations around privacy, transparency, and accountability. With diligent cross-disciplinary collaboration, machine learning promises enhanced, generalizable, and trustworthy techniques to combat the serious threat posed by continuously evolving botnets across the digital ecosystem.

A partial or complete pulpotomy is a type of vital pulp therapy (VPT) that aims to remove the in-flamed, infected pulp, leaving behind healthy, vital pulp that is capable of healing. VPT has gained renewed popularity as a treatment option in permanent mature posterior teeth with irre-versible/moderate-severe pulpitis, its high success rates matching that of root canal treatment (RCT). There is currently no consensus regarding diagnostic and prognostic predictors of success of pulpotomies for managing such cases. Therefore, we conducted a scoping review to identify and analyze how these factors affect the outcome of treatment. A literature search using the PRISMA guidelines was undertaken using PubMed and Scopus on July 7, 2023. A total of 22 studies met the inclusion criteria and were qualitatively analyzed by two reviewers. The follow-ing diagnostic and prognostic factors were recognized and discussed; presenting signs and symptoms, periapical diagnosis, bleeding time, indicators of inflammation (bleeding time, con-centration of inflammatory biomarkers), patient age and medical status, the depth, activity and location of caries, and restorative factors. Based on the studies assessed, there is limited evidence to support their prognostic value. Further research is necessary to identify solid predictors of outcome.

This research paper presents a deep learning approach to early detection of skin cancer using image augmentation techniques. The authors propose a two-stage image augmentation technique that involves the use of geometric augmentation and generative adversarial network (GAN) to classify skin lesions as either benign or malignant. This research utilized the public HAM10000 dataset to test the proposed model. Several pre-trained models of CNN were employed, namely Xception, Inceptionv3, Resnet152v2, EfficientnetB7, InceptionresnetV2, and VGG19. Our approach achieved accuracy, precision, recall, and F1-score of 96.90%, 97.07%, 96.87%, 96.97%, respectively, which is higher than the performance achieved by other state-of-the-art methods. The paper also discusses the use of SHapley Additive exPlanations (SHAP), an interpretable technique for skin cancer diagnosis, which can help clinicians understand the reasoning behind the diagnosis and improve trust in the system. Overall, the proposed method presents a promising approach to automated skin cancer detection that could improve patient outcomes and reduce healthcare costs.

Accurate prediction of the degree of airport delays under the influence of convective weather is crucial for collaborative traffic management implementation and improving the efficiency of airport operations. However, existing studies usually only consider numerical-type quantitative features of weather-affected traffic in their models, and lack the introduction of spatial information to comprehensively portray the traffic operation scenarios under the influence of weather. In order to overcome this problem, this paper firstly designs a new image representation of weather-affected air traffic, and constructs a multi-channel traffic and weather scene image (MTWSI) by populating the airspace two-dimensional grid with traffic and meteorological information to represent the overall traffic operation situation in the terminal area under the influence of convective weather; then, a deep convolutional neural network-based airport delay prediction model ( ADLCNN), which takes MTWSI images as input and uses a specific CNN model to extract the deep features that affect traffic operation in it to input into the subsequent classification algorithm to predict the flight delay level; finally, a series of comparative experiments are carried out on the operational data of Guangzhou Baiyun Airport, and the experimental validation shows that, compared with the traditional machine learning methods, the proposed CNN-based airport delay prediction The experimental validation shows that the proposed CNN-based airport delay prediction model has satisfactory prediction performance compared with the traditional machine learning methods, which also proves that the proposed MTWSI method can more comprehensively respond to the real traffic conditions.

Robotics and autonomous technologies enable space travel. Robotics change space colonization. We study space-based robotics. Human-centric missions need robotics. Vision, decision-making, movement, and manipulation follow. These developments influence resource utilization, extravehicular activities, planetary surface exploration, long-duration space missions, and colonization. Robots improve research, productivity, and astronaut safety but present problems. Highlighting research and knowledge gaps. Space ethics, human-robot interaction, and failure recovery are gaps. This extensive study showed how robots and autonomous systems may transform space exploration and colonization. Researchers, engineers, and mission planners may benefit. Robotics and autonomy will improve space exploration.

Self-supervised learning is a method that learns general representation from unlabeled data. Masked image modeling (MIM), one of the generative self-supervised learning methods, has drawn attention showing state-of-the-art performance on various downstream tasks, though showing poor linear separability resulting from the token-level approach. In this paper, we propose a contrastive learning-based multi-view masked autoencoder for MIM, exploiting an image-level approach by learning common features from two different augmented views. We strengthen MIM by learning long-range global patterns from contrastive loss. Our framework adopts simple encoder-decoder architecture, learning rich and general representation by following a simple process: 1) two different views are generated from an input image with random masking and by contrastive loss, we can learn semantic distance of the representations generated by an encoder. By applying a high mask ratio, 80%, it works as strong augmentation and alleviates the representation collapse problem. 2) With reconstruction loss, decoder learns to reconstruct an original image from the masked image. We assess our framework by several experiments on benchmark datasets of image classification, object detection, and semantic segmentation. We achieve 84.3% fine-tuning accuracy on ImageNet-1K classification and 76.7% in linear probing, exceeding previous studies and show promising results on other downstream tasks. Experimental results demonstrate that our work can learn rich and general image representation by applying contrastive loss to masked image modeling.

Medical image analysis is an important branch in the field of medicine, which mainly uses image processing and analysis techniques to interpret and diagnose medical image data. Medical image data helps doctors to effectively observe and diagnose patients' body structures, tissues and lesions. Medical image analysis has been an important research area in the medical field, and it is important for disease diagnosis, treatment planning, and condition monitoring. In recent years, the rapid development of deep learning and computer vision technologies has contributed greatly to the automation, multimodal data fusion, real-time application, and accuracy improvement of medical image analysis. In addition, the development of deep learning has given rise to some new research areas in medical image analysis, such as Generative Adversarial Networks (GANs) for synthetic medical images, self-supervised learning for unsupervised feature learning, and neural network interpretability. In this paper, we will introduce some optimisation methods for medical images which are effective in improving the accuracy, efficiency and reliability of medical image analysis.

