Adaptive Learning Techniques Research Articles

Enhancing Precision and Stability: A Cognitive Approach for Pesticide Image Segmentation in Crop Leaves

The precise delineation of pests from crop foliage is a crucial stage in the field of intelligent pest identification. This study presents a novel cognitive segmentation methodology that aims to enhance the accuracy and reliability of this crucial procedure. The technique comprises a number of essential stages: To begin with, the proposed method utilises sophisticated image block processing techniques to partition the pest image into smaller, more manageable parts. Additionally, an adaptive learning technique is utilised to carefully choose the initial cluster centres, hence guaranteeing the precision of the segmentation procedure. Subsequently, the use of K-means clustering facilitates the acquisition of initial segmentation outcomes, hence augmenting the procedure of identification. In order to mitigate the impact of leaf veins, the proposed approach utilises three digital morphological characteristics that are closely linked to ellipses. The study involved conducting experimental segmentation trials on crop photos that contained whiteflies. The findings of the study provide compelling evidence that the suggested cognitive segmentation method outperforms existing techniques in terms of accuracy and robustness. This technological development provides a robust basis for future advancements in pest identification and crop management

Enhancing Signature Verification through Neural Network Ensemble

This study presents a signature authentication mechanism to prevent forgery. In the actual world, handling a large collection of data and detecting genuine signatures with reasonable accuracy is often difficult for any verification system. As a result, artificial intelligence techniques are used that can learn from a large data set during the training phase and reply effectively during the application phase without wasting a lot of storage memory space or processing time. It should also be able to refresh its expertise based on real-world encounters on a regular basis. A Multi-Layered Neural Network Model is one such adaptive machine learning technique that is used in this study. Initially, a massive amount of data is gathered by photographing several authentic and fake signatures. The image quality is increased by applying image processing, which is followed by the feature extraction phase, which extracts specific unique standard statistical features.

Supernova search with active learning in ZTF DR3

Context. We provide the first results from the complete SNAD adaptive learning pipeline in the context of a broad scope of data from large-scale astronomical surveys. Aims. The main goal of this work is to explore the potential of adaptive learning techniques in application to big data sets. Methods. Our SNAD team used Active Anomaly Discovery (AAD) as a tool to search for new supernova (SN) candidates in the photometric data from the first 9.4 months of the Zwicky Transient Facility (ZTF) survey, namely, between March 17 and December 31, 2018 (58 194 ≤ MJD ≤ 58 483). We analysed 70 ZTF fields at a high galactic latitude and visually inspected 2100 outliers. Results. This resulted in 104 SN-like objects being found, 57 of which were reported to the Transient Name Server for the first time and with 47 having previously been mentioned in other catalogues, either as SNe with known types or as SN candidates. We visually inspected the multi-colour light curves of the non-catalogued transients and performed fittings with different supernova models to assign it to a probable photometric class: Ia, Ib/c, IIP, IIL, or IIn. Moreover, we also identified unreported slow-evolving transients that are good superluminous SN candidates, along with a few other non-catalogued objects, such as red dwarf flares and active galactic nuclei. Conclusions. Beyond confirming the effectiveness of human-machine integration underlying the AAD strategy, our results shed light on potential leaks in currently available pipelines. These findings can help avoid similar losses in future large-scale astronomical surveys. Furthermore, the algorithm enables direct searches of any type of data and based on any definition of an anomaly set by the expert.

Experimental multiparameter quantum metrology in adaptive regime

Relevant metrological scenarios involve the simultaneous estimation of multiple parameters. The fundamental ingredient to achieve quantum-enhanced performance is based on the use of appropriately tailored quantum probes. However, reaching the ultimate resolution allowed by physical laws requires nontrivial estimation strategies from both a theoretical and a practical point of view. A crucial tool for this purpose is the application of adaptive learning techniques. Indeed, adaptive strategies provide a flexible approach to obtain optimal parameter-independent performance and optimize convergence to the fundamental bounds with a limited amount of resources. Here, we combine on the same platform quantum-enhanced multiparameter estimation attaining the corresponding quantum limit and adaptive techniques. We demonstrate the simultaneous estimation of three optical phases in a programmable integrated photonic circuit, in the limited-resource regime. The obtained results show the possibility of successfully combining different fundamental methodologies towards transition to quantum sensors applications.

