Limited Computational Resources Research Articles

A Localization Method of High Energy Transients for All-sky Gamma-ray Monitor

Fast and reliable localization of high-energy transients is crucial for characterizing the burst properties and guiding the follow-up observations. Localization based on the relative counts of different detectors has been widely used for all-sky gamma-ray monitors. There are two major methods for this count distribution localization: χ 2 minimization method and the Bayesian method. Here we propose a modified Bayesian method that could take advantage of both the accuracy of the Bayesian method and the simplicity of the χ 2 method. With comprehensive simulations, we find that our Bayesian method with Poisson likelihood is generally more applicable for various bursts than the χ 2 method, especially for weak bursts. We further proposed a location-spectrum iteration approach based on the Bayesian inference, which could alleviate the problems caused by the spectral difference between the burst and location templates. Our method is very suitable for scenarios with limited computation resources or time-sensitive applications, such as in-flight localization software, and low-latency localization for rapidly follow-up observations.

FedGST: An Efficient Federated Graph Neural Network for Spatio-temporal PoI Recommendation

With the proliferation of sensor networks in urban areas, vast amounts of data from location-based social network platforms are now available, thus enabling the stakeholders to develop location-aware services for the end users. PoI (Point of Interests) recommendation is one of the most trending services. PoI recommendation models are developed by considering geographical information and historical records. More recently, with the demand for achieving PoI recommendations on mobile devices, embedded devices, or Internet of Things (IoT) devices, the challenges posed by the limited computational resources, malicious clients, and data silos, the model performance gets immensely affected. To address the above challenges and achieve efficient PoI recommendations, we propose an efficient federated graph learning-based model for mining complex spatiotemporal features to generate recommendations. We implement a GRU-based encoder-decoder to learn the temporal hidden state embeddings. Simultaneously, a 2-layer graph network is used to understand spatial embedding vectors. We also introduce an efficient contribution evaluation method to speed up the training process and improve the recommendation performance. Experiments on the PoI recommendation task based on real-life check-in data validate the effectiveness of our proposed model, and the results indicate that our recommendation model can achieve competitive results with lower computational costs.

Practical feature filter strategy to machine learning for small datasets in chemistry

Many potential use cases for machine learning in chemistry and materials science suffer from small dataset sizes, which demands special care for the model design in order to deliver reliable predictions. Hence, feature selection as the key determinant for dataset design is essential here. We propose a practical and efficient feature filter strategy to determine the best input feature candidates. We illustrate this strategy for the prediction of adsorption energies based on a public dataset and sublimation enthalpies using an in-house training dataset. The input of adsorption energies reduces the feature space from 12 dimensions to two and still delivers accurate results. For the sublimation enthalpies, three input configurations are filtered from 14 possible configurations with different dimensions for further productive predictions as being most relevant by using our feature filter strategy. The best extreme gradient boosting regression model possesses a good performance and is evaluated from statistical and theoretical perspectives, reaching a level of accuracy comparable to density functional theory computations and allowing for physical interpretations of the predictions. Overall, the results indicate that the feature filter strategy can help interdisciplinary scientists without rich professional AI knowledge and limited computational resources to establish a reliable small training dataset first, which may make the final machine learning model training easier and more accurate, avoiding time-consuming hyperparameter explorations and improper feature selection.

Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Data

Despite achieving remarkable performance, Federated Learning (FL) encounters two important problems, i.e., low training efficiency and limited computational resources. In this paper, we propose a new FL framework, i.e., FedDUMAP, with three original contributions, to leverage the shared insensitive data on the server in addition to the distributed data in edge devices so as to efficiently train a global model. First, we propose a simple dynamic server update algorithm, which takes advantage of the shared insensitive data on the server while dynamically adjusting the update steps on the server in order to speed up the convergence and improve the accuracy. Second, we propose an adaptive optimization method with the dynamic server update algorithm to exploit the global momentum on the server and each local device for superior accuracy. Third, we develop a layer-adaptive model pruning method to carry out specific pruning operations, which is adapted to the diverse features of each layer so as to attain an excellent trade-off between effectiveness and efficiency. Our proposed FL model, FedDUMAP, combines the three original techniques and has a significantly better performance compared with baseline approaches in terms of efficiency (up to 16.9 times faster), accuracy (up to 20.4% higher), and computational cost (up to 62.6% smaller).