Radiator reliability is crucial in environments characterized by high temperatures and friction, where prompt interventions are often required to prevent system failures. This study introduces a proactive approach to radiator fault diagnosis, leveraging the integration of Gaussian Mixture Model (GMM) and Long-Short Term Memory (LSTM) autoencoders. Vibration signals from radiators were systematically collected through randomized durability vibration bench tests, resulting in four operating states—two normal, one unknown, and one faulty. Time-domain statistical features of these signals were extracted and subjected to Principal Component Analysis (PCA) to facilitate efficient data interpretation. Subsequently, this study discusses the comparative effectiveness of GMM and LSTM in fault detection. GMMs are deployed for initial fault classification, leveraging their clustering capabilities, while LSTM autoencoders excel in capturing time-dependent sequences, facilitating advanced anomaly detection for previously unencountered faults. This alignment offers a potent and adaptable solution for radiator fault diagnosis, particularly in challenging high-temperature or high-friction environments. Consequently, the proposed methodology not only provides a robust framework for early-stage fault diagnosis but also effectively balances diagnostic capabilities during operation. Additionally, this study presents the foundation for advancing reliability life assessment in accelerated life testing, achieved through dynamic threshold adjustments using both the absolute log-likelihood distribution of the GMM and the reconstruction error distribution of the LSTM autoencoder model.

This study leverages transformer-based models and focuses on data representation strategies in the named entity recognition task, including "single" (one sentence per vector), "merged" (multiple sentences per vector), and "context" (sentences joined with attention to context). Performance analysis reveals that models trained with a single strategy may not perform well on different data representations. A combined training procedure is proposed to address this limitation, using all three strategies to enhance the stability and adaptability of the model. The results of this approach are presented and discussed for various datasets for four languages (English, Polish, Czech, and German), demonstrating the effectiveness of the combined strategy.

Radiological imaging is an essential component of a swallowing assessment. Artificial intelligence (AI), and especially deep learning (DL) models, have enhanced the efficiency and efficacy through which imaging is interpreted, and subsequently have important implications for swallow diagnostics and intervention planning. However, the application of AI for the interpretation of videofluoroscopic swallowing studies (VFSS) is still emerging. This review showcases recent literature in the use of AI to interpret VFSS and highlights clinical implications for speech pathologists (SPs). With a surge in AI research, there have been advances made in dysphagia assessment. Several studies have demonstrated successful implementation of DL algorithms to analyze VFSS. Notably, convolutional neural networks (CNNs) have been used to detect pertinent aspects of the swallowing process with high levels of precision. DL algorithms have the potential to streamline VFSS interpretation, improve efficiency and accuracy, and enable precise interpretation of instrumental dysphagia evaluation, which is especially advantageous when access to skilled clinicians is not ubiquitous. By enhancing precision, speed, and depth of VFSS interpretation, SPs can obtain a more comprehensive understanding of swallow physiology and deliver targeted and timely intervention that is tailored towards the individual. This has practical applications for both clinical practice and dysphagia research. As this research area grows and AI technologies progress, the application of DL in the field of VFSS interpretation is clinically beneficial and has the potential to transform dysphagia assessment and management. With broader validation and inter-disciplinary collaborations, AI-augmented VFSS interpretation is likely to transform swallow evaluation and ultimately improve outcomes for individuals with dysphagia.

The Colony-Forming Unit (CFU) counting problem remains a complex issue without a universal solution in biomedical and food safety domains. A multitude of sophisticated heuristics and segmentation-driven approaches have been proposed by numerous researchers. Among those, U-Net is the most frequently cited and popular Deep Learning method. The latter approach provides a segmentation output map and requires an additional counting procedure which accounts for unique segmented regions and detected microbial colonies. However, because of pixel-based targets it tends to generate irrelevant artifacts or errant pixels, leading to inaccurate and mixed post-processing results. In response to these challenges, we propose a novel hybrid counting approach, incorporating a multi-loss U-Net reformulation and a post-processing Petri dish localization algorithm. First of all, our unique innovation lies in the multi-loss U-Net reformulation. We introduce an additional loss term at the bottleneck U-Net layer, focusing on delivering an auxiliary signal indicating where to look for distinct CFUs. Second, our novel localization algorithm accurately incorporates an agar plate and its bezel into the CFU counting routines. Finally, our proposition is further enhanced by the integration of a fully automated solution. This comprises a specially designed uniform Petri dish illumination system and a counting web application. The latter application is capable of directly receiving images from the camera, which are subsequently processed, and the segmentation results are sent back to the user. This feature provides an opportunity to correct the CFU counts, offering a feedback loop that contributes to the continued development of the Deep Learning model. Through extensive experimentation, we have found that all probed multi-loss U-Net architectures incorporated in our hybrid approach consistently outperform their single-loss counterparts which utilize exclusively the combination of Tversky and Cross-Entropy training losses at the output U-Net layer. We report further significant improvements by the means of our novel localization algorithm. This reaffirms the effectiveness of our proposed hybrid solution in addressing contemporary challenges of the precise in-vitro CFU counting.

Binarization of degraded documents is an important preprocessing task for various document analysis such as OCR and historical document analysis. Existing studies have applied various convolutional neural network (CNN) models and generative models for document binarization, but they do not show generalized performance for noise that the model has not seen and it suffers from extracting elaborate text strokes. In this paper, to overcome these challenges, we utilize latent diffusion model (LDM), which is known for high-quality image generation model, for the first time in document binarization. By utilizing the iterative diffusion-denoising process in latent space, it shows high-quality cleaned binarized image generation and high generalized performance through using both data distribution and time step while training. Additionally, we apply gated U-Net to the backbone network to preserve text strokes using trainable gating value. Gated convolution can extract elaborate text stroke by allowing the model to focus on text region by combining gating value and feature. Furthermore, we maximize the effectiveness of the proposed model by training it with a combination of LDM loss and pixel-level loss, which is suitable for the model structure. Experiments on H-DIBCO and DIBCO benchmark datasets show that the proposed model outperforms existing methods.