Emerging robust and data‐driven control methods for uncertain learning systems

Emerging robust and data‐driven control methods for uncertain learning systems

FP-AGL: Filter Pruning With Adaptive Gradient Learning for Accelerating Deep Convolutional Neural Networks

Filter pruning is a technique that reduces computational complexity, inference time, and memory footprint by removing unnecessary filters in convolutional neural networks (CNNs) with an acceptable drop in accuracy, consequently accelerating the network. Unlike traditional filter pruning methods utilizing zeroing-out filters, we propose two techniques to achieve the effect of pruning more filters with less performance degradation, inspired by the existing research on centripetal stochastic gradient descent (C-SGD), wherein the filters are removed only when the ones that need to be pruned have the same value. First, to minimize the negative effect of centripetal vectors that gradually make filters come closer to each other, we redesign the vectors by considering the effect of each vector on the loss-function using the Taylor-based method. Second, we propose an adaptive gradient learning (AGL) technique that updates weights while adaptively changing the gradients. Through AGL, performance degradation can be mitigated because some gradients maintain their original direction, and AGL also minimizes the accuracy loss by perfectly converging the filters, which require pruning, to a single point. Finally, we demonstrate the superiority of the proposed method on various datasets and networks. In particular, on the ILSVRC-2012 dataset, our method removed 52.09% FLOPs with a negligible 0.15% top-1 accuracy drop on ResNet-50. As a result, we achieve the most outstanding performance compared to those reported in previous studies in terms of the trade-off between accuracy and computational complexity.

Toward Fine-grained Image Retrieval with Adaptive Deep Learning for Cultural Heritage Image

Fine-grained image classification is a challenging research topic because of the high degree of similarity among categories and the high degree of dissimilarity for a specific category caused by different poses and scales. A cultural heritage image is one of the fine-grained images because each image has the same similarity in most cases. Using the classification technique, distinguishing cultural heritage architecture may be difficult. This study proposes a cultural heritage content retrieval method using adaptive deep learning for fine-grained image retrieval. The key contribution of this research was the creation of a retrieval model that could handle incremental streams of new categories while maintaining its past performance in old categories and not losing the old categorization of a cultural heritage image. The goal of the proposed method is to perform a retrieval task for classes. Incremental learning for new classes was conducted to reduce the re-training process. In this step, the original class is not necessary for re-training which we call an adaptive deep learning technique. Cultural heritage in the case of Thai archaeological site architecture was retrieved through machine learning and image processing. We analyze the experimental results of incremental learning for fine-grained images with images of Thai archaeological site architecture from world heritage provinces in Thailand, which have a similar architecture. Using a fine-grained image retrieval technique for this group of cultural heritage images in a database can solve the problem of a high degree of similarity among categories and a high degree of dissimilarity for a specific category. The proposed method for retrieving the correct image from a database can deliver an average accuracy of 85 percent. Adaptive deep learning for fine-grained image retrieval was used to retrieve cultural heritage content, and it outperformed state-of-the-art methods in fine-grained image retrieval.

Drift Detection Method Using Distance Measures and Windowing Schemes for Sentiment Classification

Textual data streams have been extensively used in practical applications where consumers of online products have expressed their views regarding online products. Due to changes in data distribution, commonly referred to as concept drift, mining this data stream is a challenging problem for researchers. The majority of the existing drift detection techniques are based on classification errors, which have higher probabilities of false-positive or missed detections. To improve classification accuracy, there is a need to develop more intuitive detection techniques that can identify a great number of drifts in the data streams. This paper presents an adaptive unsupervised learning technique, an ensemble classifier based on drift detection for opinion mining and sentiment classification. To improve classification performance, this approach uses four different dissimilarity measures to determine the degree of concept drifts in the data stream. Whenever a drift is detected, the proposed method builds and adds a new classifier to the ensemble. To add a new classifier, the total number of classifiers in the ensemble is first checked if the limit is exceeded before the classifier with the least weight is removed from the ensemble. To this end, a weighting mechanism is used to calculate the weight of each classifier, which decides the contribution of each classifier in the final classification results. Several experiments were conducted on real-world datasets and the results were evaluated on the false positive rate, miss detection rate, and accuracy measures. The proposed method is also compared with the state-of-the-art methods, which include DDM, EDDM, and PageHinkley with support vector machine (SVM) and Naïve Bayes classifiers that are frequently used in concept drift detection studies. In all cases, the results show the efficiency of our proposed method.

