Search

In this paper, we propose an ultrascaled WS 2 field-effect transistor equipped with a Pd/Pt sensitive gate for high-performance and low-power hydrogen gas sensing applications. The proposed nanosensor is simulated by self-consistently solving a quantum transport equation with electrostatics at the ballistic limit. The gas sensing principle is based on the gas-induced change in the metal gate work function. The hydrogen gas nanosensor leverages the high sensitivity of two-dimensional WS2 to its sur-rounding electrostatic environment. The computational investigation encompasses the nanosensor's behavior in terms of potential profile, charge density, current spectrum, local density of states (LDOS), transfer characteristics, and sensitivity. Additionally, the downscaling-sensitivity trade-off is analyzed by considering the impact of drain-to-source voltage and the electrostatics parameters on subthreshold performance. The simulation results indicate that the downscaling-sensitivity trade-off can be optimized through enhancements in electrostatics, such as utilizing high-k dielectrics and reducing oxide thickness, as well as applying a low drain-to-source voltage, which also contributes to improved energy efficiency. The proposed nanodevice meets the prerequisites for cutting-edge gas nanosensors, offering high sensing performance, improved scaling capability, low power consumption, and complementary metal-oxide-semiconductor compatibility, making it a compelling candidate for the next generation of ultrascaled FET-based gas nanosensors.

Human activity recognition is a critical task for various applications across healthcare, sports, security, gaming, and other fields. This paper presents BodyFlow, a comprehensive library that seamlessly integrates human pose estimation and multiple-person estimation and tracking, along with activity recognition modules. BodyFlow enables users to effortlessly identify common activities and 2D/3D body joints from input sources such as videos, image sets, or webcams. Additionally, the library can simultaneously process inertial sensor data, offering users the flexibility to choose their preferred input, thus facilitating multimodal human activity recognition. BodyFlow incorporates state-of-the-art algorithms for 2D and 3D pose estimation and three distinct models for human activity recognition.

Human activity recognition is known as the backbone of the development of interactive systems, such as computer games. This process is usually performed by either vision-based or depth sensors. So far, various solutions have been developed for this purpose; however, all the challenges of this process have not been completely resolved. In this paper, a solution based on pattern recognition has been developed for labeling and scoring physical exercises performed in front of the Kinect sensor. Extracting the features from human skeletal joints and then generating relative descriptors among them is the first step of our method. This has led to quantification of the meaningful relationships between different parts of the skeletal joints during exercise performance. In this method, the discriminating descriptors of each exercise motion are used to identify the adaptive kernels of the Constrained Energy Minimization method as a target detector operator. The results indicated an accuracy of 95.9% in the labeling process of physical exercise motions. Scoring the exercise motions was the second step after the labeling process, in which a geometric method was used to interpolate numerical quantities extracted from descriptor vectors to transform into semantic scores. The results demonstrated the scoring process coincided with the scores derived by the sports coach by a 99.5 grade in the R 2 index.

Passive wireless surface acoustic wave (SAW) sensors are very useful for on-site monitoring of the working status of machines in complex environments, such as high-temperature rotating objects. For rotating parts, it is difficult to realize real-time and continuous monitoring because of the unstable sensing signal caused by the continuous change of the relative position of the rotating part to the sensor and shielding of the signal. In our SAW sensing system, we propose a loop antenna integrated with the rotating part to obtain a stable sensing signal owing to its omnidirectional radiation pattern. Methodologies for determining the antenna dimension, system operating frequency, and procedures for designing a SAW sensor tag are discussed in this paper. By fully utilizing the influence of metal rotor on antenna performance, the antenna needs no impedance matching elements while it provides sufficient gain, which equips the antenna with nearly zero temperature drift at a wide temperature-sensing range. Experimental verification results show that this sensing system can greatly improve the stability of the sensing signal significantly and can achieve a temperature sensing accuracy of ~1 °C at different rotational speeds, demonstrated by the feasibility of the loop antenna for monitoring the working status of rotating metal parts.

In this study, we propose a practical and efficient scheme for ship detection in remote sensing imagery. Our method is developed using both ship body detection and ship wake detection and combines deep learning and feature-based image processing. A deep convolutional neural network is used to achieve ship body detection, and a feature-based processing method is proposed to detect ship wakes. For better analysis, we model the sea region and evaluate the quality of the image. Generally, the wake detection result is used to assist ship detection and obtain the sailing direction. Conventional methods cannot detect ships that are covered by clouds or outside the image boundary. The method proposed in this paper uses the wake to detect such ships, with a certain level of confidence and low false alarm probability in detection. Practical aspects such as the method's applicability and time efficiency are considered in our method for real applications. We demonstrate the effectiveness of our method in a real remote sensing dataset. The results show that over 93.5% of ships and over 70% of targets with no visible ship body can be successfully detected. This illustrates that the proposed detection framework can fill the gap regarding the detection of sailing ships in a remote sensing image.

