Step Size Research Articles

Plant Disease Detection Using Machine Learning

In this project, we have developed a plant disease detection model using a machine learning approach on a dataset named “Plant Disease Expert” which is available on Kaggle. The dataset contains 199,611 images across 58 subdirectories. The splitting of the dataset in training, validation and testing is done in ratio 90:5:5. The data preprocessing included resizing the images, normalizing pixel values and applying augmentation techniques. We have used different libraries throughout the project such as NumPy, Pandas, Operating system, Time, Matplotlib, OpenCV, Shutil, TensorFlow, Keras, Seaborn, etc. EfficientNetB3 is used as the base model. EfficientNetB3 is a convolutional neural network architecture developed by Google Brain researchers [1]. It is known for its efficiency and effectiveness in image classification tasks. Additional custom layers such as max pooling, batch normalization, dense layers, and activation functions are used to optimize the performance. The adamax optimizer and categorical cross-entropy were used during training. The model was trained for 10 epochs with a batch size of 20 and a learning rate of 0.01. For evaluation, classification report, accuracy, precision, recall, F1-score and support were used. The model achieved an accuracy of 98.76% [1].

BiodiViz: Leveraging NER and RE for Automated Knowledge Graph Generation in Biodiversity Research

In biodiversity research, the integration of machine learning and data visualization is increasingly important for uncovering valuable insights from academic literature. This study introduces an innovative knowledge graph application, BiodiViz, designed to translate intricate text into intuitive visual representations, fostering a deeper comprehension of biodiversity relationships. BiodiViz uses the top-performing Named Entity Recognition (NER) and Relation Extraction (RE) models to automatically generate a comprehensive knowledge graph for biodiversity research. The NER model extracts and categorizes entities like organisms, phenomena, and habitats, while the RE model identifies relationships such as "have," "occur in," and "influence" from the BiodivNERE dataset (Abdelmageed et al. 2022). These entities and relationships are organized into nodes and edges within a graph. Researchers input text into BiodiViz, producing a visual knowledge graph that simplifies the analysis of complex biodiversity data, reducing manual effort and enhancing efficiency. Named Entity Recognition & Relation Extraction BiodiViz leverages advanced Bidirectional Encoder Representations from Transformers (BERT)-based Large Language Models (LLMs) (Rogers et al. 2020), fine-tuned specifically for NER and RE tasks using the BiodivNERE dataset. The fine-tuning process involved various models, including BERT (Devlin et al. 2019), ELECTRA (Clark et al. 2020), and BiodivBERT (Abdelmageed et al. 2023). These models were evaluated for performance using the results of their F1-score as the main metric, which is the harmonic mean of precision (the proportion of true positive results among all positive predictions) and recall (the proportion of true positive results among all actual positives), with BiodivBERT achieving an F1-score of 77.16% for the NER task, while BERT excelled in the RE task with an F1-score of 81.28%. Rigorous hyperparameter optimization further enhanced the performance of BiodivBERT in the RE task by 3.38%. The BiodivNERE corpora by Abdelmageed et al. (2022) were used to fine-tune several models for NER and RE tasks in the biodiversity domain. The first corpus from the BiodivNERE corpora is BiodivNER, which is a gold standard dataset (manually labelled test corpora) for evaluating NER tasks. The fine-tuning process employed the token classification method from the Hugging Face library (Hugging Face 2023b), which assigns labels to each token in a sequence. Experiments were conducted with a batch size of four, meaning the model processes four examples/rows of data at a time before making an update to improve its learning. This is due to the constraints of the NVIDIA® GeForce RTX™ 3060 graphics processor. (NVIDIA 2024) Model performance was evaluated using the seqeval library (Nakayama 2018), focusing on accuracy, precision, recall, and F1 scores. For text classification, the second corpus, BiodivRE, was utilized, following previous research recommendations to explore fine-tuning settings for BiodivBERT. Hyperparameter optimization (Feurer and Hutter 2019) was conducted using Hugging Face’s Trainer API with an Optuna backend (Hugging Face 2023a), concentrating on learning rate and the number of training epochs (i.e., the number of complete passes through the entire dataset during model training). The BiodiViz Knowledge Graph Application The fine-tuned NER and RE models with the best F1-scores—BiodivBERT and BERT, respectively—were integrated into the knowledge graph application. Fig. 1 illustrates the flowchart of the application pipeline. Each sentence in the input text will go through the NER model to identify and label the entities within the sentence. Subsequently, these labeled entities, together with the original sentence, will be input into the RE model. The RE model will analyze every pair of entities for a potential relation and output the type of relation they share. The application will then utilize this data to create a graph with appropriate labels and color-coding. An example of the application's user interface with the knowledge graph is shown in Fig. 2. This study highlights the practical application of machine learning and data visualization in advancing biodiversity research, emphasizing the importance of developing user-friendly tools to support scientific exploration and discovery. The BiodiViz application, including the code and resources, is available on GitHub*1, providing an accessible tool for biodiversity researchers to streamline their analyses.

