Within an Internet of Multimedia Things, the risk of disclosing streamed video content, such as arising from video surveillance, is of heightened concern. This leads to the encryption of that content. To reduce the overhead and lack of flexibility arising from full encryption of the content, a good number of selective-encryption algorithms have been proposed in the last decade. Some of them have limitations, in terms of significant delay due to computational cost, or excess memory utilization, or, despite being energy efficient, do not provide a satisfactory level of confidentiality, due to their simplicity. To address such issues, this paper presents a lightweight selective encryption scheme, in which encoder syntax elements are encrypted with the innovative EXPer (EXtended Permutation with exclusive OR). The selected syntax elements are taken from the final stage of video encoding that is during entropy coding. As a diagnostic tool, the Encryption Space Ratio measures encoding complexity of the video relative to the level of encryption so as to judge the success of the encryption process, according to entropy coder. A detailed comparative analysis of EXPer with state-of-the-art algorithms confirms that the EXPer provides significant confidentiality with a small computational cost and negligible encryption bitrate overhead. Thus, the results demonstrate that the proposed security scheme is a suitable choice for constrained devices in an Internet of Multimedia Things environment.

Today, the style of light construction materials used in building is one of the most important factors in reducing building's dead load and better performance of the structures in the earthquake. One of the ways to reduce the structure weight is to use lightweight blocks instead of using traditional materials. The main purpose of this research is to compare density, compressive strength and water absorption volume of non-load-bearing lightweight blocks made of natural and artificial lightweight aggregates. Scoria lightweight aggregates of Sanandaj, Ghorveh mine, pumice in Tabriz, Bostanabad mine, and Leca in Leca enterprise have been used to make the samples. Given the importance of the materials used, grading of coarse-grained materials has been conducted based on the standard of 7657 and grading of fine materials have been conducted based on the standard of 302.The experiments' results show that Scoria blocks due to hard texture, and high mechanical resistance of their lightweight aggregates, have had higher compressive strength, and density and lower water absorption volume compared to pumice and Lika lightweight aggregate blocks. Pumice blocks despite having desirable compressive strength and lower density compared to the two other blocks have higher water absorption volume, and do not meet the standard conditions. This same factor causes it faces with less interest. Among these Lika blocks with density of 1151.94 (kg per cubic meter) below 2000 kilograms per cubic meter of Iran density standard of 7782 (28-day compressive strength of 2.57 MPa), higher than 2.5 MPa of Iran compressive strength standard of 7782 (and water absorption volume of 282.92 kg per cubic meter) below 288 kilograms per cubic meter of Iran water absorption volume standard of 7782 (as a non-load-bearing lightweight block) have been diagnosed desirable.

Surface defect detection based on machine vision and convolutional neural networks (CNNs) is an important and necessary process that enables rubber ring manufacturers to improve production quality and efficiency. However, such automatic detection always consumes substantial computer resources to guarantee detection accuracy. To solve this problem, in this paper, we present a CNNs optimization algorithm based on the Ghost module. First, we replace the convolutional layer with the Ghost module in CNNs so that feature maps can be generated using cheaper linear operations. Second, we use an optimization method to obtain the best replacement of the Ghost module to achieve a balance between computer resource consumption and detection accuracy. Finally, we use an image preprocessing method that includes inverting colors. We integrated this algorithm into YOLOv5, which we trained on a dataset with 122 images of rubber ring surface defects. Compared with the original network, the network size decreased by 30.5% and the computational cost decreased by 23.1% whereas average precision only decreased by 1.8%. Additionally, the network's training time decreased by 16.1% as a result of preprocessing. These results show that the proposed approach greatly helped practical rubber ring surface defect detection.

To improve the interfacial compatibility between cement matrix and expanded polystyrene (EPS) in the core-shell lightweight aggregates (CSLA), the effects of sodium silicate, Polyvinyl alcohol (PVA) emulsion, Vinyl acetate-ethylene (VAE) emulsion, acrylic acid, and acetic acid on the cement-EPS interface were investigated. The denseness of the interface was studied by scanning electron microscopy (SEM), and the effect of interfacial agents on the hydration process of cement was studied by the heat of hydration and induction resistivity. The macroscopic properties of the interface of the CSLA were characterized by the "leak-white" rate, drop resistance and numerical crushing strength. The results show that the sodium silicate densifies the interface by generating hydration products on the EPS surface. At the same time, organic acid enhances the interfacial properties of EPS and cement by increasing the surface roughness and allowing hydration products to grow in the surface micropores. In terms of the cement hydration process, both two interfacial agents delay the cement hydration. Above all, with comprehensive interface properties, "leak-white" rate, and mechanical properties, VAE emulsion and sodium silicate can achieve the best performance with a final crushing resistance of 5.7 MPa.

This paper deals with the merger of the two lightweight stream ciphers—A5/1 and Trivium. The idea is to make the key stream generation more secure and to remove the attacks of the individual algorithms. The bits generated by the Trivium cipher (output) will act as the input of the A5/1 cipher. The registers used in the A5/1 cipher will be filled by the output bits of the Trivium cipher. The three registers will then be connected to generate an output which will be our required key stream.

The persistent security challenges in Industry 4.0 due to resource-constrained IoT devices necessitate innovative solutions. Addressing this, a study introduces the ASCON algorithm for lightweight Authenticated Encryption with Associated Data, enhancing confidentiality, integrity, and authenticity within IoT limitations. By integrating Digital Twins, the framework emphasizes the need for robust security in Industry 4.0, with ASCON ensuring secure data transmission, bolstering system resilience against cyber threats. Practical validation using MQTT protocol confirms ASCON’s efficacy over AES-GCM, highlighting its potential for enhanced security in Industry 4.0. Future research should focus on optimizing ASCON for microprocessors and developing secure remote access tailored to resource-constrained devices, ensuring adaptability in the digital era

With the progression of AI, embedding advanced AI technologies into small robotics and mobile devices has become essential, driving research towards lightweighting AI models. Our study enhances the EPINET depth estimation model for light field images, aiming for compactness and faster inference while preserving accuracy. We conducted two-step experiments aimed at enhancing inference efficiency: Initially, by adjusting input streams and convolution layers, we simplified the CNN model, achieving faster inference times at the cost of reduced accuracy. To address this reduction in accuracy, we then applied knowledge distillation, allowing the simplified model to learn from the original model’s more complex patterns. In our quantitative experiments using two error metrics, MSE (Mean Squared Error) and BadPix, we identified optimal knowledge positions and evaluated the required complexity for the student model. As a result, our method improved MSE by 21% and BadPix by 14% compared to training without it. Furthermore, the student model achieved an inference speed 13% faster than the teacher model and surpassed its accuracy by 10% in MSE. Additionally, we demonstrated that repeatedly applying our approach could further enhance both model compactness and accuracy.

With the continuous development of deep learning, the application of object detection based on deep neural network in the coal mine has been expanding. Simultaneously, as the production applications demand higher recognition accuracy, most research chooses to enlarge the depth and parameters of the network to improve accuracy. However, due to the limited computing resources in the coal mining face, it is challenging to meet the computation demands of a large number of hardware resources. Therefore, this paper proposes a lightweight object detection algorithm designed specifically for coal mining face, referred to as CM-YOLOv8. The algorithm introduces adaptive predefined anchor boxes tailored to the coal mining face dataset to enhance the detection performance of various targets. Simultaneously, a pruning method based on the L1 norm is designed, significantly compressing the model's computation and parameter volume without compromising accuracy. The proposed algorithm is validated on the coal mining dataset DsLMF+, achieving a compression rate of 40% on the model volume with less than a 1% drop in accuracy. Comparative analysis with other existing algorithms demonstrates its efficiency and practicality in coal mining scenarios. The experiments confirm that CM-YOLOv8 significantly reduces the model's computational requirements and volume while maintaining high accuracy.

Consensus algorithms are the core technology of blockchain and a focus in the current distributed system research. The consensus algorithms are widely used in distributed systems, it has solved the decentralization problem. The traditional consensus algorithm needs the process of node legitimacy checking, identity authentication, and primary node view change, so the time cost of reaching an agreement between nodes is still exponential. In response to the problem, a lightweight consensus algorithm based on graph (LCAG) is proposed for the Internet of Things (IoT) in this paper, which is proposes an access control table, and reaches an agreement among nodes by calculating the probability of nodes in the control table, and reduces the time overhead of the reaching an agreement in distributed systems. We have carried out simulation experiments for the new algorithm, and the experiments show that: the new algorithm needs less time overhead than the classical Byzantine algorithm need, as well as Byzantine Generals problem (BGP), practical Byzantine fault-tolerant algorithm (PBFT) and directed acyclic graph (DAG) algorithm, and so on. The new algorithm can be applied to the devices of IoT, which have limited computing power.

Lightweight concrete is a promising alternative in modern construction due to its reduced weight and potential to improve thermal and structural efficiency. Incorporating sustainable materials, such as nopal mucilage and aloe vera, can optimize its properties, promoting more eco-friendly practices in the industry. This study evaluates six concrete mixtures using different dosages of tuff, expanded clay, nopal mucilage, and aloe vera. Physical and mechanical tests were conducted, and the results revealed varied behaviors: mixtures with aloe vera showed extremes in water absorption and consistency, with tuff being very fluid and expanded clay having good workability. Mixtures with nopal mucilage were drier and less workable. In contrast, mixtures with expanded clay showed higher bulk density and variations in consistency and water absorption. Compressive strength varied depending on the lightweight agents used: mixtures with nopal mucilage-expanded clay and aloe vera-expanded clay showed moderate strengths, suggesting that these combinations can improve the strength of lightweight concrete. The different lightweight agents also affected the thermal and physical properties and the fractal dimension of the mixtures, indicating a greater structural complexity and better heat retention in combinations of expanded clay with nopal mucilage or aloe vera.

