Memory Constraints Research Articles

MemoriaNova: Optimizing Memory-Aware Model Inference for Edge Computing

In recent years, deploying deep learning models on edge devices has become pervasive, driven by the increasing demand for intelligent edge computing solutions across various industries. From industrial automation to intelligent surveillance and healthcare, edge devices are being leveraged for real-time analytics and decision-making. Existing methods face two challenges when deploying machine learning models on edge devices. The first challenge is handling the execution order of operators with a simple strategy, which can lead to a potential waste of memory resources when dealing with directed acyclic graph structure models. The second challenge is that they usually process operators of a model one by one to optimize the inference latency, which may lead to the optimization problem getting trapped in local optima. We present MemoriaNova, comprising BTSearch and GenEFlow, to solve these two problems. BTSearch is a graph state backtracking algorithm with efficient pruning and hashing strategies designed to minimize memory overhead during inference and enlarge latency optimization search space. GenEFlow, based on genetic algorithms, integrates latency modeling and memory constraints to optimize distributed inference latency. This innovative approach considers a comprehensive search space for model partitioning, ensuring robust and adaptable solutions. We implement BTSearch and GenEFlow and test them on eleven deep-learning models with different structures and scales. The results show that BTSearch can reach 12% memory optimization compared with the widely used random execution strategy. At the same time, GenEFlow reduces inference latency by 33.9% in distributed systems with four-edge devices.

Benchmarking In-Sensor Machine Learning Computing: An Extension to the MLCommons-Tiny Suite

This paper proposes a new benchmark specifically designed for in-sensor digital machine learning computing to meet an ultra-low embedded memory requirement. With the exponential growth of edge devices, efficient local processing is essential to mitigate economic costs, latency, and privacy concerns associated with the centralized cloud processing. Emerging intelligent sensors equipped with computing assets to run neural network inferences and embedded in the same package, which hosts the sensing elements, present new challenges due to their limited memory resources and computational skills. This benchmark evaluates models trained with Quantization Aware Training (QAT) and compares their performance with Post-Training Quantization (PTQ) across three use cases: Human Activity Recognition (HAR) by means of the SHL dataset, Physical Activity Monitoring (PAM) by means of the PAMAP2 dataset, and superficial electromyography (sEMG) regression with the NINAPRO DB8 dataset. The results demonstrate the effectiveness of QAT over PTQ in most scenarios, highlighting the potential for deploying advanced AI models on highly resource-constrained sensors. The INT8 versions of the models always outperformed their FP32, regarding memory and latency reductions, except for the activations for CNN. The CNN model exhibited reduced memory usage and latency with respect to its Dense counterpart, allowing it to meet the stringent 8KiB data RAM and 32 KiB program RAM limits of the ISPU. The TCN model proved to be too large to fit within the memory constraints of the ISPU, primarily due to its greater capacity in terms of number of parameters, designed for processing more complex signals like EMG. This benchmark aims to guide the development of efficient AI solutions for In-Sensor Machine Learning Computing, fostering innovation in the field of Edge AI benchmarking, such as the one conducted by the MLCommons-Tiny working group.

Using the Discrete Wavelet Transform for Lossy On‐the‐Fly Compression of GPU Fluid Simulations

ABSTRACTHigh‐performance computing in fluid dynamics frequently confronts substantial memory demands, especially in large‐scale applications. Data compression techniques can alleviate these memory constraints, but introduce new challenges. This paper introduces an innovative on‐the‐fly low‐overhead lossy compression technique tailored for GPU‐based fluid simulations, utilizing the discrete wavelet transform (DWT). The technique is applicable to any numerical scheme where the data is stored on a regular grid and the time step is computed using a stencil. Our approach significantly diminishes memory requirements, achieving up to a 10‐fold long‐term reduction on a D3Q27 simulation, while minimally impacting the simulation accuracy. The methodology is built around careful design choices to achieve a satisfactory compression ratio/speed trade‐off. It effectively maintains mass conservation and accurately preserves essential discontinuities in simulations. Extensive testing with a D3Q27 Lattice‐Boltzmann method (LBM) simulation on a single GPU has shown that large‐scale grids can be processed with minimal impact on the simulation accuracy and acceptable compression times. This compression technique demonstrates a robust capability to handle memory limitations in fluid simulations, opening the door to more complex and larger‐scale simulations.