Lightweight Network Bearing Intelligent Fault Diagnosis Based on VMD-FK-ShuffleNetV2

With the increasing complexity of mechanical equipment and diversification of deep learning models, vibration signals collected from such equipment are susceptible to noise interference. Moreover, traditional neural network models struggle to be effectively deployed in production environments with limited computational resources, severely impacting the accurate extraction and effective diagnosis of FK fault characteristics. In response to this challenge, this study proposes a fault diagnosis method for rolling bearings, integrating a lightweight ShuffleNetV2 network with variational mode decomposition (VMD) and the fast kurtogram (FK) algorithm. Initially, this paper introduces an enhanced FK method where the VMD algorithm is employed for data denoising, extracting FK post-denoising. These feature maps not only preserve critical signal information but also simplify data complexity. Subsequently, these feature maps are utilized to train and test the ShuffleNetV2 model, facilitating effective fault identification and classification. Ultimately, by conducting experimental comparisons with several mainstream lightweight network models, such as MobileNet and SqueezeNet, as well as traditional convolutional neural network models, this study validates the effectiveness of the proposed method in extracting fault characteristics from vibration signals, demonstrating superior diagnostic accuracy and computational efficiency. This provides a novel technical approach for health monitoring and fault diagnosis of industrial bearings and offers theoretical and experimental support for the deployment of lightweight networks in industrial applications.

Verification Study of in Silico Computed Intracardiac Blood Flow With 4D Flow MRI.

Major challenges for clinical applications of in silico medicine are limitations in time and computational resources. Computational approaches should therefore be tailored to specific applications with relatively low complexity and must be verified and validated against clinical gold standards. This study performed computational fluid dynamics simulations of left ventricular hemodynamics of different complexity based on shape reconstruction from steady state gradient echo magnetic resonance imaging (MRI) data. Computed flow results of a rigid wall model (RWM) and a prescribed motion fluid-structure interaction (PM-FSI) model were compared against phase-contrast MRI measurements for three healthy subjects. Extracted boundary conditions from the steady state MRI sequences as well as computed metrics, such as flow rate, valve velocities, and kinetic energy show good agreement with in vivo flow measurements. Regional flow analysis reveals larger differences. Basic flow structures are well captured with RWM and PM-FSI. For the computation of further biomarkers like washout or flow efficiency, usage of PM-FSI is required. Regarding boundary-near flow, more accurate anatomical models are inevitable. These results delineate areas of application of both methods and lay a foundation for larger validation studies and sensitivity analysis for healthy and diseased cases, being an essential step upon clinical translations.

Integration of the WRF model and IoT sensors to develop an early cold snap warning system for inland fishponds

The cold weather-related economic losses in the aquaculture and fisheries industries are enormous and will only increase due to future climate change. Advancements in weather forecasting have increased the accuracy of predicting environmental factors like air temperature, solar radiation, and wind speed. However, the water temperature of fishponds, which affects the lives of fish, cannot be accurately predicted. As a result, fishermen are unable to implement early disaster mitigation and avoidance measures effectively. In this study, we developed an early warning system for extreme temperature events in fishponds by using a weather forecasting model in combination with local observations from a customized sensor placed in a pond. This system could provide water temperature forecasts with up to 120 h of lead time. A fishpond and multiple events were selected to assess the performance. Compared to the actual observations, the predicted water temperature difference had a root mean square error of <2 °C for up to 72 h of lead time. Furthermore, due to limited computational resources for weather forecasting models, the water temperature and depth data collected by the sensor improved the accuracy of temperature prediction specific to each pond. The results have confirmed that the integrated method can effectively predict the water temperature of farmed fishponds and assist fishermen in implementing precautionary measures in time.

Lightweight Single-Stage Ship Object Detection Algorithm for Unmanned Surface Vessels Based on Improved YOLOv5.