Rigid pavements at military airfields experience surface deterioration within 6-18 months of construction. The cause of this degradation is mainly due to combined exposure to repeated heat shocks from jet engine exhaust and spilled aviation oils (hydrocarbons). Surface degradation occurs in the form of disintegration of aggregates and cement paste into small pieces that pose severe risks of physical injury to maintenance crews or damage to an aircraft engine. Since coarse aggregates typically occupy 60-80% of the concrete volume, aggregates' thermal properties and microstructure should play a crucial role in the degrading mechanism. At high temperatures, concrete with lightweight aggregates is reported to have better performance compared to concrete with normal-weight aggregate. Thus, the present study carried out a detailed investigation of the mechanical and thermal performance of lightweight aggregate concrete exposed to the combined effects of high temperature and hydrocarbon oils simultaneously. To identify the resistance of different concrete with various lightweight coarse aggregates, pumice, perlite, lytag (sintered fly ash), and crushed brick were used as lightweight coarse aggregates in concrete. Also, basalt aggregate concrete was used as a reference. After cyclic exposures, all specimens were tested for residual mechanical, thermal, chemical, and microstructural properties. Overall, concrete with crushed brick aggregate and LYTAG used in this study showed superior resistance to the simulated airfield conditions.

Concrete cracks and local damage can affect the bond performance between concrete and steel bars, thereby reducing the durability of reinforced concrete structures. Compared with general concrete crack repair methods, biomineralization repair not only has effective bonding capabilities but is also particularly environmentally friendly. In view of this, this study aimed to apply biomineralization technology to repair damaged fiber-reinforced lightweight aggregate concrete (LWAC). Two groups of LWAC specimens were prepared. The control group used lightweight aggregates (LWAs) without bacterial spores and nutrient sources, and the experimental group used LWAs containing bacterial spores and nutrient sources. These specimens were first subjected to compression tests and pull-out tests, respectively, and thus were damaged. After the damaged specimen healed itself in different ways for 28 days, secondary compression and pull-out tests were conducted. The self-healing method of the control group involved placing the specimens in an incubator. The experimental group was further divided into experimental group I and experimental group II. The self-healing method of experimental group I was the same as that of the control group. The self-healing method of experimental group II involved soaking the specimen in a mixed solution of urea and calcium acetate for two days, and then taking it out and placing it in an incubator for two days, with a cycle of four days. The test results showed that, compared with the control group specimens, the relative bond strength ratio of the experimental group II specimens increased by 17.9%. Moreover, the EDS and XRD analysis results confirmed that the precipitate formed at the crack was calcium carbonate, which improved the compressive strength and bond strength after self-healing. This indicates that the biomineralization maintenance method used in experimental group II is more effective.

Using lightweight fire-rated board (LFRB) presents cost-effective opportunities for various passive fire protection measures. The aim of the project is to develop a LFRB with enhanced fire resistance, acoustic properties, and mechanical properties. These properties were determined using the Bunsen burner, furnace, energy dispersive X-Ray, impedance tube instrument, and Instron universal testing machine. To fabricate the LFRBs, vermiculite and perlite were blended with flame-retardant bind-ers, and four types of LFRBs were produced. A fire test was conducted to compare the fire-resistance performance of the LFRBs with a commercially available flame retardant board. The B2 prototype showed exceptional fire-resistant properties, with a temperature reduction of up to 73.0 °C as compared to the commercially available fire-rated magnesium board. Incorporating nano chicken eggshell into the specially formulated flame-retardant binder preserved the LFRBs’ structural integrity, enabling them to withstand fire for up to 120 minutes with an equilibrium temperature of 92.6 °C. This approach also provided an absorption coefficient of α = 2.0, a high flexural strength of 3.54 MPa, and effective flame retardancy properties with a low oxygen/carbon ratio of 2.60. These results make the LFRBs valuable for passive fire protection applications in the construction and building materials industry.

Computer vision models of salient object detection attempt to mimic the ability of the human visual system to select relevant objects in images. To this end, the development of deep neural networks on high-end computers has recently made it possible to achieve high performance. However, it remains a challenge to develop deep neural network models of the same performance for devices with much more limited resources. In this work, we propose a new approach for a lightweight salient object detection neural network model, inspired by the cone and spatial opponent processes of the primary visual cortex (V1), that inextricably link color and shape in human color perception. Our proposed model, namely CoSOV1net, is trained from scratch, without using backbones from image classification or other tasks. Experiments, on the most widely used and challenging datasets for salient object detection, show that CoSOV1Net achieves competitive performance (i.e. Fβ=0.931 on the ECSSD dataset) with state-of-the-art salient object detection models, while having low number of parameters (1.14M), low FLOPS (1.4G) and high FPS (211.2) on GPU (nvidia Geforce RTX 3090 TI) compared to the state-of-the-art in the salient object detection or lightweight salient object detection task. Thus, CoSOV1net turns out to be a lightweight salient object detection that can be adapted to mobile environments and resource-constrained devices.

Expanded Polystyrene (EPS) beads lightweight soil is a new type of artificial geotechnical material with low density and high strength, to promote the wide application of EPS beads lightweight soil in the project, replacing some cement with fly ash as a curing agent, which can consume the waste fly ash and reduce the cost of the project. EPS beads were used as a lightweight material, and cement and fly ash were used as curing agents into the raw soil to make fly ash EPS lightweight soil. The EPS beads contents are 0.5%, 1%, 1.5%, and 2%, the total curing agent contents are 10%, 15%, 20%, and 25%, and the proportions of cement replaced by fly ash are 0%, 15%, 30%, 45%, and 60%, respectively. Unconfined compressive strength (UCS) test and scanning electron microscopy (SEM) test were conducted. The results show that the EPS content, the total curing agent content, and the proportion of cement replaced by fly ash have a significant impact on the UCS of lightweight soil. It decreases with an increase in the EPS content, increases with an increase in the total curing agent content, and decreases with an increase in the proportion of cement replaced by fly ash. When the proportion of cement replaced by fly ash is not too high, the strength of lightweight soil decreases less, and its performance can still meet the engineering needs. At the same time, it can also consume fly ash and reduce environmental pollution. EPS lightweight soil mixed with fly ash still has advantages, and it is recommended that the proportion of cement replaced by fly ash is controlled to less than 30%. The failure patterns of lightweight soil mainly include splitting failure, oblique shear failure and bulging failure, which are related to the material mix ratio.

Robot grasp modeling and implementation is one of essential abilities for a robot with embodied artificial intelligence. However, most existing deep learning-based grasp methods suffer a large number of parameters and heavy computation overheads. To address this issue, by fully exploiting the complementary capabilities of both CNNs and Transformers, we propose a smart grasp deep network with one-way fusion strategy via context path and spatial path (SGNet), which enjoys a lightweight structure, fast inference speed and easy deployment on devices with limited computation resources. Specifically, the context path employs lightweight depthwise separable convolution to achieve fast down-sampling while a novel DSFormer module mainly by integrating Transformer is to extract global and context-rich features. The spatial path efficiently fuses feature information from the context path in one-way manner and generate high-resolution feature maps via point-by-point convolution operations. Experimental results show the proposed model with only 1M parameters has a significantly overall performance, achieving 99.4% accuracy on Cornell dataset and 93.4% accuracy on Jacquard dataset, as well as within 12.5ms inference time.

Object detection algorithms for open water aerial images present challenges such as small object size, unsatisfactory detection accuracy, numerous network parameters, and enormous computational demands. Current detection algorithms struggle to meet the accuracy and speed requirements while being deployable on small mobile devices. This paper proposes DFLM-YOLO, a lightweight small-object detection network based on the YOLOv8 algorithm with multiscale feature fusion. Firstly, to solve the class imbalance problem of the SeaDroneSee dataset, we propose a data augmentation algorithm called Small Object Multiplication (SOM). SOM enhance dataset balance by increasing the number of objects in specific categories, thereby improving model accuracy and generalization capabilities. Secondly, we optimize the backbone network structure by implementing Depthwise Separable Convolution (DSConv) and the newly designed FC-C2f, which reduces the model's parameters and inference time. Finally, we design the Lightweight Multiscale Feature Fusion Network (LMFN) to address the challenges of multiscale variations by gradually fusing the four feature layers extracted from the backbone network in three stages. In addition, LMFN incorporates the Dilated Re-param Block structure to increase the effective receptive field and improve the model's classification ability and detection accuracy. Experimental results on the SeaDroneSea dataset indicate that DFLM-YOLO improves mAP by 12.4% compared to the original YOLOv8s, while reducing parameters by 67.2%. This achievement provides a new solution for UAVs to conduct object detection missions in open water efficiently.

Aiming at the problem of small size of some spots on apple leaves and the difficulty of accurate detection of spot targets brought by the complex background of the orchard, this paper takes the alternaria leaf spot, rust, brown spot, grey spot and frog eye leaf spot on apple leaves as the research object, and proposes a high-accuracy detection model YOLOv5-Res and lightweight detection model YOLOv5-Res4 are proposed. Firstly, a multiscale feature extraction module ResBlock is designed by combining the Inception multi-branch structure and ResNet residual idea. Secondly, a lightweight feature fusion module C4 is designed to reduce the number of model parameters while improving the detection ability of small targets. Finally, a parameter streamlining strategy based on optimized model architecture is proposed. The experimental results show that the performance of YOLOv5-Res model and YOLOv5-Res4 model is significantly improved, the mAP@0.5 value is improved by 2.8% and 2.2% compared with YOLOv5s model and YOLOv5n model, respectively, and the size of YOLOv5-Res model and YOLOv5-Res4 model is only 10.8MB and 2.4MB, and the number of model parameters is reduced compared with YOLOv5s model and YOLOv5n model. counts are reduced by 22% and 38.3% compared to the YOLOv5s model and YOLOv5n model.

The multi-objective optimization design of hydraulic climbing mechanism (the core mechanism of gantry crane) was realized by using the method of combining central composite design (CCD), Kriging and multi-objective genetic algorithm (MOGA). Firstly, the hydraulic climbing mechanism model was established and the appropriate design variables were selected. The mass, maximum deformation and maximum equivalent stress of the hydraulic climbing mechanism was taken as the optimization objectives. Through the comparative analysis of the parameters of wedge block, anchor block, anchor plate、baffle, the parameters that have the greatest impact on the optimization objectives are selected as geometric constraints. Then, according to the results of experimental design, Kriging model was used to establish the response surface optimization model of objective function. Finally, the optimal results were obtained by using MOGA method. The experimental results show that the optimization strategy is reliable, and the mass of the optimized model is reduced by 10.28%. While meeting the actual production requirements, the lightweight design of the hydraulic climbing mechanism is realized, which saves the design cost and improves the material utilization rate.