The falling cost of cameras, the advancement of AI based computer vision algorithms, and powerful hardware accelerators for deep learning have enabled wide-spread deployment of surveillance cameras with the ability to automatically analyze streaming video feeds to detect events of interest. While streaming video analytics is currently largely done in the cloud, edge computing has emerged as a pivotal component due to its advantages of low latency, reduced bandwidth, and enhanced privacy. However, a distinct gap persists between the state-of-the-art computer vision algorithms, and successful practical implementation of edge-based streaming video analytics systems. This paper presents a comprehensive review of more than 30 research papers published over the last 6 years on edge video analytics systems. The papers are analyzed across 17 distinct dimensions. Unlike prior reviews, we examine each system holistically, identifying their strengths and weaknesses in diverse implementations. Our findings suggest that certain critical topics necessary for the practical realization of edge video analytics systems are not sufficiently addressed in current research. Based on these observations, we propose research trajectories across short, medium, and long term horizons. Additionally, we explore trending topics in other computing areas that can significantly impact the field of edge video analytics.

Abstract: The surge of diabetes poses a significant global health challenge, particularly in Oman and the Middle East. Early detection of diabetes is crucial for proactive intervention and improved patient outcomes. This research leverages the power of machine learning, specifically, Convolutional Neural Networks (CNNs), to develop an innovative 4D CNN model dedicated to early diabetes prediction. A region-specific dataset from Oman is utilized to enhance health outcomes for individuals at risk of developing diabetes. The proposed model showcases remarkable accuracy, achieving an average accuracy of 98.49% to 99.17% across various epochs. Additionally, it demonstrates excellent F1 score, recall, and sensitivity, highlighting its ability to identify true positive cases. The findings contribute to the ongoing effort to combat diabetes and pave the way for future research in using deep learning for early disease detection and proactive healthcare.

Millions of tons of wool waste are produced yearly by textile industries, which may become a serious environmental hazard in the near future. Given this concern, it is crucial to explore strategies to reduce the amount of wool waste generated worldwide and adopt more sustainable practices for dissolving and regenerating wool keratin (WK) from textile waste. Most traditional methods involve the use of expensive, toxic, harmful, and poorly biodegradable compounds. To overcome these limitations and facilitate the reuse of wool waste through a cascade valorization strategy, researchers have started testing the use of deep eutectic solvents (DES) as a more sus-tainable and eco-friendlier alternative for WK dissolution and regeneration. In this study, the potential of two different DES mixtures, Choline chloride (ChCl): Urea and L-Cysteine (L-Cys): Lactic acid (LA), was explored for dissolving wool waste. Subsequently, the obtained gels based on DES-WK were blended with polyvinyl alcohol (PVA) in different ratios to produce nanofibers using the electrospinning technique. The effect of pH and the properties of the electrospinning solutions, namely electrical conductivity and viscosity, on the morphology of the gel solutions were evaluated. Moreover, the morphological features of the produced gel-based electrospun PVA/DES-WK nanofibrous membranes were analyzed using scanning electron mi-croscopy (SEM). Additionally, the PVA/L-Cys: LA DES-WK, which proved to be the most effective DES mixture for fabricating WK gel-based nanofibers, were characterized through Fourier transform infrared spectroscopy (FTIR) and tensile tests. Furthermore, their antioxidant and an-timicrobial abilities were evaluated. The results obtained revealed that this approach to valorize textile waste offers a unique avenue for the development of sustainable functional materials with potential applications in various biomedical and industrial fields.

The objective of this study is to investigate the use of excavation behavior prediction and analysis software in the field of civil en-gineering. PLAXIS and SoilWorks, widely used in the engineering and academic communities, were employed as research tools for analyzing gravel layers and deriving appropriate ranges of soil elastic modulus for different software programs. By collecting excavation cases in the Xindian area of New Taipei City, Taiwan, and conducting deep excavation analysis using the displacement of retaining walls, this study provides recommended ranges for localized selection of soil elastic modulus. The suggested range for PLAXIS is 7,840 N/m² to 9,800 N/m², while Soil-Works suggests a range of 2,450 N/m² to 3,430 N/m². These ranges allow for reasonable estimation of maximum deformations during the final excavation stage. Based on the research findings, it is recommended that engineers refer to the provided ranges when selecting soil elastic modulus for excavation analysis in gravel layers using different soft-ware programs in the Xindian area of Taiwan to improve the accuracy of deformation predictions during the final excavation stage. These results serve as important references for engineers and contribute to the effective prediction and management of excavation behavior in civil engineering projects.

Background: We studied the outcomes of SARS-CoV-2 (COVID) hospitalizations and their association with myocardial injury and thrombosis. Methods: Retrospective analysis of the National Inpatient Sample 2020 database. Results: We identified 335,799 hospitalizations with COVID. Of these, 1.6% (5,355) were diagnosed with non-ST-segment myocardial infarction (COVNSTEMI). The mean age of COVID hospitalizations was 71.7, with 60.50% being males. The population prevalence included 53.10% Whites, 17.80% Blacks, 19.20% Hispanics, and 4.10% Asians. The average length of stay (LOS) was 10 days, and 37.60% of patients died during their hospitalization. The average cost of hospitalization (TOTCHG) was $156,633. The COVSTEMI group comprised 1,364 cases, with a mean age of 67.4, in-hospital mortality of 47.4%, and the mean TOTCHG was $177,600. The DVTCOV group comprised 2,869 cases, while the PECOV group had 4,828 cases. Male predominance was observed in both groups, with mean ages of 66 years in the DVTCOV group and 64 years in the PECOV group. The DVTCOV group had a LOS of 16 days, with 24.71% mortality, while the PECOV group had a LOS of 11 days, with 19.20% mortality. The average TOTCHG in the DVTCOV group was $248,900, whereas it was $145,378 in the PECOV group. Conclusion: Our study revealed significant mortality rates across different groups, including 38% in COVNSTEMI, 47% in COVSTEMI, 25% in DVTCOV, and 19% in PECOV. These findings highlight the severity of COVID-related complications and the substantial financial burden of hospitalization.

