Memory Architecture Research Articles

The Role of Memory in LLMs: Persistent Context for Smarter Conversations

Memory in LLMs has given way to more logical and sensible interactions between the system and the user. This is different from other models that are session bound, such that the responses to any one query are not related to past and future interactions with the same user, but memory-enabled LLMs retain information across sessions and continually update interactions with the person they are communicating with. The role of permanent memory in LLMs is considered in this work, provided through the analysis of the role of memory mechanisms in maintaining conversation flows, improving user interaction, and supporting practical applications in various industries, including customer service, healthcare, and education. Discussing how the idea and architectures of memory correspond to storage and retrieval procedures and the management of memory in LLMs this paper outlines the opportunities and challenges for AI systems that want to include contextual intelligence but also remain ethical. The synthesis of important concepts underlines the promising prospects of memory-augmented models in improving the communication with users and points to the imperatively important aspect of controlling the memory process at the design stage of LLMs. We also offer recommendations for privacy and ethical concerns that should be avoided in the case of future AI memory advancements in an effort to pursue sustainable technological progress while also incorporating user-oriented values into the process.

Realizing the Calculation of a Fully Normalized Associated Legendre Function Based on an FPGA

A large number of fully normalized associated Legendre function (fnALF) calculations are required to compute Earth’s gravity field elements using ultra high-order gravity field coefficient models. In the surveying and mapping industry, researchers typically rely on CPU-based systems for these calculations, which leads to limitations in execution speed and power efficiency. Although modern CPUs improve instruction execution efficiency through instruction-level parallelism, the constraints of a shared memory architecture impose further limitations on the execution speed and power efficiency. This results in exponential increases in computation time as demand rises alongside high power consumption. In this article, we present a new computational implementation of an fnALF based on the ZYNQ platform. We design a task-parallel “pipeline” architecture which converts the original serial logic into a more efficient hardware implementation, and we utilize a redundant calculation layer to handle repetitive coefficient computations separately. The experimental results demonstrate that our system achieved accurate and rapid calculations. Under the only one geocentric residual latitude condition, we measured the computation times for spherical harmonic coefficient degrees of 360, 720, and 1080 to be 0.155922 s, 0.520950 s, and 1.401609 s, respectively. In the case of the multiple geocentric residual latitudes condition, our design generally yielded efficiency gains of over three times those of MATLAB R2020b implementation. Additionally, our calculated results were used to determine the geoid height in the field with an error of less than ±0.1m, confirming the reliability of our computations.

GPU Parallel Computing Architectures : Unlocking the Power of Parallelism for High-Performance Applications

Graphics Processing Units (GPUs) have evolved from specialized graphics rendering hardware to become powerful parallel computing architectures, revolutionizing high-performance computing across diverse domains. This comprehensive article explores the fundamental principles of GPU parallel computing architectures, their design, and their impact on modern computational challenges. We begin by examining the multi-core structure, memory hierarchy, and data processing capabilities of GPUs, including the SIMD execution model and thread organization. The article then delves into prominent programming models like CUDA and OpenCL, discussing their features and comparative advantages. We explore how GPUs are leveraged for general-purpose computing in scientific simulations, machine learning, and big data analytics, while also addressing the challenges inherent in GPU parallel computing, such as data transfer bottlenecks and load balancing. Recent technological advancements, including tensor cores, unified memory architecture, and ray tracing acceleration, are analyzed for their transformative potential. The article concludes by examining future directions in GPU technology, including integration with emerging technologies like quantum computing, advancements in energy efficiency, and the potential impact on solving complex global challenges. Through this comprehensive analysis, we illustrate the pivotal role of GPU parallel computing architectures in shaping the future of high-performance computing and their potential to address some of the world's most pressing computational problems.

RlaNet: A Residual Convolution Nested Long-Short-Term Memory Model with an Attention Mechanism for Wind Turbine Fault Diagnosis

This paper proposes a new fault diagnosis model for wind power systems called residual convolution nested long short-term memory network with an attention mechanism (rlaNet). The method first preprocesses the SCADA data through feature engineering, uses the Hermite interpolation method to handle missing data, and uses the mutual information-based dimensionality reduction technique to improve data quality and eliminate redundant information. rlaNet combines residual networks and nested long short-term memory networks to replace traditional convolutional neural networks and standard long short-term memory architectures, thereby improving feature extraction and ensuring the abstractness and depth of the extracted features. In addition, the model emphasizes the weighted learning of spatiotemporal features in the input data, enhances the focus on key features, and improves training efficiency. Experimental results show that rlaNet achieves an accuracy of more than 90% in wind turbine fault diagnosis, showing good robustness. Furthermore, noise simulation experiments verify the model’s resistance to interference, providing a reliable solution for wind turbine fault diagnosis under complex operating conditions.