The airborne and satellite-based synthetic aperture radar enables the acquisition of high-resolution SAR oceanographic images in which even the outlines of ships can be identified. The detection of ship targets from SAR images has a wide range of applications, such as the military, where the dynamic grasp of enemy targets can help improve the early warning capability of naval defence, and the civilian detection of illegal fishing vessels can help improve the level of maritime management. Due to the density of ships in SAR images, the extreme imbalance between foreground and background clutter, and the diversity of target sizes, achieving lightweight and highly accurate multi-scale ship target detection remains a great challenge. To this end, this paper proposes an attention mechanism for multiscale receptive fields convolution block (AMMRF). AMMRF not only makes full use of the location information of the feature map to accurately capture the regions in the feature map that are useful for detection results, but also effectively captures the relationship between the feature map channels, so as to better learn the relationship between the ship and the background. Based on this, a new YOLOv7-based ship target detection method, You Only Look Once SAR Ship Identification (YOLO-SARSI), is proposed, which acquires the abstract semantic information extracted from the high-level convolution while retaining the detailed semantic information extracted from the low-level convolution. Compared to the deep learning detection methods proposed by previous authors, our model is more lightweight, only 18.43M. We examined the effectiveness of our method on two SAR image public datasets: the High-Resolution SAR Images Dataset (HRSID) and the Large-Scale SAR Ship Detection Dataset-v1.0 (LS-SSDD-V1.0). The results show that the average accuracy AP50 of the detection method YOLO-SARSI proposed in this paper on the HRSID and LS-SSDD-V1.0 datasets is 4.9% and 5% higher than that of YOLOv7, respectively.

Real-time tracking is one of the most challenging problems in computer vision. Most Transformer-based trackers usually require expensive computational and storage power, which leads to the inability of these robust trackers to achieve real-time performance in resource-constrained devices. In this work, we propose a lightweight tracker, AnteaTrack. To localize the target more precisely, we develop a scaling-invariant max-filtering operator employing a sliding window combined with local max-pooling, which filters out the suspected target from the feature and performs an augmented representation while suppressing the background. For a more tight bounding box, we employ Pixel-Shuffle to increase the resolution of the feature map and get a more fine-grained representation of the target. In addition, AnteaTrack can run in real-time at 47 frames per second(FPS) on the CPU. We tested AnteaTrack on 5 datasets, and a large number of experiments have shown that AnteaTrack provides the most efficient solution compared to the same type of CPU real-time trackers. The code will be available at https://github.com/cnchange/AnteaTrack.

The rampant misuse of drones poses a serious threat to national security and human life. Currently, the CNN method has been widely used in drone detection. However, there is a challenge that traditional CNN cannot cope with, which is small drone targets often have reduced amplitude or even lost features in infrared images. This paper proposes a Progressive Feature Fusion Network (PFFNet) that gradually increases the response amplitude of the target in the deep network. The Feature Selection Model (FSM) is designed to improve the utilisation of the output coding graph and enhance the feature representation of the target in the network. A lightweight segmentation head is also designed to achieve progressive feature fusion with multi-layer outputs. Experimental results show that the proposed algorithm can achieve low duration and high accuracy in drone target detection. On the public dataset, the IoU is improved by 2.53% and the detection time is reduced by 81.03%.

Recently, with the rapid advancement of technology, Internet of Things (IoT‏‏‏‏) security has become more efficient and more complex, especially for resource-limited devices such as embedded devices, wireless sensors and radio frequency identification tags (RFID). Lightweight block ciphers (LBCs) provide security for these technologies to protect them against adversaries, but the need for low power consumption in LBCs is one of the most important challenges for IoT‏ technologies. Furthermore, these LBCs are subject to multiple attacks and side channel attacks (SCAs) are among the mentioned threats to these cryptosystems. A type of SCA is correlation power analysis (CPA) in which the attacker tries to reach the key using the relationship between the power consumption of the chip during the algorithm running, data processing, and operations. In this article, a CPA attack is designed to discover master key of the Midori-64 block cipher. According to the proposed method, an attack is done to the first round S-boxes to get half of the key bits. Then, the second round S-boxes were attacked to other half of key bits just use 300 plain text samples. Finally, the most important physical attacks performed on the Midori, are compared to our proposed CPA attack.

Protecting sensitive data, such as data collected from sensors, is crucial for ensuring the accurate assessment of sensing devices and preventing unauthorized access. In this regard, Internet of Things (IoT) devices offer a promising alternative for in-situ monitoring. However, IoT sensing devices are often constrained by limited processing power and memory. Therefore, lightweight and efficient security algorithms are essential. This review paper assesses the implementation of lightweight cryptographic algorithms for power-constrained microcontrollers in IoT systems using symmetric cryptography. The implemented algorithms analyze the resource constraints of the IoT devices and compare their performance for efficient implementation of secure monitoring systems. Experimental results demonstrate the performance of various lightweight encryption algorithms on low-power microcontrollers. The analysis reveals the comparative performance of these algorithms in terms of average power and energy consumption, memory usage, latency, and throughput.

This paper proposes a novel facial expression recognition network called the Lightweight Facial Network with Spatial Bias (LFNSB). The LFNSB model balances model complexity and recognition accuracy. It has two key components: a lightweight feature extraction network (LFN) and a Spatial Bias (SB) module for aggregating global information. The LFN introduces combined channel operations and depthwise convolution techniques, effectively reducing the number of parameters while enhancing feature representation capability. The Spatial Bias module enables the model to focus on local facial features while also capturing the dependencies between different facial regions. Additionally, a novel loss function called Cosine-Harmony Loss is designed. This function optimizes the relative positions of feature vectors in high-dimensional space, resulting in better feature separation and clustering. Experimental results on the AffectNet and RAF-DB datasets show that the proposed LFNSB model performs excellently in facial expression recognition tasks. It achieves high recognition accuracy while significantly reducing the number of parameters, thus substantially lowering model complexity.

Accurate segmentation of skin lesions from dermoscopic images is crucial for early skin cancer detection, yet variations in lesion appearance and image artifacts present challenges. This study proposes two deep learning models, UCM-NetV2 and BNN-UCM-NetV2, to improve accuracy and computational efficiency. UCM-NetV2 enhances the UCM-Net architecture with a novel "cyber-structure" combining Multilayer Perceptron and CNN layers, improving prediction accu-racy without increasing the model's parameter count. BNN-UCM-NetV2 further optimizes for mobile deployment by binarizing activations and weights into 1-bit values, reducing computa-tional complexity and model size. Evaluations on the ISIC2017 and ISIC2018 datasets demonstrate that UCM-NetV2 outperforms existing methods in both accuracy and computational efficiency, achieving this with less than 0.04 GFLOPs. These models have the potential to make skin lesion analysis accessible to a broader population, particularly in resource-limited settings, allowing for proactive skin health monitoring and facilitating teledermatology. To foster further innovation in mobile health diagnostics, the source code for UCM-NetV2 will be available on GitHub: https://github.com/chunyuyuan/UCMV2-Net.

In order to shorten the detection time and improve the average precision on embedded devices, A lightweight and high accuracy model is proposed for passion fruit in complex environments (backlight, occlusion, overlap, sunny, cloudy, rainy). Firstly, replacing the backbone network of YOLOv5 with a lightweight GhostNet model reduces the number of parameters and computation while improving detection speed. Secondly, a new feature branch is added to the GhostNet network, and the feature fusion layer in the neck network is reconstructed to effectively combine the lower-level and higher-level features, which not only improves the accuracy of the model but also maintains its lightweight. Finally, the knowledge distillation methods are used to transfer the knowledge from the more capable teacher model to the less capable student model, which significantly improving the detection accuracy. The improved model is denoted as G-YOLO-NK. The average accuracy of the G-YOLO-NK network is 96.00%, which is 1.00% higher than the original YOLOv5s model. Furthermore, the improved model size is 7.14MB, reduced to half of the original model, and the real-time detection frame rate is 11.25 FPS on the Jetson Nano. Compared to the state-of-the-art model, the proposed model outperforms them in terms of average precision and detection performance. The present work provides an effective model for real-time detection of passion fruits in complex orchard scenes, which can provide valuable technical support for the development of orchard picking robots and greatly improve the intelligence level of orchards.

This study aimed to use biomineralization technology to improve the bond strength of fiber-reinforced lightweight aggregate concrete (LWAC) after exposure to temperatures of 300 °C and 500 °C. The specimens of a control group (Group A) and two experimental groups (Group B and Group C) were prepared. These specimens healed themselves in different ways after exposure to high temperatures and pull-out tests. The self-healing method of Group A involved placing the specimen into an incubator. The self-healing method of Group B was the same as that of Group A. The self-healing method of Group C involved immersing the specimen in a mixed solution of urea and calcium acetate for two days, then taking it out and placing it in an incubator for two days. A cycle of four days was undertaken until the desired age was reached. After the specimens were healed to the planned age, the first and secondary pull-out tests and repair compound identification were carried out. After exposure to a temperature of 300 °C and self-healing for 90 days, compared with the specimens in Group A, the relative bond strength ratios of the secondary pull-out tests of the specimens in Group C increased by 20.3%. This indicates that biomineralization can effectively improve the bond strength of LWAC after high-temperature damage.

