Lightweight Solution Research Articles

DIRformer: A Novel Image Restoration Approach Based on U-shaped Transformer and Diffusion Models

Image restoration (IR) involves the retrieval of missing or damaged image information and represents a significant challenge in the field of visual reconstruction. Currently, U-Net based Diffusion Models (DMs) display favorable results when utilized for IR tasks. However, the Diffusion Model (DM) based on U-Net demonstrates shortcomings in capturing the global context for IR. To address this issue, we propose a Novel Image Restoration Approach Based on U-shaped Transformer and Diffusion Models (DIRformer). DIRformer enhances the modeling capacity for long-range dependencies within DMs. In particular, DIRformer replaces the traditional U-Net downsampling with Patch merging, dedicated to improving detail preservation, and replaces upsampling with Dual up-sample, strategically designed to alleviate checkerboard artifacts. Besides, as a lightweight and versatile transformer-based solution for IR, DIRformer incorporates time and degradation mapping into the transformer design, all while preserving the fundamental U-shaped structural framework. We assess the efficacy of DIRformer in a multi-tasking IR setting across four datasets. The experimental performance illustrates that DIRformer achieves competitive performance on distortion metrics, including PSNR and SSIM. Remarkably, our proposed approach is almost 25× smaller and 2× faster than the existing methods while achieving comparable high performance.

Design of a lightweight broadband vibration reduction structure with embedded acoustic black holes in viscoelastic damping materials

Viscoelastic damping materials (VDMs) are valued for their high damping characteristics in vibration and noise control. However, they typically underperform at lower frequencies and add substantial mass to structures. This study introduces an innovative approach by embedding an acoustic black hole (ABH) structure within VDMs (ABH-VDM) to achieve lightweight and broadband vibration damping. Firstly, a finite element method-based vibration model is developed to analyse the propagation and attenuation characteristics of vibrations in a plate strip embedded with ABH-VDM. This analysis provides insights into the dynamic behaviour and damping effectiveness of the proposed structure. Secondly, the study investigates the vibration reduction capabilities and mass implications of ABH-VDM on large-scale plate structures. The influence of ABH structural parameters, including the power exponent, cutoff thickness, and array configuration, is systematically investigated to optimize damping performance. Finally, experimental validation confirms that ABH-VDM achieves an additional 1.4 dB reduction in vibration across the entire frequency spectrum, with a bandwidth extension of 900 Hz. Moreover, ABH-VDM reduces mass by 8.6 %, demonstrating its potential for lightweight vibration control in structural applications. This research contributes valuable insights into advancing lightweight and broadband damping solutions for enhanced vibration management in engineering systems.

MAR-YOLOv9: A multi-dataset object detection method for agricultural fields based on YOLOv9

With the development of deep learning technology, object detection has been widely applied in various fields. However, in cross-dataset object detection, conventional deep learning models often face performance degradation issues. This is particularly true in the agricultural field, where there is a multitude of crop types and a complex and variable environment. Existing technologies still face performance bottlenecks when dealing with diverse scenarios. To address these issues, this study proposes a lightweight, cross-dataset enhanced object detection method for the agricultural domain based on YOLOv9, named Multi-Adapt Recognition-YOLOv9 (MAR-YOLOv9). The traditional 32x downsampling Backbone network has been optimized, and a 16x downsampling Backbone network has been innovatively designed. A more streamlined and lightweight Main Neck structure has been introduced, along with innovative methods for feature extraction, up-sampling, and Concat connection. The hybrid connection strategy allows the model to flexibly utilize features from different levels. This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. Additionally, MAR-YOLOv9 demonstrated significant advantages in detecting complex agricultural images, providing an efficient, lightweight, and adaptable solution for object detection tasks in the agricultural field. The curated data and code can be accessed at the following link: https://github.com/YangxuWangamI/MAR-YOLOv9.

Polymer Composite Coatings Enhanced with Superhydrophobic Properties for Flexible Electronics Applications: A Review

ABSTRACT Flexible electronics have revolutionized various industries by offering lightweight and conformable solutions for diverse applications. However, their vulnerability to environmental factors, particularly moisture, remains a critical challenge. Polymer composite coatings enriched with superhydrophobic properties have gained considerable attention as a promising solution to safeguard flexible electronics. The present research report is a comprehensive review of the recent advancements in the development and application of superhydrophobic polymer composite coatings in flexible electronics, highlighting its potential applications in sensors and EMI shielding. The improvement in superhydrophobic characteristics hinges upon the choice of materials, fabrication techniques, surface morphology, and topographical features. This review article elaborates on the selection criteria for various organic and inorganic fillers suitable for polymers possessing innate hydrophobic or conducting properties. The different materials used as fillers in polymer matrix for fabricating superhydrophobic coating, the factors affecting the superhydrophobic properties of surfaces, and the superhydrophobic properties of fabricated surfaces using different materials have been reported.

