Search Results (18)

Soil moisture content (SMC) is a critical parameter for agricultural productivity, particularly in semi-arid regions, where irrigation practices are extensively used to offset water deficits and ensure decent yields. Yet, the socio-economic and remote context of these regions prevents sufficiently dense SMC monitoring in space and time to support farmers in their work to avoid unsustainable irrigation practices and preserve water resource availability. In this context, our study addresses the challenge of high spatial resolution (i.e., 20 m) SMC estimation by integrating remote sensing datasets in machine learning models. For this purpose, a dataset made of 166 soil samples’ SMC along with corresponding SMC, precipitation, and radar signal derived from Soil Moisture Active Passive (SMAP), Integrated Multi-satellitE Retrievals for GPM (IMERG), and Sentinel-1 (S1), respectively, was used to assess four machine learning models’ (Decision Tree—DT, Random Forest—RF, Gradient Boosting—GB, Extreme Gradient Boosting—XGB) reliability for SMC mapping. First, each model was trained/validated using only the coarse spatial resolution (i.e., 10 km) SMAP SMC and IMERG precipitation estimates as independent features, and, second, S1 information (i.e., 20 m) derived from single scenes and/or composite images was added as independent features to highlight the benefit of information (i.e., S1 information) for SMC mapping at high spatial resolution (i.e., 20 m). Results show that integrating S1 information from both single scenes and composite images to SMAP SMC and IMERG precipitation data significantly improves model reliability, as R² increased by 12% to 16%, while RMSE decreased by 10% to 18%, depending on the considered model (i.e., RF, XGB, DT, GB). Overall, all models provided reliable SMC estimates at 20 m spatial resolution, with the GB model performing the best (R² = 0.86, RMSE = 2.55%). Full article

Fuzzy clustering is a form of unsupervised learning that assigns the elements of a dataset into multiple clusters with varying degrees of membership rather than assigning them to a single cluster. The classical Fuzzy C-Means algorithm operates as an iterative procedure that minimizes an objective function defined based on the weighted distance between each point and the cluster centers. The algorithm operates decently in many datasets but struggles with datasets that exhibit irregularities in overlapping shapes, densities, and sizes of clusters. Meanwhile, there is a growing demand for accurate and scalable clustering techniques, especially in high-dimensional data analysis. This research work aims to address these infirmities of the classical fuzzy clustering algorithm by applying several modification approaches on the objective function of this algorithm. These modifications include several regularization terms aiming to make the algorithm more robust in specific types of datasets. The optimization of the modified objective functions is handled based on several numerical methods: gradient descent, root mean square propagation (RMSprop), and adaptive mean estimation (Adam). These methods are implemented in a Python environment, and extensive experimental studies are conducted, following carefully the steps of dataset selection, algorithm implementation, hyper-parameter tuning, picking the evaluation metrics, and analyzing the results. A comparison of the features of these algorithms on various datasets is carefully summarized. Full article

Parkinson’s disease (PD) is a neurodegenerative illness that affects the central nervous system and leads to a gradual degeneration of neurons that results in movement slowness, mental health problems, speaking difficulties, etc. In the past 20 years, the frequency of PD has doubled. Global estimates revealed that over 8.5 million cases have been identified so far. Thus, early and accurate detection of PD is crucial for treatment. Traditional detection methods are subjective and prone to delays, as they are reliant on clinical evaluation and imaging. Alternatively, artificial intelligence (AI) has recently emerged as a transformative technology in the healthcare sector, showing decent and promising results. However, an effective algorithm needs to be investigated for the most accurate prediction of a particular disease. Thus, this paper explores the ability of different machine learning algorithms in regard to the effective detection of PD. A total of 26 algorithms were implemented using the Scikit-Learn library on the Oxford PD detection dataset. This is a collection of 195 voice measurements recorded from 31 individuals, of which 23 have PD. The implemented algorithms are logistic regression, decision tree, k-nearest neighbors, random forest, support vector machine, Gaussian naïve bayes, multi-layered perceptron (MLP), extreme gradient boosting, adaptive boosting, stochastic gradient descent, gradient boosting machine, extra tree classifier, light gradient boosting machine, categorical boosting, Bernoulli naïve bayes, complement naïve bayes, multinomial naïve bayes, histogram-based gradient boosting, nearest centroid, radius neighbors classifier, logistic regression with elastic net regularization, extreme learning machine, ridge classifier, huber classifier, perceptron classifier, and voting classifier. Among them, MLP outperformed the other algorithms with a testing accuracy of 95%, precision of 94%, sensitivity of 100%, F1 score of 97%, and AUC of 98%. Thus, it successfully discriminates healthy individuals from those with PD, thereby helping for accurate early detection of PD for new patients using their voice measurements. Full article

