Explore the vast range of titles available.

Precision agriculture is the mechanism which controls the land productivity and maximizes the revinue and minimizes the impact on sorroundings by automating the complete agriculture processes. This projected work relies on independent internet of things (IoT) enabled wireless sensor network (WSN) framework consisting of soil moisture (MC) probe, soil temperature measuring device, environmental temperature sensor, environmental humidity sensing device, CO 2 sensor, daylight intensity device (light dependent resistor) to acquire real-time farm information through multi-point measurement. The projected observance technique consists of all standalone IoT-enabled WSN nodes used for timely data acquisitions and storage of agriculture information. The farm history is additionally stored for generating necessary action throughout the whole course of farming. The work summarizes the optimum usage of irrigation by the precise management of water valve using neural network-based prediction of soil water requirement in 1 h ahead. Our proposed irrigation control scheme utilizes structural similarity (SSIM)-based water valve management mechanism which is used to locate farm regions having water deficiency. Moreover, a close comparative study of optimization techniques, like variable learning rate gradient descent, gradient descent for feedforward neural network-based pattern classification, is performed and the best practice is employed to forecast soil MC on hourly basis together with interpolation method for generating soil moisture content (MC) distribution map. Finally, SSIM index-based soil MC deficiency is calculated to manipulate the specified valves for maintaining uniform water requirement through the entire farm area. The valve control commands are again processed using fuzzy logic-based weather condition modeling system to manipulate control commands by considering different weather conditions.

Relative smoothness—a notion introduced in Birnbaum et al. (Proceedings of the 12th ACM conference on electronic commerce, ACM, pp 127–136, 2011) and recently rediscovered in Bauschke et al. (Math Oper Res 330–348, 2016) and Lu et al. (Relatively-smooth convex optimization by first-order methods, and applications, arXiv:1610.05708, 2016)—generalizes the standard notion of smoothness typically used in the analysis of gradient type methods. In this work we are taking ideas from well studied field of stochastic convex optimization and using them in order to obtain faster algorithms for minimizing relatively smooth functions. We propose and analyze two new algorithms: Relative Randomized Coordinate Descent (relRCD) and Relative Stochastic Gradient Descent (relSGD), both generalizing famous algorithms in the standard smooth setting. The methods we propose can be in fact seen as particular instances of stochastic mirror descent algorithms, which has been usually analyzed under stronger assumptions: Lipschitzness of the objective and strong convexity of the reference function. As a consequence, one of the proposed methods, relRCD corresponds to the first stochastic variant of mirror descent algorithm with linear convergence rate.

Handwritten digit recognition is a complex problem that has stumped even the brilliant minds of this century. Getting precise results from different handwritten samples has been a challenge that needs to be addressed due to the occurrence of this issue in several sectors like document verification, post mail, deciphering, etc. Hence, we introduce our paper as a response to the requirement of an accurate model that can acutely recognize and then predict the handwriting of a variety of individuals with ease. Our model aims to do number recognition through the implementation of neural networks. We tested out different models with each optimizer to verify which model provided the best performance and with which optimizer. Optimizers are an inherent part of Deep learning, and they are used to upgrade the weights, so the model can learn accordingly and get a more accurate system. Instead of just comparing the performance of various optimizers with only one model, we compared different model performances, while trying to select the optimizer that would best suit that learning model. Rigorous training and experimentalizing have resulted in an accuracy of 98.55% for an ANN model employed with an Adagrad optimizer.

Zero-velocity assumption has been used for estimation of foot trajectory and stride length during running from the data of foot-mounted inertial measurement units (IMUs). Although the assumption provides a reasonable initialization for foot trajectory and stride length estimation, the other source of errors related to the IMU’s orientation still remains. The purpose of this study was to develop an improved foot trajectory and stride length estimation method for the level ground running based on the displacement of the foot. Seventy-nine runners performed running trials at 5 different paces and their running motions were captured using a motion capture system. The accelerations and angular velocities of left and right feet were measured with two IMUs mounted on the dorsum of each foot. In this study, foot trajectory and stride length were estimated using zero-velocity assumption with IMU data, and the orientation of IMU was estimated to calculate the mediolateral and vertical distance of the foot between two consecutive midstance events. Calculated foot trajectory and stride length were compared with motion capture data. The results show that the method used in this study can provide accurate estimation of foot trajectory and stride length for level ground running across a range of running speeds.

Deep neural networks (DNN) are commonly employed. Deep networks' many parameters require extensive training. Complex optimizers with multiple hyper parameters speed up network training and increase generalisation. Complex optimizer hyper parameter tuning is generally trial-and-error. In this study, we visually assess the distinct contributions of training samples to a parameter update. Adaptive stochastic gradient descent is a variation of batch stochastic gradient descent for neural networks using ReLU in hidden layers (aSGD). It involves the mean effective gradient as the genuine slope for boundary changes, in contrast to earlier procedures. Experiments on MNIST show that aSGD speeds up DNN optimization and improves accuracy without added hyper parameters. Experiments on synthetic datasets demonstrate it can locate redundant nodes, which helps model compression.

