Search

DLSIA (Deep Learning for Scientific Image Analysis) is a Python-based machine learning library that empowers scientists and researchers across diverse scientific domains with a range of customizable convolutional neural network (CNN) architectures for a wide variety of tasks in image analysis to be used in downstream data processing. DLSIA features easy-to-use architectures, such as autoencoders, tunable U-Nets and parameter-lean mixed-scale dense networks (MSDNets). Additionally, this article introduces sparse mixed-scale networks (SMSNets), generated using random graphs, sparse connections and dilated convolutions connecting different length scales. For verification, several DLSIA-instantiated networks and training scripts are employed in multiple applications, including inpainting for X-ray scattering data using U-Nets and MSDNets, segmenting 3D fibers in X-ray tomographic reconstructions of concrete using an ensemble of SMSNets, and leveraging autoencoder latent spaces for data compression and clustering. As experimental data continue to grow in scale and complexity, DLSIA provides accessible CNN construction and abstracts CNN complexities, allowing scientists to tailor their machine learning approaches, accelerate discoveries, foster interdisciplinary collaboration and advance research in scientific image analysis.

The different flow regimes in a two-dimensional silo with a vibrated base are studied in terms of the usual statistical techniques and information theory. The passage of granular material through the mouth of the silo is analyzed by real-time analysis of images captured by a standard video camera. The brightness of these images is measured and recorded at very small time intervals (100 frames per second). The experiment is repeated for different values of the vibration intensity. Data recognizer wlzip directly treats the resulting b(t) files (brightness time series) based on data compressor techniques, yielding the information content measured by the mutability μ function. μ has not previously been considered as part of the conventional treatment of flow in granular media. The results obtained here clearly demonstrate the usefulness of mutability as a tool for distinguishing between different flowing regimes directly from the brightness sequence, with no manipulation of the series. This shows that information theory techniques can provide a complementary description of the discharge of granular materials and its control through data compression algorithms. [ABSTRACT FROM AUTHOR]

Electrocardiogram (ECG) signals generate massive volume of digital data, so they need to be suitably compressed for efficient transmission and storage. Polynomial approximations and polynomial interpolation have been used for ECG data compression where the data signal is described by polynomial coefficients only. Here, we propose approximation using hermite polynomial interpolation with chebyshev nodes for compressing ECG signals that consequently denoises them too. Recommended algorithm is applied on various ECG signals taken from MIT-BIH arrhythmia database without any additional noise as the signals are already contaminated with noise. Performance of the proposed algorithm is evaluated using various performance metrics and compared with some recent compression techniques. Experimental results prove that the proposed method efficiently compresses the ECG signals while preserving the minute details of important morphological features of ECG signal required for clinical diagnosis. [ABSTRACT FROM AUTHOR]

As the data volume continues to grow exponentially, there is an increasing demand for large storage system capacity. Data compression techniques effectively reduce the volume of written data, enhancing space efficiency. As a result, many modern SSDs have already incorporated data compression capabilities. However, data compression introduces additional processing overhead in critical I/O paths, potentially affecting system performance. Currently, most compression solutions in flash-based storage systems employ fixed compression algorithms for all incoming data without leveraging differences among various data access patterns. This leads to sub-optimal compression efficiency. This article proposes a data-type-aware Flash Translation Layer (DAFTL) scheme to maximize space efficiency without compromising system performance. First, we propose an I/O behavior prediction method to forecast future access on specific data. Then, DAFTL matches data types with distinct I/O behaviors to compression algorithms of varying intensities, achieving an optimal balance between performance and space efficiency. Specifically, it employs higher-intensity compression algorithms for less frequently accessed data to maximize space efficiency. For frequently accessed data, it utilizes lower-intensity but faster compression algorithms to maintain system performance. Finally, an improved compact compression method is proposed to effectively eliminate page fragmentation and further enhance space efficiency. Extensive evaluations using a variety of real-world workloads, as well as the workloads with real data we collected on our platforms, demonstrate that DAFTL achieves more data reductions than other approaches. When compared to the state-of-the-art compression schemes, DAFTL reduces the total number of pages written to the SSD by an average of 8%, 21.3%, and 25.6% for data with high, medium, and low compressibility, respectively. In the case of workloads with real data, DAFTL achieves an average reduction of 10.4% in the total number of pages written to SSD. Furthermore, DAFTL exhibits comparable or even improved read and write performance compared to other solutions. [ABSTRACT FROM AUTHOR]

Optical analog image processing technology is expected to provide an effective solution for high-throughput and real-time data processing with low power consumption. In various operations, optical spatial differential operations are essential in edge extraction, data compression, and feature classification. Unfortunately, existing methods can only perform low-order or selectively perform a particular high-order differential operation. Here, we propose and experimentally demonstrate a Bessel vortex modulated metalens composed of a single complex amplitude metasurface, which can perform multiple-order radial differential operations over a wide band by presetting the order of the corresponding Bessel vortex. This architecture further enables angle multiplexing to create multiple information channels that synchronously perform multi-order spatial differential operations, indicating the superiority of the proposed devices in parallel processing. Our approach may find various applications in artificial intelligence, machine vision, autonomous driving, and advanced biomedical imaging. A Bessel vortex modulated metalens is used for wide-band, multiple-order radial differential operations by presetting the order of the corresponding Bessel vortex. This enables synchronous spatial differential operations, with applications in optical data processing, machine vision and bio-imaging. [ABSTRACT FROM AUTHOR]

The automation of rail track inspection addresses key issues in railway transportation, notably reducing maintenance costs and improving safety. However, it presents numerous technical challenges, including sensor selection, calibration, data acquisition, defect detection, and storage. This paper introduces a compression method tailored for laser triangulation scanners, which are crucial for scanning the entire rail track, including the rails, rail fasteners, sleepers, and ballast, and capturing rail profiles for geometry measurement. The compression technique capitalizes on the regularity of rail track data and the sensors' limited measurement range and resolution. By transforming scans, they can be stored using widely available image compression formats, such as PNG. This method achieved a compression ratio of 7.5 for rail scans used in the rail geometry computation and maintained rail gauge reproducibility. For the scans employed in defect detection, a compression ratio of 5.6 was attained without visibly compromising the scan quality. Lossless compression resulted in compression ratios of 5.1 for the rail geometry computation scans and 3.8 for the rail track inspection scans. [ABSTRACT FROM AUTHOR]