Accurate diagnosis of Alzheimer’s Disease (AD) has largely focused on its later stages, often overlooking the critical need for early detection of Early Mild Cognitive Impairment (EMCI). Early detection is essential for potentially reducing mortality rates; however, distinguishing EMCI from Normal Cognitive (NC) individuals is challenging due to similarities in their brain patterns. To address this, we have developed a subject-level 3D-CNN architecture enhanced by preprocessing techniques to improve classification accuracy between these groups. Our experiments utilized structural Magnetic Resonance Imaging (sMRI) data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, specifically the ADNI3 collection. We included 446 subjects from the baseline and year 1 phases, comprising 164 individuals diagnosed with EMCI and 282 individuals with NC. When evaluated using 4-fold stratified cross-validation, our model achieved a validation AUC of 91.5%. On the test set, it attained an accuracy of 81.80% along with a recall of 82.50%, precision of 81.80%, and specificity of 80.50%, effectively distinguishing between the NC and EMCI groups. Additionally, a gradient class activation map was employed to highlight key regions influencing model predictions. In comparative evaluations against pretrained models and existing literature, our approach demonstrated decent performance in early AD detection. Full article

This paper investigates the sparse $\beta$ model with ${𝓁}_1$ penalty in the field of network data models, which is a hot topic in both statistical and social network research. We present a refined algorithm designed for parameter estimation in the proposed model. Its effectiveness is highlighted through its alignment with the proximal gradient descent method, stemming from the convexity of the loss function. We study the estimation consistency and establish an optimal bound for the proposed estimator. Empirical validations facilitated through meticulously designed simulation studies corroborate the efficacy of our methodology. These assessments highlight the prospective contributions of our methodology to the advanced field of network data analysis. Full article

The advent of Artificial Intelligence (AI) has had a broad impact on life to solve various tasks. Building AI models and integrating them with modern technologies is a central challenge for researchers. These technologies include wearables and implants in living beings, and their use is known as human augmentation, using technology to enhance human abilities. Combining human augmentation with artificial intelligence (AI), especially after the recent successes of the latter, is the most significant advancement in their applicability. In the first section, we briefly introduce these modern applications in health care and examples of their use cases. Then, we present a computationally efficient AI-driven method to diagnose heart failure events by leveraging actual heart failure data. The classifier model is designed without conventional models such as gradient descent. Instead, a heuristic is used to discover the optimal parameters of a linear model. An analysis of the proposed model shows that it achieves an accuracy of 84% and an $F_1$ score of 0.72 with only one feature. With five features for diagnosis, the accuracy achieved is 83%, and the $F_1$ score is 0.74. Moreover, the model is flexible, allowing experts to determine which variables are more important than others when implementing diagnostic systems. Full article

Connected and automated vehicles (CAVs) will be a key component of future cooperative intelligent transportation systems (C-ITS). Since the adoption of C-ITS is not foreseen to happen instantly, not all of its elements are going to be connected at the early deployment stages. We consider a scenario where vehicles approaching a traffic light are connected to each other, but the traffic light itself is not cooperative. Information about indented trajectories such as decisions on how and when to accelerate, decelerate and stop, is communicated among the vehicles involved. We provide an optimization-based procedure for efficient and safe passing of traffic lights (or other temporary road blockage) using vehicle-to-vehicle communication (V2V). We locally optimize objectives that promote efficiency such as less deceleration and larger minimum velocity, while maintaining safety in terms of no collisions. The procedure is computationally efficient as it mainly involves a gradient decent algorithm for one single parameter. Full article

Dual mobility (DM) implants are being increasingly used for total hip arthroplasties due to the additional range of motion and joint stability they afford over more traditional implant types. Currently, there are no reported methods for monitoring their motions under realistic operating conditions while in vitro and, therefore, it is challenging to predict how they will function under clinically relevant conditions and what failure modes may exist. This study reports the development, calibration, and validation of a novel inertial tracking system that directly mounts to the mobile liner of DM implants. The tracker was custom built and based on a miniaturized, off-the-shelf inertial measurement unit (IMU) and employed a gradient-decent sensor fusion algorithm for amalgamating nine degree-of-freedom IMU readings into three-axis orientation estimates. Additionally, a novel approach to magnetic interference mitigation using a fixed solenoid and magnetic field simulation was evaluated. The system produced orientation measurements to within 1.0° of the true value under ideal conditions and 3.9° with a negligible drift while in vitro, submerged in lubricant, and without a line of sight. Full article