TBM has been widely used in underground engineering and construction, but there is no precedent for the application of open TBM in the inclined shafts of coal mines, which brings new challenges to the support system. The distribution of the axial forces on anchors and the range of loosening of the surrounding rock are crucial considerations in tunnel support design. Existing methods for measuring the axial forces in anchors and determining the extent of loosening in the surrounding rock typically remain at the inspection level, lacking long-term and real-time monitoring capabilities. This paper presents a new self-sensing anchor with embedded optical fibers (made using an improved stirrer) and proposes an intelligent tunnel rock monitoring system. The paper also outlines a method for identifying loosening zones in surrounding rock based on monitoring data and theoretical analysis. Installing self-sensing anchors in the deep sections of the rock surrounding a tunnel provides three-dimensional, round-the-clock real-time monitoring of the axial forces acting on the anchors, using new technology and methods to recognize the deformation characteristics of loosening zones within the surrounding rock. This new self-sensing fiber optic anchor was first applied to an open TBM tunneling project in an inclined shaft in the Kekegai coal mine, and monitoring data indicate that self-sensing optical fiber anchors can accurately reflect stress patterns in real time. The axial force curve can be divided into four segments: the borehole area, the loosening zone, the stable zone, and the anchoring zone. Consequently, it accurately identifies the thickness of loosening zones at different positions within the tunnel's surrounding rock. This information is compared and verified against results obtained from bolt dynamometers and borehole inspection. On this basis, an intelligent monitoring system was established to provide a basis for making engineering construction decisions, which makes tunnel construction smarter and helps technicians timely adjust TBM driving and support parameters.

The traditional passive heat dissipation method has low heat dissipation efficiency, which is not suitable for the heat dissipation of the concentrated heat source inside the long-focal aerial camera, resulting in temperature level changes and temperature gradients in the optical system near the heat source, which seriously affect the imaging performance of the aerial camera. To solve this problem, an active heat dissipation method of liquid cooling cycle is proposed in this paper. To improve the solving efficiency and ensure simulation accuracy, a dynamic boundary information transfer method based on grid area weighting is proposed. The thermal simulation results show that the liquid cooling method reduces the heat source temperature by 70.12%, and the boundary temperature transfer error is 0.015%. The accuracy of thermal simulation is verified by thermal test, and the simulation error is less than 6.44%. In addition, the performance of the optical system is further analyzed, and the results show that the MTF of the optical system is increased from 0.077 to 0.194 under the proposed active liquid cooling cycle heat dissipation method.

At present, tomato transplanting in facility agriculture is mainly manual operation. In an attempt to resolve the problems of high labor intensity and low efficiency of manual operation, this paper designs a clip stem automatic transplanting and seedling picking device based on the yolov5 algorithm. First of all, through the study of the characteristics of tomato seedlings of different seedling ages, the age of tomato seedlings suitable for transplanting was obtained. Secondly, the improved yolov5 algorithm was used to determine the position and shape of tomato seedlings. By adding a lightweight upsampling operator (CARAFE) and an improved loss function, the feature extraction ability and detection speed of tomato seedling stems were improved. The accuracy of the improved yolov5 algorithm reached 92.6%, and mAP_0.5 reached 95.4%. Finally, the seedling verification test was carried out with tomato seedlings of about 40 days old. The test results show that the damage rate of the device is 7.2%, and the success rate is not less than 90.3%. This study can provide a reference for research into automatic transplanting machines.

This paper considers UAVs as edge computing nodes and investigates a novel network resource allocation method for federated learning within a three-layer wireless network architecture containing cloud, edges (UAVs), and clients. To address the issue of fair bandwidth resource allocation among clients participating in federated learning, a contribution calculation strategy based on the Shapley value (SV) used as the weight for model aggregation is proposed. On this basis, a client selection and wireless resource allocation method based on model contribution is further designed. By reducing the training and aggregation frequency of the low-contribution clients during the asynchronous aggregation phase, the limited bandwidth resources are allocated to high-contribution clients, thus improving the convergence speed and accuracy of the global model. Simulation experiments demonstrate that the proposed method can significantly reduce the system delay and total energy consumption with gains between 15% and 50% while also improving the final accuracy of the global model by 0.3% and 2% on both short-term and long-term perspectives, respectively.