ShieldCXL: A Practical Obliviousness Support with Sealed CXL Memory

The CXL (Compute Express Link) technology is an emerging memory interface with high-level commands. Recent studies applied the CXL memory expanding technique to mitigate the capacity limitation of the conventional DDRx memory. Unlike the prior studies to use the CXL memory as the capacity expander, this study proposes to use the CXL-based memory as a secure main memory device, while removing the conventional memory. In the conventional DDRx memory, to provide confidentiality, integrity, replay protection, and obliviousness, costly mechanisms such as counter-based integrity trees and location shuffling by ORAM (Oblivious RAM) are used. Such mechanisms incur significant performance degradation in the current DDR-based memory systems, and their costs increase as the capacity of the memory increases. To mitigate the performance degradation, the prior work proposed an obfuscated channel for a secure memory module enclosing its controller in the package. Based on the approach, we propose a secure CXL-only memory architecture called ShieldCXL . It uses the channel encryption and integrity protection mechanism of the CXL interface to provide a practical ORAM while supporting confidentiality, integrity, and replay protection from physical attacks and rowhammers. To protect the PCIe-connected memory expanding board, this study proposes to use the standard physical sealing technique to detect physical intrusion. To mitigate the increased latency with the sealed CXL memory module, the study further optimizes performance by adopting an in-package DRAM cache. In addition, this study investigates destination obfuscation when a CXL switch is used to route among multiple hosts and memory devices. The evaluation shows that ShieldCXL provides 9.16x performance improvements over the prior ORAM technique.

Yield curve extrapolation with machine learning

Abstract Yield curve extrapolation to unobservable tenors is a key technique for the market-consistent valuation of actuarial liabilities required by Solvency II and forthcoming similar regulations. Since the regulatory method, the Smith–Wilson method, is inconsistent with observable yield curve dynamics, parsimonious parametric models, the Nelson–Siegel model and its extensions, are often used for yield curve extrapolation in risk management. However, it is difficult for the parsimonious parametric models to extrapolate yield curves without excessive volatility because of their limited ability to represent observed yield curves with a limited number of parameters. To extend the representational capabilities, we propose a novel yield curve extrapolation method using machine learning. Using the long short-term memory architecture, we achieve purely data-driven yield curve extrapolation with better generalization performance, stability, and consistency with observed yield curve dynamics than the previous parsimonious parametric models on US and Japanese yield curve data. In addition, our method has model interpretability using the backpropagation algorithm. The findings of this study prove that neural networks, which have recently received considerable attention in mortality forecasting, are useful for yield curve extrapolation, where they have not been used before.

PragFormer: Data-Driven Parallel Source Code Classification with Transformers

AbstractMulti-core shared memory architectures have become ubiquitous in computing hardware nowadays. As a result, there is a growing need to fully utilize these architectures by introducing appropriate parallelization schemes, such as OpenMP worksharing-loop constructs, to applications. However, most developers find introducing OpenMP directives to their code hard due to pervasive pitfalls in managing parallel shared memory. To assist developers in this process, many compilers, as well as source-to-source (S2S) translation tools, have been developed over the years, tasked with inserting OpenMP directives into code automatically. In addition to having limited robustness to their input format, these compilers still do not achieve satisfactory coverage and precision in locating parallelizable code and generating appropriate directives. Recently, many data-driven AI-based code completion (CC) tools, such as GitHub CoPilot, have been developed to ease and improve programming productivity. Leveraging the insights from existing AI-based programming-assistance tools, this work presents a novel AI model that can serve as a parallel-programming assistant. Specifically, our model, named PragFormer, is tasked with identifying loops that can benefit from conversion to parallel worksharing-loop construct (OpenMP directive) and even predict the need for specific data-sharing attributes clauses on the fly. We created a unique database, named Open-OMP, specifically for this goal. Open-OMP contains over 32,000 unique code snippets from different domains, half of which contain OpenMP directives, while the other half do not. We experimented with different model design parameters for these tasks and showed that our best-performing model outperforms a statistically-trained baseline as well as a state-of-the-art S2S compiler. In fact, it even outperforms the popular generative AI model of ChatGPT. In the spirit of advancing research on this topic, we have already released source code for PragFormer as well as Open-OMP dataset to public. Moreover, an interactive demo of our tool, as well as a Hugging Face webpage to experiment with our tool, are already available.