Object detection is applied extensively in various domains, including industrial manufacturing, road traffic management, warehousing and logistics, and healthcare. In ship object detection tasks, detection networks are frequently deployed on devices with limited computational resources, e.g., unmanned surface vessels. This creates a need to balance accuracy with a low parameter count and low computational load. This paper proposes an improved object detection network based on YOLOv5. To reduce the model parameter count and computational load, we utilize an enhanced ShuffleNetV2 network as the backbone. In addition, a split-DLKA module is devised and implemented in the small object detection layer to improve detection accuracy. Finally, we introduce the WIOUv3 loss function to minimize the impact of low-quality samples on the model. Experiments conducted on the SeaShips dataset demonstrate that the proposed method reduces parameters by 71% and computational load by 58% compared to YOLOv5s. In addition, the proposed method increases the mAP@0.5 and mAP@0.5:0.95 values by 3.9% and 3.3%, respectively. Thus, the proposed method exhibits excellent performance in both real-time processing and accuracy.

Deep reinforcement learning-based low-latency task offloading for mobile-edge computing networks

Wireless Mobile Edge Computing (MEC) is an emerging solution to facilitate users’ computing. However, there are still some drawbacks, such as slow learning speed and high task latency. To overcome these difficulties, a deep reinforcement learning (DRL)-based task offloading (DRTO) framework is proposed, taking into account the time-varying nature of wireless channels and the unpredictability of task arrivals in multi-user MEC systems. Many deep neural networks (DNNs) are also used as scalable solutions to quickly determine the best offloading strategy by combining the perceptual capabilities of deep learning with the decision making capabilities of reinforcement learning (RL). Additionally, the concept of a minimum upper bound on the target Q-value is utilized to address the value overestimation problem that occurs during offload policy updates. This approach aims to minimize the latency of offload decisions by considering different channel environments, variable latency constraints among many users, and limited computational resources. Simulation results show that the algorithm reduces computation time and latency while achieving near-optimal performance compared to traditional Deep Deterministic Policy Gradient (DDPG) and Q-learning optimization methods. In addition, DRTO achieves more than 99.6% computational speedup compared to current almost ideal benchmarking techniques. Thus, the DRTO computational offload approach offers great potential for reducing overall system latency and improving the user experience.

1D-CLANet: A Novel Network for NLoS Classification in UWB Indoor Positioning System

Ultra-Wideband (UWB) technology is crucial for indoor localization systems due to its high accuracy and robustness in multipath environments. However, Non-Line-of-Sight (NLoS) conditions can cause UWB signal distortion, significantly reducing positioning accuracy. Thus, distinguishing between NLoS and LoS scenarios and mitigating positioning errors is crucial for enhancing UWB system performance. This research proposes a novel 1D-ConvLSTM-Attention network (1D-CLANet) for extracting UWB temporal channel impulse response (CIR) features and identifying NLoS scenarios. The model combines the convolutional neural network (CNN) and Long Short-Term memory (LSTM) architectures to extract temporal CIR features and introduces the Squeeze-and-Excitation (SE) attention mechanism to enhance critical features. Integrating SE attention with LSTM outputs boosts the model’s ability to differentiate between various NLoS categories. Experimental results show that the proposed 1D-CLANet with SE attention achieves superior performance in differentiating multiple NLoS scenarios with limited computational resources, attaining an accuracy of 95.58%. It outperforms other attention mechanisms and the version of 1D-CLANet without attention. Compared to advanced methods, the SE-enhanced 1D-CLANet significantly improves the ability to distinguish between LoS and similar NLoS scenarios, such as human obstructions, enhancing overall recognition accuracy in complex environments.

A low-complexity parallel local remote microphone technology for multichannel narrowband active noise control systems

Narrowband active noise control (NANC) systems can effectively eliminate periodic disturbances at its error sensors, but sometimes the error sensors are inconvenient to be placed at target locations for a long period. Remote microphone technology (RMT) can tackle this problem by moving quiet zones to the target areas. Nevertheless, the RMT-NANC system has significantly higher computational complexity than conventional NANC systems, particularly for multichannel systems. This hinders their implementation in real-time systems with limited computational resources. The additional computational burden stems from multiple convolutions involving the estimated global high-order secondary paths and observation filters when estimating the virtual error signals. To address this problem, a low-complexity parallel local RMT is proposed based on the narrowband filtered-x least mean square (PLRMT-NFxLMS) algorithm in this paper. Using a two-step local modeling approach, multiple local modeling low-order filters for both secondary paths and observation filters are constructed during the training stage. In the subsequent control stage, virtual error signals are estimated in parallel for different frequency components using these filters instead of global modeling filters, thereby alleviating the substantial computational cost arising from convolutions between lengthy vectors. Moreover, a filtered-error structure, termed the PLRMT-NFeLMS algorithm, is introduced in the proposed algorithm to further reduce the computational complexity. A comprehensive analysis of computational complexity is provided to demonstrate the superiority of the two proposed algorithms. Extensive simulations and real-time experiments were conducted to validate the feasibility and practicability of these proposed methods.