Defect detection plays a pivotal role in quality control for fabrics. In order to enhance the accuracy and efficiency of fabric defect detection, we have proposed the PRC-Light YOLO model for fabric defect detection and have established a detection system. Firstly, we add new convolution operators in Backbone for the YOLOv7 and integrate them with Extended-Efficient Layer Aggregation Network. This combination constructs a new feature extraction module that not only reduces the computational effort of the network model, but also extracts spatial features effectively. Secondly, we employ multi-branch dilated convolutions feature pyramid, and introduce lightweight upsampling operators to improve performance of the feature fusion network. This module achieves an expanded receptive field by generating real-time adaptive convolution kernels, allowing for the collection of crucial information from regions with a richer contextual context. To further minimize the computation during network model training, we adopt the HardSwish activation function. Finally, we apply the Wise-IOU v3 bounding box loss function as a dynamic non-monotonic focusing mechanism, which decreases adverse gradients from low-quality instances. We conduct data augmentation on real fabric dataset to raise the generalization capability of the PRC-Light YOLO model. Compared with the YOLOv7 model, numerous simulation experiments show that our proposed methods reduce the model’s parameters and computation by 18.03% and 20.53%, respectively. Simultaneously, there has been a 7.6% improvement in mAP.

Maritime search and rescue is a crucial component of the national emergency response system, which currently mainly relies on Unmanned Aerial Vehicles (UAVs) to detect the objects. Most traditional object detection methods focus on boosting the detection accuracy while neglecting the detection speed of the heavy model. However, it is also essential to improve the detection speed which can provide timely maritime search and rescue. To address the issues, we propose a lightweight object detector named Shuffle-GhostNet-based detector (SG-Det). First, we construct a lightweight backbone, named Shuffle-GhostNet, which enhances the information flow between channel groups by redesigning the correlation group convolution and introducing the channel shuffle operation. Second, we propose an improved feature pyramid model, namely BiFPN-tiny, which has a lighter structure while being capable of reinforcing small object features. Furthermore, we incorporate the atrous spatial pyramid pooling module (ASPP) to the network, which employs atrous convolution with different sampling rates to obtain multi-scale information. Finally, we generate three sets of bounding boxes at different scales – large, medium, and small – to detect objects of different sizes. Compared with other lightweight detectors, SG-Det achieves better tradeoffs across performance metrics, and enables real-time detection with an accuracy rate of over 90% for maritime objects, which shows that it can be better meet the actual requirements of maritime search and rescue.

Detecting cracks in structural health monitoring is crucial for ensuring infrastructure safety and longevity. Using drones to obtain crack images and automate processing can improve the efficiency of crack detection. To address the challenges posed by the limited computing resources of edge devices in practical applications, we propose CrackScopeNet, a lightweight segmentation network model that simultaneously considers local and global crack features, suitable for deployment on drone platforms with limited computational power and memory. CrackScopeNet features a multi-scale branch to improve sensitivity to cracks of varying sizes without substantial computational overhead and a stripe-wise context attention mechanism to enhance the capture of long-range contextual information, mitigating the interference from complex backgrounds. Experimental results on CrackSeg9k dataset demonstrate that CrackScopeNet leads to a significant improvement in prediction performance, with the highest mean intersection over union (mIoU) scores reaching 82.12%, while maintaining a lightweight architecture with only 1.05M parameters and 1.58G floating point operations (FLOPs). Besides, CrackScopeNet excels in inference speed on edge devices without GPU because of its low FLOPs. CrackScopeNet contributes to the development of efficient and effective crack segmentation networks, suitable for practical structural health monitoring applications using drone platforms.

Research into lightweight structural concrete using volcanic tuff is of great importance to the construction industry. These materials have excellent thermal insulation properties, which helps improve the energy efficiency of buildings. A three-factor experimental design was used to build the statistical model. The test methods used were methods for determining the crushability of volcanic tuff, determining the average density, compressive strength and thermal conductivity of lightweight structural concrete. The influence of basalt fiber on the properties of lightweight structural concrete has been determined. The optimal compositions of lightweight structural concrete using tuff have been selected. The compressive strength of lightweight structural concrete reached 32.0 MPa. The average density range is 1754.6-2114.0 kg/m³. Good thermal conductivity values ​​were obtained in the range of 0.653-0.818 W/m·K. The article obtained the optimal compositions of lightweight structural concrete using volcanic tuff as a filler.

The Azores Archipelago is a collection of volcanic islands near northwestern Portugal in the Atlantic Ocean. Because of the importance of accurate environmental monitoring for the advancement of research, transportation and tourism, a LoRaWan Sensor Network was developed to monitor levels of air pollution across these islands. This study presents an approach to the implementation of a blockchain network that is both lightweight and scalable, with the goal of preventing man-in-the-middle attacks on the design of sensor networks.

In high-traffic harbor waters, marine radar frequently encounters signal interference stemming from various obstructive elements, thereby presenting formidable obstacles in the precise identification of ships. To achieve precise pixel-level ship identification in the complex environments, a customized neural network-based ship segmentation algorithm named MrisNet is proposed. MrisNet employs a lightweight and efficient FasterYOLO network to extract features from radar images at different levels, capturing fine-grained edge information and deep semantic features of ship pixels. To address the limitation of deep features in the backbone network lacking detailed shape and structured information, an adaptive attention mechanism is introduced after the FasterYOLO network to enhance crucial ship features. To fully utilize the multi-dimensional feature outputs, MrisNet incorporates a Transformer structure to reconstruct the PANet feature fusion network, allowing for the fusion of contextual information and capturing more essential ship information and semantic correlations. In the prediction stage, MrisNet optimizes the target position loss using the EIoU function, enabling the algorithm to adapt to ship position deviations and size variations, thereby improving segmentation accuracy and convergence speed. Experimental results demonstrate that MrisNet achieves high recall and precision rates of 94.8% and 95.2%, respectively, in ship instance segmentation, outperforming various YOLO and other single-stage algorithms. Moreover, MrisNet has a model parameter size of 13.8M and real-time computational cost of 23.5G, demonstrating notable advantages in terms of convolutional efficiency. In conclusion, MrisNet accurately segments ships with different spot features and under diverse environmental conditions in marine radar images. It exhibits outstanding performance, particularly in extreme scenarios and challenging interference conditions, showcasing robustness and applicability.

A real-time monitoring system for the operational status of fishing vessels is an essential element for the modernization of the fishing industry. The operational status of fishing vessels can be identified by using onboard cameras to detect the deck crew and the use of fishing nets. Due to the typically limited processing capacity of shipboard equipment and the significant memory consumption of detection models, however, general target detection models are unable to perform real-time image detection to identify the operational status of fishing vessels. In this paper, we propose a lightweight real-time deck crew and the use of fishing nets detection method, YOLOv5s-SGC. It is based on the YOLOv5s model, which uses surveillance cameras to obtain video of fishing vessels operating at sea and enhances the dataset. YOLOv5s-SGC replaces YOLOv5s’s backbone and the ordinary convolutional blocks in the feature fusion network with ShufflNetV2 and Ghost module.

Rapid advancements in the fifth generation (5G) communication technology and mobile edge computing (MEC) paradigm lead to the proliferation of unmanned aerial vehicles (UAV) in urban air mobility (UAM) networks, which provide intelligent services for diversified smart city scenarios. Meanwhile, the widely deployed internet of drones (IoD) in smart cities also brings up new concerns on performance, security, and privacy. The centralized framework adopted by conventional UAM networks is not adequate to handle high mobility and dynamicity. Moreover, it is necessary to ensure device authentication, data integrity, and privacy preservation in UAM networks. Thanks to characteristics of decentralization, traceability, and unalterability, Blockchain is recognized as a promising technology to enhance security and privacy for UAM networks. In this paper, we introduce LightMAN, a lightweight microchained fabric for data assurance and resilience-oriented UAM networks. LightMAN is tailored for small-scale permissioned UAV networks, in which a microchain acts as a lightweight distributed ledger for security guarantees. Thus, participants are enabled to authenticate drones and verify the genuineness of data that is sent to/from drones without relying on a third-party agency. In addition, a hybrid on-chain and off-chain storage strategy is adopted that not only improves performance (e.g,.latency and throughput) but also ensures privacy preservation for sensitive information in UAM networks. A proof-of-concept prototype is implemented and tested on a Micro Air Vehicle Link (MAVLink) simulator. The experimental evaluation validates the feasibility and effectiveness of the proposed LightMAN solution.

A characteristic feature of lightweight constructions is their low thermal mass which causes high internal temperature fluctuations that require high heating and cooling demand throughout the year. Phase Change Materials (PCMs) is effective in providing thermal inertia to low thermal mass buildings. The aim of this paper is to analyse the thermal behaviour of two proposed lightweight buildings designed for homeless people and to investigate the potential benefit achievable through the use of different types of PCM in the temperate climatic conditions of Christchurch, New Zealand. For this purpose, over 300 numerical simulations have been conducted using the simulation software DesignBuilder®. The bulk of the simulations were carried out under the assumption that the whole opaque building envelope is equipped with PCM. The results showed significant energy saving and comfort enhancement through the application of PCMs. Thereby, annual energy saving of over 50 % was reached for some of the PCMs considered. Additionally, the effectiveness of single, PCM-equipped structure components was investigated and substantial benefits between 19 and 27 % annual energy saving were achieved. However, occupant behaviour in terms of ventilation habits, occupancy of zones etc. remains one of the biggest challenges in any simulation work due to insufficient data.

This research paper presents a detailed analysis of a Lightweight Block Cipher’s power consumption and security features (LWBC), specifically designed for IoT applications. To accurately measure energy consumption during the execution of the LWBC algorithm, we utilised the Qoitech Otii Arc, a specialised tool for optimising energy usage. Our experimental setup involved using the Otii Arc as a power source for an Arduino NodeMCU V3, running the LWBC security algorithm. Our methodology focused on energy consumption analysis using the shunt resistor technique. Our findings reveal that the LWBC is highly efficient and provides an effective solution for energy-limited IoT devices. We also conducted a comparative analysis of the proposed cipher against established LWBCs, which demonstrated its superior performance in terms of energy consumption per bit. The proposed LWBC was evaluated based on various key dimensions such as power efficiency, key and block size, rounds, cipher architecture, gate area, ROM, latency, and throughput. The results of our analysis indicate that the proposed LWBC is a promising cryptographic solution for energy-conscious and resource-limited IoT applications.