The surrounding rock during the coal mine excavation is prone to significant engineering disasters such as considerable deformation and rockbursts. Pressure release can improve the stress field of a deep rock mass and prevent the occurrence of dangers such as roadway collapse and coal and gas outbursts. This paper uses the ANSYS/LS-DYNA finite element software to simulate the crush area and fracture zone of a detonation charge with different diameters under in-situ stress. The stability of the surrounding rock was analyzed based on the impact stress and velocity, and was verified by field tests. The research results show that the blasting load primarily affects the damaged area near the borehole, while the in-situ stress affects the far-field crack propagation. The crack propagates in the direction of high surrounding rock pressure. When the uncoupling index is 1.5, the impact pressure of the 60 mm diameter cartridge is 8 times that of the 20 mm diameter cartridge. The impact speed can reach 2 times that of the 20 mm diameter cartridge. The high-energy event of the roof is transferred to the front of the working face, the distribution is no longer concentrated, and a better blasting pressure relief effect is achieved. The research results can help guide the prevention and control measures of rock bursts and other mining disasters.

Fault detection is an important step for subsurface interpretation and reservoir characterization from 3D seismic images. Due to the numerous and complicated faulting structures of seismic images, manual seismic interpretation is time taking and need intensive work. To overcome this problem, geoscientists are coming up with productive computer-aided techniques for assisting in interpreter science for many years. However, in this paper, we used a pre-trained CNN model to predict faults from the 3D seismic volume of the Poseidon field of Browse Basin, Australia. Basically, this field is highly structured with complex normal faulting throughout the targeted Plover Formations. So, our motivation for this work in this field is to compare machine learning-based fault prediction to user interpreted faults identification with supported by seismic variance attribute. We found very satisfying result using DL with having an improved fault probability volume that outperform variance technology. Therefore, we propose that this workflow could reduce time and able to predict fault quite accurately in any field area.

The root system plays an irreplaceable role in plant growth. Its improvement can increase crop productivity. However, such system is still mysterious for us. The underlying mechanism has not been fully uncovered. The investigation on proteins related to the root system is an important means to complete this task. In the previous time, lack of root-related proteins makes it impossible to adopt machine learning methods for designing efficient models for the discovery of novel root-related proteins. Recently, a public database on root-related proteins was set up and machine learning methods can be applied in this field. In this study, we proposed a machine learning based model, named Graph-Root, for identification of root-related proteins. The features derived from protein sequences and one network were extracted, where the former features were processed by graph convolutional neural network and multi-head attention, and the later features abstracted the linkage between proteins. These features were fed into the fully connected layer to make prediction. The 5-fold cross-validation and independent tests suggested its good performance. It also outperformed the only one previous model, SVM-Root. Furthermore, the importance of each feature type and component in the proposed model was investigated.

Teeth segmentation plays a pivotal role in dental diagnosis, treatment, planning, and the development of computer-aided dental systems. It enables precise identification and analysis of dental structures, aiding in detecting dental abnormalities, measuring tooth dimensions, and assessing oral health conditions. Accurate teeth segmentation also facilitates the automation of dental workflows, leading to improved efficiency and reduced human error. Artificial Intelligence (AI) has witnessed rapid advancements, with various approaches developed or enhanced. While Convolutional Neural Networks (CNNs) have been widely used in medical image segmentation, the U-Net architecture has emerged as a standout performer due to its exceptional segmentation capabilities. This paper presents a proof of concept for the Attention U-Net architecture, as previously used in [1], applied to teeth segmentation. The study demonstrates the superior performance of this network in accurately segmenting teeth using a newly available benchmark dataset called Tufts Dental X-Ray Dataset. When trained and tested on 10-fold cross-validation, the model achieved an average dice coefficient of 95.01%, intersection over union of 90.6%, and pixel accuracy of 98.82%. These scores surpass those of all other networks implemented on the same dataset. By leveraging the Attention U-Net architecture, our research showcases the potential of advanced AI techniques in dental radiography. The findings contribute to the ongoing efforts to develop automated systems to assist dental professionals in their clinical practice.

Early stable deep molecular response (DMR) of nilotinib is associated with goal of treatment-free remission (TFR) for patients with chronic-phase chronic myeloid leukemia (CML-CP). It is significant to early distinguish patients who can obtain DMR and fit for TFR. We performed a multicenter study to explore early cumulative MR4.5 rate by 18 months with nilotinib in patients with newly diagnosed CML-CP (ND-CML-CP) in China. From 29 institutes, 106 ND-CML-CP patients received nilotinib (300mg BID). The cumulative MR4.5 rate of nilotinib by 18 months was 69.8% (74/106). The cumulative MMR and MR4.0 rates of nilotinib by 18 months were 94.3% (100/106) and 84.9% (90/106), respectively. Patients with ultra-early molecular response (u-EMR) at 6 weeks were not significantly different to obtain DMR or MMR by 24 months compared to those without u-EMR (P=0.7584, P=0.9543, respectively). Our study demonstrated that treatment with nilotinib in patients with ND-CML-CP contributed to obtain high early MR4.5.

When an aircraft malfunctions, quickly and accurately identifying the faulty unit is essential for ensuring normal operation. Unfortunately, maintenance engineers often struggle to acquire the necessary fault-related knowledge due to poor management and utilization of aircraft fault documents. To address this issue, we introduce knowledge graph technology into the field of aircraft fault diagnosis, exploring its construction and application for effective knowledge management. Our work starts by analyzing the critical knowledge elements required for aircraft fault diagnosis and designing a schema layer for fault knowledge graphs. We then we then combine deep learning and heuristic rules to extract fault knowledge from both structured and unstructured data, enabling the construction of aircraft fault knowledge graphs. Finally, we develop a fault question-answering system based on fault knowledge graphs that can accurately give solutions to questions posed by maintenance engineers. Our practice demonstrates that knowledge graphs provide an effective means of managing aircraft fault knowledge, assisting engineers in locating fault reasons accurately and quickly.