MixQuantBio: Towards extreme face and periocular recognition model compression with mixed-precision quantization

Current periocular and face recognition approaches utilize computationally costly deep neural networks, achieving notable recognition accuracies. Deploying such solutions in applications with limited computational resources requires minimizing their computational demand while maintaining similar recognition accuracies. Model compression techniques like model quantization can be used to reduce the computational costs of deep models. This approach is widely studied and applied to different machine-learning tasks, however it is understudied and investigated for biometrics. We propose in this work to reduce the computational cost of face and periocular recognition models using fixed- and mixed-precision model quantization. Specifically, we first quantize the full-precision models to fixed 8 and 6 bits, reducing the required memory footprint by 5x while maintaining, to a very large degree, the recognition accuracies. However, our achieved results demonstrated that by quantizing the models to extremely low b bits, e.g., below 6 bits, the accuracies significantly dropped, which motivated our investigation on mixed-precision quantization. Hence, we propose to utilize an iterative mixed-precision quantization scheme. In each iteration, the least important parameters are selected based on their weight magnitude and quantized to low b-bit precision and the model is fine-tuned. This approach is repeated until all parameters are quantized to low b-bit precision, achieving extreme reduction in memory footprint, e.g., 16x times, without significant loss in the model accuracies. The effectiveness of mixed- and fixed-precision quantization for biometric recognition models is studied and proved for two modalities, face and periocular, using three different deep network architectures and using different b bit precision.

User-tailored sub-selection of climate model ensemble members for impact studies

Climate model ensembles serve as an input to all impact studies that use sector-specific models (e.g., hydrological, ecological, crop models, fire hazard) at regional or local scales. These models require regionally scaled climate information to simulate the potential environmental and socio-economic sectoral impacts of climate change. Such simulations are based on comprehensive multi-member climate ensembles derived from the bias-adjusted and downscaled global and regional climate models. Due to limited computational resources, users of climate scenarios often can only include a small number of the ensemble members in their calculations, and therefore they often select them at random. A pre-selection of meaningful, consistent and case-specific members is therefore desired by the climate data users. In this work, we aim to fill this gap and present a novel user-tailored procedure for sub-selecting ensemble members for a variety of applications. Our method is based on the ranking of the climate change signal (CCS) calculated for a set of climate indices (e.g., mean temperature or number of hot days). Based on the CCS strength, three ensemble members representing the strongest, weakest, and median CCS are selected for each application. We also demonstrate the robustness of our approach in a specific hydrological impact model framework. Providing a systematic procedure not only assists impact modelers in selecting appropriate members, but also improves the consistency and comparability of different impact studies.

SN-CNN: A Lightweight and Accurate Line Extraction Algorithm for Seedling Navigation in Ridge-Planted Vegetables