Adaptive time step selection for spectral deferred correction

AbstractSpectral Deferred Correction (SDC) is an iterative method for the numerical solution of ordinary differential equations. It works by refining the numerical solution for an initial value problem by approximately solving differential equations for the error, and can be interpreted as a preconditioned fixed-point iteration for solving the fully implicit collocation problem. We adopt techniques from embedded Runge-Kutta Methods (RKM) to SDC in order to provide a mechanism for adaptive time step size selection and thus increase computational efficiency of SDC. We propose two SDC-specific estimates of the local error that are generic and do not rely on problem specific quantities. We demonstrate a gain in efficiency over standard SDC with fixed step size and compare efficiency favorably against state-of-the-art adaptive RKM.

Influence of Physical Characteristics of Obstacles on the Locomotor Pattern of Older Adults at Higher Risk of Falling

ObjectiveThis study aimed to investigate the locomotor behavior of older adults with and without a history of falls as they avoided obstacles with different physical characteristics. MethodsTwenty-one older adults participated in this study. The group was divided into higher risk of falling (n = 10) and lower risk of falling (n = 11). The following conditions were carried out: (1) walking and avoiding a solid obstacle and (2) walking and avoiding a fragile obstacle. ResultsOlder adults at higher risk of falling had worse performance during the obstacle approach phase. Both groups performed worse when avoiding the fragile obstacle than when avoiding the solid obstacle. Older adults at higher risk of falling had their feet closer when avoiding the obstacle, and both groups raised their limbs higher to avoid a fragile obstacle. Older adults at higher risk of falling were closer to obstacles after avoiding them. ConclusionFor the participants in this study, the physical characteristics of the obstacle did not interfere with the locomotor performance of older adults during obstacle avoidance. This study found that older adults at higher risk of falls modulated their locomotor pattern before avoiding the obstacles, presenting lower velocity, shorter step length, and greater step width compared with older adults at lower risk of falling.

Photovoltaic Maximum Power Point Tracking Technology Based on Power Prediction Algorithm Combined with Variable Step Length Disturbance Observation Method

Under partial shading conditions, the system operating sequence of photovoltaic cells does not fall on a single characteristic curve, and the traditional maximum power point tracking (MPPT) control algorithm is prone to causing the system output power to oscillate around the maximum power point. In the case of multiple peaks, the traditional MPPT algorithm is prone to being trapped in a local optimum solution. This paper proposes an MPPT control algorithm based on the WOA-RF prediction algorithm combined with a variable step disturbance observation method. By establishing a photovoltaic system simulation model, the improved algorithm is verified through simulation. The improved MPPT control algorithm can adaptively adjust the step size under different conditions to ensure that the system can quickly and accurately track the maximum power point. At the same time, by optimizing the algorithm logic and parameter settings, it can effectively avoid problems such as local optimum solutions and instability in the system, and improve the system convergence speed and tracking accuracy.