Extensive amount of research on additively manufactured (AM) lattice structures has been made to develop a generalized model that can interpret how strongly operational variables affect mechanical properties. However, the currently used techniques such as physics models and multi-physics simulations provide a specific interpretation of those qualities, and are not general enough to assess the mechanical properties of AM lattice structures of different topologies produced on different materials via several fabrication methods. To tackle this problem, this study develops an optimal deep learning (DL) model based on more than 4000 data points, which has been optimized by analyzing three different hyper-parameters optimization schemes including gradient boost regression trees (GBRT), gaussian process (GP), and random forest (RF) with different data distribution schemes such as normal distribution, nth root transformation, and robust scaler. With the robust scaler and nth root transformation, the accuracy of the model increases from R² = 0.85 (for simple distribution) to R² = 0.94 and R² = 0.88, respectively. After feature engineering and data correlation, the stress, unit cell size, total height, width, and relative density are chosen to be the input parameters to model the strain. The optimal DL model is able to predict the strain of different topologies of lattices (such as circular, octagonal, Gyroid, truncated cube, Truncated cuboctahedron, Rhombic do-decahedron, and many others) with decent accuracy (R² = 0.936, MAE = 0.05, and MSE = 0.025). The parametric sensitivity analysis and explainable artificial intelligence (by using DeepSHAP library) based insights confirm that stress is the most sensitive input to the strain followed by the relative density from the modeling perspective of the AM lattices. The findings of this study would be helpful for the industry and the researchers to design AM lattice structures of different topologies for various engineering applications. Full article

During heavy rain on 1–2 June 2015 in central China, the Wuhan mesosphere–stratosphere–troposphere (MST) radar was applied to record the atmospheric responses to the rain with a 30 min period. According to the vertical gradient of the echo power above 500 hPa, the tropopause height could be determined by MST radar detection. The tropopause descent was clearly observed by the Wuhan MST radar a few hours before the rain, and then the tropopause recovered to usual heights during the rain. The observation of the radiosonde in Wuhan was in line with that of the radar. Both the potential vorticity and the ozone mass mixing ratio variations at 100 hPa level implied the fall of the tropopause. During the tropopause decent, enhanced radar echoes appeared in the upper troposphere, the echo spectral widths became broader, and the large vertical wind velocities were recorded and indicated the occurrence of strong convective activities. The relative humidity was also found to increase at all tropospheric heights, including the region close to the tropopause. The convective flow may have transported water vapor to the tropopause heights, and a temperature decrease in this region was also recorded. It is very likely that water vapor cooling induced the tropopause descent. Full article

Flow cytometry technique (FC) is a standard diagnostic tool for diagnostics of B-cell precursor acute lymphoblastic leukemia (BCP-ALL) assessing the immunophenotype of blast cells. BCP-ALL is often associated with underlying genetic aberrations, that have evidenced prognostic significance and can impact the disease outcome. Since the determination of patient prognosis is already important at the initial phase of BCP-ALL diagnostics, we aimed to reveal specific genetic aberrations by finding specific multiple antigen expression patterns with FC immunophenotyping. The FC immunophenotype data were analysed using machine learning methods (gradient boosting, decision trees, classification rules). The obtained results were verified with the use of repeated cross-validation. The t(12;21)/ETV6-RUNX1 aberration occurs more often when blasts present high expression of CD10, CD38, low CD34, CD45 and specific low expression of CD81. The t(v;11q23)/KMT2A is associated with positive NG2 expression and low CD10, CD34, TdT and CD24. Hyperdiploidy is associated with CD123, CD66c and CD34 expression on blast cells. In turn, high expression of CD81, low expression of CD45, CD22 and lack of CD123 and NG2 indicates that none of the studied aberrations is present. Detecting aberrations in pediatric BCP-ALL, based on the expression of multiple markers, can be done with decent efficiency. Full article

Conductive hydrogels are widely used in sports monitoring, healthcare, energy storage, and other fields, due to their excellent physical and chemical properties. However, synthesizing a hydrogel with synergistically good mechanical and electrical properties is still challenging. Current fabrication strategies are mainly focused on the polymerization of hydrogels with a single component, with less emphasis on combining and matching different conductive hydrogels. Inspired by the gradient modulus structures of the human skin, we propose a bilayer structure of conductive hydrogels, composed of a spray-coated poly(3,4-dihydrothieno-1,4-dioxin): poly(styrene sulfonate) (PEDOT:PSS) as the bonding interface, a relatively low modulus hydrogel on the top, and a relatively high modulus hydrogel on the bottom. The spray-coated PEDOT:PSS constructs an interlocking interface between the top and bottom hydrogels. Compared to the single layer counterparts, both the mechanical and electrical properties were significantly improved. The as-prepared hydrogel showed outstanding stretchability (1763.85 ± 161.66%), quite high toughness (9.27 ± 0.49 MJ/m³), good tensile strength (0.92 ± 0.08 MPa), and decent elastic modulus (69.16 ± 8.02 kPa). A stretchable strain sensor based on the proposed hydrogel shows good conductivity (1.76 S/m), high sensitivity (a maximum gauge factor of 18.14), and a wide response range (0–1869%). Benefitting from the modulus matching between the two layers of the hydrogels, the interfacial interlocking network, and the patch effect of the PEDOT:PSS, the strain sensor exhibits excellent interface robustness with stable performance (>12,500 cycles). These results indicate that the proposed bilayer conductive hydrogel is a promising material for stretchable electronics, soft robots, and next-generation wearables. Full article