Robust control of uncertain nonlinear systems using adaptive regressive Neural-based deep learning technique

In this paper, a novel adaptive Improved Global Regressive Neural Networks (Imp-GRNN) controller is developed, which provides novel improvement to the basic GRNN neural model. Proposed Imp-GRNN is designed to handle the multivariable uncertain nonlinear systems. The significant improvements of Imp-GRNN include the addition of a new output layer connected directly with the input layer via newly adaptable weights. Also, the Imp-GRNN input-hidden weights are designed to be adaptively auto-tuning instead of being static, as in most of the precedent adaptive neural controllers. Besides, a new smoothen coefficient σ is introduced to eradicate the requirement to set it beforehand or to adapt it online. The superiority of proposed Imp-GRNN method is proven quite perfect compared of GRNN and other advanced neural controllers as demonstrated via the two numerical benchmark test results.

Adaptive neural optimal control via command filter for nonlinear multi‐agent systems including time‐varying output constraints

AbstractIn this article, an optimal command‐filtered backstepping control approach is proposed for uncertain strict‐feedback nonlinear multi‐agent systems (MASs) including output constraints and unmodeled dynamics. One‐to‐one nonlinear mapping (NM) is utilized to recast constrained systems as corresponding unrestricted systems. A dynamical signal is applied to cope with unmodeled dynamics. Based on dynamic surface control (DSC), the feedforward controller is designed by introducing error compensating signals. The optimal feedback controller is produced applying adaptive dynamic programming (ADP) and integral reinforcement learning (IRL) techniques in which neural networks are utilized to approximate the relevant cost functions online with established weight updating laws. Therefore, the entire controller, including feedforward and feedback controllers, not only ensures that all signals in the closed‐loop systems are cooperative semi‐globally uniformly ultimately bounded (SGUUB) and the outputs maintain in the provided time‐varying constraints, but also makes sure that the cost functions achieve minimization. A simulation example is presented to illustrate the feasibility of the proposed control algorithm.

Introducing Adaptive Machine Learning Technique for Solving Short-Term Hydrothermal Scheduling with Prohibited Discharge Zones

The short-term hydrothermal scheduling (STHTS) problem has paramount importance in an interconnected power system. Owing to an operational research problem, it has been a basic concern of power companies to minimize fuel costs. To solve STHTS, a cascaded topology of four hydel generators with one equivalent thermal generator is considered. The problem is complex and non-linear and has equality and inequality constraints, including water discharge rate constraint, power generation constraint of hydel and thermal power generators, power balance constraint, reservoir storage constraint, initial and end volume constraint of water reservoirs, and hydraulic continuity constraint. The time delays in the transport of water from one reservoir to the other are also considered. A supervised machine learning (ML) model is developed that takes the solution of the STHTS problem without PDZ, by any metaheuristic technique, as input and outputs an optimized solution to STHTS with PDZ and valve point loading (VPL) effect. The results are quite promising and better compared to the literature. The versatility and effectiveness of the proposed approach are tested by applying it to the previous works and comparing the cost of power generation given by this model with those in the literature. A comparison of results and the monetary savings that could be achieved by using this approach instead of using only metaheuristic algorithms for PDZ and VPL are also given. The slipups in the VPL case in the literature are also addressed.

Remote sensing image fusion on 3D scenarios: A review of applications for agriculture and forestry

Three-dimensional (3D) image mapping of real-world scenarios has a great potential to provide the user with a more accurate scene understanding. This will enable, among others, unsupervised automatic sampling of meaningful material classes from the target area for adaptive semi-supervised deep learning techniques. This path is already being taken by the recent and fast-developing research in computational fields, however, some issues related to computationally expensive processes in the integration of multi-source sensing data remain. Recent studies focused on Earth observation and characterization are enhanced by the proliferation of Unmanned Aerial Vehicles (UAV) and sensors able to capture massive datasets with a high spatial resolution. In this scope, many approaches have been presented for 3D modeling, remote sensing, image processing and mapping, and multi-source data fusion. This survey aims to present a summary of previous work according to the most relevant contributions for the reconstruction and analysis of 3D models of real scenarios using multispectral, thermal and hyperspectral imagery. Surveyed applications are focused on agriculture and forestry since these fields concentrate most applications and are widely studied. Many challenges are currently being overcome by recent methods based on the reconstruction of multi-sensorial 3D scenarios. In parallel, the processing of large image datasets has recently been accelerated by General-Purpose Graphics Processing Unit (GPGPU) approaches that are also summarized in this work. Finally, as a conclusion, some open issues and future research directions are presented.