We provide computationally efficient methods for unranking derangements and ménage permutations. That is, we provide a polynomial-time algorithm to extract the k th such permutation under the lexicographic ordering. More generally, we show that there exists a polynomial-time algorithm for unranking words in lexicographic order whenever there exists a polynomial-time algorithm for counting the number of such words with a given prefix. We use rook theory to give a polynomial-time algorithm for counting the number of derangements and ménage permutations with a given prefix and in turn use this to give an unranking algorithm. This has applications to combinatorics, probability, modeling, and data compression. [ABSTRACT FROM AUTHOR]

Genomic sequencing has become increasingly prevalent, generating massive amounts of data and facing a significant challenge in long-term storage and transmission. A solution that reduces the storage and transfer requirements without compromising data integrity is needed. The effectiveness of neural networks has already been endorsed in tasks like image and speech compression. Adapting them to recognize the intricate patterns in genomic sequences could help to find more redundancies and reduce storage requirements. The proposed method, called DNACoder, leverages deep learning techniques to achieve significant compression ratios while preserving the essential information in genomic data and offers a high-performance compression for genomic sequences in any data format. The results of the experiments clearly demonstrate the effectiveness of the method and its potential applications in genomic data storage. Our proposed method improves compression by 21.1% on bits per base compared to existing compressors on the benchmarked dataset. By using a deep learning prediction model that is structured as a convolutional layer followed by an attention-based long short-term memory network, we propose a novel lossless and reference-free compression approach (DNACoder), which can also be utilized as a reference-based compressor. The experimental outcome on the tested data illustrates that the advocated compression algorithm's CNN-LSTM model makes generalizations effectively for genomic sequence data and outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Evaluation of clustering validity to set up an optimal cluster-data space (CDS) is a vital task in many fields related to data mining. Almost existing clustering validity indexes (CVIs) lack stability due to being too sensitive to noise, especially impulse noise. Here, we (1) propose a new CVI named DzI (Dzung Index) or fRisk2 using analysis of fuzzy-set-based accumulated risk degree (FARD), and (2) present a new algorithm named fRisk2-bA for determining the optimal number of data clusters. It is a method of evaluation of the centroid-based fuzzy clustering validity. In essence, the fRisk2 still focuses on enhancing the data compression in each cluster and expanding the separation between cluster centroids. However, these features are exploited indirectly through FARD. As a result, the proposed method not only can avoid the difficulties of the traditional ones relying on the compression and separation properties directly but also can distill better local and global attributes in the data distribution to estimate the CDS more fully. Along with the proved theory basis, surveys, including the ones based on noisy datasets from measurements, showed the compared advantages of fRisk2 as follows. (1) The accuracy, stability, and convergence of the fRisk2 are outstanding. (2) Its total calculating cost is lower than the other surveyed CVIs. [ABSTRACT FROM AUTHOR]

With the development of Convolutional Neural Networks (CNNs), there is a growing requirement for their deployment on edge devices. At the same time, Compute-In-Memory (CIM) technology has gained significant attention in edge CNN applications due to its ability to minimize data movement between memory and computing units. However, the deployment of complex deep neural network models on edge devices with restricted hardware resources continues to be challenged by a lack of adequate storage for intermediate layer data. In this article, we propose an optimized JPEG Lossless Compression (JPEG-LS) algorithm that implements serial context parameter updating alongside parallel encoding. This method is designed for the global prediction and efficient compression of intermediate data layers in neural networks employing CIM techniques. The results indicate average compression ratios of 6.44× for VGG16, 3.62× for ResNet34, 1.67× for MobileNetV2, and 2.31× for InceptionV3. Moreover, the implementation achieves a data throughput of 32 bits per cycle at 600 MHz on the TSMC 28 nm, with a hardware cost of 122 K Gate Count. [ABSTRACT FROM AUTHOR]

This paper develops the theory of factorial numbers formed by positional number systems with mixed-base factorial number systems. The fundamentals of the theory of factorial numbers are outlined, a method for obtaining them is given, their range is determined, and noise immunity is assessed. The addition and subtraction operations on factorial numbers are considered, and examples of their implementation are given. Methods for transitioning from positional numbers to factorial numbers and back are proposed. Methods are given for converting factorial numbers into permutations and permutations into factorial numbers. The operations of adding and subtracting permutations using factorial numbers are described. The noise immunity of permutations and the ability to detect and correct errors are assessed. The prospects of using permutations formed by factorial numbers for constructing noise-resistant ciphers are shown. [ABSTRACT FROM AUTHOR]

Loss-less data compression becomes the need of the hour for effective data compression and computation in VLSI test vector generation and testing in addition to hardware AI/ML computations. Golomb code is one of the effective technique for lossless data compression and it becomes valid only when the divisor can be expressed as power of two. This work aims to increase compression ratio by further encoding the unary part of the Golomb Rice (GR) code so as to decrease the amount of bits used, it mainly focuses on optimizing the hardware for encoding side. The algorithm was developed and coded in Verilog and simulated using Modelsim. This code was then synthesised in Cadence Encounter RTL Synthesiser. The modifications carried out show around 6% to 19% reduction in bits used for a linearly distributed data set. Worst-case delays have been reduced by 3% to 8%. Area reduction varies from 22% to 36% for different methods. Simulation for Power consumption shows nearly 7% reduction in switching power. This ideally suggest the usage of Golomb Rice coding technique for test vector compression and data computation for multiple data types, which should ideally have a geometrical distribution. [ABSTRACT FROM AUTHOR]