‘Esmeralda’ is an orange fleshed peach cultivar primarily used for juice extraction and secondarily used for the fresh fruit market. Fruit yield and quality depend on several local environmental and managerial factors, mainly on nitrogen, which must be balanced with other nutrients. Similar to other perennial crops, peach trees show carryover effects of carbohydrates and nutrients and of nutrients stored in their tissues. The aims of the present study are (i) to identify the major sources of seasonal variability in fruit yield and qu Fruit Tree Department of Federal University of Pelotas (UFPEL), Pelotas 96010610ality; and (ii) to establish the N dose and the internal nutrient balance to reach high fruit yield and quality. The experiment was conducted from 2014 to 2017 in Southern Brazil and it followed five N treatments (0, 40, 80, 120 and 160 kg N ha⁻¹ year⁻¹). Foliar compositions were centered log-ratio (clr) transformed in order to account for multiple nutrient interactions and allow computing distances between compositions. Based on the feature ranking, chilling hours, degree-days and rainfall were the most influential features. Machine learning models k-nearest neighbors (KNN) and stochastic gradient decent (SGD) performed well on yield and quality indices, and reached accuracy from 0.75 to 1.00. In 2014, fruit production did not respond to added N, and it indicated the carryover effects of previously stored carbohydrates and nutrients. The plant had a quadratic response (p < 0.05) to N addition in 2015 and 2016, which reached maximum yield of 80 kg N ha⁻¹. In 2017, harvest was a failure due to the chilling hours (198 h) and the relatively small number of fruits per tree. Fruit yield and antioxidant content increased abruptly when foliar clr_Cu was >−5.410. The higher foliar P linearly decreased total titratable acidity and increased pulp firmness when clr_P > 0.556. Foliar N concentration range was narrow at high fruit yield and quality. The present results have emphasized the need of accounting for carryover effects, nutrient interactions and local factors in order to predict peach yield and nutrient dosage. Full article

Buildings in hot climate areas are responsible for high energy consumption due to high cooling load requirements which lead to high greenhouse gas emissions. In order to curtail the stress on the national grid and reduce the atmospheric emissions, it is of prime importance that buildings produce their own onsite electrical energy using renewable energy resources. Photovoltaic (PV) technology is the most favorable option to produce onsite electricity in buildings. Installation of PV modules on the roof of the buildings in hot climate areas has a twofold advantage of acting as a shading device for the roof to reduce the cooling energy requirement of the building while producing electricity. A high ground coverage ratio provides more shading, but it decreases the efficiency of the PV system because of self-shading of the PV modules. The aim of this paper was to determine the optimal value of the ground coverage ratio which gives maximum overall performance of the roof-mounted PV system by considering roof surface shading and self-shading of the parallel PV modules. An unsupervised artificial neural network approach was implemented for Net levelized cost of energy (Net-LCOE) optimization. The gradient decent learning rule was used to optimize the network connection weights and the optimal ground coverage ratio was obtained. The proposed optimized roof-mounted PV system was shown to have many distinct performance advantages over a typical ground-mounted PV configuration such as 2.9% better capacity factor, 15.9% more energy yield, 40% high performance ratio, 14.4% less LCOE, and 18.6% shorter payback period. The research work validates that a roof-mounted PV system in a hot climate area is a very useful option to meet the energy demand of buildings. Full article

Convolutional neural networks (CNNs) have made great achievements on computer vision tasks, especially the image classification. With the improvement of network structure and loss functions, the performance of image classification is getting higher and higher. The classic Softmax + cross-entropy loss has been the norm for training neural networks for years, which is calculated from the output probability of the ground-truth class. Then the network’s weight is updated by gradient calculation of the loss. However, after several epochs of training, the back-propagation errors usually become almost negligible. For the above considerations, we proposed that batch normalization with adjustable scale could be added after network output to alleviate the problem of vanishing gradient problem in deep learning. The experimental results show that our method can significantly improve the final classification accuracy on different network structures, and is also better than many other improved classification Loss. Full article