CLOUDSPAM: Contrastive Learning On Unlabeled Data for Segmentation and Pre-Training Using Aggregated Point Clouds and MoCo

SegContrast TEST paved the way for contrastive learning on outdoor point clouds. Its original formulation targeted individual scans in applications like autonomous driving and object detection. However, mobile mapping purposes such as digital twin cities and urban planning require large-scale dense datasets to capture the full complexity and diversity present in outdoor environments. In this paper, the SegContrast method is revisited and adapted to overcome its limitations associated with mobile mapping datasets, namely the scarcity of contrastive pairs and memory constraints. To overcome the scarcity of contrastive pairs, we propose the merging of heterogeneous datasets. However, this merging is not a straightforward procedure due to the variety of size and number of points in the point clouds of these datasets. Therefore, a data augmentation approach is designed to create a vast number of segments while optimizing the size of the point cloud samples to the allocated memory. This methodology, called CLOUDSPAM, guarantees the performance of the self-supervised model for both small- and large-scale mobile mapping point clouds. Overall, the results demonstrate the benefits of utilizing datasets with a wide range of densities and class diversity. CLOUDSPAM matched the state of the art on the KITTI-360 dataset, with a 63.6% mIoU, and came in second place on the Toronto-3D dataset. Finally, CLOUDSPAM achieved competitive results against its fully supervised counterpart with only 10% of labeled data.

Visual Lock - Enhancing Security with Visual Password

The prevailing method of user authentication commonly involves the submission of a text-based password along with a username. However, this approach has inherent drawbacks that have been widely acknowledged. A significant challenge is the difficulty users face in remembering passwords, leading to the adoption of short and simplistic ones, which in turn renders them susceptible to easy guessing or hacking. To address these concerns, this article introduces a novel financial graphical password authentication system. The operational details are elucidated through real-world examples, emphasizing key features of the system. In response to the limitations of conventional text-based password authentication, a groundbreaking financial graphical password method is proposed in this article. The prevailing issue of users resorting to short and easily guessable passwords due to memory constraints is addressed through this innovative approach. The article not only explains the functioning of the new system using real-world instances but also underscores its crucial features that enhance security in user authentication

Accelerating the clean-SC and CMF beamforming deconvolution methods using neural gridcompression

Deconvolution algorithms can considerably improve the spatial resolution of sound sources when applied to beamforming techniques. However, they are often associated with additional computation time, which can be prohibitive for real-time applications, especially when using high-resolution scanning grids. Additionally, depending on the size of the problem, full deconvolution may not even be possible due to memory constraints. Recently, it has been shown that a neural network approach to compress the possible source directions can speed up the results of the DAMAS deconvolution algorithm by orders of magnitude. In this paper, this neural grid compression preprocessing is evaluated for the CLEAN-SC and CMF deconvolution techniques, and it is shown that it is possible to achieve dramatic speedups without significant loss of accuracy and even improve the results in some examples, especially for the CLEAN-SC technique.

Lightweight medical image segmentation network with multi-scale feature-guided fusion

In the field of computer-aided medical diagnosis, it is crucial to adapt medical image segmentation to limited computing resources. There is tremendous value in developing accurate, real-time vision processing models that require minimal computational resources. When building lightweight models, there is always a trade-off between computational cost and segmentation performance. Performance often suffers when applying models to meet resource-constrained scenarios characterized by computation, memory, or storage constraints. This remains an ongoing challenge. This paper proposes a lightweight network for medical image segmentation. It introduces a lightweight transformer, proposes a simplified core feature extraction network to capture more semantic information, and builds a multi-scale feature interaction guidance framework. The fusion module embedded in this framework is designed to address spatial and channel complexities. Through the multi-scale feature interaction guidance framework and fusion module, the proposed network achieves robust semantic information extraction from low-resolution feature maps and rich spatial information retrieval from high-resolution feature maps while ensuring segmentation performance. This significantly reduces the parameter requirements for maintaining deep features within the network, resulting in faster inference and reduced floating-point operations (FLOPs) and parameter counts. Experimental results on ISIC2017 and ISIC2018 datasets confirm the effectiveness of the proposed network in medical image segmentation tasks. For instance, on the ISIC2017 dataset, the proposed network achieved a segmentation accuracy of 82.33 % mIoU, and a speed of 71.26 FPS on 256 × 256 images using a GeForce GTX 3090 GPU. Furthermore, the proposed network is tremendously lightweight, containing only 0.524M parameters. The corresponding source codes are available at https://github.com/CurbUni/LMIS-lightweight-network.