The circular scan architecture (CSA) is a widely used scan design technique in digital circuit testing that involves scanning test data through a circuit in a circular pattern. Several optimization approaches have been suggested so far to lessen the Test Data Volume (TDV), but no one has shown satisfactory results. Therefore, this paper proposes a Modified and Customized Wingsuit Flying Search algorithm to decrease the test data volume time. The proposed MCWFS-SBA-CSA introduces some novel features that distinguish it from traditional circular scan approaches. The concept of wingsuit flying is an innovative approach in the field of scan systems. This allows the scan that moves more dynamically and efficiently, enabling it to cover a larger area in a shorter time than traditional circular-scan approaches. After this phase, only scan-chosen inputs are required to obtain the next test pattern from the captured response. Therefore, required less Automatic test equipment (ATE) memory in this research so there is a Decreased cost in system-on-chip (SOC). The proposed method attains fast global searching capacity. The efficiency of the proposed technique attains 26.42%, 32.45%, and 29.34% higher compression ratio (CR), Test Application Time (TAT) reduction of SC-128 attains 29.45%, 34.67%, and 40.22% higher, TDV of SC-256 attains 32.23%, 36.34%, and 39.23% higher than existing methods, such as TDV for Circular Scan Approaches utilizing Modified Shuffled Shepard Optimization (TDV-CSA-MSSO), Effectual Very-large-scale integration Test data compression system for CSA under modified and colony metaheuristic (ETDC-CSA-MACMH), and Test Data Compression Utilizing Tetrad state Skip System (TDC-DC-TSSC) for Digital Circuits, respectively. [ABSTRACT FROM AUTHOR]

AbstractIn this article we present an algorithm for faster computation of HMM likelihood gradients when the observation space is discrete. Many parameter estimation algorithms for HMM require repeated computation of gradient to optimize the likelihood function. Gradient computation is costly therefore its faster computation can improve their performance greatly. We develop an algorithm for faster computation of gradient using ideas from data compression. Our algorithm decreased computation cost of gradients by a factor of three to five. We apply our methods to speed up the Baum-Welch algorithm by similar factors. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusion Photon‐counting CT (PCCT) systems acquire multiple spectral measurements at high spatial resolution, providing numerous image quality benefits while also increasing the amount of data that must be transferred through the gantry slip ring.This study proposes a lossy method to compress photon‐counting CT data using eigenvector analysis, with the goal of providing image quality sufficient for applications that require a rapid initial reconstruction, such as to confirm anatomical coverage, scan quality, and to support automated advanced applications. The eigenbin compression method was experimentally evaluated on a clinical silicon PCCT prototype system.The proposed eigenbin method performs principal component analysis (PCA) on a set of PCCT calibration measurements. PCA finds the orthogonal axes or eigenvectors, which capture the maximum variance in the N dimensional photon‐count data space, where N is the number of acquired energy bins. To reduce the dimensionality of the PCCT data, the data are linearly transformed into a lower dimensional space spanned by the M < N eigenvectors with highest eigenvalues (i.e., the vectors that account for most of the information in the data). Only M coefficients are then transferred per measurement, which we term eigenbin values. After transmission, the original N energy‐bin measurements are estimated as a linear combination of the M eigenvectors. Two versions of the eigenbin method were investigated: pixel‐specific and pixel‐general. The pixel‐specific eigenbin method determines eigenvectors for each individual detector pixel, while the more practically realizable pixel‐general eigenbin method finds one set of eigenvectors for the entire detector array. The eigenbin method was experimentally evaluated by scanning a 20 cm diameter Gammex Multienergy phantom with different material inserts on a clinical silicon‐based PCCT prototype. The method was evaluated with the number of eigenbins varied between two and four. In each case, the eigenbins were used to estimate the original 8‐bin data, after which material decomposition was performed. The mean, standard deviation, and contrast‐to‐noise ratio (CNR) of values in the reconstructed basis and virtual monoenergetic images (VMI) were compared for the original 8‐bin data and for the eigenbin data.The pixel‐specific eigenbin method reduced photon‐counting CT data size by a factor of four with <5% change in mean values and a small noise penalty (mean change in noise of <12%, maximum change in noise of 20% for basis images). The pixel‐general eigenbin compression method reduced data size by a factor of 2.67 with <5% change in mean values and a less than 10% noise penalty in the basis images (average noise penalty ≤5%). The noise penalty and errors were less for the VMIs than for the basis images, resulting in <5% change in CNR in the VMIs.The eigenbin compression method reduced photon‐counting CT data size by a factor of two to four with less than 5% change in mean values, noise penalty of less than 10%–20%, and change in CNR ranging from 15% decrease to 24% increase. Eigenbin compression reduces the data transfer time and storage space of photon‐counting CT data for applications that require rapid initial reconstructions. [ABSTRACT FROM AUTHOR]

One of the fundamental tasks in quantum information theory is quantum data compression, which can be realized via quantum autoencoders that first compress quantum states to low-dimensional ones and then recover to the original ones with a reference state. When taking a pure reference state, there exists an upper bound for the encoding fidelity, which limits the compression of states with high entropy. To overcome the entropy inconsistency, we allow the reference state to be a mixed state and propose a cost function that combines the encoding fidelity and the quantum mutual information. We consider the reference states to be a mixture of maximally mixed states and pure states and propose three strategies for setting the ratio of mixedness. Numerical simulations of different states and experimental implementations on IBM quantum computers illustrate the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

In the field of collaborative visual simultaneous localization and mapping (CVSLAM), efficient data communication poses a significant challenge, particularly in environments with limited bandwidth. To address this issue, we introduce a method aimed at reducing communication consumption. Our approach starts with a strategic culling of map points, aiming at maximizing pose-visibility and expanding spatial diversity to effectively eliminate redundant data in CVSLAM. We achieve this by formulating the problem of maximizing pose-visibility and spatial diversity as a minimum-cost maximum-flow graph optimization problem. Subsequently, we apply finite state entropy encoding for the compression of visual information, further alleviating bandwidth constraints. To verify the proposed method, we implement it within a centralized collaborative monocular simultaneous localization and mapping (SLAM) system. Our approach has been tested on publicly available datasets and in real-world scene. The results show a prominent reduction in bandwidth usage by 49% while maintaining mapping accuracy and without introducing additional latency, confirming its effectiveness in a multi-agent system setting. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSNs) are structured for monitoring an area with distributed sensors and built-in batteries. However, most of their battery energy is consumed during the data transmission process. In recent years, several methodologies, like routing optimization, topology control, and sleep scheduling algorithms, have been introduced to improve the energy efficiency of WSNs. This study introduces a novel method based on a deep learning approach that utilizes variational autoencoders (VAEs) to improve the energy efficiency of WSNs by compressing transmission data. The VAE approach is customized in this work for compressing WSN data by retaining its important features. This is achieved by analyzing the statistical structure of the sensor data rather than providing a fixed-size latent representation. The performance of the proposed model is verified using a MATLAB simulation platform, integrating a pre-trained variational autoencoder model with openly available wireless sensor data. The performance of the proposed model is found to be satisfactory in comparison to traditional methods, like the compressed sensing technique, lightweight temporal compression, and the autoencoder, in terms of having an average compression rate of 1.5572. The WSN simulation also indicates that the VAE-incorporated architecture attains a maximum network lifetime of 1491 s and suggests that VAE could be used for compression-based transmission using WSNs, as its reconstruction rate is 0.9902, which is better than results from all the other techniques. [ABSTRACT FROM AUTHOR]