In precision agriculture, after vegetable transplanters plant the seedlings, field management during the seedling stage is necessary to optimize the vegetable yield. Accurately identifying and extracting the centerlines of crop rows during the seedling stage is crucial for achieving the autonomous navigation of robots. However, the transplanted ridges often experience missing seedling rows. Additionally, due to the limited computational resources of field agricultural robots, a more lightweight navigation line fitting algorithm is required. To address these issues, this study focuses on mid-to-high ridges planted with double-row vegetables and develops a seedling band-based navigation line extraction model, a Seedling Navigation Convolutional Neural Network (SN-CNN). Firstly, we proposed the C2f_UIB module, which effectively reduces redundant computations by integrating Network Architecture Search (NAS) technologies, thus improving the model’s efficiency. Additionally, the model incorporates the Simplified Attention Mechanism (SimAM) in the neck section, enhancing the focus on hard-to-recognize samples. The experimental results demonstrate that the proposed SN-CNN model outperforms YOLOv5s, YOLOv7-tiny, YOLOv8n, and YOLOv8s in terms of the model parameters and accuracy. The SN-CNN model has a parameter count of only 2.37 M and achieves an mAP@0.5 of 94.6%. Compared to the baseline model, the parameter count is reduced by 28.4%, and the accuracy is improved by 2%. Finally, for practical deployment, the SN-CNN algorithm was implemented on the NVIDIA Jetson AGX Xavier, an embedded computing platform, to evaluate its real-time performance in navigation line fitting. We compared two fitting methods: Random Sample Consensus (RANSAC) and least squares (LS), using 100 images (50 test images and 50 field-collected images) to assess the accuracy and processing speed. The RANSAC method achieved a root mean square error (RMSE) of 5.7 pixels and a processing time of 25 milliseconds per image, demonstrating a superior fitting accuracy, while meeting the real-time requirements for navigation line detection. This performance highlights the potential of the SN-CNN model as an effective solution for autonomous navigation in field cross-ridge walking robots.

Decoupling framework for large-scale energy systems simultaneously addressing carbon emissions and energy flow relationships through sector units: A case study on uncertainty in China's carbon emission targets

The energy system requires meticulous planning to achieve low-carbon development goals cost-effectively. However, optimizing large-scale energy systems with high spatial-temporal resolution and a rich variety of technologies has always been a challenge due to limited computational resources. Therefore, this study proposes a soft-linkage framework to deconstruct large-scale energy system optimization models based on sectors while ensuring the total carbon emission limit and the electricity supply-demand balance. Using China's energy system as a case study, the impact of uncertainty on emission reduction targets is analyzed. A long-term emission target curve is only described by the total carbon budget and its temporal distribution. Results show that different carbon budget time series can lead to total transition cost variations of up to nearly 100 trillion yuan. Moreover, although a lower carbon budget would increase the total cumulative transition cost quadratically, excessively high carbon budgets raise national natural gas demand, threatening energy security.

EAIA: An Efficient and Anonymous Identity-Authentication Scheme in 5G-V2V.

Vehicle Ad-hoc Networks (VANETs) have experienced significant development in recent years, playing a crucial role in enhancing the driving experience by enabling safer and more efficient inter-vehicle interactions through information exchange. Vehicle-to-Vehicle (V2V) communication is particularly vital as it not only helps to prevent collisions and improve traffic efficiency but also provides essential situational awareness to drivers or autonomous driving systems. Communication is typically supported by roadside units (RSUs); however, in practical applications, vehicles may exceed the communication range of RSUs, thus exposing them to various malicious attacks. Additionally, considering the limited computational resources of onboard units (OBUs) in vehicles, there is a high demand for designing lightweight security protocols that support V2V communication. To address this issue, this paper proposes an efficient anonymous V2V identity-authentication protocol tailored for scenarios that lack RSU support. The proposed protocol was formally assessed using the Scyther tool, demonstrating its capability to withstand major typical malicious attacks. Performance evaluations indicate that the proposed protocol is efficient in terms of communication and computational overhead, making it a viable solution for V2V communication.

A Systematic Literature Review on the Use of Federated Learning and Bioinspired Computing

Federated learning (FL) and bioinspired computing (BIC), two distinct, yet complementary fields, have gained significant attention in the machine learning community due to their unique characteristics. FL enables decentralized machine learning by allowing models to be trained on data residing across multiple devices or servers without exchanging raw data, thus enhancing privacy and reducing communication overhead. Conversely, BIC draws inspiration from nature to develop robust and adaptive computational solutions for complex problems. This paper explores the state of the art in the integration of FL and BIC, introducing BIC techniques and discussing the motivations for their integration with FL. The convergence of these fields can lead to improved model accuracy, enhanced privacy, energy efficiency, and reduced communication overhead. This synergy addresses inherent challenges in FL, such as data heterogeneity and limited computational resources, and opens up new avenues for developing more efficient and autonomous learning systems. The integration of FL and BIC holds promise for various application domains, including healthcare, finance, and smart cities, where privacy-preserving and efficient computation is paramount. This survey provides a systematic review of the current research landscape, identifies key challenges and opportunities, and suggests future directions for the successful integration of FL and BIC.