Correction to: Fuzzy logic and CPSO-optimized key management for secure communication in decentralized IoT networks: A lightweight solution

Correction to: Fuzzy logic and CPSO-optimized key management for secure communication in decentralized IoT networks: A lightweight solution

Elliptic curves cryptography for lightweight devices in IoT system

The Internet of Things (IoT) is revolutionizing industries by connecting billions of devices, ranging from home appliances to industrial machines, to the internet. This transformation enables unprecedented automation, data collection, and process optimization. However, the widespread adoption of IoT also introduces significant security challenges, especially for lightweight devices with limited computational power and energy resources. Ensuring secure communication and data integrity in such constrained environments is critical. This paper explores and compares the performance of implemented algorithms within IoT devices. A comparison between Rivest-Shamir-Adleman (RSA) and Elliptic Curve Cryptography (ECC) implementations is made to identify a lightweight, secure, and efficient solution for IoT environments. Our results indicate that ECC outperforms RSA in terms of memory requirements, overall energy consumption, key sizes, signature generation time, key generation and execution time, and decryption time in a resource-constrained environment. However, RSA performs better in signature verification and encryption.

Beyond Performance Metrics: The Critical Role of Resource-Based Evaluation in Assessing IoT Attack Detectors

The proliferation of threats within the Internet of Things (IoT) environment is intensifying, largely due to the inherent limitations of this technology. The panoply of anti-threats based on artificial intelligence suffer from the complete embedment of models in limited resources. Tiny Machine Learning (TinyML) is presented as an opportunity in optimizing and selecting machine learning algorithms specifically tailored for intrusion detection systems (IDS) on limited-resource devices. This article addresses the challenges that must be overcome to enable the deployment of machine learning models on devices with constrained resources. In particular, it introduces additional indicators that could influence the algorithmic design of IoT models. Utilizing the PyCaret tool on the TON_IoT dataset, which encompasses nine distinct attacks, we developed and evaluated our approach for selecting the optimal algorithm from fourteen supervised learning models. The proposed tool, beyond the traditional six performance metrics, emphasizes resource consumption metrics, including memory, processor usage, battery life, and execution time – key considerations for TinyML in model refinement and selection. This study has identified less resource-intensive models suitable for developers in the design of IDS for IoT systems. We believe this research offers a foundational framework for the development of lightweight and efficient IoT vulnerability detection solutions.

MTS-YOLO: A Multi-Task Lightweight and Efficient Model for Tomato Fruit Bunch Maturity and Stem Detection

The accurate identification of tomato maturity and picking positions is essential for efficient picking. Current deep-learning models face challenges such as large parameter sizes, single-task limitations, and insufficient precision. This study proposes MTS-YOLO, a lightweight and efficient model for detecting tomato fruit bunch maturity and stem picking positions. We reconstruct the YOLOv8 neck network and propose the high- and low-level interactive screening path aggregation network (HLIS-PAN), which achieves excellent multi-scale feature extraction through the alternating screening and fusion of high- and low-level information while reducing the number of parameters. Furthermore, We utilize DySample for efficient upsampling, bypassing complex kernel computations with point sampling. Moreover, context anchor attention (CAA) is introduced to enhance the model’s ability to recognize elongated targets such as tomato fruit bunches and stems. Experimental results indicate that MTS-YOLO achieves an F1-score of 88.7% and an mAP@0.5 of 92.0%. Compared to mainstream models, MTS-YOLO not only enhances accuracy but also optimizes the model size, effectively reducing computational costs and inference time. The model precisely identifies the foreground targets that need to be harvested while ignoring background objects, contributing to improved picking efficiency. This study provides a lightweight and efficient technical solution for intelligent agricultural picking.

Unsupervised, piecewise linear decoding enables an accurate prediction of muscle activity in a multi-task brain computer interface.