Adaptive-Learning-Based Vehicle-to-Vehicle Opportunistic Resource-Sharing Framework

With an ever-increasing number of connected devices on roads, it becomes unsustainable to provide nearby specialized execution resources (compute and storage) for servicing innovative applications. Moreover, the vehicular environment being inherently ad hoc and opportunistic, not to mention highly mobile, makes it unsuitable to use traditional cloud computing due to delayed and interrupted services. Thus, there is a possibility to introduce potential collaboration among nearby connected vehicles. However, the underlying decision model for the selection of the most suitable vehicle for task offloading is challenging in such a dynamic environment. In this study, we propose a collaborative vehicular computing framework that adopts online learning for efficient task assignment between local and neighboring computing resources. The underlying workload adaptive task offloading intends to balance out the workload across neighboring vehicles. The framework is compared against three techniques including two adaptive learning techniques in terms of service delay, efficiency, task delivery rate, task failures, and learning regret. The results demonstrate the effectiveness of the proposed resource-sharing network, improving service quality and throughput for servicing innovative intelligent transportation applications.

Incremental Adaptive Gesture Classifier for Upper Limb Prostheses

Myoelectric pattern recognition is widely used to control upper limb prostheses. However, the non-stationary characteristics of electromyography (EMG) signals, caused by physiological changes (e.g. muscle fatigue) or non-physiological changes (e.g. the electrode- skin impedance), hinder the use of prostheses and deteriorate the performance of the myoelectric control system. In this paper, a set of robust features is proposed to be integrated with adaptive learning techniques in order to improve the myoelectric performance. Four types of features are proposed, namely the H, HI, AI, and AIH features. The H features correspond to the histogram-oriented gradient (HOG) algorithm of the High-Density surface Electromyography map (HD-sEMG map). On the other hand, the HI features are generated by combining the H features and the intensity feature that is evaluated from the HD-sEMG map. AI is the intensity features calculated from the segmented HD-sEMG maps constructed in the individual channel. Finally, AIH features are obtained by combining the H features and AI features. Offline and online adaptive tests are conducted to evaluate the proposed features. The results show that employing the proposed AI features with an adaptive classifier improves the classification accuracy from 91.58% to 97.2% in online classification setups. Results also show that the AI features are more robust against noise than TD features. The average classification accuracy is reduced by 0.7% when additive White Gaussian noise is applied, in comparison to 5.8% reduction in accuracy when TD features is used. The results confirm the robustness of the proposed features extracted from the HD-sEMG map.

Adaptive Learning Techniques for a Personalized Educational Software in Developing Teachers’ Technological Pedagogical Content Knowledge

The authors discuss the design and utilization of e-TPCK, a self-paced adaptive electronic learning environment designed to promote the development of teachers’ Technological Pedagogical Content Knowledge (TPCK). The system employs a technological solution that promotes teachers’ ongoing TPCK development by engaging them in personalized learning experiences using technology-infused design scenarios. Results from an experimental research study revealed that the experimental group outperformed the control group in developing TPCK on two design tasks, substantiating the claim that the use of technology can better facilitate the development of TPCK than traditional instruction. Furthermore, e-TPCK’s adaptive guidance using worked-out examples led to mathemagenic learning effects for novice student-teachers, while for the more experienced student-teachers learning with e-TPCK proved beneficial only at the beginning of their engagement with the system. Hence, the relative effectiveness of instructional techniques embedded in e-TPCK became less effective as a result of student-teachers’ increasing expertise, providing evidence for the expertise reversal effect. In conclusion, the findings of the research are encouraging for the advantages of personalized learning in teacher education and showed that the design of adaptive learning technologies must account for learners’ prior knowledge and changing levels of expertise throughout the ongoing interaction with the computer system.

Demand Based Cost Optimization of Electric Bills for Household Users

Abstract- Internet of Things (IoT) is increasingly becoming the vehicle to automate, optimize and enhance the performance of systems in the energy, environment, and health sectors. In this paper, we use Wi-Fi wrapped sensors to provide online and in realtime the current energy consumptions at a device level, in a manner to allow for automatic control of peak energy consumption at a household, factory level, and eventually at a region level, where a region can be defined as an area supported by a distinct energy source. This allows to decrease the bill by avoiding heavily and controllable loads during high tariff slice and/or peak period per household and to optimize the energy production and distribution in a given region. The proposed model relies on adaptive learning techniques to help adjust the current load, while taking into consideration the actual and real need of the consumer. The experiments used in this study makes use of current and voltage sensors, Arduino platform, and simulation system. The main performance indexes used are the control of a peak consumption level, and the minimum time needed to adjust the distribution of load in the system. The system was able to keep the maximum load at a maximum of 10 kW in less than 10 seconds of response time. The level and response time are controllable parameters.