The Development Mask R-CNN Model for Identification of Melon Plant Leaves and Branches

The quality of melons can be enhanced and optimized by pruning melon plants. Pruning is a removal process carried out on specific parts of the plant. Currently, melon plants are still pruned manually by farmers, but there are many drawbacks to this method. In this research, pruning is conducted on the branches and leaves of melon plants. Pruning can be facilitated with the assistance of a robot capable of recognizing leaves and branches. In this study, the method used to detect branches and leaves is the Mask Region-based Convolutional Neural Network (Mask R-CNN). Hyperparameter tuning technique is employed to obtain the best parameter values, including learning rate, weight decay, and learning momentum. Two scenarios are considered in this research, one with 10 epochs and the other with 30 epochs. The obtained Average Precision (AP) values at 10 epochs are 32.2% for leaf objects and 0% for branches. At 30 epochs, the AP values are 56.8% for leaf objects and 4.1% for branches. The mean Average Precision (mAP) is 16.1% for 10 epochs and 28.4% for 30 epochs.

Internal Combustion Engine Fault Detection Based on Random Convolutional Neural Networks

The internal combustion engine plays a very important role in many fields, and when the internal combustion engine fails, if it is not found in time, it may cause continuous damage to the internal combustion engine, and further affect the life of the entire mechanical system. To solve the above problems, this paper proposes fault detection of internal combustion engines based on a random convolutional neural network. The cylinder burst noise signal of the internal combustion engine is decomposed by a stationary wavelet, and the inclusion matrix is composed of partial decomposition coefficients. Using singular value theory, the singular value containing matrix is extracted as the characteristic of cylinder burst noise signal. The singular value is used as the input of a random convolutional neural network to train and identify faults. The AdaBound optimizer was then applied to adapt the learning rate to changes, thereby accelerating the weight update of the model. At the same time, the neurons in the structure are randomly deactivated by dropout technology to prevent complex collaborative responses to the training data, and the diagnosis results of each network model are integrated by Dempster synthesis rules. The experimental results show that the minimum mean square error of 0.00165 is achieved when there are 15 neurons in the hidden layer, and it gradually increases as the number of neurons increases. Therefore, it is determined that there should be 15 neurons in the hidden layer, and the trainLM algorithm is used. The decision factors for training, validation, cross-validation, and overall data are 0.98947, 0.98597, 0.97738, and 0.9801, respectively, all reaching the control accuracy of 0.95, which indicates that the random convolutional neural network proposed has a high accuracy for internal combustion engine fault detection. For the main bearing Y-directional force, as the gap increases, its fluctuation trend strengthens; the main bearing force changes within a small range at first, then increases sharply when the gap reaches 0.2[Formula: see text]mm, and some main bearings even experience significant impact loads.

Deep Convolutional Neural Network for Accurate Classification of Myofibroblastic Lesions on Patch-Based Images.

This study aimed to implement and evaluate a Deep Convolutional Neural Network for classifying myofibroblastic lesions into benign and malignant categories based on patch-based images. A Residual Neural Network (ResNet50) model, pre-trained with weights from ImageNet, was fine-tuned to classify a cohort of 20 patients (11 benign and 9 malignant cases). Following annotation of tumor regions, the whole-slide images (WSIs) were fragmented into smaller patches (224 × 224 pixels). These patches were non-randomly divided into training (308,843 patches), validation (43,268 patches), and test (42,061 patches) subsets, maintaining a 78:11:11 ratio. The CNN training was caried out for 75 epochs utilizing a batch size of 4, the Adam optimizer, and a learning rate of 0.00001. ResNet50 achieved an accuracy of 98.97%, precision of 99.91%, sensitivity of 97.98%, specificity of 99.91%, F1 score of 98.94%, and AUC of 0.99. The ResNet50 model developed exhibited high accuracy during training and robust generalization capabilities in unseen data, indicating nearly flawless performance in distinguishing between benign and malignant myofibroblastic tumors, despite the small sample size. The excellent performance of the AI model in separating such histologically similar classes could be attributed to its ability to identify hidden discriminative features, as well as to use a wide range of features and benefit from proper data preprocessing.