Creating an intracortical brain-computer interface (iBCI) capable of seamless transitions between tasks and contexts would greatly enhance user experience. However, the nonlinearity in neural activity presents challenges to computing a global iBCI decoder. We aimed to develop a method that differs from a globally optimized decoder to address this issue. We devised an unsupervised approach that relies on the structure of a low-dimensional neural manifold to implement a piecewise linear decoder. We created a distinctive dataset in which monkeys performed a diverse set of tasks, some trained, others innate, while we recorded neural signals from the motor cortex (M1) and electromyographs (EMGs) from upper limb muscles. We used both linear and nonlinear dimensionality reduction techniques to discover neural manifolds and applied unsupervised algorithms to identify clusters within those spaces. Finally, we fit a linear decoder of EMG for each cluster. A specific decoder was activated corresponding to the cluster each new neural data point belonged to. We found clusters in the neural manifolds corresponding with the different tasks or task sub-phases. The performance of piecewise decoding improved as the number of clusters increased and plateaued gradually. With only two clusters it already outperformed a global linear decoder, and unexpectedly, it outperformed even a global recurrent neural network (RNN) decoder with 10-12 clusters. This study introduced a computationally lightweight solution for creating iBCI decoders that can function effectively across a broad range of tasks. EMG decoding is particularly challenging, as muscle activity is used, under varying contexts, to control interaction forces and limb stiffness, as well as motion. The results suggest that a piecewise linear decoder can provide a good approximation to the nonlinearity between neural activity and motor outputs, a result of our increased understanding of the structure of neural manifolds in motor cortex.

The ways and mechanisms of using CFRP materials to strengthen the flexural performance of reinforced concrete beams

Due to the increasing demand for structural strengthening and retrofitting solutions, Fiber-reinforced plastic (FRP) materials has emerged as a promising technology to improve the performance of existing structures. FRP material is a composite material composed of fiber-reinforced plastics, known for its excellent strength and resistance to corrosion. The primary components of this material consists of various fibers, such as glass fiber, carbon fiber, or aramid fiber, along with a resin matrix, such as epoxy resin, polyester resin. FRP materials are commonly employed in construction engineering to enhance the flexural strength of concrete structures. This paper, through methods of literature review and building physical models, investigates the effectiveness of Carbon Fiber Reinforced Polymer (CFRP) materials in enhancing the bending strength of reinforced concrete beams. This study aims to examine the impact of carbon fiber reinforced polymer (CFRP) sheets on the flexural strength of reinforced concrete beams, which aims to establish calculation formulas based on the specific impacts observed. The findings of this study demonstrate the capacity of FRP materials, specifically CFRP materials, to improve the bending strength of reinforced concrete beams. The usage of FRP materials for structural reinforcement offers a durable, corrosion-resistant, and lightweight solution that can prolong the lifespan and improve the structural efficacy of existing infrastructure.

OneTrack - An End2End approach to enhance MOT with Transformers

This paper introduces OneTrack, an innovative end-to-end transformer-based model for Multiple Object Tracking (MOT), focusing on enhancing efficiency without significantly compromising accuracy. Addressing the challenges inherent in MOT, such as occlusions, varied object sizes, and motion prediction, OneTrack leverages the power of vision transformers and attention layers, optimizing them for real-time applications. Utilizing a unique Object Sequence Patch Input and a Vision Transformer Encoder, the model simplifies the standard transformer approach by employing only the encoder component, significantly reducing computational costs. This approach is validated using the MOT17 dataset, a benchmark in the field, ensuring a comprehensive evaluation against established metrics like MOTA, HOTA, and IDF1. The experimental results demonstrate OneTrack's capability to outperform other transformer-based models in inference speed, with a marginal trade-off in accuracy metrics. The model's inherent design limitations, such as a maximum of 100 objects per window, are adjustable to suit specific applications, offering flexibility in various scenarios. The conclusion highlights the model's potential as a lightweight solution for MOT tasks, suggesting future work directions that include exploring alternative data representations and encoders, and developing a dedicated loss function to further enhance detection and tracking capabilities. OneTrack presents a promising step towards efficient and effective MOT solutions, catering to the demands of real-time applications.