Human–robot interaction: predicting research agenda by long short-term memory

The article addresses the identification and prediction of research topics in human–robot interaction (HRI), fundamental in Industry 4.0 (I4.0) and future Industry 5.0 (I5.0). In the absence of research agendas in the scientific literature, the study proposes a multilayered model to create a precise agenda to guide the scientific community in new developments in collaborative robotics and HRI technologies. The methodology is divided into four stages, which make up the three layers of the model. In the first two stages, scientific articles on HRI for the period 2020–2021 were collected and analyzed using data mining techniques together with VantagePoint and Gephi software to identify keywords and their relationships. These initial stages form layer 1 of the model, where the main scientific themes are recognized. In the third stage, article titles and abstracts are cleaned and processed using natural language processing (NLP) techniques, generating word embeddings models that highlight relevant HRI-related terms, forming layer 2. The fourth and final stage uses Recurrent Neural Networks (RNN) with long short-term memory (LSTM) architecture to predict future topics, consolidating the previously identified terms and forming layer 3 of the model. The results show that in layer 1 HRI has intensive application in various sectors through advanced computational algorithms, with trust as a key feature. In layer 2, terms such as vision, sensors, communication, collaboration and anthropomorphic aspects are fundamental, while layer 3 anticipates future topics such as design, performance, method and controllers, essential to improve robot interaction. The study concludes that the methodology is effective in defining a robust and relevant research agenda. By identifying future trends and needs, this work fills a gap in the scientific literature, providing a valuable tool for the research community in the field of HRI.

The impact of social media discourse on financial performance of e-commerce companies listed on Borsa Istanbul

This research investigates how changes in public discourse on social media (particularly Twitter, now X) influence financial performance of companies listed on the e-commerce XTCRT index of Borsa Istanbul amid the COVID-19 pandemic. Utilising a unique 4-layer network structure, the study integrates daily closing prices, highest and lowest values, and trading volume data of these companies with Twitter discussions on six categories: culture, economy, health, politics, technology, world affairs. By using advanced computational methods such as multilayer network analysis, long short-term memory architecture, nonlinear autoregressive distributed lag analysis, we find a high responsiveness of the e-commerce index to social media content, particularly in discussions related to health, technology, world affairs. The study underscores that social media discussions significantly shape index composition, resulting in noticeable shifts in market dynamics, including fluctuations in stock prices, trading volumes, and market sentiment. Our study advocates for a more advanced approach to market analysis that incorporates the dynamics of online public discussions.

Sequence-to-Sequence Models and Their Evaluation for Spoken Language Normalization of Slovenian

Sequence-to-sequence models have been applied to many challenging problems, including those in text and speech technologies. Normalization is one of them. It refers to transforming non-standard language forms into their standard counterparts. Non-standard language forms come from different written and spoken sources. This paper deals with one such source, namely speech from the less-resourced highly inflected Slovenian language. The paper explores speech corpora recently collected in public and private environments. We analyze the efficiencies of three sequence-to-sequence models for automatic normalization from literal transcriptions to standard forms. Experiments were performed using words, subwords, and characters as basic units for normalization. In the article, we demonstrate that the superiority of the approach is linked to the choice of the basic modeling unit. Statistical models prefer words, while neural network-based models prefer characters. The experimental results show that the best results are obtained with neural architectures based on characters. Long short-term memory and transformer architectures gave comparable results. We also present a novel analysis tool, which we use for in-depth error analysis of results obtained by character-based models. This analysis showed that systems with similar overall results can differ in the performance for different types of errors. Errors obtained with the transformer architecture are easier to correct in the post-editing process. This is an important insight, as creating speech corpora is a time-consuming and costly process. The analysis tool also incorporates two statistical significance tests: approximate randomization and bootstrap resampling. Both statistical tests confirm the improved results of neural network-based models compared to statistical ones.