High quality and sensitivity phononic crystal channel drop filter to detect ethyl lactate in mixtures of ethyl lactate and 2-butoxy ethanol

This paper introduces a new sensing approach utilizing a solid-solid phononic crystal (PnC) channel drop filter structure for the detection of varying molar fractions of Ethyl lactate within a mixture of Ethyl lactate and 2-butoxy ethanol. The sensor features a two-dimensional PnC constructed from poly methyl methacrylate as the background material, incorporating a regular arrangement of circular Tungsten columns. The design integrates a bus waveguide linked to two interconnected ring resonators, which are coupled to a drop waveguide. Each ring resonator is equipped with three strategically positioned pillars near the coupling region, allowing for the accommodation of varying concentrations of Ethyl lactate. The sensor’s performance is significantly influenced by the ring resonators and the integrated pillars. It identifies specific resonance frequencies that shift in response to changes in Ethyl lactate concentrations within the resonators. The transmission resonance frequency exhibits valuable sensitivity to these concentration variations, reflecting the unique sound velocities and mass densities associated with each level of Ethyl lactate. The effectiveness of the proposed sensor is validated through coupled mode theory, demonstrating a close match with the device’s observed behavior. The measured frequency range spans from 1.972 MHz to 1.979 MHz with a step size of 1 Hz. Notably, the sensor displays considerable characteristics, including an average quality factor of 90,613, an average sensitivity of 3816 Hz, an average figure of merit of 172, an average signal-to-noise ratio of 137, an average resolution of 22 Hz, an average damping ratio of 0.56 × 10− 5, and an average limit of detection of 34 × 10− 5. These results underscore the potential of the channel drop filter for the accurate detection of Ethyl lactate concentrations with high quality factor and sensitivity. The sensor can effectively identify variations in Ethyl lactate levels, which are prevalent in various applications, including pharmaceuticals and food additives.

Matrix Factorization and Prediction for High-Dimensional Co-Occurrence Count Data via Shared Parameter Alternating Zero Inflated Gamma Model

High-dimensional sparse matrix data frequently arise in various applications. A notable example is the weighted word–word co-occurrence count data, which summarizes the weighted frequency of word pairs appearing within the same context window. This type of data typically contains highly skewed non-negative values with an abundance of zeros. Another example is the co-occurrence of item–item or user–item pairs in e-commerce, which also generates high-dimensional data. The objective is to utilize these data to predict the relevance between items or users. In this paper, we assume that items or users can be represented by unknown dense vectors. The model treats the co-occurrence counts as arising from zero-inflated Gamma random variables and employs cosine similarity between the unknown vectors to summarize item–item relevance. The unknown values are estimated using the shared parameter alternating zero-inflated Gamma regression models (SA-ZIG). Both canonical link and log link models are considered. Two parameter updating schemes are proposed, along with an algorithm to estimate the unknown parameters. Convergence analysis is presented analytically. Numerical studies demonstrate that the SA-ZIG using Fisher scoring without learning rate adjustment may fail to find the maximum likelihood estimate. However, the SA-ZIG with learning rate adjustment performs satisfactorily in our simulation studies.

The effect of functional exercise program on physical functioning in older adults aged 60 years or more: A systematic review and meta-analysis of randomized controlled trials

ObjectiveIn this systematic review and meta-analysis, we assessed the impact of functional exercise training on physical functioning parameters in older adults 60 years and older. MethodDatabases including PubMed, MEDLINE, CINAHL, SPORTDiscus, and Cochrane Library were systematically searched. ResultsSixteen articles were included. Meta-analysis demonstrated that functional training significantly improved Barthel index (p = 0.01), gait speed (p = 0.002), gait cadence (p = 0.0002), Berg Balance Scale (p = 0.0003), Timed Up and Go test (TUG; p = 0.02), step length (p < 0.0001), Five Chair Stand (p < 0.0001) and physical activity questionnaire for the older adults score (p < 0.00001). However, hand grip strength remained unchanged. DiscussionThese findings underscore the significance of incorporating functional exercises in interventions for healthy aging and maintaining independence among older individuals. Further investigation is needed to explore long-term effects and optimal implementation strategies for functional exercise regimens in this populations.

