Descent Process Research Articles

RETRACTED ARTICLE: Big data tracking and automatic measurement technology for unmanned aerial vehicle trajectory based on MEMS sensor

The usage of unmanned aerial vehicles (UAVs) is rapidly increasing in the current era as these devices are capable enough in providing unique solutions in applications such as inspection of environment, identification of disaster, rescue operations, and defense systems. For the governance of the flight missions in a complex defense environment, the usage of these systems necessitated a sound command over data mining process. The large volume of data is generated by UAVs and processing of this data is a challenging issue. The existing data tracking and management systems are expensive and complex. For defense systems, smarter solutions are needed to process the large volume of data at low cost and with high accuracy. Therefore, a technique of tracking the data generated by UAV and automatic measurement of trajectory based on micro-electro-mechanical systems sensor in UAV has been proposed in this paper to provide inexpensive solutions to overcome the problems of the existing data tracking and processing systems. An iterative learning control algorithm is utilized in UAV to ascertain the disturbance and modeling errors. The finest characteristics of the Kalman filter technique are used for estimations of UAV trajectory. The quadratic performance function is introduced in discrete equation to solve the model error disturbance. Then on the basis of gyroscope data, the quaternion differential equation is formulated. The gradient descent process is also used to speed up the processing of UAV data. The results depict that the proposed technique has the lowest data tracking error of the UAV trajectory (0.09%) and has good measurement accuracy of 92%. The proposed method also reduces time complexity and searches the solution space in a faster manner.

A New Algorithm for Spectral Conjugate Gradient in Nonlinear Optimization

CJG is a nonlinear conjugation gradient. Algorithms have been used to solve large-scale unconstrained enhancement problems. Because of their minimal memory needs and global convergence qualities, they are widely used in a variety of fields. This approach has lately undergone many investigations and modifications to enhance it. In our daily lives, the conjugate gradient is incredibly significant. For example, whatever we do, we strive for the best outcomes, such as the highest profit, the lowest loss, the shortest road, or the shortest time, which are referred to as the minimum and maximum in mathematics, and one of these ways is the process of spectral gradient descent. For multidimensional unbounded objective function, the spectrum conjugated gradient (SCJG) approach is a strong tool. In this study, we describe a revolutionary SCG technique in which performance is quantified. Based on assumptions, we constructed the descent condition, sufficient descent theorem, conjugacy condition, and global convergence criteria using a robust Wolfe and Powell line search. Numerical data and graphs were constructed utilizing benchmark functions, which are often used in many classical functions, to demonstrate the efficacy of the recommended approach. According to numerical statistics, the suggested strategy is more efficient than some current techniques. In addition, we show how the unique method may be utilized to improve solutions and outcomes.

Extracting hierarchical features of cultural variation using network-based clustering.

High-dimensional datasets on cultural characters contribute to uncovering insights about factors that influence cultural evolution. Because cultural variation in part reflects descent processes with a hierarchical structure – including the descent of populations and vertical transmission of cultural traits – methods designed for hierarchically structured data have potential to find applications in the analysis of cultural variation. We adapt a network-based hierarchical clustering method for use in analysing cultural variation. Given a set of entities, the method constructs a similarity network, hierarchically depicting community structure among them. We illustrate the approach using four datasets: pronunciation variation in the US mid-Atlantic region, folklore variation in worldwide cultures, phonemic variation across worldwide languages and temporal variation in first names in the US. In these examples, the method provides insights into processes that affect cultural variation, uncovering geographic and other influences on observed patterns and cultural characters that make important contributions to them.

Overview of Algorithms for Natural Language Processing and Time Series Analyses.

A host of machine learning algorithms have been used to perform several different tasks in NLP and TSA. Prior to implementing these algorithms, some degree of data preprocessing is required. Deep learning approaches utilizing multilayer perceptrons, recurrent neural networks (RNNs), and convolutional neural networks (CNNs) represent commonly used techniques. In supervised learning applications, all these models map inputs into a predicted output and then model the discrepancy between predicted values and the real output according to a loss function. The parameters of the mapping function are then optimized through the process of gradient descent and backward propagation in order to minimize this loss. This is the main premise behind many supervised learning algorithms. As experience with these algorithms grows, increased applications in the fields of medicine and neuroscience are anticipated.