Existing deep convolutional neural networks that rely on large datasets typically require images with high resolution and deep neural network models trained and called upon to improve accuracy of image recognition and classification. It is needed to use lightweight model to adapt to such low-power devices. However, lightweight small models are limited in their ability to classify and recognize small-sized images with low-resolution and are constrained by the number of parameters in the model and unable to perform deep-level feature extraction, since the low-resolution indicates small sample information. In the intelligent interaction in digital media, capturing, storing, transmitting, and computing high-resolution, high-precision images incur high power consumption and operating costs. When deploying an image recognition system on the client-side of IoT devices, it is difficult to meet the hardware requirements of high storage space and fast computation speed. It is also challenging to directly use high-resolution image data for model fine-tuning and training, and the size and parameter updates of the model are also limited by the storage and operating capacity of the hardware facilities. We proposed a low-power image recognition framework consists data pre-processing part and lightweight modeling architecture part. The data pre-processing method for image data based on an Auto-Encoder that filters R, G, B color channel data using a resolution filter to realize data compression, that is Downscaling large input data to a smaller size, thus to address the limitations of low-power deep learning model deployment and training. Based on the resolution filter, a channel normalization method is proposed to perform batch normalization on each channel dimension to encode the original image data at the same size and improve the mean squared error discrimination of the image data. And the lightweight model uses a depth-separable convolutional neural network and two kinds of blocks: one with batch normalization and the other without, EdgeNet. The architecture makes it possible to deploy more suitable for IoT device. The proposed framework achieves only a small precision loss within permission, but improves the forward inference speed of the model, and reduce the memory storage to 8.7 MB. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new method of representing images using highly compressed features for classification and image content retrieval – called PCA-ResFeats. They are obtained by fusing high- and low-level features from the outputs of ResNet-50 residual blocks and applying to them principal component analysis, which leads to a significant reduction in dimensionality. Further on, by applying a floating-point compression, we are able to reduce the memory required to store a single image by up to 1,200 times compared to jpg images and 220 times compared to features obtained by simple output fusion of ResNet-50. As a result, the representation of a single image from the dataset can be as low as 35 bytes on average. In comparison with the classification results on features from fusion of the last ResNet-50 residual block, we achieve a comparable accuracy (no worse than five percentage points), while preserving two orders of magnitude data compression. We also tested our method in the content-based image retrieval task, achieving better results than other known methods using sparse features. Moreover, our method enables the creation of concise summaries of image content, which can find numerous applications in databases. [ABSTRACT FROM AUTHOR]

Extensive literature has shown that women's employment contributes to increasing rates of household savings and economic growth. Likewise, evidence has been reported that in an economic integration scheme, such as that of Central America, the strong economic interdependence existing between countries, because of their relatively high trade flows of imports and exports, gives rise to the spread of economic developments occurring in a country. This paper investigates the extent to which the increase in female employment in the countries of the Northern Triangle of Central America (Guatemala, El Salvador, and Honduras) leads to the increase in growth rates in the other countries (Nicaragua, Costa Rica, and Panama). For this purpose, principal components, which is a data compression methodology, is used. The variables that are included in the vector of principal components are the female-to-male employment ratios in the industrial sectors of the Northern Triangle countries. All data used in the analyses were taken from the World Bank's World Development Indicators. The first principal component of these variables explains 77 percent of the variance, and its decrease represents the deindustrialization of the respective countries. The second principal component accounts for 17 percent of the variance, and its increase represents the expansion of the service sector in the countries. The estimation of error correction equations showed that the first principal component of the female-to-male employment ratios of the industrial sector in Guatemala, El Salvador, and Costa Rica, exerted positive impacts on the economic growth rates of Nicaragua, Costa Rica, and Panama, while the second principal component exerted negative impacts. The results also showed that the ratios of female to male industrial employment, as well as the first principal component, fell as tariffs on imports were reduced, reflecting a process of deindustrialization which has led to losses in economic growth, and a decrease in trade flows, and rising youth unemployment and increases of the underground economy with adverse impacts on productivity. Likewise, trends towards economic stagnation and rising unemployment have led to increases in irregular emigration and remittances. Another important result is that the process of deindustrialization, fueled by the extreme openness of economies, has generated a substantial increase in the homicide rate. In summary, the results show that female employment generates increases in the economic growth rate of the respective country and in the other member countries. However, this process of regional employment induction is undermined by the extreme openness of economies, which means that the main beneficiaries of the economic dynamism imparted by the increase in female employment may be the countries from which it is imported. In other words, "globalization" or "openness" frustrates national efforts at economic and social development. It should be noted that in the 1960s and 1970s, when the model of import substitution prevailed, the Central American economies grew at rates twice as high as those prevailing after the "reforms." The economic policy recommendations are based on the promotion of women's employment by increasing the levels of female schooling, the establishment of national networks of childcare centers, combating discrimination against women in the workplace, etc. Efforts to increase women's employment will be better developed if they are structured within the framework of a national/regional employment strategy, in which objectives and targets would be established for each country, and the actions to be carried out in the areas of obtaining resources, identifying, approving and supervising projects would be outlined, and the results goals would be established with the respective indicators to be achieved in the medium and long term. But it should be pointed out that these actions cannot yield the results sought in the current structure of extreme openness of economies, which makes it necessary to design and implement policies to achieve the reindustrialization and re-agriculturalization of the economies, seeking, in addition to increasing economic dynamism, the increase of quality employment, and the reduction of violence and irregular emigration, the achievement of self-sufficiency and sustained increases in the production of goods of special importance. The results of this work have shown that in efforts to reignite economic growth, women's employment and Central American economic integration can play important roles. [ABSTRACT FROM AUTHOR]