Indetermsoft-Set-Based D* Extra Lite Framework for Resource Provisioning in Cloud Computing

Cloud computing is an immensely complex, huge-scale, and highly diverse computing platform that allows the deployment of highly resource-constrained scientific and personal applications. Resource provisioning in cloud computing is difficult because of the uncertainty associated with it in terms of dynamic elasticity, rapid performance change, large-scale virtualization, loosely coupled applications, the elastic escalation of user demands, etc. Hence, there is a need to develop an intelligent framework that allows effective resource provisioning under uncertainties. The Indetermsoft set is a promising mathematical model that is an extension of the traditional soft set that is designed to handle uncertain forms of data. The D* extra lite algorithm is a dynamic heuristic algorithm that makes use of the history of knowledge from past search experience to arrive at decisions. In this paper, the D* extra lite algorithm is enabled with the Indetermsoft set to perform proficient resource provisioning under uncertainty. The experimental results show that the performance of the proposed algorithm is found to be promising in performance metrics such as power consumption, resource utilization, total execution time, and learning rate. The expected value analysis also validated the experimental results obtained.

Neo-Hookean modeling of nonlinear coupled behavior in circular plates supported by micro-pillars

In the contemporary era, the enhancement of wearable capacitive sensors is achieved through the utilization of polymeric micropillars as filler materials between electrode plates. To gain a deeper understanding of the dynamic response of the system, nonlinear coupled governing equations of a circular microplate motion resting on an array of polymeric micropillars have been derived. These equations are used to model the system’s behavior. In addition, the squeezing motion of the micro-pillars is characterized using the incompressible Neo-Hookean model. Both static and dynamic responses, including transient and steady-state solutions, are investigated in detail by discretizing over spatial coordinates using a weak formulation approach. A frequency response analysis is conducted using a continuation-based method. This entails expanding the steady-state solution using a Fourier transform and employing the energy balance principle. The unknown coefficients of the expansion series are calculated using a gradient descent-based learning approach that is physically motivated. Furthermore, a dynamic step size strategy for frequency increments is employed to effectively follow the solution path. This strategy is implemented via the ARC length method. In this study, we examine the impact of varying PDMS (polydimethylsiloxane) hydrogel mechanical and geometrical configurations. It can be reasonably concluded that the mechanical properties of the pillars and the geometrical configuration of the circular plate and micropillars have a significant impact on the maximum tolerable pressure, fast transient response, and frequency response analysis.

Dynamic step opposition-based learning sparrow search algorithm for UAV path planning

In this paper, aiming at the problems of large randomness, low convergence accuracy, and easy falling into local optimum in the application of sparrow search algorithm to UAV three-dimensional path planning, a dynamic step opposition-based learning sparrow search algorithm is proposed. The algorithm first uses a good point set in the population initialization phase to improve the quality of the initial solution; secondly, the piecewise dynamic step size is used to optimize the update formula of the discoverer, and the extensive search is carried out in the early stage of the iteration. In the later stage, the known area is mined as much as possible to improve the search accuracy and convergence speed of the algorithm. Then, the crazy operator is integrated to optimize the predator update formula and improve the local search ability. Finally, t-distribution opposition-based learning is used to prevent the algorithm from falling into the local optimum. In this paper, the effectiveness of the improved algorithm is verified by six test functions and applied to the three-dimensional path planning of UAVs. The experimental results show that the proposed algorithm has a faster convergence speed than the traditional algorithm, and the planned path is shorter.

A multi-objective indirect neural adaptive processes control design for minimization of energy consumption: An experimental validation on a transesterification reactor

Nowadays, energy management environment is a very important issue that technologies have focused on in order to save costs and minimize energy waste. This objective can be achieved by means of an energy resource management approach through an appropriate optimization technique. However, energy savings can conflict with other objective functions, to solve the problem a multi-objective optimization that considers the minimization of the control energy can be adopted. In this paper, we propose to use a multi-objective indirect neural adaptive control concept for nonlinear systems with unknown dynamics. The control scheme consists of an adaptive instantaneous neural emulator and neural controller built on fully connected real-time recurrent learning networks (RTRL). The multi-objective particle swarm optimization (MOPSO) algorithm is used as a mechanism to find NE and NC adaptive learning rates that optimize the proposed objective functions: control energy minimization and closed-loop preservation. Comparative studies and experimental validation on a semi-batch reactor, used to generate cleaner biofuels, are performed to confirm the effectiveness of the proposed strategy.