Efficient time series adaptive representation learning via Dynamic Routing Sparse Attention

Time series prediction plays a crucial role in various fields but also faces significant challenges. Converting original 1D time series data into 2D data through dimension transformation allows capturing more hidden features but incurs high memory consumption and low time efficiency. We have designed a sparse attention mechanism with dynamic routing perception called Dynamic Routing Sparse Attention (DRSA) to address these issues. Specifically, DRSA can effectively handle variations of complex time series data. Meanwhile, under memory constraints, the Dynamic Routing Filter (DRF) module further refines it by filtering the blocked 2D time series data to identify the most relevant feature vectors in the local context. We conducted predictive experiments on six real-world time series datasets with fine granularity and long sequence dependencies. Compared to eight state-of-the-art (SOTA) models, DRSA demonstrated relative improvements ranging from 4.18% to 81.02%. Furthermore, its time efficiency is 2 to 5 times higher than the baseline. Our code and dataset will be available at https://github.com/wwy8/DRSA_main.

Learning-Augmented Sketching Offers Improved Performance for Privacy Preserving and Secure GWAS.

The introduction of trusted execution environments (TEEs), such as secure enclaves provided by the Intel SGX technology has enabled secure and privacy-preserving computation on the cloud. The stringent resource limitations, such as memory constraints, required by some TEEs necessitates the development of computational approaches with reduced memory usage, such as sketching. One example is the SkSES method for GWAS on a cohort of case and control samples from multiple institutions, which identifies the most significant SNPs in a privacy-preserving manner without disclosing sensitive genotype information to other institutions or the cloud service provider. Here we show how to improve the performance of SkSES on large datasets by augmenting it with a learning-augmented approach. Specifically, we show how individual institutions can perform smaller scale GWAS on their own datasets and identify two sets of variants according to certain criteria, which are then used to guide the sketching process to more accurately identify significant variants over the collective dataset. The new method achieves up to 40% accuracy gain compared to the original SkSES method under the same memory constraints on datasets we tested on. The code is available at https://github.com/alreadydone/sgx-genome-variants-search.

Lossy Image Compression with Stochastic Quantization

Introduction. Lossy image compression algorithms play a crucial role in various domains, including graphics, and image processing. As image information density increases, so do the resources required for processing and transmission. One of the most prominent approaches to address this challenge is color quantization, proposed by Orchard et al. (1991). This technique optimally maps each pixel of an image to a color from a limited palette, maintaining image resolution while significantly reducing information content. Color quantization can be interpreted as a clustering problem (Krishna et al. (1997), Wan (2019)), where image pixels are represented in a three-dimensional space, with each axis corresponding to the intensity of an RGB channel. The purpose of the paper. Scaling of traditional algorithms like K-Means can be challenging for large data, such as modern images with millions of colors. This paper reframes color quantization as a three-dimensional stochastic transportation problem between the set of image pixels and an optimal color palette, where the number of colors is a predefined hyperparameter. We employ Stochastic Quantization (SQ) with a seeding technique proposed by Arthur et al. (2007) to enhance the scalability of color quantization. This method introduces a probabilistic element to the quantization process, potentially improving efficiency and adaptability to diverse image characteristics. Results. To demonstrate the efficiency of our approach, we present experimental results using images from the ImageNet dataset. These experiments illustrate the performance of our Stochastic Quantization method in terms of compression quality, computational efficiency, and scalability compared to traditional color quantization techniques. Conclusions. This study introduces a scalable algorithm for solving the color quantization problem without memory constraints, demonstrating its efficiency on a subset of images from the ImageNet dataset. The convergence speed of the algorithm can be further enhanced by modifying the update rule with alternative methods to Stochastic Gradient Descent (SGD) that incorporate adaptive learning rates. Moreover, the stochastic nature of the proposed solution enables the utilization of parallelization techniques to simultaneously update the positions of multiple quants, potentially leading to significant performance improvements. This aspect of parallelization and its impact on algorithm efficiency presents a topic for future research. The proposed method not only addresses the limitations of existing color quantization techniques but also opens up new possibilities for optimizing image compression algorithms in resource-constrained environments. Keywords: non-convex optimization, stochastic optimization, stochastic quantization, color quantization, lossy compression.