In sheet metal forming, the interaction between virtual models and the real world remains challenging. Process simulations can exhibit significant errors, and reliable measurements are often scarce during early production stages. This study presents a hybrid twin framework that systematically unifies computer-aided design, simulation, and measurement data in an adaptive manner. Central to this framework is a reverse engineering algorithm that reconstructs and transforms the geometry of deep-drawn components from optical scan data into B-spline surfaces. The algorithm demonstrated high precision, indicating its suitability for process control and geometric analysis. The hybrid twin framework integrates virtual data from simulations and real-world data, as evidenced by a sensor concept for inline surface measurement. The framework ensures robust and redundant measurement concepts by estimating complete geometries from a few systematically preselected measuring points. This adaptive approach permits continuous updates and extensions to the database, accommodating both sparse inline signals and offline inspection data. This framework provides a conceptual model for integrating direct feedback interactions between virtual and physical environments, thereby enhancing the precision of analytical and predictive models in sheet metal forming processes. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Beijing University of Technology is the property of Journal of Beijing University of Technology, Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Content Addressable Memory (CAM) is utilized in Artificial Neural Networks, data compression, IP packet filtering, and network routers due to its high performance in the microprocessor. However, the use of CAM is limited because of its increased power consumption, especially in high capacitive Match-Lines (ML). The activation of every comparison circuit on every clock cycle is primarily responsible for the significant power dissipation, which leads to increased recharge activity and multiple transition occurrences in the ML. In order to overcome this issue, a novel Common Match Line Scheme (CMS) with a Pull Up/Pull Down (PUPD) Circuit is proposed. The new design of the CMS CAM architecture leverages by utilizing these technique, the mismatched tagline entries are kept in the pre-discharged phases, and only the matching tagline entry gets charged. Consequently, these approaches effectively reduce pre-charge activity and mitigate evaluate-power, thereby alleviating power dissipation concerns associated with CAM 13–45% and reducing delay 3–16% while comparing to the existing architectures without significant impact on the performance of the processor. Proposed CMS CAM outperforms the existing architectures in terms of noise also with minimal area overhead and it is a technology independent one which can be used in high performance microprocessor systems. [ABSTRACT FROM AUTHOR]

We study the Compressed Sensing (CS) problem, which is the problem of finding the most sparse vector that satisfies a set of linear measurements up to some numerical tolerance. CS is a central problem in Statistics, Operations Research and Machine Learning which arises in applications such as signal processing, data compression, image reconstruction, and multi-label learning. We introduce an ℓ 2 regularized formulation of CS which we reformulate as a mixed integer second order cone program. We derive a second order cone relaxation of this problem and show that under mild conditions on the regularization parameter, the resulting relaxation is equivalent to the well studied basis pursuit denoising problem. We present a semidefinite relaxation that strengthens the second order cone relaxation and develop a custom branch-and-bound algorithm that leverages our second order cone relaxation to solve small-scale instances of CS to certifiable optimality. When compared against solutions produced by three state of the art benchmark methods on synthetic data, our numerical results show that our approach produces solutions that are on average 6.22 % more sparse. When compared only against the experiment-wise best performing benchmark method on synthetic data, our approach produces solutions that are on average 3.10 % more sparse. On real world ECG data, for a given ℓ 2 reconstruction error our approach produces solutions that are on average 9.95 % more sparse than benchmark methods ( 3.88 % more sparse if only compared against the best performing benchmark), while for a given sparsity level our approach produces solutions that have on average 10.77 % lower reconstruction error than benchmark methods ( 1.42 % lower error if only compared against the best performing benchmark). When used as a component of a multi-label classification algorithm, our approach achieves greater classification accuracy than benchmark compressed sensing methods. This improved accuracy comes at the cost of an increase in computation time by several orders of magnitude. Thus, for applications where runtime is not of critical importance, leveraging integer optimization can yield sparser and lower error solutions to CS than existing benchmarks. [ABSTRACT FROM AUTHOR]

The motor is essential for manufacturing industries, but wear can cause unexpected failure. Predictive and health management (PHM) for motors is critical in manufacturing sites. In particular, data-driven PHM using deep learning methods has gained popularity because it reduces the need for domain expertise. However, the massive amount of data poses challenges to traditional cloud-based PHM, making edge computing a promising solution. This study proposes a novel approach to motor PHM in edge devices. Our approach integrates principal component analysis (PCA) and an autoencoder (AE) encoder achieving effective data compression while preserving fault detection and severity estimation integrity. The compressed data is visualized using t-SNE, and its ability to retain information is assessed through clustering performance metrics. The proposed method is tested on a custom-made experimental platform dataset, demonstrating robustness across various fault scenarios and providing valuable insights for practical applications in manufacturing. [ABSTRACT FROM AUTHOR]

Cloud computing is one of the promising technologies that offers costeffective choices for processing and storing the huge volumes of data. In today’s world, data is the most important asset that one can have but it needs to be handled and protected properly. Portability of data can be increased by reducing the size of the data to be stored because of the limited storage space. As a result, data compression has arisen significantly. Data compression is a useful technique for reducing data size and increasing the effectiveness of data transit and storage. Data compression reduces the size of a data file while using lossy or lossless compression. One of the newest techniques for data compression is data duplication, which can reduce the amount of data saved while removing unnecessary data and maintaining an exact copy of the data. This analysis presents an Efficient data compression and storage technique with key management authentication in cloud space. This approach uses Regressive probabilistic key encryption (RPKE) to encrypt the cloud data and Lempel-Ziv-77-Huffman coding (LZ77-HM) is used to compress the huge amounts of cloud data. The Performance of presented approach is evaluated in terms of compression ratio and compression rate. [ABSTRACT FROM AUTHOR]

Technologies like data-driven methods for battery state estimation, fleet monitoring and cloud-based BMSs are emerging. However, challenges in data compression and storage hinder their widespread adoption. This paper addresses these issues by proposing a novel, efficient lossy voltage data compression method for measurements in electric vehicles. The method is grounded in polynomial regression and enables the use of the adaptive method without the need for parameters or training of the model which, representing an improvement over existing techniques. At a compression rate of 99.75% in an ambient temperature of 25 °C on average across all drive cycles compared, the root mean square error (RMSE) was 5.62 mV. Impressively, at a compression rate of 99%, the RMSE decreased to 3.12 mV. Furthermore, an implementation on a low-power STM32 microcontroller can compress 600 data points in just 35 milliseconds, demonstrating its suitability for real-time applications. These results highlight the potential of our approach to significantly improve the efficiency and accuracy of voltage measurement compression in electric vehicles, paving the way for advancements in electric vehicle technology. [ABSTRACT FROM AUTHOR]