With many distribution networks adopting photovoltaic (PV) generation systems in their networks, there is a significant risk of over-voltages, reverse power flow, line congestion, and increased harmonics. Therefore, there is a need to estimate the amount of PV that can be injected into the distribution network without pushing the network towards these threats. The largest amount of PV a distribution system can accommodate is the PV hosting capacity (PVHC). The paper proposes an efficient method for estimating the PVHC of distribution networks that combines particle swarm optimization (PSO) and the gradient descent algorithm (GD). PSO has a powerful exploration of the solution space but poor exploitation of the local search. On the other hand, GD has great exploitation of local search to obtain local optima but needs better global search capabilities. The proposed method aims to harness the advantages of both PSO and GD while alleviating the ills of each. The numerical case studies show that the proposed method is more efficient, stable, and superior to the other meta-heuristic approaches.

This paper presents an adaptive PID using stochastic gradient descent with momentum (SGDM) for a proton exchange membrane fuel cell (PEMFC) power system. PEMFC is a nonlinear system that encounters external disturbances such as inlet gas pressures and temperature variations, for which an adaptive control law should be designed. The SGDM algorithm is employed to minimize the cost function and adapt the PID parameters according to the perturbation changes. The whale optimization algorithm (WOA) was chosen to enhance the adaptive rates in the offline mode. The proposed controller is compared with PID stochastic gradient descent (PIDSGD) and PID Ziegler Nichols tuning (PID-ZN). The control strategies’ robustnesses are tested under a variety of temperatures and loads. Unlike the PIDSGD and PID-ZN controllers, the PIDSGDM controller can attain the required control performance, such as fast convergence and high robustness. Simulation results using Matlab/Simulink have been studied and illustrate the effectiveness of the proposed controller.

Deep learning (DL) models are used in a variety of real-world applications but are often vulnerable to privacy attacks. Nevertheless, this DL model is attacked by membership inference attacks, model inversion attacks, reconstruction attacks, model extraction attacks, gradient leakage attacks, correlation attacks, and white box attacks (inference attacks). In order to mitigate this issue, various existing research has attempted to design an effective privacy mechanism. However, the existing schemes failed to obtain higher security in DL because of several limitations like computational complexity, lower efficiency, difficult-to-select parameters, cumulative privacy loss, etc. Recently, the auto-encoder-based deep learning model has become more popular due to its great ability, and its variants have achieved notable success in various fields such as medicine, healthcare and NLP (Natural Language Programming). However, the privacy of the auto-encoder model is affected because of the vulnerable attacks. Thus, to avoid this issue, the proposed study prefers the differential privacy (DP) method for securing the deep auto-encoder model. DP is a privacy-preserving technique that can be used to protect deep learning models from the aforementioned attacks. In this paper, a Differential Privacy-Improved Stochastic Gradient Descent (DP-ISGD) algorithm is proposed to improve the privacy and utility of the Deep Autoencoder method by adding Gaussian noise to the gradients before the clipping process. Thus, the convergence speed and accuracy of the proposed algorithm are enhanced. The experimentation is conducted in the Python platform, and metrics like convergence, accuracy and TPVD (Total Parameters Value Difference) are evaluated to measure the performance of the proposed study. The comparative analysis is performed for the no privacy, privacy with SGD, privacy with batch gradient descent (BGD) and mini-batch gradient descent (MBGD) models. The proposed approach is evaluated against six datasets, Pima Indians Diabetes (PID), Adult, MNIST, CIFAR-10, MovieLens 20 M and CD-FSL, with improved accuracy results of 98.6%, 98.6%, 98.3%, 98.14%, 97.92% and 98.17% for each dataset at the epsilon ( ε ) value of 0.2. The comparison analysis showed that the proposed algorithm achieves better accuracy than other privacy protection methods. Thus, the significant findings in the proposed work state that the proposed privacy model is suitable for several applications, including medical fields, algorithm development, education and awareness, by affording strong privacy guarantees.

The paper presents a review of the current state of subgradient and accelerated convex optimization methods, including the cases with the presence of noise and access to various information about the objective function (function value, gradient, stochastic gradient, higher derivatives). For nonconvex problems, the Polyak–Lojasiewicz condition is considered and a review of the main results is given. The behavior of numerical methods in the presence of a sharp minimum is considered. The aim of this review is to show the influence of the works of B.T. Polyak (1935–2023) on gradient optimization methods and their surroundings on the modern development of numerical optimization methods.