A Numerical Study on the Optimization of the Material Pressure of the Feeding System

To solve the problem of high energy consumption caused by the large initial material pressure of the feeding system, the macroscopic and mesoscopic laws of the effect of the movement of the feeder on the material pressure were studied, and an optimization method of changing the initial position of the feeder to reduce the initial material pressure is proposed. First, the influence of the movement direction of the feeder on the material pressure was studied based on the discrete element method and verified by experiments. A single-factor experiment was designed to analyze the influence of particle size, material repose angle, and bin slope on material pressure, drawing the applicable conditions of the proposed method. On this basis, the influence of the movement state of the feeder on the change of material pressure during the descent process was studied. Then, the motion parameters of the selected feeder descending process were optimized by the response surface method. Finally, case analyses of the vibrating feeding system and the scraper feeding system were carried out. The Discrete Element Method (DEM) calculation results show that the movement of the feeder will cause different distributions and evolution of the force chain on the mesoscale, which will result in different changes in the macroscopic material pressure. The initial material pressure and the material resistance were reduced in the optimized feeding system.

Assessing Energy Descent Scenarios for the Ecological Transition in Spain 2020–2030

A global energy consumption reduction is essential to address the many dimensions of the current ecological crisis. In this paper we have compiled the reasons that justify the necessity to start this energy descent process in the countries of the global North, where the annual per capita final energy consumption was 118 GJ in 2017. Based on recent research, we approach the necessary redistribution of energy consumption at the global level and the elements that should be present in energy descent strategies. We establish an approximate threshold of minimum and maximum per capita final energy consumption, between 15.6 GJ and 31.0 GJ for the year 2050, which serves as a reference for evaluating scenarios. We continue with an analysis of two ecological transition scenarios for Spain between 2020 and 2030, Green New Deal and Degrowth. Based on a schematic calculation model defined in “Labor Scenarios in the Ecosocial Transition 2020–2030” report, we evaluate the variations in energy consumption for 86 sectors of economic activity. Results show an annual final energy consumption per capita in 2030 of 44.6 GJ and 36.8 GJ for each scenario. We conclude by analyzing the hypothetical main drivers of this sharp decline in energy consumption.

An adaptive federated learning scheme with differential privacy preserving

Driven by the upcoming development of the sixth-generation communication system (6G), the distributed machine learning schemes represented by federated learning has shown advantages in data utilization and multi-party cooperative model training. The total communication costs of federated learning is related to the number of communication rounds, the communication consumption of each participants, the setting of reasonable learning rate and the guarantee of calculation fairness. In addition, the isolating data strategy in the federated learning framework cannot completely guarantee the privacy security of users. Motivated by the above problems, this paper proposes a federated learning scheme combined with the adaptive gradient descent strategy and differential privacy mechanism, which is suitable for multi-party collaborative modeling scenarios. To ensure that federated learning scheme can train efficiently with limited communications costs, the adaptive learning rate algorithm is innovatively used to adjust the gradient descent process and avoid the model overfitting and fluctuation phenomena, so as to improve the modeling efficiency and performance in multi-party calculation scenarios. Furthermore, in order to adapt to the ultra-large-scale distributed secure computing scenario, this research introduces differential privacy mechanism to resist various background knowledge attacks. Experimental results demonstrate that the proposed adaptive federated learning model performs better than the traditional models under fixed communication costs. This novel modeling scheme also has strong robustness to different super-parameter settings and provides stronger quantifiable privacy preserving for federated learning process.