HDF5 in the exascale era: Delivering efficient and scalable parallel I/O for exascale applications

Accurately modeling real-world systems requires scientific applications at exascale to generate massive amounts of data and manage data storage efficiently. However, parallel input and output (I/O) faces challenges due to new application workflows and the state-of-the-art memory, interconnect, and storage architectures considered in exascale designs. The storage hierarchy has expanded with node-local persistent memory, solid-state storage, and traditional disk and tape-based storage, thus requiring efficiency at each layer and much more efficient data movement among these layers. This paper discusses how the ExaHDF5 project improved the I/O performance and data management for exascale architectures by enhancing HDF5, a widely used parallel I/O library. The team developed an Asynchronous I/O Virtual Object Layer (VOL) connector that allowed overlapping I/O with computation. They also created a Cache VOL to complement asynchronous I/O by incorporating fast storage layers, such as burst buffer and node-local storage, into the parallel I/O workflow through caching and staging data. Additionally, the team enabled data aggregation and I/O at the node level by using a Subfiling Virtual File Driver (VFD). To demonstrate superior I/O performance with HDF5 at exascale, the ExaHDF5 team collaborated with several exascale applications. In this paper, we show I/O performance improvements for three applications: Cabana (a particle-based simulation library), EQSIM (a regional earthquake simulation software), and E3SM (a climate system modeling library).

Exploring noise-induced techniques to strengthen deep learning model resilience

AbstractIn artificial intelligence, combating overfitting and enhancing model generalization is crucial. This research explores innovative noise-induced regularization techniques, focusing on natural language processing tasks. Inspired by gradient noise and Dropout, this study investigates the interplay between controlled noise, model complexity, and overfitting prevention. Utilizing long short-term memory and bidirectional long short term memory architectures, this study examines the impact of noise-induced regularization on robustness to noisy input data. Through extensive experimentation, this study shows that introducing controlled noise improves model generalization, especially in language understanding. This contributes to the theoretical understanding of noise-induced regularization, advancing reliable and adaptable artificial intelligence systems for natural language processing.

COVINet: a deep learning-based and interpretable prediction model for the county-wise trajectories of COVID-19 in the United States

The devastating impact of COVID-19 on the United States has been profound since its onset in January 2020. Predicting the trajectory of epidemics accurately and devising strategies to curb their progression are currently formidable challenges. In response to this crisis, we propose COVINet, which combines the architecture of Long Short-Term Memory and Gated Recurrent Unit, incorporating actionable covariates to offer high-accuracy prediction and explainable response. First, we train COVINet models for confirmed cases and total deaths with five input features, and compare Mean Absolute Errors (MAEs) and Mean Relative Errors (MREs) of COVINet against ten competing models from the United States CDC in the last four weeks before April 26, 2021. The results show COVINet outperforms all competing models for MAEs and MREs when predicting total deaths. Then, we focus on prediction for the most severe county in each of the top 10 hot-spot states using COVINet. The MREs are small for all predictions made in the last 7 or 30 days before March 23, 2023. Beyond predictive accuracy, COVINet offers high interpretability, enhancing the understanding of pandemic dynamics. This dual capability positions COVINet as a powerful tool for informing effective strategies in pandemic prevention and governmental decision-making.

Physics-informed neural networks for efficient aeroacoustic computational based on two time sequence prediction models

Physics-informed neural networks (PINNs) have been proven powerful for solving partial differential equations (PDEs). However, conventional PINNs fail handling time/space variables in the training data distinctly and overlook the temporal relationships among data points, which is critical for accurately modeling dynamic systems. To address this issue, this work proposes two novel PINN models based on the transformer and the convolutional long short-term memory (ConvLSTM) architectures, respectively. An encoder-decoder neural network structure is adopted to enhance handling of time-space variables and a high-order finite-difference method is used to compute partial derivatives. These computations are implemented using the convolution within the PyTorch framework that incorporates both physical and mathematical information into the neural networks. The efficacy of the proposed methods has been evaluated for the wave equation and the Reynolds-Averaged Navier-Stokes equations. Results suggest that the transformer-based PINN outperforms both the conventional and ConvLSTM-based PINN in terms of accuracy, efficiency and generalizability.