Deep learning analysis of histopathological images predicts immunotherapy prognosis and reveals tumour microenvironment features in non-small cell lung cancer.

Non-small cell lung cancer (NSCLC) is one of the leading causes of cancer mortality worldwide. Immune checkpoint inhibitors (ICIs) have emerged as a crucial treatment option for patients with advanced NSCLC. However, only a subset of patients experience clinical benefit from ICIs. Therefore, identifying biomarkers that can predict response to ICIs is imperative for optimising patient selection. Hematoxylin and eosin (H&E) images of NSCLC patients were obtained from the local cohort (n = 106) and The Cancer Genome Atlas (TCGA) (n = 899). We developed an ICI-related pathological prognostic signature (ir-PPS) based on H&E stained histopathology images to predict prognosis in NSCLC patients treated with ICIs using deep learning. To accomplish this, we employed a modified ResNet model (ResNet18-PG), a widely-used deep learning architecture well-known for its effectiveness in handling complex image recognition tasks. Our modifications include a progressive growing strategy to improve the stability of model training and the use of the AdamW optimiser, which enhances the optimisation process by adjusting the learning rate based on training dynamics. The deep learning model, ResNet18-PG, achieved an area under the receiver operating characteristic curve (AUC) of 0.918 and a recall of 0.995 on the local cohort. The ir-PPS effectively risk-stratified NSCLC patients. Patients in the low-risk group (n = 40) had significantly improved progression-free survival (PFS) after ICI treatment compared to those in the high-risk group (n = 66, log-rank P = 0.004, hazard ratio (HR) = 3.65, 95%CI: 1.75-7.60). The ir-PPS demonstrated good discriminatory power for predicting 6-month PFS (AUC = 0.750), 12-month PFS (AUC = 0.677), and 18-month PFS (AUC = 0.662). The low-risk group exhibited increased expression of immune checkpoint molecules, cytotoxicity-related genes, an elevated abundance of tumour-infiltrating lymphocytes, and enhanced activity in immune stimulatory pathways. The ir-PPS signature derived from H&E images using deep learning could predict ICIs prognosis in NSCLC patients. The ir-PPS provides a novel imaging biomarker that may help select optimal candidates for ICIs therapy in NSCLC.

Optimizing rehabilitation strategies in Parkinson’s disease: a comparison of dual cognitive-walking treadmill training and single treadmill training

Dual cognitive-walking treadmill training (DTT), designed to replicate real-life walking conditions, has shown promise effect in individuals with Parkinson’s disease (PD). This study aims to compare the effects of DTT versus single treadmill training (STT) on cognitive and walking performance under both single and dual task conditions, as well as on fall, patients’ subjective feeling, and quality of life. Sixteen individuals with PD were randomly assigned to DTT or STT group and underwent 8 weeks of training. The DTT group received treadmill training with cognitive loads, while the STT group received treadmill training without cognitive load. Outcome measures included gait parameters (speed, step length) and cognitive performance (reaction time, accuracy, composite score) under both single and dual task conditions. Unified Parkinson’s Disease Rating Scale-part III (UPDRS-III), Falls Efficacy Scale (FES), Patient Global Impression of Change (PGIC), and Parkinson’s Disease Questionnaire (PDQ-39) were also measured. Both DTT and STT groups showed increased comfortable walking speed and step length. Only the DTT group demonstrated significant improvements in cognitive composite score under both single and dual task conditions, as well as UPDRS-III, FES, and PDQ-39(p < 0.05). DTT can enhance cognitive function without compromising walking ability and also have real-world transferability.

Exploring age-related differences in the relationship between spatial and temporal contributions to step length asymmetry during split-belt adaptation.