Public safety and intelligent surveillance systems critically depend on anomaly behavior detection for effective monitoring. In real-world pedestrian detection scenarios, prevalent challenges such as missed detections, complex background interference, and small target sizes hinder accurate anomaly identification. To address these issues, this study introduces YOLO-ABD, a lightweight method for anomaly behavior detection that integrates small target detection and channel shuffling. This method employs YOLOv8n as the baseline model, incorporating a small target detection mechanism in the Head part and utilizing GSConv convolution in the Backbone to enhance perceptual capability. Additionally, the SimAM attention mechanism is integrated to mitigate complex background interference, thereby improving target detection performance. Evaluation on the IITB-Corridor dataset demonstrated mAP50 and mAP50-95 scores of 89.3% and 60.6%, respectively. Generalization testing on the street-view-gdogo dataset further highlighted the superiority of YOLO-ABD over advanced detection algorithms, underscoring its effectiveness and generalizability. With a relatively small parameter count, YOLO-ABD presents an excellent lightweight solution for pedestrian anomaly behavior detection.

The application of artificial intelligence to point-of-care testing (POCT) disease detection has become a hot research field, in which breath detection which detects the patient's exhaled VOCs combined with sensor arrays of Convolutional Neural Network (CNN) algorithms as a new lung cancer detection is attracting more researchers' attention. However, due to low accuracy, high complexity computation and large number of parameters make the CNN algorithms difficult transplant to the embedded system of POCT devices. A lightweight neural network (LTNet) in this work is proposed to deal with this problem, and meanwhile, achieve high-precision classification of acetone and ethanol gases, which are respiratory markers for lung cancer patients. Compared to currently popular lightweight CNN models such as EfficientNet, LTNet has fewer parameters (32K) and its training weight size is only 0.155 MB. LTNet achieved an overall classification accuracy of 99.06% and 99.14% in the own mixed gas dataset and the University of California (UCI) dataset, which are both higher than that of the five existing models’, and it also offers the shortest training (844.38s and 584.67s) and inference time (23s and 14s) in the same validation set. Compared to the existing CNN models, LTNet is more suitable for resource-limited POCT devices.

This article describes the choice of an optimization algorithm for solving problems and the optimal design of an unmanned aerial vehicle propeller. To solve the problem using evolutionary algorithms, it was transformed into an unconstrained optimization problem using a penalty function. The airfoil contours were constructed using a Bezier curve. Design variables were divided into two types: those that describe in general terms the propeller geometry or operation, such as propeller diameter, number of blades, and rev/min; and those that vary with propeller radius, such as chord length, effective airfoil angle, and airfoil geometry. The objective function is the calculation of the propeller power required to achieve a given thrust. The differential evolution algorithm was used to solve this problem.

In the case of solid slabs made of reinforced concrete that are usually subjected to bending, large areas of the structure are stressed well below their load-bearing capacity. Contrary to this are shell structures, which can bridge large spans with little material if designed according to the force flow. To improve the efficiency of ceiling slabs, we want to utilize the shell load-bearing behavior on a smaller scale by resolving the solid interior accordingly. In order to be able to study a wide range of such constructions virtually, a parametric multiobjective simulation environment is being developed in an ongoing research project. The basic analysis approaches which were implemented are presented in this paper. The basic workflow, the used programs and material models and their calibration on the tests on textile-reinforced concrete (TRC) samples are described.

This study aimed to compare the differences in durability and prestress loss between normal-weight concrete (NC) and lightweight aggregate concrete (LWC) prestressed box girders, which were constructed at the same time in the same area, so as to verify the superiority of using synthetic lightweight aggregate (LWA) made from reservoir sediments in prestressed bridges. For the NCs and LWCs used in prestressed box girders, the basic mechanical properties were tested on the one hand, and the durability properties were tested on the other hand. Then, through the prestress monitoring system, the prestress loss of the two groups of the prestressed box girders was tracked. The results of the durability test confirmed that LWC can inhibit the penetration of air, water, and chloride ions by strengthening the interfacial transition zone between the aggregate and the cement paste, thereby improving its durability. Moreover, the magnetic flux prestress loss of the NC prestressed box girder reached 8.1%. In contrast, the magnetic flux prestress losses on both sides of the LWC prestressed box girder were 4.6% and 4.9%, respectively. This verified that, under the same environmental conditions, the use of LWC produced less of a prestress loss than the use of NC.

This study presents structural analysis and optimization for the lightweight design of a buoyant rotor-type permanent magnet (BRPM) generator, which was first presented in Bang (2010), and compares its structural performances to a conventional generator with a spoke arm-type rotor and stator. The main benefit of a BRPM is that it can be realized as a bearing-less drive system, free from the mechanical failure of rotor bearings, by using a buoyant rotor. Also, the deformation of a generator by blade vibration can be effectively suppressed using joint couplings between the blades and the rotor. For the design optimization, the objective is set as the mass of the rotor and the stator, and the maximum deformation of the airgap clearance between the rotor and the stator by external forces is constrained below 10% of the gap width. The commercial software Optistruct is used for the analysis and optimization. In this investigation, the analysis and optimization are conducted for a 10 MW wind turbine generator. However, the proposed methods can be extended to larger generator designs without requiring considerable modification. The mass of the opti-mized 10MW BRPM generator is 160.7 tons (19.3 tons for the rotor and 141.4 tons for the stator) while that of an optimized conventional spoke arm-type generator is obtained as 325.6 tons.

In engineering practice, one can often encounter issues related to optimization where the goal is to minimize material consumption, minimize stresses or deflections of the structure. In most cases, these issues are addressed with finite element analysis software and simple optimization algorithms. However, in the case of optimization of certain structures, it is not co straightforward. An example of such constructions are bubble deck ceilings, where in order to reduce the dead weight, air cavities are used, which are regularly arranged over the entire surface of the ceiling. In the case of these slabs, the flexural stiffness is not constant in all its cross-sections, which means that the use of structural finite elements (plate or shell) for static calculations is not possible, and therefore the optimization process becomes more difficult. The paper presents a minimization procedure of the weight of bubble deck slabs using numerical homogenization and sequential quadratic programming with constraints. Homogenization allows to determine the effective stiffnesses of the floor, which in the next step are sequentially corrected by changing the geometrical parameters of the floor and voids in order to achieve the assumed deflection. The presented procedure allows to minimize the use of material in a quick and effective way by automatically determining the optimal parameters describing the geometry of the bubble deck floor cross-section.

In recent years, the demand for coffee has increased tremendously. During the production process, green coffee beans are traditionally screened manually for defective beans before they are packed into coffee bean packages; however, this method is not only time-consuming but also increases the rate of human error due to fatigue. Therefore, this paper proposed a lightweight deep convolutional neural network (LDCNN) for the quality detection system of green coffee beans, which combined depthwise separable convolution (DSC), squeeze-and-excite block (SE block), skip block, and other frameworks. To avoid the influence of low parameters of the lightweight model caused by the model training process, rectified Adam (RA), lookahead (LA), and gradient centralization (GC) were included to improve efficiency; the model was also put into the embedded system. Finally, the local interpretable model-agnostic explanations (LIME) model was employed to explain the predictions of the model. The experimental results indicated that the accuracy rate of the model could reach up to 98.38% and the F1 score could be as high as 98.24% when detecting the quality of green coffee beans. Hence, it can obtain higher accuracy, lower computing time, and lower parameters. Moreover, the interpretable model verified that the lightweight model in this work is reliable, providing the basis for screening personnel to understand the judgment through its interpretability, thereby improving the classification and prediction of the model.

Underwater imaging presents unique challenges, notably color distortions and reduced contrast due to light attenuation and scattering. Most underwater image enhancement methods, first use linear transformations for color compensation and then enhance the image. We observed that linear transformation for color compensation is not suitable for certain images. For such images, a non-linear mapping is a better choice. Our paper introduces a unique underwater image restoration approach leveraging a streamlined convolutional neural network (CNN) for dynamic weight learning for linear and non-linear mapping. In the first phase, a classifier is applied that classifies the input images into Type-I or Type-II. In the second phase, depending on the classification, the Deep Line Model (DLM) for Type-I images or the Deep Curve Model (DCM) for Type-II images. For mapping an input image to an output image, DML creatively combines color compensation and contrast adjustment in a single step and uses deep lines for transformation, whereas DCM employs higher-order curves. Both models utilize lightweight neural networks that learn per-pixel dynamic weights based on the input image’s characteristics. Comprehensive evaluations on benchmark datasets using metrics like peak signal-to-noise ratio(PSNR) and root mean squares error (RMSE) affirm our method’s effectiveness in accurately restoring underwater images, outperforming existing techniques.

Multi-rotor drones, a kind of unmanned equipment which is widely used in military, commercial consumption and other fields, has been developed very rapidly in recent years. However, their short flight time has hindered the expansion of their application range. This can be addressed by utilizing hydrogen fuel cells, which exhibit high energy density, strong adaptability to ambient temperature, and no pollution emissions, as the power source. Accordingly, the application of hydrogen fuel cells as the power source in multi-rotor drones is a promising technology that has attracted significant research attention. This paper summarizes the development process of hydrogen fuel cell mul-ti-rotor drones and analyzes the key obstacles that need to be addressed for the further development of hydrogen fuel cell multi-rotor drones, including structural lightweight, hydrogen storage methods, energy management strategies. Additionally, prospects for the future development of hydrogen fuel cell multi-rotor drones are presented.

CubeSats, known for their compact size and cost-effectiveness, have gained significant popularity. However, their limited size imposes restrictions on optical aperture and, consequently, Ground Resolution Distance in Earth Observation missions. To overcome this limitation, the concept of deployable optical payloads with segmented primary mirrors which can unfold like petals has emerged, enabling larger synthetic apertures and enhanced spatial resolution. This study explores the potential benefits of leveraging Additive Manufacturing (AM) and Topology Optimization (TO) in the realm of ultra-precision machining, specifically single point diamond machining. The goal is to reduce fixture weight while improving stiffness to minimize deformations caused by rotational and cutting forces which compromise optical performance. Through Finite Element Analysis, this research compares conventionally machined fixtures with those produced using AM and TO techniques. The results reveal that concept designs created through TO can achieve a remarkable 68% reduction in weight. This reduction makes the assembly, including the machining fixture and 12U deployable segments, manageable by a single operator without the need for specialized lifting equipment. Moreover, these innovative designs lead to substantial reductions of up to 86% and 51% in deformation induced by rotational and cutting forces, respectively.