Recently, tensor decompositions have attracted increasing attention and shown promising performance in processing multi-dimensional data. However, the existing tensor decompositions assume that the correlation along one mode is homogeneous and thus cannot characterize the multiple types of correlations (i.e., heterogeneous correlation) along the mode in real data. To address this issue, we propose a heterogeneous tensor product that allows us to explore this heterogeneous correlation, which can degenerate into the classic tensor products (e.g., mode product and tensor–tensor product). Equipped with this heterogeneous tensor product, we develop a generalized tensor decomposition (GTD) framework for third-order tensors, which not only induces many novel tensor decompositions but also helps us to better understand the interrelationships between the new tensor decompositions and the existing tensor decompositions. Especially, under the GTD framework, we find that new tensor decompositions can faithfully characterize the multiple types of correlations along the mode. To examine the effectiveness of the new tensor decomposition, we evaluate its performance on a representative data compression task. Extensive experimental results on multispectral images, light field images, and videos compression demonstrate the superior performance of our developed tensor decomposition compared to other existing tensor decompositions. [ABSTRACT FROM AUTHOR]

A real-time and reliable automatic detection system for epileptic seizures holds significant value in assisting physicians with rapid diagnosis and treatment of epilepsy. Aiming to address this issue, a novel lightweight model called Convolutional Neural Network-Reformer (CNN-Reformer) is proposed for seizure detection on long-term EEG. The CNN-Reformer consists of two main parts: the Data Reshaping (DR) module and the Efficient Attention and Concentration (EAC) module. This framework reduces network parameters while retaining effective feature extraction of multi-channel EEGs, thereby improving model computational efficiency and real-time performance. Initially, the raw EEG signals undergo Discrete Wavelet Transform (DWT) for signal filtering, and then fed into the DR module for data compression and reshaping while preserving local features. Subsequently, these local features are sent to the EAC module to extract global features and perform categorization. Post-processing involving sliding window averaging, thresholding, and collar techniques is further deployed to reduce the false detection rate (FDR) and improve detection performance. On the CHB-MIT scalp EEG dataset, our method achieves an average sensitivity of 97.57%, accuracy of 98.09%, and specificity of 98.11% at segment-based level, and a sensitivity of 96.81%, along with FDR of 0.27/h, and latency of 17.81 s at the event-based level. On the SH-SDU dataset we collected, our method yielded segment-based sensitivity of 94.51%, specificity of 92.83%, and accuracy of 92.81%, along with event-based sensitivity of 94.11%. The average testing time for 1 h of multi-channel EEG signals is 1.92 s. The excellent results and fast computational speed of the CNN-Reformer model demonstrate its potential for efficient seizure detection. [ABSTRACT FROM AUTHOR]

The compression strategy plays an important role in the performance of IoT time series data storage system.However, the current compression strategies can not adapt to the characteristics of NVM and IoT time series data.This paper proposes a polymorphic cooperative compression strategy for IoT time-series data based on NVM.Firstly, the overall structure of IoT time series data is given.Then, to address the consistent patterns in IoT time series data and the different granularity between user-space and kernel-space operations on NVM, a dual-compression strategy is devised.Initially, a lightweight compression method is applied directly as IoT time series data is received in user-space.This method efficiently reduces the volume of data for storage, while minimizing the impact on the timeliness of data storage.Moreover, a deep compression algorithm is designed for the kernel-space, primarily focusing on querying and analyzing anomalous time series data.Additionally, to address the competition for NVM bandwidth between deep compression and data storage, a dynamic adjustment algorithm that guarantees write bandwidth is proposed.Finally, a prototype of the polymorphic cooperative compression strategy is implemented and YCSB-TS is used to evaluate the results.The results show that the proposed method can effectively improve the write throughput of IoT time-series data by up to 161.3% and reduce the storage space by up to 14.6%, compared with InfluxDB, OpenTSDB, KairosDB and TVStore.

Abstract Research into the hunting behavior in members of the Cricetidae family offers an opportunity to reveal what changes in the predatory behavioral sequences occur when a rodent species shifts from an omnivorous to a predatory lifestyle. The study tests the following hypotheses: are there phylogenetic differences in the divergence of species’ predatory lifestyles in hamsters or do ecological factors lead to shaping their hunting behavior? We applied the data compression approach for performing comparative analysis of hunting patterns as biological “texts.” The study presents a comparative analysis of hunting behaviors in five Cricetinae species, focusing on the new data obtained for the desert hamster Phodopus roborovskii whose behavior has never been studied before. The hunting behavior of P. roborovskii appeared to be the most variable one. In contrast, behavioral sequences in P. campbelli and Allocricetulus curtatus display more significant order and predictability of behavior during hunting. Optional hunting behavior in the most ancient species P. roborovskii displayed similarities with obligate patterns in “young” Allocricetulus species. It thus turned out to be the most advanced hunter among members of the Phodopus genus. Differences in hunting sequences among Phodopus representatives suggest that the hunting behavior of these species, despite its optional mode, was subject to selection during species splitting within the genus. These results did not reveal the role played by phylogenetic differences in the divergence of species’ predatory lifestyles. They suggested that ecological conditions are the main factors in speciation of the hunting behavior in hamsters.

The motor is essential for manufacturing industries, but wear can cause unexpected failure. Predictive and health management (PHM) for motors is critical in manufacturing sites. In particular, data-driven PHM using deep learning methods has gained popularity because it reduces the need for domain expertise. However, the massive amount of data poses challenges to traditional cloud-based PHM, making edge computing a promising solution. This study proposes a novel approach to motor PHM in edge devices. Our approach integrates principal component analysis (PCA) and an autoencoder (AE) encoder achieving effective data compression while preserving fault detection and severity estimation integrity. The compressed data is visualized using t-SNE, and its ability to retain information is assessed through clustering performance metrics. The proposed method is tested on a custom-made experimental platform dataset, demonstrating robustness across various fault scenarios and providing valuable insights for practical applications in manufacturing.