Generative AI with WGAN-GP for boosting seizure detection accuracy.

Imbalanced datasets pose challenges for developing accurate seizure detection systems based on electroencephalogram (EEG) data. Generative AI techniques may help augment minority class data to facilitate automatic epileptic seizure detection. This study investigates the impact of various data augmentation (DA) approaches, including Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP), Vanilla GAN, Conditional GAN (CGAN), and Cramer GAN, on classification performance with Random Forest models. The best-performing GAN variant, WGAN-GP, was then integrated with a bidirectional Long Short-Term Memory (LSTM) architecture and compared against traditional and synthetic oversampling methods. The evaluation of different GAN variants for data augmentation with Random Forest classifiers identified WGAN-GP as the most effective approach. The integration of WGAN-GP with bidirectional LSTM yielded substantial performance improvements, outperforming traditional oversampling methods and achieving an accuracy of 91.73% on the augmented data, compared to 86% accuracy on real data without augmentation. The proposed generative AI approach combining WGAN-GP and recurrent neural network models outperforms comparative synthetic oversampling methods on metrics relevant for reliable seizure detection from imbalanced EEG datasets. Incorporating the WGAN-GP generative AI technique for data augmentation and integrating it with bidirectional LSTM elevates seizure detection accuracy for imbalanced EEG datasets, surpassing the performance of traditional oversampling and class weight adjustment methods. This approach shows promise for improving epilepsy monitoring and management through enhanced automated detection system effectiveness.

Ontology-Based Data Collection for a Hybrid Outbreak Detection Method Using Social Media.

Given the persistent global challenge presented by rapidly spreading diseases, as evidenced notably by the widespread impact of the COVID-19 pandemic on both human health and economies worldwide, the necessity of developing effective infectious disease prediction models has become of utmost importance. In this context, the utilization of online social media platforms as valuable tools in healthcare settings has gained prominence, offering direct avenues for disseminating critical health information to the public in a timely and accessible manner. Propelled by the ubiquitous accessibility of the internet through computers and mobile devices, these platforms promise to revolutionize traditional detection methods, providing more immediate and reliable epidemiological insights. Leveraging this paradigm shift, our proposed framework harnesses Twitter data associated with infectious disease symptoms, employing ontology to identify and curate relevant tweets. Central to our methodology is a hybrid model that integrates XGBoost and Bidirectional Long Short-Term Memory (BiLSTM) architectures. The integration of XGBoost addresses the challenge of handling small dataset sizes, inherent during outbreaks due to limited time series data. XGBoost serves as a cornerstone for minimizing the loss function and identifying optimal features from our multivariate time series data. Subsequently, the combined dataset, comprising original features and predicted values by XGBoost, is channeled into the BiLSTM for further processing. Through extensive experimentation with a dataset spanning multiple infectious disease outbreaks, our hybrid model demonstrates superior predictive performance compared to state-of-the-art and baseline models. By enhancing forecasting accuracy and outbreak tracking capabilities, our model offers promising prospects for assisting health authorities in mitigating fatalities and proactively preparing for potential outbreaks.

Character-Level Embedding using FastText and LSTM for Biomedical Named Entity Recognition

Extracting biomedical entities has caught many researchers’ attention in which the recent technique of word embedding is employed for such a task. Yet, the traditional word embedding architectures of Word2vec or Glove are still suffering from the ‘out-of-vocabulary’ (OOV) problem. This problem occurs when an unseen term might be encountered during the testing which leads to absence of embedding vector. Hence, this study aims to propose a character-level embedding through FastText architecture. In fact, handling the character-level seems a promising solution for the OOV problem. To this end, the proposed FastText architecture has been used to generate embedding vectors for the possible N-gram combinations of each word. Consequentially, these vectors have been fed to a Long Short Term Memory (LSTM) architecture for classifying the words into its biomedical classes. Using two benchmark datasets of BioCreative-II and NCBI, the proposed method was able to produce an f-measure of 0.912 and 0.918 respectively. Comparing these results with the baseline studies demonstrates the superiority of the proposed character-level embedding of FastText in terms of Biomedical Named Entity Recognition (BNER) task.