Gait adaptability is crucial for meeting environmental demands, and impaired gait adaptation increases fall risk, particularly in older adults. While prior research exists on older adults' gait adaptation, particularly in perturbation studies, the specific contributions of temporal and spatial adaptation strategies to step length asymmetry (SLA) during split-belt treadmill walking require further examination. This study fills this gap by evaluating how distinct adaptation strategies contribute to SLA in healthy young and older adults. 19 healthy young adults (20.4 ± 1.1years) and 19 healthy older adults (68.3 ± 8.1years) walked on a split-belt treadmill requiring their non-dominant leg to move twice as fast as their dominant leg. Repeated measures ANOVA investigated (1) spatial and temporal contributions to SLA, (2) SLA across gait adaptation epochs, and (3) rates of adaptation and deadaptation. Older adults displayed reduced temporal contributions to SLA compared to younger adults (F1,36 = 6.42, p = .02, ŋ2 = .15), but no group differences were observed in spatial contributions to SLA (F1,36 = 3.23, p = .08, ŋ2 = .082). SLA during adaptation and deadaptation did not differ by age group, nor did the rate of adaptation (F1,34.7 = 0.594, p = .45) or deadaptation F1,33.6 = 2.886, p = .09). These findings suggest that while older adults rely less on temporal strategies for gait adaptation, but maintain overall adaptability comparable to younger adults. Findings enhance our understanding of age-related changes in gait adaptation mechanisms and may inform targeted interventions to improve gait adaptability in older populations.

6G Self‐Evolution Network for IoT Using Rainbow Deep Q‐Network Based on Decision‐Making

ABSTRACTIn recent trends, the development of 6G technology has provided a critical focus on its core network architecture which facilitates the robust foundation for entire network. A solution of self‐evolving networks for 6G is under consideration, in which networks develop their autonomy as a key perspective in the decision‐making process. Till now, various decision‐making mechanisms are identified, such as their key features, individual theoretical analyzes, and customized for 6G networks. To reduce the network load and improve system utilization, a decision‐making based on Rainbow Deep Q‐Network (RDQN) is proposed in this research. This methodology considers distributed decision‐making scenarios in which IoT devices enhance the quality of experience (QoE) with low training. Furthermore, it aims at a community of self‐evolving networks to show the improvements in 6G technologies and accelerates the learning rate. From the result analysis, it evidently displays that proposed RDQN has better training rate than other algorithms and requires fewer rounds of approximately 20 for a high number of episodes (500). Similarly, while evaluating QoE utility value, the proposed RDQN demonstrates a higher value of 100 when the number of target customers is large which outperforms the other existing models. The above results prove that the proposed RDQN is more efficient in IoT traffic monitoring and more suitable for the 6G environment.

Multiphasic movement and step-selection patterns of dispersed tigers in the central Indian landscape.

Large carnivores play a crucial role in the ecosystem, though their conservation needs a landscape-level approach due to their wide range of habitats and dispersal events. The study of tigers in a human-dominated landscape matrix and their adaptation and adjustment of movement behaviours during the dispersal phase is essential for long-term conservation planning and management policy. We studied the dispersal event of five VHF/GPS collared individuals during 2009-2020. We investigated movement parameters (step length), and the effects of anthropogenic pressures (distance from village), distance from water and vegetation cover, on behavioural phase under a Hidden Markov Model framework. We also tested the effects of distance from village, vegetation cover, and habitat types on animal movement using an integrated Step Selection Function framework. The mean step length (405.44±10.63 m/hr) varied widely by different time of day. Displacement was high during the night (665.28±21.36 m/hr) compared to day (434.16±17.37 m/hr). Tigers moved fast (872.7m; 95% CI 839.1-906.3m) with longer step length and a directional turning angle in non-forested areas (i.e. the human-dominated landscape), likely to avoid conflict with humans. Individuals distinctly exhibited two behavioural states: encamping (~32% of the time) and travelling (~68% of the time). Further, they avoided the human-dominated landscape and mostly remained in and forested areas, especially during nighttime. Our study is the first attempt to understand behavioural transition of dispersal tigers and their habitat selection. Lesser anthropogenic disturbance and high vegetation cover positively influenced the tiger dispersal, while water availability did not affect their state transitional probability. Additionally, dispersers showed high affinity towards forested land during nighttime for travelling.The findings of this study show the importance of functional corridors and stepping stones (mostly encamping areas), and also provide baseline knowledge for integrated landscape management planning and policymaking for the long-term survival of tigers in metapopulation framework.