3D Lightweight Cryptosystem Design For IoT Applications Based On Composite S-Box

The security of the Internet of Things (IoT) depends on strong cryptographic functions that require extensive computation and resources. The security of Internet of Things (IoT) relies on the use of strong cryptographic functions that demand extensive computation and resources. Therefore, the selection of a cryptographic system is influenced by the computational and communicational capabilities of IoT devices, including their energy requirements, memory constraints, and execution time. This paper aims to develop a lightweight and secure encryption algorithm for IoT applications, focusing on advancing cryptanalysis techniques. We propose a new lightweight algorithm named enhanced 3D RECTANGLE, designed to deliver robust security for IoT applications and optimized for cell phones with minimal memory usage, low power consumption, and efficient performance. The RECTANGLE block cipher was chosen for this research due to its high efficiency and speed relative to other lightweight algorithms, despite some security issues. The proposed enhanced 3D RECTANGLE algorithm improves confusion and diffusion properties through a new 3D array block rotation method for 4x4 plaintext, based on a 128-bit key and 16 rounds. Additionally, we designed a 4x4 composite S-Box with a Galois field pipelining structure, offering a more advanced solution compared to the Look-Up Table method. The cryptanalysis, avalanche effect, and bit error rate tests were conducted to verify the security strength of the proposed algorithm. The proposed algorithm was evaluated against two existing algorithms, RECTANGLE and Extended 3D RECTANGLE. The enhanced 3D RECTANGLE algorithm provides better cryptanalysis, demonstrating a 40% avalanche effect and achieving a bit error rate (BER) of 31%, indicating its greater effectiveness compared to the other two lightweight algorithms.

Robust Left-Right Hashing Scheme for Ubiquitous Computing

Ubiquitous computing systems possess the capability to collect and process data, which is subsequently shared with other devices. These systems encounter resource challenges such as memory constraints, processor speed limitations, power consumption considerations, and the availability of data storage. Therefore, maintaining data access and query processing speed in ubiquitous computing is challenging. Hashing is crucial to search operations and has caught the interest of many researchers. Several hashing techniques have been proposed and Cuckoo Hashing is found efficient to use in several applications. There are two variants of Cuckoo Hashing: Parallel Cuckoo Hashing and Sequential Cuckoo Hashing. Cuckoo Hashing suffers from challenges like high insertion latency, inefficient memory usage, and data migration. This paper proposes two hashing schemes: Left-Right Hashing and Robust Left-Right Hashing that successfully address and solve the major challenges of Sequential Cuckoo Hashing. The proposed schemes adopt the Combinatorial Hashing technique after modification and use this with a new collision resolution technique called Left-Right Random Probing. Left-Right Random Probing is a variant of random probing and uses prime numbers and Fibonacci numbers. In addition, this paper proposes a new performance indicator, degree of dexterity to estimate the performance of hashing techniques. Sequential Cuckoo Hashing suffers from hidden switching costs which are identified and its estimation is given by a new performance indicator called, T.R.C./Key. Performance of Sequential Cuckoo Hashing is order dependent.

Pipeline Leak Detection System for a Smart City: Leveraging Acoustic Emission Sensing and Sequential Deep Learning

This study explores a novel approach utilizing acoustic emission (AE) signaling technology for pipeline leakage detection and analysis. Pipeline leaks are a significant concern in the liquids and gases industries, prompting the development of innovative detection methods. Unlike conventional methods, which often require contact and visual inspection with the pipeline surface, the proposed time-series-based deep learning approach offers real-time detection with higher safety and efficiency. In this study, we propose an automatic detection system of pipeline leakage for efficient transportation of liquid (water) and gas across the city, considering the smart city approach. We propose an AE-based framework combined with time-series deep learning algorithms to detect pipeline leaks through time-series features. The time-series AE signal detection module is designed to capture subtle changes in the AE signal state caused by leaks. Sequential deep learning models, including long short-term memory (LSTM), bi-directional LSTM (Bi-LSTM), and gated recurrent units (GRUs), are used to classify the AE response into normal and leakage detection from minor seepage, moderate leakage, and major ruptures in the pipeline. Three AE sensors are installed at different configurations on a pipeline, and data are acquired at 1 MHz sample/sec, which is decimated to 4K sample/second for efficiently utilizing the memory constraints of a remote system. The performance of these models is evaluated using metrics, namely accuracy, precision, recall, F1 score, and convergence, demonstrating classification accuracies of up to 99.78%. An accuracy comparison shows that BiLSTM performed better mostly with all hyperparameter settings. This research contributes to the advancement of pipeline leakage detection technology, offering improved accuracy and reliability in identifying and addressing pipeline integrity issues.