About managing the number of simultaneously functioning software robots of different types

Objectives. The study sets out to justify the relevance and investigate approaches for solving the problem of managing the number of simultaneously functioning software robots of various types under conditions of limited computational resources and changes in sets of executable tasks.Methods. A proposed solution is based on models and methods of scenario management, linear programming, inventory management, queuing theory, and machine learning. The described methods are valid for different compositions and preconditions for generating initial data, as well as ensuring the relevance horizons of the obtained solutions.Results. The initial data is obtained via the presented approach for determining the computational resource parameters for operating a single software robot. The resources are determined by analyzing the composition of the software and information services used by an actual software robot. Problem statements and mathematical models are developed for cases involving scenario management and linear programming methods. Methods for real-time management of the number of software robots and their sequential local optimization are proposed based on the abovementioned solution sequences. The developed method for generating statistical data based the results of applying the sequential local optimization method is used to identify deficient and non-deficient computational resources. Some results of working in the multi-functional center of RTU MIREA software robots developed on the Аtоm.RITA platform are outlined.Conclusions. The emerging problem of managing the number of simultaneously operating software robots of various types for cases involving scenario control methods and linear programming is formalized. This problem is relevant in the field of automation of business processes of organizations. The use of mathematical methods for solving this problem opens up opportunities for expanding the functional capabilities of robotic process automation platforms, as well as increasing their economic efficiency to create competitive advantages by optimizing the use of IT infrastructure components.

A cross-modal high-resolution image generation approach based on cloud-terminal collaboration for low-altitude intelligent network

The advancement of digitization and automation in Low Altitude Intelligent Networking (LAIN) is constrained by limited computational resources and the absence of a dedicated modal transformation mechanism, affecting the performance of latency-sensitive missions. This study addresses these challenges by proposing a Downscaling Reconstruction Multi-scale Locally Focused Generative Adversarial Network (DR-MFGAN) with Federated Learning (FL). This integration employs wavelet transform downscaling and zero-shot residual learning techniques to create noise-suppressed image pairs, ultimately facilitating high-quality image reconstruction. The core network structure is composed of multidimensional residual blocks and generative confrontation network, and feature extraction is further enhanced through cross channel attention mechanism. Finally, distributed training based on Federated Learning ensures the training effectiveness of nodes with small data volumes.Experimental results demonstrate significant improvements: an 18.18% reduction in Mean Squared Error (MSE), a 33.52% increase in Peak Signal to Noise Ratio (PSNR), and a 39.54% improvement in Learned Perceptual Image Patch Similarity (LPIPS). The edge terminal can provide high-resolution imagery with limited data, achieving precise cross-modal transformations. This approach enhances LAIN capabilities, addressing computational and transformation challenges to support critical latency-sensitive missions.

DLE-YOLO: An Efficient Object Detection Algorithm with Dual-branch Lightweight Excitation Network

As a computer vision task, object detection algorithms can be applied to various real-world scenarios. However, efficient algorithms often come with a large number of parameters and high computational complexity. To meet the demand for high-performance object detection algorithms on mobile devices and embedded devices with limited computational resources, we propose a new lightweight object detection algorithm called DLE-YOLO. Firstly, we design a novel backbone called Dual-branch Lightweight Excitation Network (DLEN) for feature extraction, which is mainly constructed by Dual-branch Lightweight Excitation Units (DLEU). DLEU is stacked with different numbers of Dual-branch Lightweight Excitation Blocks (DLEB), which can extract comprehensive features and integrate information between different channels of features. Secondly, in order to enhance the network to capture key feature information in the regions of interest, the attention model HS-Coordinate Attention (HS-CA) is introduced into the network. Thirdly, the localization loss utilizes SIoU loss to further optimize the accuracy of the bounding box. Our method achieves a mAP value of 46.0% on the MS-COCO dataset, which is a 2% mAP improvement compared to the baseline YOLOv5-m, while bringing a 19.3% reduction in parameter count and a 12.9% decrease in GFLOPs. Furthermore, our method outperforms some advanced lightweight object detection algorithms, validating the effectiveness of our approach.