“A Picture is worth a thousand words”. Given an image, humans are able to deduce various cause-and-effect captions of past, current, and future events beyond the image. The task of visual commonsense generation aims at generating three cause-and-effect captions (1) what needed to happen before, (2) what is the current intent, and (3) what will happen after for a given image. However, such a task is challenging for machines owing to two limitations: existing approaches (1) directly utilize conventional vision-language transformers to learn relationships between input modalities, and (2) ignore relations among target cause-and-effect captions but consider each caption independently. We propose Cause-and-Effect BART (CE-BART) which is based on (1) Structured Graph Reasoner that captures intra- and inter-modality relationships among visual and textual representations, and (2) Cause-and-Effect Generator that generates cause-and-effect captions by considering the causal relations among inferences. We demonstrate the validity of CE-BART on VisualCOMET and AVSD benchmarks. CE-BART achieves SOTA performances on both benchmarks, while extensive ablation study and qualitative analysis demonstrate the performance gain and improved interpretability.

In recent years, the demand for coffee has increased tremendously. During the production process, green coffee beans are traditionally screened manually for defective beans before they are packed into coffee bean packages; however, this method is not only time-consuming but also increases the rate of human error due to fatigue. Therefore, this paper proposed a lightweight deep convolutional neural network (LDCNN) for the quality detection system of green coffee beans, which combined depthwise separable convolution (DSC), squeeze-and-excite block (SE block), skip block, and other frameworks. To avoid the influence of low parameters of the lightweight model caused by the model training process, rectified Adam (RA), lookahead (LA), and gradient centralization (GC) were included to improve efficiency; the model was also put into the embedded system. Finally, the local interpretable model-agnostic explanations (LIME) model was employed to explain the predictions of the model. The experimental results indicated that the accuracy rate of the model could reach up to 98.38% and the F1 score could be as high as 98.24% when detecting the quality of green coffee beans. Hence, it can obtain higher accuracy, lower computing time, and lower parameters. Moreover, the interpretable model verified that the lightweight model in this work is reliable, providing the basis for screening personnel to understand the judgment through its interpretability, thereby improving the classification and prediction of the model.

Manual visual inspections typically conducted after an earthquake are high-risk, subjective, and time-consuming. Delays from inspections often exacerbate the social and economic impact of the disaster on affected communities. Rapid and autonomous inspection using images acquired from unmanned aerial vehicles offer the potential to reduce such delays. Indeed, a vast amount of re-search has been conducted toward developing automated vision-based methods to assess the health of infrastructure at the component and structure level. Most proposed methods typically rely on images of the damaged structure, but seldom consider how the images were acquired. To achieve autonomous inspections, methods must be evaluated in a comprehensive end-to-end manner, incorporating both data acquisition and data processing. In this paper, we leverage recent advances in computer generated imagery (CGI) to construct a 3D synthetic environment for simulation of post-earthquake inspections that allows for comprehensive evaluation and valida-tion of autonomous inspection strategies. A critical issue is how to simulate and subsequently render the damage in the structure after an earthquake. To this end, a high-fidelity nonlinear finite element model is incorporated in the synthetic environment to provide a representation of earthquake-induced damage; this finite element model, combined with photo-realistic rendering of the damage, is termed herein a physics-based graphics models (PBGM). The 3D synthetic en-vironment with PBGMs provide a comprehensive end-to-end approach for development and validation of autonomous post-earthquake strategies using UAVs, including: (i) simulation of path planning of virtual UAVs and image capture under different environmental conditions; (ii) au-tomatic labeling of captured images, potentially providing an infinite amount of data for training deep neural networks; (iii) availability of the ground truth damage state from the results of the finite-element simulation; and (iv) direct comparison of different approaches to autonomous as-sessments. Moreover, the synthetic data generated has the potential to be used to augment field datasets. To demonstrate the efficacy of PBGMs, models of reinforced concrete moment-frame buildings with masonry infill walls are examined. The 3D synthetic environment employing PBGMs is shown to provide an effective testbed for development and validation of autonomous vision-based post-earthquake inspections that can serve as an important building block for ad-vancing autonomous data to decision frameworks.

What does the way autistics bypass, learn, and eventually master language tell us about humans’ genetically encoded linguistic ability? In this theoretical review, we argue that autistic non-social acquisition of language, as well as autistic savant abilities, provide a strong argument for an innate, human-specific orientation toward (and mastery of) complex embedded structures. Autistic non-social language learning may represent a widening of the material processed during development beyond oral language. Structure detection and manipulation and generative production of non-linguistic embedded and chained material (savant abilities in calendar calculation, musical composition and interpretation, three-dimensional drawing) may thus represent an application of such innate mechanisms to non-standard materials. Typical language learning through exposure to the child’s mother tongue may represent but one of many possible achievements of the same capacity. The deviation from typical language development in autism may ultimately allow access to oral language, sometimes in its most elaborate forms, but also explains the possibility of the absence of its development when applied exclusively to non-linguistic structured material. Such an extension of human capacities beyond, or in parallel to, their usual limits call into question what we consider to be specific or expected in humans and, therefore, does not necessarily represent a genetic “error”. Regardless of the adaptive success or failure of non-social language learning, it is up to science and ethical principles to strive to maintain autism as a human potentiality to further foster our vision of a plural society.

Intelligent systems are transforming the world, as well as our healthcare system. We propose a deep learning-based cough sound classification model that can distinguish between children with healthy versus pathological coughs such as asthma, upper respiratory tract infection (URTI), and lower respiratory tract infection (LRTI). In order to train a deep neural network model, we collected a new dataset of cough sounds, labelled with clinician's diagnosis. The chosen model is a bidirectional long-short term memory network (BiLSTM) based on Mel Frequency Cepstral Coefficients (MFCCs) features. The resulting trained model when trained for classifying two classes of coughs -- healthy or pathology (in general or belonging to a specific respiratory pathology), reaches accuracy exceeding 84\% when classifying cough to the label provided by the physicians' diagnosis. In order to classify subject's respiratory pathology condition, results of multiple cough epochs per subject were combined. The resulting prediction accuracy exceeds 91\% for all three respiratory pathologies. However, when the model is trained to classify and discriminate among the four classes of coughs, overall accuracy dropped: one class of pathological coughs are often misclassified as other. However, if one consider the healthy cough classified as healthy and pathological cough classified to have some kind of pathologies, then the overall accuracy of four class model is above 84\%. A longitudinal study of MFCC feature space when comparing pathologicial and recovered coughs collected from the same subjects revealed the fact that pathological cough irrespective of the underlying conditions occupy the same feature space making it harder to differentiate only using MFCC features.