Towards Non-Region Specific Large-Scale Inundation Modelling with Machine Learning Methods

Traditional flood inundation modelling methods are computationally expensive and not suitable for near-real time inundation prediction. In this study we explore a data-driven machine learning method to complement and, in some cases, replace existing methods. Given sufficient training data and model capacity, our design enables a single neural network instance to approximate the flow characteristics of any input region, opening the possibility of applying the model to regions without available training data. To demonstrate the method we apply it to a very large >8000 km2 region of the Fitzroy river basin in Western Australia with a spatial resolution of 30 m × 30 m, placing an emphasis on efficiency and scalability. In this work we identify and address a range of practical limitations, e.g., we develop a novel water height regression method and cost function to address extreme class imbalances and by carefully constructing the input data, we introduce some natural physical constraints. Furthermore, a compact neural network design and training method was developed to enable the training problem to fit within GPU memory constraints and a novel dataset was constructed from the output of a calibrated two-dimensional hydrodynamic model. A good correlation between the predicted and groundtruth water heights was observed.

The impact of visual working memory constraints on object recognition

ABSTRACT We explored the impact of visual working memory (VWM) constraints on the processing of complex objects, with a VWM task where participants (N = 75) adjusted the orientation of a bar to match a previously viewed one. Additionally, they performed a delayed match-to-sample task involving faces, houses, and pseudowords, where individual features or feature configurations were manipulated. Results showed a robust link between VWM precision for simple stimuli and memory for configural information in houses, beyond faces and pseudowords. Expert categories (faces, words) reduce VWM demands, while non-expert categories (houses) impose greater demands, especially for configural processing. Featural processing of non-expert categories places less demand on VWM. Extensive experience with an object category allows creating integrated chunks, facilitating rapid recognition and processing. Overall, configural processing of non-expert categories may place more demands on visual working memory than both featural processing of such categories and featural and configural processing of expert categories.

Anatomy-constrained synthesis for spleen segmentation improvement in unpaired mouse micro-CT scans with 3D CycleGAN

Objective. Auto-segmentation in mouse micro-CT enhances the efficiency and consistency of preclinical experiments but often struggles with low-native-contrast and morphologically complex organs, such as the spleen, resulting in poor segmentation performance. While CT contrast agents can improve organ conspicuity, their use complicates experimental protocols and reduces feasibility. We developed a 3D Cycle Generative Adversarial Network (CycleGAN) incorporating anatomy-constrained U-Net models to leverage contrast-enhanced CT (CECT) insights to improve unenhanced native CT (NACT) segmentation. Approach. We employed a standard CycleGAN with an anatomical loss function to synthesize virtual CECT images from unpaired NACT scans at two different resolutions. Prior to training, two U-Nets were trained to automatically segment six major organs in NACT and CECT datasets, respectively. These pretrained 3D U-Nets were integrated during the CycleGAN training, segmenting synthetic images, and comparing them against ground truth annotations. The compound loss within the CycleGAN maintained anatomical fidelity. Full image processing was achieved for low-resolution datasets, while high-resolution datasets employed a patch-based method due to GPU memory constraints. Automated segmentation was applied to original NACT and synthetic CECT scans to evaluate CycleGAN performance using the Dice Similarity Coefficient (DSC) and the 95th percentile Hausdorff Distance (HD95p). Main results. High-resolution scans showed improved auto-segmentation, with an average DSC increase from 0.728 to 0.773 and a reduced HD95p from 1.19 mm to 0.94 mm. Low-resolution scans benefited more from synthetic contrast, showing a DSC increase from 0.586 to 0.682 and an HD95p reduction from 3.46 mm to 1.24 mm. Significance. Implementing CycleGAN to synthesize CECT scans substantially improved the visibility of the mouse spleen, leading to more precise auto-segmentation. This approach shows the potential in preclinical imaging studies where contrast agent use is impractical.