A new procedure for optimization of hidden layer neurons during learning through gradient descent process of neural network and improvement of performance in the chaos forecasting

A new procedure for optimization of hidden layer neurons during learning through gradient descent process of neural network and improvement of performance in the chaos forecasting

Smoothed amplitude flow-based phase retrieval algorithm

Phase retrieval recovers signals from linear phaseless measurements via minimizing a quadratic or amplitude function, while its loss function is generally either non-convex or non-smooth. Existing methods are used to add a truncation procedure or reweighting to the gradient during the gradient descent process to address the non-smooth problem. However, these methods often cause inconsistency in the search direction and increase the sampling complexity. This paperproposes a smoothed amplitude flow-based phase retrieval (SAFPR) algorithm to solve these problems. By introducing the smoothing function into the phase retrieval problem, the loss function is smoothed, significantly reducing the sampling complexity. Moreover, we also develop a stochastic smooth amplitude flow-based phase retrieval (SSAF) algorithm with practical, scalable, and fast in large-scale applications. Experimental results show that whether SAFPR or SSAF, the number of measurements required to reconstruct the signal entirely is better than the existing most advanced phase retrieval algorithms. The proposed methods also perform well in terms of time cost and convergence rate.

Improved Genetic Algorithm (VNS-GA) using polar coordinate classification for workload balanced multiple Traveling Salesman Problem (mTSP)

The multiple traveling salesman problem (mTSP) is an extension of the traveling salesman problem (TSP), which has wider applications in real life than the traveling salesman problem such as transportation and delivery, task allocation, etc. In this paper, an improved genetic algorithm (VNS-GA) that uses polar coordinate classification to generate the initial solutions is proposed. It integrates the variable neighbourhood algorithm to solve the multiple objective optimization of the mTSP with workload balance. Aiming to workload balance, the first design of this paper is about generating initial solutions based on the polar coordinate classification. Then a distance comparison insertion operator is designed as a neighbourhood action for allocating paths in a targeted manner. Finally, the neighbourhood descent process in the variable neighbourhood algorithm is fused into the genetic algorithm for the expansion of search space. The improved algorithm is tested on the TSPLIB standard data set and compared with other genetic algorithms. The results show that the improved genetic algorithm can increase computational efficiency and obtain a better solution for workload balance and this algorithm has wild applications in real life such as multiple robots task allocation, school bus routing problem and other optimization problems.

BDNF is upregulated by androgen in the inguinal fat pad of immature mice and may regulate inguinoscrotal testicular descent.

Androgens control rodent inguinoscrotal testicular descent during a "programming window" (E12-17). It is proposed that androgen masculinises the genitofemoral nerve, but the mechanism remains unknown. We investigate androgen receptor (AR)-containing target organs: inguinal fat pad (IFP) and mammary bud (MB), supplied by the genitofemoral nerve, hypothesizing that neurotrophic factors may retrogradely masculinise the GFN. The IFP, MB and bulbocavernosus (BC) muscle were collected at E12.5/E17.5 from androgen receptor knockout (ARKO) mice and wild-type (WT) littermates. Immunofluorescence and gene expression (RT-qPCR; n = 8/group) for Bdnf, active (TrkB) and inactive (truncated TrkB) receptors, Cntf and Cntf receptor were performed. In the IFP at E12.5, ARKO TrkB mRNA expression was significantly downregulated compared to WT males (p < 0.0026). By E17.5, there was increased Bdnf expression (p < 0.0233). The MB had no differences at E12.5 and had regressed in WT males by E17.5. The BC had no differences at E12.5, but at E17.5 had significant upregulation of Bdnf expression in ARKO, compared to WT males. There were no differences in CNTF or CNTF receptor expression. Androgen alters active TrkB and Bdnf expression in the IFP. IFP Bdnf signalling may regulate "masculinisation" of the GFN sensory nerves to indirectly control inguinoscrotal testicular descent. Androgen mediates neurotrophin release in the inguinal fat pad in mice, which may facilitate normal testicular descent by masculinising the GFN by peripheral uptake of neurotrophin. This is the first study to examine the role of neurotrophins in testicular descent. This suggests novel steps in the mechanical process of normal testicular descent that may be abnormal in some children with undescended testes.