What does the way autistics bypass, learn, and eventually master language tell us about human linguistic ability? Here, we argue that non-social acquisition of language, in addition to representing a strong argument for nativist models of human language, may be encompassed within the human-specific orientation and mastery of complex embedded structures, of which language represents one realization. Non-social language learning could thus represent the extension of available linguistic, and non-linguistic material processed by human genetic constraints, allowing language acquisition. This deviation from typical developmental language acquisition may ultimately allow access to language, sometimes in its most elaborate forms, and also explains the possibility of the absence of its development when applied to primarily non-linguistic structured material. However, such enlargement of material-specificity does not cast doubts about its human nature. Regardless of the adaptive success or failure of non-social language learning, it is up to science, legal policies, and ethical principles to strive to maintain autism as a human potentiality to further foster our vision of a plural society.

This study introduces a comparative analysis of two deep learning (multilayer perceptron neural networks (MLP-NN) and the long short term memory networks (LSTMN)) models for transit travel time prediction. The two models were trained and tested using one-year worth of data for a bus route in Blacksburg, Virginia. In this study, the travel time was predicted between each two successive stations to all the model to be extended to include bus dwell times. Additionally, two additional models were developed for each category (MLP of LSTM): one for only segments including controlled intersections (controlled segments) and another for segments with no control devices along them (uncontrolled segments). The results show that the LSTM models outperform the MLP models with a RMSE of 17.69 sec compared to 18.81 sec. When splitting the data into controlled and uncontrolled segments, the RMSE values reduced to 17.33 sec for the controlled segments and 4.28 sec for the uncontrolled segments when applying the LSTM model. Whereas, the RMSE values were 19.39 sec for the controlled segments and 4.67 sec for the uncontrolled segments when applying the MLP model. These results demonstrate that the uncertainty in traffic conditions introduced by traffic control devices has a significant impact on travel time predictions. Nonetheless, the results demonstrate that the LSTMN is a promising tool that can has the ability to account for the temporal correlation within the data. The developed models are also promising tools for reasonable travel time predictions in transit applications.

Anomaly occurrences in hydraulic machinery may lead to massive systems shut down, jeopardizing the safety of the machinery and its surrounding human operator(s) and environment, and the severe economic implications succeeding the faults and their associated damage. Hydraulics are mostly placed in ruthless environments, where they are consistently vulnerable to many faults. Hence, not only the machines and their components are prone to anomalies, but also the sensors attached to them, which monitor and report their health and behavioral changes. In this work, a comprehensive applicational analysis of anomalies in hydraulic systems extracted from a hydraulic test rig is thoroughly achieved. Firstly, we provided a combination of a new architecture of LSTM autoencoders and supervised machine and deep learning methodologies to perform two separate stages of fault detection and diagnosis. The two phases are condensed by: the detection phase using the LSTM autoencoder. Followed by the fault diagnosis phase represented by the classification schema. The previously mentioned framework is applied to both component and sensor faults in hydraulic systems, deployed in the form of two in-depth applicational experiments. Moreover, a thorough literature review of the past decade related work for the two stages separately is successfully conducted in this paper.

Tail-biting convolutional codes extend the classical zero-termination convolutional codes: Both encoding schemes force the equality of start and end states, but under the tail-biting each state is a valid termination. This paper proposes a machine-learning approach to improve the state-of-the-art decoding of tail-biting codes, focusing on the widely employed short length regime as in the LTE standard. This standard also includes a CRC code. First, we parameterize the circular Viterbi algorithm, a baseline decoder that exploits the circular nature of the underlying trellis. An ensemble combines multiple such weighted decoders, each decoder specializes in decoding words from a specific region of the channel words' distribution. A region corresponds to a subset of termination states; the ensemble covers the entire states space. A non-learnable gating satisfies two goals: it filters easily decoded words and mitigates the overhead of executing multiple weighted decoders. The CRC criterion is employed to choose only a subset of experts for decoding purpose. Our method achieves FER improvement of up to 0.75dB over the CVA in the waterfall region for multiple code lengths, adding negligible computational complexity compared to the circular Viterbi algorithm in high SNRs.

The calculation of echo intensity involved in the SAR image simulation is usually based on the electromagnetic formula or approximate formula derived under certain assumptions. However, the parameters used in these formulas are often difficult to obtain, and the formulas have errors with the actual situation. In this paper, a method of embedding deep neural network (DNN) into the simulation process based on ray tracing is proposed, so that the DNN model can be directly used to fit the calculation formula of echo intensity from real SAR images. Simulation results show that this method can obtain SAR images with high similarity.

Manual traffic surveillance can be a daunting task as Traffic Management Centers operate a myriad of cameras installed over a network. Injecting some level of automation could help lighten the workload of human operators performing manual surveillance and facilitate making proactive decisions which would reduce the impact of incidents and recurring congestion on roadways. This article presents a novel approach to automatically monitor real time traffic footage using deep convolutional neural networks and a stand-alone graphical user interface. The authors describe the results of research received in the process of developing models that serve as an integrated framework for an artificial intelligence enabled traffic monitoring system. The proposed system deploys several state-of-the-art deep learning algorithms to automate different traffic monitoring needs. Taking advantage of a large database of annotated video surveillance data, deep learning-based models are trained to detect queues, track stationary vehicles, and tabulate vehicle counts. A pixel-level segmentation approach is applied to detect traffic queues and predict severity. Real-time object detection algorithms coupled with different tracking systems are deployed to automatically detect stranded vehicles as well as perform vehicular counts. At each stages of development, interesting experimental results are presented to demonstrate the effectiveness of the proposed system. Overall, the results demonstrate that the proposed framework performs satisfactorily under varied conditions without being immensely impacted by environmental hazards such as blurry camera views, low illumination, rain, or snow.

The paper demonstrates the analysis of Corona Virus Disease based on a CNN probabilistic model. It involves a technique for classification and prediction by recognizing typical and diagnostically most important CT images features relating to Corona Virus. The main contributions of the research include predicting the probability of recurrences in no recurrence (first time detection) cases at applying our proposed Convolution neural network structure. The Study is validated on 2002 chest X-ray images with 60 confirmed positive covid19 cases and (650 bacterial – 412 viral -880 normal) x-ray images. The proposed CNN compared with traditional classifiers with proposed CHFS feature extraction model. The experimental study has done with real data demonstrates the feasibility and potential of the proposed approach for the said cause. The result of proposed CNN structure has been successfully done to achieve 98.20% accuracy of covid19 potential cases with comparable of traditional classifiers.