EDGE AI BASED OBJECT DETECTION SYSTEM USING TFLITE

Edge computing has gained prominence in recent years due to its ability to process data closer to the source, reducing latency and bandwidth requirements. In this paper, we propose an Edge AI Based Object Detection System using TensorFlow Lite (TFLite), designed to perform real-time object detection on resource-constrained edge devices. The system leverages the efficiency and portability of TFLite, a lightweight framework for deploying machine learning models on edge devices, to enable efficient inference without relying on cloud connectivity. Our proposed system integrates state-of-the-art object detection models, such as SSD (Single Shot Multibox Detector) and YOLO (You Only Look Once), into the TFLite runtime environment. Through optimization techniques such as model quantization, pruning, and architecture modifications, we tailor these models to meet the computational and memory constraints of edge devices while maintaining high detection accuracy. Furthermore, we explore hardware acceleration options, including GPU and DSP (Digital Signal Processor), to further enhance inference speed and energy efficiency. We evaluate the performance of the Edge AI Based Object Detection System on various edge devices, including smartphones, IoT (Internet of Things) devices, and embedded systems. Real-world deployment scenarios are considered, encompassing applications such as smart surveillance, industrial automation, and autonomous vehicles. The results demonstrate the system's ability to achieve real-time object detection with low latency and minimal resource consumption, making it well-suited for edge computing environments where real-time responsiveness and privacy are paramount concerns. Keywords: object Detection, Machine Learning, Tensor Flow lite, deep learning.

Thermopriming Induces Time-Limited Tolerance to Salt Stress.

Implementing sustainable crop protection practices is crucial to protect global harvests and ensure high-quality food supplies. While priming is an established method in seed production for the fortification of plants against various stresses, it is not yet a standard practice in transplant cultivation. Thus, we evaluated the long-term effects of thermopriming-a heat-based priming technique-on the growth, development, and fruit yield of tomato plants. Following a recovery period of about six weeks for thermoprimed plants without stress inducers, we subjected them to subsequent salt stress to ascertain the persistence of the priming effects. Additionally, we compared the efficacy of thermopriming with benzothiadiazole (BTH), a chemical elicitor, in enhancing plant resilience to abiotic stress. While BTH application negatively impacted both plant growth and fruit health, thermopriming showed no such adverse effects on these parameters. Instead, thermopriming initially enhanced the plant defense mechanisms by increasing the accumulation of protective phenols and flavonoids in the leaves. Interestingly, while thermopriming did not alter the response to salt stress, it notably strengthened the overall resilience of the plants. Our findings underscore both the potential and temporal constraints of thermopriming memory. Nonetheless, primed plants exhibited temporarily increased stress tolerance, offering a means to safeguard the offspring.

A matrix-free parallel two-level deflation preconditioner for two-dimensional heterogeneous Helmholtz problems

We propose a matrix-free parallel two-level deflation method combined with the Complex Shifted Laplacian Preconditioner (CSLP) for two-dimensional heterogeneous Helmholtz problems encountered in seismic exploration, antennas, and medical imaging. These problems pose challenges in terms of accuracy and convergence due to scalability issues with numerical solvers. Motivated by the limitations imposed by excessive computational time and memory constraints when employing a sequential solver with constructed matrices, we parallelize the two-level deflation method without constructing any matrices. Our approach utilizes preconditioned Krylov subspace methods and approximates the CSLP preconditioner with a parallel geometric multigrid V-cycle. For the two-level deflation, standard inter-grid deflation vectors and further high-order deflation vectors are considered. As another main contribution, the matrix-free Galerkin coarsening approach and a novel re-discretization scheme as well as high-order finite-difference schemes on the coarse grid are studied to obtain wavenumber-independent convergence. The optimal settings for an efficient coarse-grid problem solver are investigated. Numerical experiments of model problems show that the wavenumber independence has been obtained for medium wavenumbers. The matrix-free parallel framework shows satisfactory weak and strong parallel scalability.

Comments on technological intervention and influence on human communication: From the perspective of folkloristics

This paper explores the evolution of human communication technologies, emphasizing the intertwined relationship between oral and written mediums across different stages: orality, literacy, printing, and the internet. The study underscores the persistent importance of orality, indicating that despite technological advancements, language's core role remains unchallenged in human communication. Delving into the limitations of orality, such as constraints in human memory and auditory abilities, the work addresses the crucial invention of devices and symbolic systems to record and transmit information more effectively. The transition from oral to written communication is analyzed not merely as a technical progression, but also as a factor impacting cultural dynamics and social hierarchies. Significant changes in communication practices are traced from the creation of writing scripts to the advent of printing and digital technology. The examination of such evolutions reveals the constant human effort to overcome biological constraints and leverage technology to meet increasingly complex communication needs. The study ultimately draws a fascinating parallel between ancient oral traditions and contemporary internet communication, stressing the ongoing relevance of orality even in our digitized era.