A Structured Lightweight Encryption Architecture for Data Protection in IoT

Accelerated growth in networking and semiconductor devices led to the increase of Internet-connected devices over recent years. The applications of IoT provide pervasive admittance, scalability, and distribution of data using the cloud for the storage and processing of data. All the actors involved in the grid affect the trust. Managing security and deploying it throughout the IoT environment is required to audit and protect sensitive data. Security management involves authentication to avoid unauthorized entry and encryption at transmission. Though there are standard methodologies employed in data protection in the cloud and network layers, there is a requirement for solutions with low foot-prints suitable for constrained IoT devices. While there are existing lightweight cipher designs performing well with less memory footprint, the performance in the cloud is less compared to traditional cipher techniques. So, a balanced solution with less memory footprint and resistance against various attacks in the cloud environment is required. A lightweight cipher design is proposed to enable secure communication among devices through the cloud, which is combined with Elliptic Light (ELLI) and an Authentication Function (AF) is proposed using RC4 to ensure integrity and authentication and exchange secret key. The cipher design proposed provides increased efficiency and fixes the weakness in standard lightweight algorithms. This algorithm is simple and efficient, with 60% less memory utilization and 53% less execution time than other lightweight solutions. The stability is high in linear and differential cryptanalysis and resistive against DDoS attacks.

Performance evaluation of containers for low-latency packet processing in virtualized network environments

Packet processing in current network scenarios faces complex challenges due to the increasing prevalence of requirements such as low latency, high reliability, and resource sharing. Virtualization is a potential solution to mitigate these challenges by enabling resource sharing and on-demand provisioning; however, ensuring high reliability and ultra-low latency remains a key challenge. Since bare-metal systems are often impractical because of high cost and space usage, and the overhead of virtual machines (VMs) is substantial, we evaluate the utilization of containers as a potential lightweight solution for low-latency packet processing. Herein, we discuss the benefits and drawbacks and encourage container environments in low-latency packet processing when the degree of isolation of customer data is adequate and bare metal systems are unaffordable. Our results demonstrate that containers exhibit similar latency performance with more predictable tail-latency behavior than bare metal packet processing. Moreover, deciding which mainboard architecture to use, especially the cache division, is equally vital as containers are prone to higher latencies on more shared caches between cores especially when other optimizations cannot be used. We show that this has a higher impact on latencies within containers than on bare metal or VMs, resulting in the selection of hardware architectures following optimizations as a critical challenge. Furthermore, the results reveal that the virtualization overhead does not impact tail latencies.

Property investigation of functionally graded materials leaf spring plate fabricated through stir casting process by using new gradient evaluation method

AbstractAutomobile and aviation industries require lightweight solutions in the suspension system to improve overall performance and payload capacity. This can be achieved by materials having high strength to weight ratio. Fiber composites, known for their lightweight and high strength, face a major issue of delamination, which shortens the lifespan of fiber‐reinforced polymer leaf springs. Current researchers are emphasizing the use of functionally graded materials as a promising alternative to tackle this problem. In the present work, a functionally graded leaf spring plate was fabricated using stir casting technique with five layered gradations in the mid portion. The amount of molten material required for each gradation was ensured using a novel experimental technique. On the other hand, the matrix and reinforcement have been adopted from the output of the analysis conducted using CES EduPack 2019 software. Low density and high fatigue strength were primary focal point for the consideration of matrix and reinforcement materials. Aluminium 7075 and boron carbide were considered as matrix and reinforcement materials respectively. Stir casting technique, used in the present work, is simple, suitable and cost effective technique which creates a gradation at central part of the leaf.

Wireless power transfer in space using flexible, lightweight, coherent arrays

Space solar power (SSP), envisioned for decades as a solution for continuous, stable, and dynamically dispatchable clean energy, has seen tremendous interest and a number of experimental demonstrations in the last few years. A practical implementation has been elusive to date, owing to the high launch costs associated with heavy, rigid photovoltaic and wireless power transfer (WPT) arrays. Lightweight and flexible solutions for WPT have been demonstrated terrestrially but, to date, have not been deployed and tested in space. In this paper, we present an experimental space demonstration of a lightweight, flexible WPT array powered by custom radio-frequency integrated circuits. The transmit arrays, receive arrays, and the rest of the system were operated and tested for eight months in Low Earth Orbit (LEO). Results from these experiments, including pointing of the array’s beam to Earth and its detection by a ground station, are presented and discussed in detail. Observations and results from this mission uncover existing strengths and weaknesses that inform future steps towards realizing SSP.