Research on Prediction of Movable Fluid Percentage in Unconventional Reservoir Based on Deep Learning

In order to improve the measurement speed and prediction accuracy of unconventional reservoir parameters, the deep neural network (DNN) is used to predict movable fluid percentage of unconventional reservoirs. The Adam optimizer is used in the DNN model to ensure the stability and accuracy of the model in the gradient descent process, and the prediction effect is compared with the back propagation neural network (BPNN), K-nearest neighbor (KNN), and support vector regression model (SVR). During network training, L2 regularization is used to avoid over-fitting and improve the generalization ability of the model. Taking nuclear magnetic resonance (NMR) T2 spectrum data of laboratory unconventional core as input features, the influence of model hyperparameters on the prediction accuracy of reservoir movable fluids is also experimentally analyzed. Experimental results show that, compared with BPNN, KNN, and SVR, the deep neural network model has a better prediction effect on movable fluid percentage of unconventional reservoirs; when the model depth is five layers, the prediction accuracy of movable fluid percentage reaches the highest value, the predicted value of the DNN model is in high agreement with the laboratory measured value. Therefore, the movable fluid percentage prediction model of unconventional oil reservoirs based on the deep neural network model can provide certain guidance for the intelligent development of the laboratory’s reservoir parameter measurement.

Solving Fractional Differential Equations by Using Triangle Neural Network

In this paper, numerical methods for solving fractional differential equations by using a triangle neural network are proposed. The fractional derivative is considered Caputo type. The fractional derivative of the triangle neural network is analyzed first. Then, based on the technique of minimizing the loss function of the neural network, the proposed numerical methods reduce the fractional differential equation into a gradient descent problem or the quadratic optimization problem. By using the gradient descent process or the quadratic optimization process, the numerical solution to the FDEs can be obtained. The efficiency and accuracy of the presented methods are shown by some numerical examples. Numerical tests show that this approach is easy to implement and accurate when applied to many types of FDEs.

Formal Derivation of Mesh Neural Networks with Their Forward-Only Gradient Propagation

This paper proposes the Mesh Neural Network (MNN), a novel architecture which allows neurons to be connected in any topology, to efficiently route information. In MNNs, information is propagated between neurons throughout a state transition function. State and error gradients are then directly computed from state updates without backward computation. The MNN architecture and the error propagation schema is formalized and derived in tensor algebra. The proposed computational model can fully supply a gradient descent process, and is potentially suitable for very large scale sparse NNs, due to its expressivity and training efficiency, with respect to NNs based on back-propagation and computational graphs.

진화전략(Evolution Strategy)을 활용한 최대ㆍ최소 탐구과정 및 코딩환경 연구

The purpose of this study is to develop a curriculum of school mathematics and artificial intelligence regarding max-min problems. We also developed a coding environment for a designed curriculum that can be accessed and utilized at codingmath.org without any additional installation. The curriculum uses an evolution strategy-based gradient descent method founded on a school probability and statistics curriculum with an experiment using dice; this curriculum is designed to work when the function is not differentiable and is ultimately linked to a calculus-based gradient descent method. The coding environment, in which even middle school students can visualize the min-max problem of f(x,y), uses a three-dimensional function graph with minimal coding inputs and explores the gradient descent process using a two-dimensional Python animation. This study, which is an attempt to combine mathematical problem solving and computational thinking in the context of max-min problems, further discusses ideas regarding the ways to integrate AI and coding in mathematics education.

Process of fetal head descent as recorded by ultrasonography: How does this compare with the conventional first stage of labor?

To construct an ultrasound partogram using serial transperineal sonographic measurements of the angle of fetal head progression during the first stage of labor, and to compare it with a conventional partogram based on digital vaginal examinations. Between 2017 and 2018, a prospective cohort study at Drum Tower Hospital, Nanjing, China, recruited 375 nulliparous women with singleton pregnancy and spontaneous onset of labor at 37 or more gestational weeks. Transperineal ultrasound scans were performed to measure the angle of progression (AoP) every 0.5-1h until the second stage. Vaginal examinations were also used to measure cervical dilatation. Repeated-measures analysis was used to generate labor curves. The labor curve generated by AoP had a pattern similar to that based on cervical dilatation. There was an initial slow period lasting approximately 5.5h until the cervical dilatation or AoP reached the inflection point (4cm and 119°, respectively), followed by a second, more rapid period, lasting approximately 2.5h. Based on ultrasound data, it was feasible to construct an "angle of progression partogram" of the first stage of labor, which was similar in pattern to the partogram based on cervical dilatation measured in the same cohort.