Unmanned Aerial Vehicles (UAVs) are increasingly being used in a variety of applications, including entertainment, surveillance, and delivery. However, the real-time Motion Estimation (ME) of UAVs is challenging due to the high speed and unpredictable movements of these vehicles. This paper presents a novel algorithm for optimizing ME for Remotely Controlled Vehicles (RCVs), with a particular focus on UAVs. The proposed algorithm, called Motion Dynamics Input Search (MDIS), incorporates information from vehicle motion dynamics estimation to enhance the accuracy and efficiency of ME. The MDIS algorithm addresses the challenges associated with real-time ME in RCVs by leveraging user input to guide the search for the most similar blocks in the previous video frame. Through extensive experimentation and evaluation, this study demonstrates the effectiveness of the proposed algorithm in improving ME performance for RCVs. The findings highlight the potential impact of user interaction and motion dynamics estimation in shaping the future of ME algorithms for RCVs and similar applications. [ABSTRACT FROM AUTHOR]

3D point clouds stand as one of the prevalent representations for 3D data, offering the advantage of closely aligning with sensing technologies and providing an unbiased representation of a measured physical scene. Progressive compression is required for real‐world applications operating on networked infrastructures with restricted or variable bandwidth. We contribute a novel approach that leverages a recursive binary space partition, where the partitioning planes are not necessarily axis‐aligned and optimized via an entropy criterion. The planes are encoded via a novel adaptive quantization method combined with prediction. The input 3D point cloud is encoded as an interlaced stream of partitioning planes and number of points in the cells of the partition. Compared to previous work, the added value is an improved rate‐distortion performance, especially for very low bitrates. The latter are critical for interactive navigation of large 3D point clouds on heterogeneous networked infrastructures. [ABSTRACT FROM AUTHOR]

Rock fractures are an important indicator for assessing the quality of rock masses. The significant differences in the color and texture distributions of rock mass exposures lead to great challenges in the automated extraction of fractures from various low-contrast images. To address these issues, an adaptive generalized gamma correction enhancement algorithm for rock fracture images is proposed. First, the entire gray level is divided into three regions, namely, the fracture region, transition region, and rock mass exposure region, through piecewise linear fitting of the prepeak gray histogram and a designed evaluation function. Subsequently, a generalized gamma transform curve with dynamic nonlinear variation of the gamma factor is proposed, enabling more flexible transitions between compression and expansion effects at different grayscale levels, and its parameters are automatically determined by fitting the histogram partition data. Ten representative rock fracture images and five well-known crack datasets are used for quantitative assessment and visual analysis, with the pixel response intensity ratio introduced as the quantitative metric. The experimental results demonstrate that compared to several traditional and state-of-the-art enhancement algorithms, the proposed method exhibits stronger targeting and adaptability in enhancing fractures while effectively suppressing rock mass exposure noise, with excellent performance. [ABSTRACT FROM AUTHOR]

The representation of subgrid‐scale orography is a challenge in the physical parameterization of orographic gravity‐wave sources in weather forecasting. A significant hurdle is encoding as much physical information with as simple a representation as possible. Other issues include scale awareness, that is, the orographic representation has to change according to the grid cell size and usability on unstructured geodesic grids with non‐quadrilateral grid cells. This work introduces a novel spectral analysis method approximating a scale‐aware spectrum of subgrid‐scale orography on unstructured geodesic grids. The dimension of the physical orographic data is reduced by more than two orders of magnitude in its spectral representation. Simultaneously, the power of the approximated spectrum is close to the physical value. The method is based on well‐known least‐squares spectral analyses. However, it is robust to the choice of the free parameters, and tuning the algorithm is generally unnecessary. Numerical experiments involving an idealized setup show that this novel spectral analysis performs significantly better than a straightforward least‐squares spectral analysis in representing the physical energy of a spectrum. Studies involving real‐world topographic data are conducted, and reasonable error scores within ±10% error relative to the maximum physical quantity of interest are achieved across different grid sizes and background wind speeds. The deterministic behavior of the method is investigated along with its principal capabilities and potential biases, and it is shown that the error scores can be iteratively improved if an optimization target is known. Discussions on the method's limitations and broader applicability conclude this work. Plain Language Summary: Wind flow over terrain has wide‐ranging influences on atmospheric processes. Meteorologists want to include this effect in their weather forecasts but encounter computational limitations. For global weather forecasting, terrain features are relatively small and usually not explicitly represented in forecast models. An ongoing research question is how best to represent these small‐scale features in forecast models. However, a few difficulties arise: (a) We want to encode as much information about the terrain with as simple a representation as possible. (b) Some forecast models represent the globe with an icosahedron. Therefore, terrain information must be encoded within the triangular or hexagonal cells. (c) The information encoded has to change if the size of the triangles or hexagons changes. In this work, we present a novel method to overcome the three difficulties mentioned above. We can compress terrain information from over 50,000 to below 100 data points that can be used for climate simulations. When the relative effect of the encoded terrain on atmospheric processes is considered, the method has good accuracy despite the severe constraints and data compression, with a 10% error bound. Apart from representing terrain in weather forecasting, this method has potential applications for generic data analysis. Key Points: We introduce a novel scale‐aware spectral approximation method for subgrid‐scale orographic data on non‐quadrilateral geodesic gridsThe method yields physically sound results and achieves reasonable error scores when approximating real‐world orographic spectraThe method features over two orders of magnitude compression in complexity and has potential applications in generic spectral analyses [ABSTRACT FROM AUTHOR]

In this work, an artificial neural network (ANN) aided vapor–liquid equilibrium (VLE) model is developed and coupled with a fully compressible computational fluid dynamics (CFD) solver to simulate the transcritical processes occurring in high-pressure liquid-fueled propulsion systems. The ANN is trained in Python using TensorFlow, optimized for inference using Open Neural Network Exchange Runtime, and coupled with a C++ based CFD solver. This plug-and-play model/methodology can be used to convert any multi-component CFD solver to simulate transcritical processes using only open-source packages, without the need of in-house VLE model development. The solver is then used to study high-pressure transcritical shock-droplet interaction in both two- and four-component systems and a turbulent temporal mixing layer (TML), where both qualitative and quantitative agreement (maximum relative error less than 5%) is shown with respect to results based on both direct evaluation and the state-of-the-art in situ adaptive tabulation (ISAT) method. The ANN method showed a 6 times speed-up over the direct evaluation and a 2.2-time speed-up over the ISAT method for the two-component shock-droplet interaction case. The ANN method is faster than the ISAT method by 12 times for the four-component shock-droplet interaction. A 7 times speed-up is observed for the TML case for the ANN method compared to the ISAT method while achieving a data compression factor of 2881. The ANN method also shows intrinsic load balancing, unlike traditional VLE solvers. A strong parallel scalability of this ANN method with the number of processors was observed for all the three test cases. Code repository for 0D VLE solvers, and C++ ANN interface—https://github.com/UMN-CRFEL/ANN_VLE.git. [ABSTRACT FROM AUTHOR]