Design and mechanical performance analysis of T-BCC lattice structures

The Body-Centered Cubic (BCC) lattice structure is commonly used in high-end equipment fields, such as aerospace, due to its superior mechanical properties, lightweight characteristics, and ease of processing. However, there is a need to improve the performance-to-weight ratio of the traditional BCC lattice structure. This study utilizes topology optimization to design a T-BCC lattice structure based on the BCC unit cell, with the aim of maximizing stiffness. A model proposing the characterization of the Young's modulus of BCC lattice structures is presented. The model is based on calculations of cell porosity and beam stress analysis, assuming a large cell. This approach indirectly enables the calculation of the Young's modulus of T-BCC lattice arrays in multiple dimensions. Simulation and experimental comparison were used to analyze the compressive performance and load-bearing modes of T-BCC lattice structures, revealing the mechanisms of compressive deformation and failure modes. The accuracy of the characterization model for Young's modulus was found to be 93.1%. Compared to BCC lattice structures designed by traditional methods, T-BCC lattice structures designed via topology optimization can increase the Young's modulus by up to 36% and yield strength by 37.2%. This suggests that T-BCC lattice structures are a more lightweight and efficient solution for designing components in high-end equipment fields.

YOLO-ABD: A Multi-Scale Detection Model for Pedestrian Anomaly Behavior Detection

Public safety and intelligent surveillance systems rely on anomaly detection for effective monitoring. In real-world pedestrian detection scenarios, Pedestrians often exhibit various symmetrical features such as body contours, facial features, posture, and clothing. However, the accuracy of pedestrian anomaly detection is affected by factors such as complex backgrounds, pedestrian obstruction, and small target sizes. To address these issues, this study introduced YOLO-ABD, a lightweight method for anomaly behavior detection that integrated small object detection and channel shuffling. This approach enhanced the YOLOv8n baseline model by integrating a small-object detection mechanism at the head and employing the symmetric GSConv convolutional module in the backbone network to improve perceptual capabilities. Furthermore, it incorporated the SimAM attention mechanism to mitigate complex background interference and thus enhance target detection performance. Evaluation on the IITB-Corridor dataset showed mAP50 and mAP50-95 scores of 89.3% and 60.6%, respectively. Generalization testing on the street-view-gdogo dataset further underscored the superiority of YOLO-ABD over advanced detection algorithms, demonstrating its effectiveness and generalization capabilities. With relatively fewer parameters, YOLO-ABD provided an excellent lightweight solution for pedestrian anomaly detection.

The Focusing Properties of a Modular All-Metal Lens in the Near-Field Region.

This article proposes a modular and passive all-metal lens to achieve near-field focusing with adjustable focus. The proposed lens consists of all-metal units with the phase coverage range exceeding 360°, and the arrangement of units is guided by the phase compensation method. Specifically, using the strategy of module unit synthesis, the arrangement of lens units under different focuses can be assembled arbitrarily, which reduces the production costs by 39.3% and improves the freedom of lens design. The simulation and experimental results show that the lens exhibits excellent focusing properties and freely changes the position of the expected focus (0.30 m-0.75 m). Therefore, the modular all-metal lens designed in this article has the characteristics of high transparency and a high degree of freedom, which can provide low-cost and lightweight solutions for various applications in the field of antennas, such as near-field target detection, microwave imaging, biomedicine, and so on.

Mechanical Shock Wave Suppression Structure in Hold-Down and Release Apparatus of Spacecraft

A lightweight and compact structural solution for mechanical shock suppression in spacecraft, such as the hold-down and release apparatus of satellites, is a critical and thorny issue. In this work, a ring-shaped structure is introduced to isolate mechanical waves within cylindrical shells. The underlying mechanism is that the ring-shaped structure undergoes different forms of deformation to counteract different modes of incident waves. A subwavelength Mn-Cu alloy ring is designed as a shock wave barrier in a typical spacecraft hold-down and release apparatus structure with multimodal wave excitation. We experimentally reveal that the Mn-Cu alloy ring reduces the peak value of the acceleration frequency response by 53.4% within a wide frequency range from 1 to 10 kHz. Meanwhile, in the time domain, the instantaneous acceleration peak can be weakened by 37.9%. This work provides a new strategy for shock control of shell structures in aerospace engineering and related fields.

Composite Pressure Vessel Failure Simulation Considering Spatial Variability

Carbon fiber-reinforced polymers offer lightweight solutions for demanding applications, but material imperfections affect structural reliability. In this study, an efficient uncertainty propagation framework is applied to predict composite behavior. The framework accounts for spatial variability of fiber misalignment, uneven fiber distribution, and single-fiber strength. Spatial variability is represented at both the micro- and mesoscale. Macroscale simulations incorporate this spatial variability indirectly using homogenized material properties. The framework was applied to composite pressure vessels, whose stochastic burst pressure was predicted. The predictions were validated by experimental measurements. These measurements show that the actual burst pressure was underpredicted by an average of 5.8%. Several hypotheses were investigated to explain this discrepancy.