CONCEPT AND APPLICATION OF BASTI TREATMENT DURING PREGNANCY – A SCIENTIFIC APPROACH THROUGH AYURVEDA

Ayurveda is an indigenous system of medicine, emphasizes the Garbhavkranti (process of descent of various components in embryo) to prasava (process of labour) and sutika(puerperium) very well. In ayurveda Garbhini paricharya is planned for systemic supervision and care of a woman during nine months of pregnancy. In pregnancy only a little change in Ahara-Vihara leads to alter the doshas state. Vata dosha has a great influence on psychological built up which exerts considerable influence on maintaining normal pregnancy. Vitiated Vat dosha is the main reason for physical and psychological abnormalities in pregnant woman like PROM, IUGR etc. Basti therapy is the best curative treatment for vitiated Vata. Generally Panchakarma procedures are contraindicated in pregnancy but there are only few Basti treatments mentioned by Acharyas in Garbhini Paricharya which can give during pregnancy which are discussed in this article.&#x0D; Keywords: Pregnancy, Vata dosha, Basti.

Automatic Road Extraction From Remote Sensing Imagery Using Ensemble Learning and Postprocessing

High-resolution satellite images contain valuable road semantic information, but the occlusion of vegetation and buildings and the sparse distribution and heterogeneous appearance of roads limit the accuracy of road extraction models. In this article, we propose a novel method for extracting roads using an ensemble learning model with a postprocessing stage. The network weights and biases of our proposed deep learning model are transmitted through the random combination of layers of different submodels during forward and backward propagation. In the gradient descent process, a superior loss function is designed to solve the problem of class imbalance caused by road sparseness, and more attention is given to hard classification samples to extract narrow and covered roads. In addition, we solve road disconnection issues in the results obtained with the neural network by extracting and analyzing the geometric structures and feature points of the roads. Experiments on two challenging datasets of remote sensing imagery show that the proposed method performs better than other models and can extract road information from complex scenes.

Deep Amended Gradient Descent for Efficient Spectral Reconstruction From Single RGB Images

This paper investigates the problem of recovering hyperspectral (HS) images from single RGB images. To tackle such a severely ill-posed problem, we propose a physically-interpretable, compact, efficient, and end-to-end learning-based framework, namely AGD-Net. Precisely, by taking advantage of the imaging process, we first formulate the problem explicitly based on the classic gradient descent algorithm. Then, we design a lightweight neural network with a multi-stage architecture to mimic the formed amended gradient descent process, in which efficient convolution and novel spectral zero-mean normalization are proposed to effectively extract spatial-spectral features for regressing an initialization, a basic gradient, and an incremental gradient. Besides, based on the approximate low-rank property of HS images, we propose a novel rank loss to promote the similarity between the global structures of reconstructed and ground-truth HS images, which is optimized with our singular value weighting strategy during training. Moreover, AGD-Net, a single network after one-time training, is flexible to handle the reconstruction with various spectral response functions. Extensive experiments over three commonly-used benchmark datasets demonstrate that AGD-Net can improve the reconstruction quality by more than 1.0 dB on average while saving 67× parameters and 32× FLOPs, compared with state-of-the-art methods. The code will be publicly available at https://github.com/zbzhzhy/GD-Net .

The Variational Kernel-Based 1-D Convolutional Neural Network for Machinery Fault Diagnosis

One-dimensional convolutional neural network (1-D CNN) can be directly applied to process temporal signals in the machinery fault diagnosis. However, it requires a large amount of data to train high-quality kernels and extract meaningful features. This article develops a novel method integrating learnable variational kernels into a 1-D CNN to pay more attention to extracting important fault-related data features and offer decent performance with even limited data. In the proposed method, the variational kernel is first derived by adapting constraints and formulations of the successive variational mode decomposition (SVMD). Next, a gradient descent process based on a fault classification loss is developed to estimate the parameter of the variational kernel. Lastly, a CNN-based diagnosis model is constructed to perform machinery fault diagnoses. The proposed model is benchmarked with two standard 1-D CNNs and four wavelet kernel-based 1-D CNNs. Datasets collected from train bearing and gearbox test rigs are used for validations. Results show that the proposed model identifies important fault-related features and performs better in machinery fault diagnoses with limited training data.