The very first infected novel coronavirus case (COVID-19) was found in Hubei, China in Dec. 2019. The COVID-19 pandemic has spread over 215 countries and areas in the world, and has significantly affected every aspect of our daily lives. At the time of writing this article, the numbers of infected cases and deaths still increase significantly and have no sign of a well-controlled situation, e.g., as of 14 April 2020, a cumulative total of 1,853,265 (118,854) infected (dead) COVID-19 cases were reported in the world. Motivated by recent advances and applications of artificial intelligence (AI) and big data in various areas, this paper aims at emphasizing their importance in responding to the COVID-19 outbreak and preventing the severe effects of the COVID-19 pandemic. We firstly present an overview of AI and big data, then identify their applications in fighting against COVID-19, next highlight challenges and issues associated with state-of-the-art solutions, and finally come up with recommendations for the communications to effectively control the COVID-19 situation. It is expected that this paper provides researchers and communities with new insights into the ways AI and big data improve the COVID-19 situation, and drives further studies in stopping the COVID-19 outbreak.

In recent years, researchers have paid increasing attention on hyperspectral image (HSI) classification using deep learning methods. To improve the accuracy and reduce the training samples, we propose a double-branch dual-attention mechanism network (DBDA) for HSI classification in this paper. Two branches are designed in DBDA to capture plenty of spectral and spatial features contained in HSI. Furthermore, a channel attention block and a spatial attention block are applied to these two branches respectively, which enables DBDA to refine and optimize the extracted feature maps. A series of experiments on four hyperspectral datasets show that the proposed framework has superior performance to the state-of-the-art algorithm, especially when the training samples are signally lacking.

An increase in the use of smartphones has laid to the use of the internet and social media platforms. The most commonly used social media platforms are Twitter, Facebook, WhatsApp and Instagram. People are sharing their personal experiences, reviews, feedbacks on the web. The information which is available on the web is unstructured and enormous. Hence, there is a huge scope of research on understanding the sentiment of the data available on the web. Sentiment Analysis (SA) can be carried out on the reviews, feedbacks, discussions available on the web. There has been extensive research carried out on SA in the English language, but data on the web also contains different other languages which should be analyzed. This paper aims to analyze, review and discuss the approaches, algorithms, challenges faced by the researchers while carrying out the SA on Indigenous languages.

The upsurge of Generative Adversarial Networks (GANs) in the previous five years has led to advancements in unsupervised data manipulation, sourced feature translation, and precise input-output synthesis through a competitive optimization of the discriminator and generator networks. More specifically, the recent rise of cycle-consistent GANs enables style transfers from a discrete source (input A) to target domain (input B) by preprocessing object features for a multi-discriminative adversarial network. Traditionally, cyclical adversarial networks have been exploited for unpaired image-to-image translation and domain adaptation by determining mapped relationships between an input A graphic and an input B graphic. However, this integral mechanism of domain adaptation can be applied to the complex acoustical features of human speech. Although well-established datasets, such as the 2018 Voice Conversion Challenge repository, paved way for female-male voice transformation, cycle-GANs have rarely been re-engineered for voices outside the datasets. More critically, cycle-GANs have massive potential to extract surface-level and hidden feature to distort an input A source into a texturally unrelated target voice. By preprocessing, compressing, and packaging unique acoustical voice properties, CycleGANs can learn to decompose speech signals and implement new translation models while preserving emotion, the intent of words, rhythm, and accents. Due to the potential of CycleGAN’s autoencoder in realistic unsupervised voice-voice conversion/feature adaptation, the researchers raise the ethical implications of controlling source input A to manipulate target voice B, particularly in cases of defamation and sabotage of target B’s words. This paper analyzes the potential of cycle-consistent GANs in deceptive voice-voice conversion by manipulating interview excerpts of political candidates.

This research presents a novel methodology for classifying MRI images into two categories: tumor and non-tumor. The study utilizes a combination of two advanced Convolutional Neural Network (CNN) architectures, VGG16 and ResNet50, to address the challenges in analyzing the complexity and variability of brain MRI scans. The approach begins with a comprehensive preprocessing phase, where the MRI images are enhanced through techniques such as resizing, grayscale conversion, Gaussian blurring, and brain area isolation. Central to the approach is the application of the Multi-verse Optimizer (MVO), a metaheuristic algorithm inspired by theories of the multi-verse in physics. The MVO is utilized to optimize the parameters for data augmentation and to fine-tune the combination of trainable layers within the VGG16 and ResNet50 models. The results of this study indicate a high level of effectiveness of the combined CNN models, significantly enhanced by the MVO, in classifying MRI images. These models show marked improvements in accuracy, precision, and recall, underscoring their potential utility in enhancing brain tumor diagnosis. The paper concludes with an analysis of these findings, emphasizing the importance of this approach in medical imaging and suggesting potential avenues for future research in the area of automated MRI classification.

Objectives: To evaluate the possible long-term cerebral deposition of amyloid-β in PD patients treated with subthalamic nucleus deep brain stimulation (STN-DBS) and its possible influence on axial and cognitive variables. Methods: Consecutive PD patients treated with bilateral STN-DBS with a long-term follow-up were included. Amyloid-β deposition was evaluated postoperatively through a 18F-flutemetamol positron emission tomography (PET) study. Axial symptoms have been assessed using a standardized clinical-instrumental approach. Speech was assessed by perceptual and acoustic analysis while gait by means of the instrumented timed up and go test (iTUG). Motor severity was evaluated applying the UPDRS part III score and subscores while cognitive functions through a complete neuropsychological assessment. Different stimulation and drug conditions were assessed: on-stimulation/off-medication, off-stimulation/off-medication, on-stimulation/on-medication conditions (single and dual task). Results: 19 PD patients (male: 11; age: 63.52 years; on-stimulation/on-medication UPDRS-III: 17.05) with a five-year postoperative follow-up were included. Amyloid-β deposition was found in 21% of patients (4/19) with a prevalent involvement of prefrontal, limbic and parietal areas. Compared with patients without amyloid-β deposition, PD patients with positive 18F-flutemetamol PET study showed higher preoperative UPDRS-I (p=.037) score and lower postoperative Raven's matrices scores (p=.05). Conclusions: Our results suggest that in the long-term after STN-DBS a significant percentage of PD patients may present brain amyloid-β deposition. However, larger samples are needed to evaluate the possible role of amyloid-β deposition in the development of axial and cognitive alterations after surgery.