Individual investors often struggle to predict stock prices due to the limitations imposed by the computational capacities of personal laptop Graphics Processing Units (GPUs) when running intensive deep learning models. This study proposes solving these GPU constraints by integrating deep learning models with technical analysis methods. This integration significantly reduces analysis time and equips individual investors with the ability to identify stocks that may yield potential gains or losses in an efficient manner. Thus, a comprehensive buy and sell algorithm, compatible with average laptop GPU performance, is introduced in the study. This algorithm offers a lightweight analysis method that emphasizes factors identified by technical analysis methods, thereby providing a more accessible and efficient approach for individual investors. To evaluate the efficacy of this approach, we analyzed the performance of eight deep learning models: LSTM (4 layers), CNN, BiLSTM (4 layers), CNN Attention, BiGRU CNN BiLSTM Attention, BiLSTM Attention CNN, CNN BiLSTM Attention, and CNN Attention BiLSTM. These models were used to predict stock prices for Samsung Electronics and Celltrion Healthcare. The CNN Attention BiLSTM model displayed superior performance among these models, with the lowest validation mean absolute error value. In addition, an experiment was conducted using WandB Sweep to determine the optimal hyperparameters for four individual hybrid models. These optimal parameters were then implemented in each model to validate their back-testing rate of return. The CNN Attention BiLSTM hybrid model emerged as the highest-performing model, achieving an approximate rate of return of 5 percent. Overall, this study offers valuable insights into the performance of various deep learning and hybrid models in predicting stock prices. These findings can assist individual investors in selecting appropriate models that align with their investment strategies, thereby increasing their likelihood of success in the stock market.

This research investigates the effect of pre-soaking treatment on plant-based aggregate using a wet grout binder to formulate a high-strength lightweight concrete (HSLWC). The surface modification utilising a novel grout soaking technique with various water-to-cement (w/c) ratios indicated a new method of approach for the recent development of lightweight plant-based aggregate (LWPA). In this experiment, the fresh and hardened properties of modified LWPA lightweight concrete were assessed by verifying their workability, densities, compressive and split tensile strengths towards the modulus of elasticity. The results showed that pre-soaking plant-based lightweight aggregate (w/c: 0.6, 0.8, 1.0, and 1.2) slightly increased the density of the samples compared to untreated LWPA. The oven-dry density of treated and untreated LWPA is controlled in the range of HSLWC. The outcomes indicated that the workability of the surface- modified LWPA has significant improvement up to 40% in 6 min for (TDS)/0.6 sample compared to the original LWPA. The mechanical properties of the LWPA concrete with surface modification method exhibit substantial increment of compressive strength, split tensile strength, and modulus of elasticity were recorded at 22%, 26%, and 34%, respectively. Significantly, the findings from this scientific method revealed that the pre-soaking treatment method on LWPA has shown to be a highly recommended technique in improving interfacial bonding while performing as one of the most promising solutions to improve the properties of lightweight concrete.

To address the problems of poor recognition, low detection accuracy, a large number of model parameters and computation, complex network structure, and unfavorable portability to embedded devices in traditional tennis ball detection algorithms, this study proposes a lightweight tennis ball detection algorithm YOLOv5s-Z based on Robomater EP. The main work is as follows: Firstly, constructing lightweight G-Backbone and G-Neck network layers to reduce the number of parameters and computation of the network structure. Secondly, the convolutional coordinate attention is incorporated in G-Backbnone to embed the location information into the channel attention, which makes the network obtain the location information in a larger area through multiple convolutions and enhances the expression ability of the mobile network learning features. In addition, the Concat module in the original feature fusion is modified into a weighted bi-directional feature pyramid W-BiFPN with settable learning weights to improve the feature fusion capability and achieve efficient weighted feature fusion and bi-directional cross-scale connectivity. The EIOU loss is introduced to split the influence factor of aspect ratio and calculate the length and width of the target frame and anchor frame respectively, combined with Focal-EIOU Loss to solve the problem of imbalance between difficult and easy samples. The activation function Meta-ACON is introduced to achieve an adaptive selection of whether to activate the neurons and improve the detection accuracy. Finally, the experimental results show that compared with the original algorithm, the YOLOv5s-Z algorithm reduces the number of parameters and computation by 42$\%$ and 44$\%$, the model size by 39$\%$, and 2$\%$ improvement in average accuracy mean value, which verifies the effectiveness of the improved algorithm and the light weight of the model to meet the deployment requirements of embedded devices, and adapts Robomaster EP for accurate detection and real-time recognition of tennis balls.

The development of hybrid rockets offers excellent opportunities for the practical education of students at universities due to a high safety and a relatively low complexity of the rocket propulsion system. During the German educational program STERN, students of the Technische Universität Braunschweig obtain the possibility to design and launch a sounding rocket with a hybrid engine. The design of engine HYDRA 4X is presented and results of first engine tests are discussed. Results for measured regression rates are compared to results from literature. Furthermore, the impact of the lightweight casing material CFRP on the hybrid engine mass and flight apogee altitude is examined for rockets with different total impulse classes (10 to 50 kNs). It is shown that the benefit of a lightweight casing material on engine mass decreases with an increasing total impulse. However, a higher gain on apogee altitude, especially for bigger rockets with a comparable high total impulse is shown.

This study is focused on the experimental investigation of compressive strength and durability properties of lightweight concrete mixtures with fine expanded glass and expanded clay aggregates using different microfillers. The paper proposes the relationships between the compressive strength and density of concrete mixtures with different proportions of lightweight aggregates mentioned above. The performed experimental studies have revealed the tendencies of possible usage of different amount of fine lightweight aggregates and their combinations in the production of concrete mixtures depending on the demands of practical application. Following the requirements for structural concrete subjected to environmental effects, durability properties (alkaline corrosion and freeze–thaw resistance) of the selected concrete mixtures with expanded glass aggregate were studied. The results of the experimental investigations have shown that durability of tested concrete specimens was sufficient. The study has concluded that the mixtures under consideration can be applied for the production of structural elements to which durability requirements are significant.

Infrared and visible light image fusion technology integrates image feature information from two different modalities to generate an image that integrates complementary information from the source images. However, in low-light scenarios, the degradation of lighting in visible light images leads to existing fusion methods being unable to effectively extract texture detail information from the scene. At this time, the target prominence information provided by infrared images alone is far from sufficient. To address this challenge, this paper proposes a lightweight infrared and visible light image fusion method based on low-light enhancement, named LLE-Fuse. Firstly, the method improves the MobileOne Block by embedding the Sobel operator in the Edge-MobileOne Block to perform feature extraction and downsampling on the source images. Then, intermediate features of different scales are obtained and fused through a cross-modal attention fusion module, followed by image reconstruction using a decoder with upsampling. Next, the CLAHE algorithm is used for image enhancement of infrared and visible light images, and the enhanced loss guides the network model to learn the capability of low-light enhancement. Finally, upon completion of the network training, the method optimizes the Edge-MobileOne Block into the direct connection structure of MobileNetV1 through structural re-parameterization, effectively reducing the computational resource consumption of the model network. Through extensive experimental comparisons, this paper's method demonstrates excellent performance in both visual appeal and evaluation metrics, providing satisfactory fusion results even in low-light scenarios.

In the era of the post-quantum Internet of Things (IoT), the implementation of anti-quantum cryptographic algorithms in numerous terminals can successfully defend against prospective quantum computing assaults. Lattice-based cryptography can withstand quantum computing attacks, making it a viable substitute for the currently prevalent classical public-key cryptographic technique. Nevertheless, the algorithm’s significant time complexity will result in a substantial computational burden on the edge computing chip in the IoT terminal. The computation of polynomial multiplication is the most demanding task in lattice-based cryptographic algorithms. Therefore, the investigation into efficient methods for calculating polynomial multiplication is highly important. Quick number theory transformations (NTT) are a widely employed technique to accelerate polynomial multiplication. This study presents a hardware implementation of an efficient number theory transformation. We utilize a multi-level pipeline architecture in the design to accomplish parallel calculations and execute it on a low-profile Artix7-XC7A100T FPGA device. The performance evaluation results demonstrate that our implementation significantly enhances performance and reduces resource usage compared to other existing proposals on the same platform. We suggested NTT core can be implemented in edge computing chips to enhance computational speed due to its small and low-latency design. The experimental results show that the proposed design, which supports both NTT and inverse NTT, achieves 417-Megahertz and consumes only 541-LUTs on Artix-7 XC7A100T.

Amid the swift progression of the global automobile industry, the aspiration for lightweight vehicle design has surfaced as a crucial approach to boost fuel efficiency and curtail environmental impact. The objective of this study revolves around achieving holistic optimization of vehicle structure via detailed scrutiny of vehicle process characteristics, amalgamated with a Back Propagation neural network (BPNN) optimized by a genetic algorithm (GA) and a topology optimization (TO) method.The process initiates with an examination of the vehicle's technical characteristics, succeeded by an optimization protocol that couples GA with BPNN. This exhaustive optimization procedure derives the best-fit values of design parameters and identifies the globally optimal lightweight design approach. Subsequently, a comprehensive structural optimization is actualized by modifying the topological distribution of the structure.A simulation experiment of the conceptual car body beam skeleton is conducted as a conclusive step, and the anti-collision capacity of the car body beam skeleton is assessed by measuring deformation intrusion. The findings reveal that in the vehicle topology optimization, a comparative analysis of pre and post-optimization results indicates an improved topological density across diverse sections. The topological density of the vehicle's frontal structure escalates from 0.75 to 0.8. Following optimization, the stiffness assessment records a marginal increase (within the range of 0.02–0.05), implying that the lightweight design does not compromise the general rigidity of the structure.The optimized body structure manifests superior crashworthiness in the crash test: the deformation intrusion diminishes by 27% in front-end collisions. In side impacts, the deformation and intrusion at critical points are reduced by 13.15% to 10% respectively. The comprehensive method proposed herein proves to be an efficient strategy to actualize the lightweight design of vehicles.