A GexSe1-x switch-only-memory technology through polarized atomic distribution

Ovonic threshold switching (OTS) materials that are frequently used with a resistor (1S1R) in memory devices have been found to show controllable and reversible memory properties, which could enable new memory architectures. Here, we examine the impact of composition on the polarity-dependent memory properties of GexSe1-x OTS materials and reveal that an increase in Se content results in a higher set voltage threshold (Vth), a lower reset current (IRST), and a higher set energy. Specifically, Ge56Se44 demonstrates two distinct Vth of 5.1 and 3.8 V, which retain after annealing at 85 ℃ for one day. We fabricated Ge56Se44 into 1000 by 1000 cross-point pillar arrays and tested 100 of them. The results demonstrated that these Ge56Se44 devices show similar memory properties with a reset speed of 1 μs, a set speed of 50 ns, and an endurance of over 105 cycles. Interestingly, the Ge56Se44 pillars’ reset and set states could be attributed to polarized atomic distributions. By utilizing GexSe1-x, we demonstrate a true cross-point switch-only-memory technology and provide mechanistic insights for self-selecting OTS materials.

Real-Time Monitoring and Assessment of Rehabilitation Exercises for Low Back Pain through Interactive Dashboard Pose Analysis Using Streamlit—A Pilot Study

In the modern era, AI-driven algorithms have significantly influenced medical diagnosis and therapy. In this pilot study, we propose using Streamlit 1.38.0 to create an interactive dashboard, PoAna .v1—Pose Analysis, as a new approach to address these concerns. In real-time, our system accurately tracks and evaluates individualized rehabilitation exercises for patients suffering from low back pain using features such as exercise visualization and guidance, real-time feedback and monitoring, and personalized exercise plans. This dashboard was very effective for tracking rehabilitation progress. We recruited 32 individuals to participate in this pilot study. We monitored an individual’s overall performance for one week. Of the participants, 18.75% engaged in rehabilitative exercises less frequently than twice daily; 81.25% did so at least three times daily. The proposed Long Short-Term Memory (LSTM) architecture had a training accuracy score of 98.8% and a testing accuracy of 99.7%, with an average accuracy of 10-fold cross-validation of 98.54%. On the pre- and post-test assessments, there is a significant difference between pain levels, with a p < 0.05 and a t-stat value of 12.175. The proposed system’s usability score is 79.375, indicating that it provides a user-friendly environment for the user to use the PoAna .v1 web application. So far, our research suggests that the Streamlit 1.38.0-based dashboard improves patients’ engagement, adherence, and success with exercise. Future research aims to add more characteristics that can improve the complete care of low back pain (LBP) and validate the effectiveness of this intervention in larger patient cohorts.

Efficient physics-informed transfer learning to quantify biochemical traits of winter wheat from UAV multispectral imagery

Accurate and efficient estimation of biochemical traits, including leaf index area (LAI), leaf chlorophyll content (LCC) and canopy chlorophyll content (CCC), is crucial for crop growth monitoring in agricultural management. Recent advancements in unmanned aerial vehicle (UAV) multispectral remote sensing have enabled fast and cost-effective measurements of these traits. However, traditional statistical regression models trained on specific datasets lack scalability and transferability across practical field conditions without retraining. This study proposed an efficient physics-informed transfer learning model (PITL) for winter wheat biochemical traits estimation from UAV multispectral data. The PITL integrates the strengths of physical radiative transfer simulations and deep neural network architectures through transfer learning to improve the estimation of biochemical traits from UAV multispectral data. The PITL was tested with convolutional neural network (CNN), deep neural network (DNN), and long short-term memory (LSTM) architectures. Results indicated that PITLDNN had better accuracy than PITLCNN and PITLLSTM models in predicting LAI (R2=0.94, RMSE = 0.32 m2/m2), LCC (R2=0.81, RMSE = 5.20 μg/cm2) and CCC (R2=0.928, RMSE = 0.2 g/m2). Moreover, PITLDNN demonstrated higher capability in computational efficiency, making it suitable for processing large volumes of UAV multispectral data in crop growth monitoring applications. Furthermore, PITL's integration of radiative transfer knowledge with labeled field data yielded higher predictive accuracy compared to physically-based inversion model, pure data-driven deep neural network approaches, and hybrid models. This study highlighted the performance of PITLDNN in accurately and efficiently quantifing biochemical traits from UAV multispectral data, thereby providing timely and accurate information for guiding crop growth monitoring applications.