Adaptive 3D descattering with a dynamic synthesis network

Deep learning has been broadly applied to imaging in scattering applications. A common framework is to train a descattering network for image recovery by removing scattering artifacts. To achieve the best results on a broad spectrum of scattering conditions, individual “expert” networks need to be trained for each condition. However, the expert’s performance sharply degrades when the testing condition differs from the training. An alternative brute-force approach is to train a “generalist” network using data from diverse scattering conditions. It generally requires a larger network to encapsulate the diversity in the data and a sufficiently large training set to avoid overfitting. Here, we propose an adaptive learning framework, termed dynamic synthesis network (DSN), which dynamically adjusts the model weights and adapts to different scattering conditions. The adaptability is achieved by a novel “mixture of experts” architecture that enables dynamically synthesizing a network by blending multiple experts using a gating network. We demonstrate the DSN in holographic 3D particle imaging for a variety of scattering conditions. We show in simulation that our DSN provides generalization across a continuum of scattering conditions. In addition, we show that by training the DSN entirely on simulated data, the network can generalize to experiments and achieve robust 3D descattering. We expect the same concept can find many other applications, such as denoising and imaging in scattering media. Broadly, our dynamic synthesis framework opens up a new paradigm for designing highly adaptive deep learning and computational imaging techniques.

Interpolating detailed simulations of kilonovae: Adaptive learning and parameter inference applications

Detailed radiative transfer simulations of kilonovae are difficult to apply directly to observations; they only sparsely cover simulation parameters, such as the mass, velocity, morphology, and composition of the ejecta. On the other hand, semianalytic models for kilonovae can be evaluated continuously over model parameters, but neglect important physical details which are not incorporated in the simulations, thus introducing systematic bias. Starting with a grid of two-dimensional anisotropic simulations of kilonova light curves covering a wide range of ejecta properties, we apply adaptive learning techniques to iteratively choose new simulations and produce high-fidelity surrogate models for those simulations. These surrogate models allow for continuous evaluation across model parameters while retaining the microphysical details about the ejecta. Using a code formultimessenger inference developed by our group, we demonstrate how to use our interpolated models to infer kilonova parameters. Comparing to inferences using simplified analytic models, we recover different ejecta properties. We discuss the implications of this analysis which is qualitatively consistent with similar previous work using detailed ejecta opacity calculations and which illustrates systematic challenges for kilonova modeling. An associated data and code release provides our interpolated light-curve models, interpolation implementation which can be applied to reproduce our work or extend to new models, and our multimessenger parameter inference engine.

Efficient electro encephelogram classification system using support vector machine classifier and adaptive learning technique

Complex <span>modern signal processing is used to automate the analysis of electro encephelogram (EEG) signals. For the diagnosis of seizures, approaches that are simple and precise may be preferable rather than difficult and time-consuming. In this paper, efficient EEG classification system using support vector machine (SVM) and Adaptive learning technique is proposed. The database EEG signals are subjected to temporal and spatial filtering to remove unwanted noise and to increase the detection accuracy of the classifier by selecting the specific bands in which most of the EEG data are present. The neural network based SVM is used to classify the test EEG data with respect to training data. The cost-sensitive SVM with proposed Adaptive learning classifies the EEG signals where the adaptive learning with probability based function helps in prediction of the future samples and this leads in improving the accuracy with detection time. The detection accuracy of the proposed algorithm is compared with existing which shows that the proposed algorithm can classify the EEG signal more </span>effectively.

Dynamic Neural Network for Lossy-to-Lossless Image Coding.

Lifting-based wavelet transform has been extensively used for efficient compression of various types of visual data. Generally, the performance of such coding schemes strongly depends on the lifting operators used, namely the prediction and update filters. Unlike conventional schemes based on linear filters, we propose, in this paper, to learn these operators by exploiting neural networks. More precisely, a classical Fully Connected Neural Network (FCNN) architecture is firstly employed to perform the prediction and update. Then, we propose to improve this FCNN-based Lifting Scheme (LS) in order to better take into account the input image to be encoded. Thus, a novel dynamical FCNN model is developed, making the learning process adaptive to the input image contents for which two adaptive learning techniques are proposed. While the first one resorts to an iterative algorithm where the computation of two kinds of variables is performed in an alternating manner, the second learning method aims to learn the model parameters directly through a reformulation of the loss function. Experimental results carried out on various test images show the benefits of the proposed approaches in the context of lossy and lossless image compression.