In response to reducing the energy cost of unmanned surface vehicles (USVs) while overcoming the low accuracy problem in surface target detection, a lightweight detection algorithm with multi-scale feature fusion is proposed. Based on the popular one-stage lightweight Yolov7-tiny target detection model, a lightweight extraction module is designed first by introducing the multiscale residual module to reduce the number of parameters and computational complexity while improving accuracy. The Mish and SiLU activation functions are used to enhance network feature extraction. Second, the path aggregation network employs coordinate convolution to strengthen spatial information perception. Finally, the dynamic head, which is based on the at-tention mechanism, improves the representation ability of object detection heads without any computational overhead. According to the experimental findings, the proposed model has 22.1% fewer parameters than the original model, 15% fewer GFLOPs, a 6.2% improvement in mAP@0.5, a 4.3% rise in mAP@0.5:0.95, and it satisfies the real-time criteria. According to the research, the suggested lightweight water surface detection approach includes a lighter model, a simpler computational architecture, more accuracy, and a wide range of generalizability. It performs bet-ter in a variety of difficult water surface circumstances.

Silica fly ash, Certyd aggregate, and an alkaline solution were used to produce lightweight geo-polymer concretes. The compressive strength, water absorption, bulk density and SEM photos showing the structure of the obtained composite were carried out. Tests conducted on the specifi-cation of lightweight geopolymer concretes have revealed significant chemical interactions between the ash aggregate and the geopolymer mortar, particularly when the coarse aggregate surface has been pre-treated with an alkaline solution. Statistical analysis of the experimental data, which in-vestigated the influence of three key variables on compressive strength, water absorption, and bulk density of Lightweight Geopolymer Concrete (LBG), identified the following factors as having the most substantial impact: the quantity of alkali used, the curing temperature, and the concentration of alkali in the mixture. The optimal test series exhibited a commendable compressive strength of 20.14 megapascals (MPa), accompanied by a water absorption rate of 14.72% and a bulk density of 1486.6 kilograms per cubic meter (kg/m³). These findings underscore the importance of alkali con-tent, curing temperature, and alkali concentration in tailoring the properties of lightweight geo-polymer concrete to meet specific performance requirements.

Research on image-inpainting tasks has mainly focused on enhancing performance by augmenting various stages and modules. However, this trend does not consider the increase in the number of model parameters and operational memory, which increases the burden on computational resources. To solve this problem, we propose a Parametric Efficient Image InPainting Network (PEIPNet) for efficient and effective image-inpainting. Unlike other state-of-the-art methods, the proposed model has a one-stage inpainting framework in which depthwise and pointwise convolutions are adopted to reduce the number of parameters and computational costs. To generate semantically appealing results, we selected three unique components: spatially-adaptive denormalization (SPADE), dense dilated convolution module (DDCM), and efficient self-attention (ESA). The SPADE was adopted to conditionally normalize activations according to the mask to distinguish between damaged and undamaged regions. The DDCM was employed at every scale to overcome the gradient-vanishing obstacle and gradually fill-in pixels by capturing global information along the feature maps. The ESA was utilized to obtain clues from unmasked areas by extracting long-range information. In terms of efficiency, our model has the lowest operational memory compared with other state-of-the-art methods. Both qualitative and quantitative experiments demonstrate the generalized inpainting of our method on three public datasets: Paris StreetView, CelebA, and Places2.

Shear thickening fluids (STF) are a class of fluids whose viscosity significantly rises under external loads. The research on these fluids has been advancing in recent years regarding prospective practical applications, including developing impact-absorbing composites. Following the green agendas governments and legislators advocate, this study investigates the combination of STF and other sustainable materials. Cork is a naturally occurring cellular material with a negative carbon footprint and superior energy absorption properties. With varying concentrations of STF material, cork agglomerates were formed. Notably, the analysed blends are homogeneous, contrasting with previous literary works. A series of experiments were conducted in quasi-static and dynamic conditions to determine the various mechanical responses. STF appears to influence the mechanical behaviour of cork agglomerates by providing softer deceleration rates and dispersing more energy through disaggregation mechanisms.

The annual construction and demolition waste (CDW) generated from EU construction sector was 850 million tons, which represented 31% of the total waste generation and about 28% of CDW was ceramics (bricks and tiles). In this study, the feasibility of using CDW brick powder as the precursor of alkali activated mortar (AAM) and extruded polystyrene (XPS) as the lightweight aggregates to form lightweight brick powder AAM (LW-BP-AAM) for non-structural applications was investigated. The thermal conductivity of LP-BPAAM was 0.112 W/m·K with density of about 1,135 kg/m³ which was lower than the counterparts with similar density in literature. The acid resistance of LW-BP-AAM is comparable to conventional fly ash based AAM and superior than ordinary Portland cement. From the scanning electron microscopy with energy dispersive X-ray spectroscopy, there was no severe damage on the surface of LW-BP-AAM but aluminate was removed from the matrix which was further verified in Fourier transform infrared spectroscopy. The mass and strength loss of LP-BP-AAM was 1.5% and 33%, respectively. Although the compressive strength of the LP-BP-AAM was low (about 1.8 MPa), it can be improved by optimising the particle size of the XPS aggregates.

Recently, cloud technology has become popular for smart societies. The Cloud technology has made dynamical network changes by enabling the construction of a logical network without building a physical network. Despite recent research on the cloud, it is necessary to study security functions for the identification of fake VNFs and the encryption of communication between entities. In this paper, we proposed an LW_PKI mechanism that detects a fake VNF and guarantees data security through mutual authentication between VNFs. To evaluate the LW_PKI, we built a MANO environment to test the performance of authentication and key generation for data security. In addition, we applied the artificial intelligence algorithm to detect abnormal behavior by using real attack data in the MANO environment. The LW_PKI guaranteed the reliability of a smart service by enhancing the security of the cloud environment.

In the Formula Student Racing Car, the anti-deformation ability of the frame will affect the four-wheel positioning parameters of the racing car, and then affect the handling and stability performance of the racing car. The quality of the frame directly determines the power and economy of the racing car, so the performance of the frame is very important to the performance of the race. In order to improve the performance of the frame and reduce the total weight of the frame, the research on the lightweight design of the frame is particularly important. In this paper, based on the variable density method, the global topology optimization of the frame is carried out to obtain the distribution of the frame material, realize the efficient use of the material, and improve the torsional stiffness of the frame. Based on the adjoint variable method, the sensitivity analysis of the frame is carried out. According to the sensitivity analysis results, the size of the frame is optimized. The total mass of the frame is reduced by 12.8 %, and the performance of the maximum displacement and maximum stress is improved. The lightweight design of the frame is realized as a whole.

In the present trend of constructing taller and longer structures, the application of lightweight aggregate concrete is becoming an increasing important advanced solution in the modern construction industry. In engineering practice, the analysis of lightweight concrete elements is performed using the same algorithms used for normal concrete elements. As an alternative to traditional engineering methods, nonlinear numerical algorithms based on constitutive material models may be used. The paper presents a comparative analysis of curvature calculations for flexural lightweight concrete elements, incorporating analytical code methods EN 1992-1 and ACI 318-14, as well as a numerical analysis using the constitutive model of cracked tensile lightweight concrete recently proposed by the authors. To evaluate the adequacy of the theoretical predictions, experimental data of 51 lightweight concrete beams tested during five different programmes were collected. A comparison of theoretical and experimental results showed that the most accurate predictions are obtained using numerical analysis and the constitutive model proposed by the authors. In the future, the latter algorithm can be used as a reliable tool for improving the design standard methods or numerical modelling of lightweight concrete elements subjected to short-term loading.

In the modern construction industry, lightweight aggregate concrete (LWAC) is often used in the production of load-bearing structural members. LWAC can be up to 40% lighter by volume in comparison to normal strength concrete. On the other hand, the lack of adequate numerical models often limits the practical application of innovative building materials, such as lightweight concrete, in real projects. This trend is due to the uncertainties in design standard methods and calculation errors, the level of which is generally unacceptable to civil engineers in terms of safety and reliability. In the present paper, a comparative numerical deformation analysis of a full-scale bridge deck slab and girder has been carried out. Using the physical model proposed by the authors and the finite element software ATENA, the deformations of full–scale lightweight and traditional reinforced concrete elements under short-term effects of permanent and variable loads was compared. Depending on the safety and serviceability limit requirements, it was found that the amount of longitudinal reinforcement in lightweight reinforced concrete elements can be reduced compared to normal reinforced concrete elements with the same parameters. The results of the numerical analysis show that the deformation analysis model proposed by the authors can be a reliable tool for the design of lightweight concrete flexural members by selecting the optimum geometrical and reinforcement parameters limited by the stiffness condition.

Synthetic Aperture Radar has been extensively used in numerous fields and can gather a wealth of information about the area of interest. This large-scene data-intensive technology puts a high value on automatic target recognition (ATR) which can free the utilizers and boost the efficiency. Recent advances in artificial intelligence have made it possible to create a deep learning-based SAR ATR that can automatically identify target features from massive input data. In the last 6 years, intensive research has been conducted in this area, however, most papers in the current SAR ATR field used recurrent neural network (RNN) and convolutional neural network (CNN)-varied models to deepen the regime’s understanding of the SAR images. To equip SAR ATR with updated deep learning technology, this paper tries to apply a lightweight vision transformer (LViT)-based model to classify SAR images. The entire structure was verified by an open- accessed SAR data set and recognition results show that the final classification outcomes are robust and more accurate in comparison with referred traditional network structures without even using any convolutional layers.