As we move into the digital era, the pace of technological advancement is accelerating rapidly. Network traffic often becomes congested during the transmission of large data volumes. To mitigate this, data compression plays a crucial role in minimizing transmitted data. Vector quantization (VQ) stands out as a potent compression technique where each image block is encoded independently as an index linked to a codebook, effectively reducing the bit rate. In this paper, we introduce a novel scheme for recompressing VQ indices, enabling lossless restoration of the original indices during decoding without compromising visual quality. Our method not only considers pixel correlations within each image block but also leverages correlations between neighboring blocks, further optimizing the bit rate. The experimental results demonstrated the superior performance of our approach over existing methods. [ABSTRACT FROM AUTHOR]

End-to-end disparity estimation algorithms based on cost volume deployed in edge-end neural network accelerators have the problem of structural adaptation and need to ensure accuracy under the condition of adaptation operator. Therefore, this paper proposes a novel disparity calculation algorithm that uses low-rank approximation to approximately replace 3D convolution and transposed 3D convolution, WReLU to reduce data compression caused by the activation function, and unimodal cost volume filtering and a confidence estimation network to regularize cost volume. It alleviates the problem of disparity-matching cost distribution being far away from the true distribution and greatly reduces the computational complexity and number of parameters of the algorithm while improving accuracy. Experimental results show that compared with a typical disparity estimation network, the absolute error of the proposed algorithm is reduced by 38.3%, the three-pixel error is reduced to 1.41%, and the number of parameters is reduced by 67.3%. The calculation accuracy is better than that of other algorithms, it is easier to deploy, and it has strong structural adaptability and better practicability. [ABSTRACT FROM AUTHOR]

Research into the hunting behavior in members of the Cricetidae family offers an opportunity to reveal what changes in the predatory behavioral sequences occur when a rodent species shifts from an omnivorous to a predatory lifestyle. The study tests the following hypotheses: are there phylogenetic differences in the divergence of species' predatory lifestyles in hamsters or do ecological factors lead to shaping their hunting behavior? We applied the data compression approach for performing comparative analysis of hunting patterns as biological "texts." The study presents a comparative analysis of hunting behaviors in five Cricetinae species, focusing on the new data obtained for the desert hamster Phodopus roborovskii whose behavior has never been studied before. The hunting behavior of P. roborovskii appeared to be the most variable one. In contrast, behavioral sequences in P. campbelli and Allocricetulus curtatus display more significant order and predictability of behavior during hunting. Optional hunting behavior in the most ancient species P. roborovskii displayed similarities with obligate patterns in "young" Allocricetulus species. It thus turned out to be the most advanced hunter among members of the Phodopus genus. Differences in hunting sequences among Phodopus representatives suggest that the hunting behavior of these species, despite its optional mode, was subject to selection during species splitting within the genus. These results did not reveal the role played by phylogenetic differences in the divergence of species' predatory lifestyles. They suggested that ecological conditions are the main factors in speciation of the hunting behavior in hamsters. [ABSTRACT FROM AUTHOR]

A lossless data compression code based on a binary-coded ternary number representation is investigated. The code is complete, universal, synchronizable, and supports a direct search in a compressed file. A simple monotonous encoding and very fast decoding algorithms are constructed owing to code properties. Experiments show that in natural language text compression, the new code outperforms byte-aligned codes SCDC and RPBC either in compression ratio or in decoding speed. [ABSTRACT FROM AUTHOR]

Multi-channel acquisition systems of brain neural signals can provide a powerful tool with a wide range of information for the clinical application of brain computer interfaces. High-throughput implantable systems are limited by size and power consumption, posing challenges to system design. To acquire more comprehensive neural signals and wirelessly transmit high-throughput brain neural signals, a FPGA-based acquisition system for multi-channel brain nerve signals has been developed. And the Bluetooth transmission with low-power technology are utilized. To wirelessly transmit large amount of data with limited Bluetooth bandwidth and improve the accuracy of neural signal decoding, an improved sharing run length encoding (SRLE) is proposed to compress the spike data of brain neural signal to improve the transmission efficiency of the system. The functional prototype has been developed, which consists of multi-channel data acquisition chips, FPGA main control module with the improved SRLE, a wireless data transmitter, a wireless data receiver and an upper computer. And the developed functional prototype was tested for spike detection of brain neural signal by animal experiments. From the animal experiments, it shows that the system can successfully collect and transmit brain nerve signals. And the improved SRLE algorithm has an excellent compression effect with the average compression rate of 5.94%, compared to the double run-length encoding, the FDR encoding, and the traditional run-length encoding. The developed system, incorporating the improved SRLE algorithm, is capable of wirelessly capturing spike signals with 1024 channels, thereby realizing the implantable systems of High-throughput brain neural signals. [ABSTRACT FROM AUTHOR]

Efficient storage and sharing of massive biomedical data would open up their wide accessibility to different institutions and disciplines. However, compressors tailored for natural photos/videos are rapidly limited for biomedical data, while emerging deep learning-based methods demand huge training data and are difficult to generalize. Here, we propose to conduct Biomedical data compRession with Implicit nEural Function (BRIEF) by representing the target data with compact neural networks, which are data specific and thus have no generalization issues. Benefiting from the strong representation capability of implicit neural function, BRIEF achieves 2-3 orders of magnitude compression on diverse biomedical data at significantly higher fidelity than existing techniques. Besides, BRIEF is of consistent performance across the whole data volume, and supports customized spatially varying fidelity. BRIEF's multifold advantageous features also serve reliable downstream tasks at low bandwidth. Our approach will facilitate low-bandwidth data sharing and promote collaboration and progress in the biomedical field. [ABSTRACT FROM AUTHOR]