Solar ultraviolet (UV) is among the most important ecological factors shaping the composition of biota on the planet surface, including upper layers of waterbodies. Inhabitants of dark environments recently descending from surface organisms provide natural opportunities to study the evolutionary losses of UV adaptation mechanisms and better understand how those mechanisms function at the biochemical level. Ancient Lake Baikal is the only freshwater reservoir, where deep-water fauna emerged, and its diverse endemic amphipods (Amphipoda, Crustacea) now inhabit the whole range from highly transparent littoral to dark depths of over 1600 m, which makes them a convenient model to study UV adaptation. Here we show that adults of deep-water Baikal amphipods Ommatogammarus flavus and O. albinus indeed have high sensitivity to environmentally relevant UV levels in contrast to littoral species Eulimnogammarus cyaneus and E. verrucosus. The UV intolerance was more pronounced in deeper-dwelling O. albinus and was explainable by lower levels of carotenoids and carotenoid-binding proteins. Signs of oxidative stress were not found but specifically UV-B seemingly led to accumulation of toxic compounds. Overall, the obtained results demonstrate that UV is an important factor limiting distribution of deep-water amphipods into the littoral zone of Lake Baikal.

Thanks to the rapid advancements in Connected and Automated Vehicles (CAVs) and vehicular communication, the concept of the Internet of Vehicles (IoV) combined with Artificial Intelligence (AI) and big data technologies promotes the vision of an Intelligent Transportation System (ITS). By enabling a comprehensive data exchange platform, ITS is critical in enhancing road safety, traffic efficiency, and the overall driving experience. However, the open and dynamic nature of IoV networks brings significant performance and security challenges to IoV data acquisition, storage, and usage. To comprehensively tackle these challenges, this paper proposes a Decentralized Digital Watermarking framework for smart Vehicular networks (D2WaVe). Specifically, D2WaVe consists of two core components: FIAE-GAN, a novel feature-integrated and attention-enhanced robust image watermarking model based on a Generative Adversarial Network (GAN), and BloVA, a Blockchain-based Video frames Authentication scheme. By leveraging an encoder-noise-decoder framework, trained FIAE-GAN watermarking models can achieve the invisibility and robustness of watermarks that can be embedded in video frames to verify the authenticity of video data. Then, BloVA ensures the integrity and auditability of IoV data in the storing and sharing stages. Experimental results based on a proof-of-concept prototype implementation validate the feasibility and effectiveness of our D2WaVe scheme for securing and auditing video data exchange in smart vehicular networks.

(1) Background: Efficient detection and rectification of defects or post-processing manufacturing conditions such as sharp edges and burrs on metal components are crucial for quality control in precision manufacturing industries. (2) Methods: This paper describes a lab-scale integrated system for real-time and automated metal edge image detection using a customized YOLOv5 ma-chine vision algorithm. The YOLOv5 algorithm and model were developed and embedded in the NVIDIA Jetson Nano microprocessor. The YOLOv5 model can detect three different image types for classification i.e., normal, sharp, and burrs edge on aluminum workpiece blocks. An integrated system connects the NVIDIA Jetson Nano with an embedded YOLOv5 model to a Mitsubishi Electric Melfa RV-2F-1D1-S15 manipulator to perform selective automated chamfer-ing and grinding when certain condition defects are detected. (3) Results: The model demonstrates durable performance, achieving a mean average precision of 0.886 across defect classes with minimal misclassifications. The Mitsubishi Electric Melfa RV-2F-1D1-S15 manipulator received input from the machine vision system and performed an automated chamfering and grinding process accordingly; (4) Conclusions: By integrating camera, embedded deep learning in the microprocessor and manipulator, automated chamfering and grinding process in metal component shapes can be efficiently rectified. This tailored solution promises to improve productivity and consistency in metal manufacturing and remanufacturing.

In this study, we propose a scalable deep learning approach to automated phenotyping using UAV multispectral imagery, exemplified by yellow rust detection in winter wheat. We adopt a high granularity scoring method (1 to 9 scale) to align with international standards and plant breeders’ needs. Using a lower spatial resolution (60m flight height at 2.5cm GSD), we reduce the data volume by a factor of 3.4, making large-scale phenotyping faster and more cost-effective while obtaining results comparable to those of the state-of-the-art. Our model incorporates explainability components to optimise spectral bands and flight schedules, achieving top-3 accuracies of 0.87 for validation and 0.67 and 0.70 on two separate test sets. We demonstrate that a minimal set of bands (EVI, Red, and GNDVI) can achieve results comparable to more complex setups, highlighting the potential for cost-effective solutions. Additionally, we show that high performance can be maintained with fewer time steps, reducing operational complexity. Our interpretable model components improve performance through regularisation and provide actionable insights for agronomists and plant breeders. This scalable and explainable approach offers an efficient solution for yellow rust phenotyping and can be adapted for other phenotypes and species, with future work focusing on optimising the balance between spatial, spectral, and temporal resolutions.

Deep convolutional neural networks (CNNs) have revolutionised computer vision technology by automatically learning hierarchical representations of image data, leading to state-of-the-art performance in visual recognition tasks. This article presents a comprehensive review of deep CNNs, from their evolution and architectures to the current state-of-the-art research. The review also provides the core concepts and building blocks of CNNs and their concise mathematical representations. Furthermore, it explores applications of deep CNNs in three popular domains, including medical diagnosis, remote sensing, and facial recognition. This review will benefit researchers and practitioners in computer vision and artificial intelligence, as well as industry professionals seeking to leverage the latest advancements in deep learning technologies.