A new lateral force-resisting wall panel is presented for applications in mid-rise prefabricated lightweight steel construction in seismic prone regions. This panelised system is composed of a hot-rolled frame and cold-formed studs and tracks, which works as a lateral force resisting system in lightweight steel framing. The proposed hybrid panel system exhibits proper ductility and energy dissipation behaviour. The hysteretic responses of full-scale panel experiments demonstrate that the system can safely resist high cyclic loads. The hot-rolled steel part, on the other hand, can significantly improve the initial lateral stiffness of the total system that will control the maximum allowable drift of multi-story buildings. Finally, in a case study, by applying the proposed system to the design of a mid-rise building in a high seismic area, the performance of the hybrid panels, are compared with those of fully hot-rolled systems (moment resisting frames) and fully cold formed systems. The findings indicate that applying hybrid panels will result in lower weights and better performance in seismic prone regions.

The main aim of this paper is to analyse the performance of different intelligent compaction measurement values (ICMVs) and compare them with spot test measurements for asphalt pavement. To accomplish this, a two-layer asphalt testbed was constructed using an instrumented double-drum roller. All ICMVs [compaction meter value ( ), compaction control value ( ), roller-integrated stiffness ( ), and vibratory modulus ( )] were calculated using the same accelerometer data collected during the construction of the asphalt testbed. A novel method using the cross-correlation technique was developed to estimate the phase lag between the excitation force of the roller drum and the ground reaction, which is required for and calculations. The analysis of ICMV data showed a strong correlation between and , while and demonstrated a strong correlation only when double jump of the roller drum did not occur. Further, none of the ICMVs recorded during the last roller pass of asphalt compaction showed an acceptable correlation with asphalt densities [measured using a non-nuclear density gauge (NNDG)], mainly due to the influences of the underlying support and asphalt temperature on ICMVs. A correction method to decouple the influence of underlying support on was developed and validated using existing data from the literature. The applicability of this method for different field scenarios was demonstrated using numerical modelling.

K-band radar waves have high penetration and low attenuation coefficients. However, the wavelength of this radar wave is relatively short; thus, designing and preparing both broadband and wide-angle radar wave absorbers in this band presents considerable challenges. In this study, a resin-based K-band radar wave absorber with a biomimetic lotus leaf structure was designed and formed by UV curing. Here, microscale lotus leaf papillae and antireflection structures were prepared using a DLP 3D printer, and the contact angle between the material and water droplets was increased from 56° to 130°. In addition, the influence of the geometric parameters of the lotus leaf antireflection structure on the electromagnetic absorption performance and mechanical strength was investigated. After simulation optimization, the maximum electromagnetic loss of the lotus leaf structure 3D printed sample was −32.3 dB, and the electromagnetic loss was below −10 dB in the 20.8–26.5 GHz frequency range. When the radar incidence angle was 60°, the maximum electromagnetic loss was still less than −10 dB. The designed lotus leaf structure has a higher mechanical energy absorption per unit volume (337.22 KJ/m3) and per unit mass (0.55 KJ/Kg) than commonly used honeycomb lightweight structures during the elastic deformation stage, and we expect that the designed structure can be used as an effective lightweight material for K-band radar stealth.

As the world increasingly becomes more interconnected, the demand for safety and security is ever-increasing, particularly for industrial networks. This has prompted numerous researchers to investigate different methodologies and techniques suitable for intrusion detection systems (IDS) requirements. Over the years, many studies have proposed various solutions in this regard including signature-based and machine-learning (ML) based systems. More recently, researchers are considering deep learning (DL) based anomaly detection approaches. Most proposed works in this research field aimed to achieve either one or a combination of high accuracy, considerably low false alarm rates (FARs), high classification specificity and detection sensitivity, achieving lightweight DL models, or other ML and DL-related performance measurement metrics. In this study, we propose a novel method to convert a raw dataset to an image dataset to magnify patterns. Based on this we devise an anomaly detection for IDS using a lightweight convolutional neural network (CNN) that classifies denial of service and distributed denial of service. The proposed methods were evaluated using a modern dataset, CSE-CIC-IDS2018, and a legacy dataset, NSL-KDD. We have also applied a combined dataset to assess the generalization of the proposed model across various datasets. Our experimental results have demonstrated that the proposed methods achieved high accuracy and considerably low FARs with high specificity and sensitivity. The resulting loss and accuracy curves have also demonstrated the excellent generalization of the proposed lightweight CNN model, effectively avoiding overfitting. This holds for both the modern and legacy datasets, including their mixed version.

As the embedded device and internet of things (IoTs) concept prevalent in today's world, there is an increasing demand for the security and performance requirements on deploying these devices to private and public sectors. The crucial part of it is to protect privacy, confidentiality and integrity, meanwhile, maintain an adequate level of performance during transmission, storage and access of critical information. While the conventional cryptography methods, such as the Advanced Encryption Standard (AES), SHA$-$2 hashing method and RSA and Diffie Hellman for message authentication and identification, work well on systems which have reasonable processing power and memory capabilities. These do not scale well into a world with embedded systems and sensor networks, in conjunction with their nature of smaller size and lower cost. Thus, in the context of resource constrained device, lightweight cryptography methods are proposed to overcome many of the problems of conventional cryptography possessed. This includes constraints related to physical size, processing requirement, memory limitation, energy drain and production cost. This paper provides a survey of the architectures that are defined as replacements for conventional ciphers within an IoTs space and discuss some trends in the design of future lightweight algorithms. The performance metrics are carefully chosen to reflect and assess the suitability for embedded devices. The aim of this research is to identify the various performance metrics applied on different types of symmetric block ciphers especially lightweight ciphers and compare the results on versatile platforms with stream ciphers and public key methods. The comparative analysis on efficient LW cipher will be tested against other similar block ciphers on both MacBook Pro with Intel core and resource constrained device Raspberry Pi with ARM processor.

Due to the special characteristics of the shooting distance and angle of remote sensing satellites, the pixel area ratio of ship targets is small and the feature expression is insufficient, which leads to unsatisfactory ship detection performance and even situations such as missed detection and false detection. In this study, we propose an improved-YOLOv5 algorithm. The improvement strategies mainly include: (1) Add the Convolutional Block Attention Module (CBAM) into the Backbone to enhance the extraction of target-adaptive optimal features; (2) Introduce cross-layer connection channel and lightweight GSConv structure into the Neck to achieve higher-level multi-scale feature fusion and reduce the number of model parameters; (3) The Wise-IoU loss function is used to cal-culate the localization loss in the Output, and assign reasonable gradient gains to cope with dif-ferences in image quality. In addition, during the preprocessing stage of experimental data, a me-dian and bilateral filter method is used for noise reduction to reduce interference from ripples and waves and highlight the information of ship features. The experimental results show that Im-proved-YOLOv5 has a significant improvement in recognition accuracy compared to various mainstream target detection algorithms; Compared to the original YOLOv5s, the mean Average Precision (mAP) has improved by 3.2% and the Frames Per Second (FPN) has accelerated by 8.7%.

Keywords: Artificial Neural Network (ANN), Support Vector Machine (SVM), Support Vector Regression (SVR), Lightweight Gradient Boosting Machines (Light GBM), Machine Learning, Solar Irradiance (SI), Solar forecasting

Lung and colon cancers are among the leading causes of cancer-related mortality worldwide. Early and accurate detection of these cancers is crucial for effective treatment and improved patient outcomes. False or incorrect detection is more harmful. Accurately detecting cancer in a patient's tissue is crucial to their effective treatment. While analyzing tissue samples is complicated and time-consuming, deep learning techniques have made it possible to complete this process more efficiently and accurately. As a result, researchers can study more patients in a shorter amount of time and at a lower cost. Much research has been conducted to investigate deep learning models that require great computational ability and resources. However, None of these have had a 100% accurate detection rate for these life-threatening malignancies. Misclassified or falsely detecting cancer can have more harmful consequences. This research proposes a new lightweight, parameter-efficient, and mobile-embedded deep learning model based on a 1D convolutional neural network with Squeeze-and-Excitation layers for efficient lung and colon cancer detection. This proposed model diagnoses and classifies lung squamous cell carcinomas and adenocarcinoma of the lung and colon from digital pathology images. Extensive experiment demonstrates that our proposed model achieves 100% accuracy for detecting lung, colon, and lung and colon cancers from the histopathological (LC25000) lung and colon datasets, which is considered the best accuracy for around 0.35 million trainable parameters and around 6.4 million flops. Compared with the existing results, our proposed architecture shows state-of-the-art performance in lung, colon, and lung and colon cancer detection.

The use of Light Amplification by Stimulated Emission of Radiation (i.e., LASERs or lasers) by the U.S. Department of Defense is not new and includes laser weapons guidance, laser-aided measurements, even lasers as weapons (e.g., Airborne Laser). Lasers in support of telecommunications is also not new. The use of laser light in fiber optics shattered thoughts on communications bandwidth and throughput. Even the use of lasers in space is no longer new. Lasers are being used for satellite-to-satellite crosslinking. Laser communication can transmit orders-of-magnitude more data using orders-of-magnitude less power and can do so with minimal risk of exposure to the sending and receiving terminals. What is new is using lasers as the uplink and downlink between the terrestrial segment and the space segment of satellite systems. More so, the use of lasers to transmit and receive data between moving terrestrial segments (e.g., ships at sea, airplanes in flight) and geosynchronous satellites is burgeoning. This manuscript examines the technological maturation of employing lasers as the signal carrier for satellite communications linking terrestrial and space systems. The purpose of the manuscript is to develop key performance parameters (KPPs) to inform U.S. Department of Defense initial capabilities documents (ICDs) for near-future satellite acquisition and development. By appreciating the history and technological challenges of employing lasers rather than traditional radio frequency sources for satellite uplink and downlink signal carrier, this manuscript recommends ways for the U.S. Department of Defense to employ lasers to transmit and receive high bandwidth, large-throughput data from moving platforms that need to retain low probabilities of detection, intercept, and exploitation (e.g., carrier battle group transiting to a hostile area of operations, unmanned aerial vehicle collecting over adversary areas). The manuscript also intends to identify commercial sector early-adopter fields and those fields likely to adapt to laser employment for transmission and receipt.