On-chip spectrometers are increasingly becoming tools that might help in everyday life needs. The possibility offered by several available integration technologies and materials to be used to miniaturize spectrometers has led to a plethora of very different devices, that in principle can be compared according to their metrics. Having access to a reference database can help in selecting the best-performing on-chip spectrometers and being up to date in terms of standards and developments. In this paper, an overview of the most relevant publications available in the literature on miniaturized spectrometers is reported and a database is provided as an open-source project to which researchers can have access and participate in order to improve the share of knowledge in the interested scientific community.

Laser range-gated underwater imaging technology, by removing most of the backscattering noise, can effectively increase image contrast and extend the detection range. The optical signal captured by a range-gated imaging system primarily comprises reflected light from the object and backscattered light from the surrounding water. Consequently, surfaces with low reflectivity or highly turbid water environments substantially constrain the applicability of the range-gated imaging system. To enhance the detection capability of underwater laser range-gated imaging, this paper proposes the incorporation of underwater polarized light imaging technology as an enhancement method. Based on polarization differences, backscattered light and reflected light from an object can be distinguished. Experimental results indicate that, compared to images obtained using a conventional range-gated laser imaging system, those captured with a polarization-enhanced system exhibit an increase of up to 47% for the corresponding Enhancement Measure Evaluation (EME) index. The proposed approach, which integrates polarization imaging with range-gated laser imaging, has the potential to broaden the applicability of underwater laser imaging scenarios, such as deep-sea exploration and military applications.

Although grid maps help mobile robots navigate in indoor environments, some lack semantic information that would allow the robot to perform advanced autonomous tasks. In this paper, a semantic map production system is proposed to facilitate indoor mobile robot navigation tasks. The developed system is based on the employment of LiDAR technology and a vision-based system to obtain a semantic map with rich information, and it has been validated using the robot operating system (ROS) and you only look once (YOLO) v3 object detection model in simulation experiments conducted in indoor environments, adopting low-cost, -size, and -memory computers for increased accessibility. The obtained results are efficient in terms of object recognition accuracy, object localization error, and semantic map production precision, with an average map construction accuracy of 78.86%.

This paper presents an 8 × 8 channel optoelectronic readout array (ORA) realized in the TSMC 180 nm 1P6M RF CMOS process for the applications of short-range light detection and ranging (LiDAR) sensors. We propose several circuit techniques in this work, including an amplitude-to-voltage (A2V) converter that reduces the notorious walk errors by intensity compensation and a time-to-voltage (T2V) converter that acquires the linear slope of the output signals by exploiting a charging circuit, thus extending the input dynamic range significantly from 5 μA pp to 1.1 mA pp , i.e., 46.8 dB. These results correspond to the maximum detection range of 8.2 m via the action of the A2V converter and the minimum detection range of 56 cm with the aid of the proposed T2V converter. Optical measurements utilizing an 850 nm laser diode confirm that the proposed 8 × 8 ORA with 64 on-chip avalanche photodiodes (APDs) can successfully recover the narrow 5 ns light pulses even at the shortest distance of 56 cm. Hence, this work provides a potential CMOS solution for low-cost, low-power, short-range LiDAR sensors.

With the ubiquitous deployment of mobile and sensor technologies in modes of transportation, taxis have become a significant component of public transportation. However, vacant taxis represent an important waste of transportation resources. Forecasting taxi demand within a short time achieves a supply-demand balance and reduces oil emissions. Although earlier studies have forwarded highly developed machine learning- and deep learning-based models to forecast taxicab demands, these models often face significant computational expenses and cannot effectively utilize large-scale trajectory sensor data. To address these challenges, in this paper, we propose a hybrid deep learning-based model for taxi demand prediction. In particular, the Variational Mode Decomposition (VMD) algorithm is integrated along with a Bidirectional Long Short-Term Memory (BiLSTM) model to perform the prediction process. The VMD algorithm is applied to decompose time series-aware traffic features into multiple sub-modes of different frequencies. After that, the BiLSTM method is utilized to predict time series data fed with the relevant demand features. To overcome the limitation of high computational expenses, the designed model is performed on the Spark distributed platform. The performance of the proposed model is tested using a real-world dataset, and it surpasses existing state-of-the-art predictive models in terms of accuracy, efficiency, and distributed performance. These findings provide insights for enhancing the efficiency of passenger search and increasing the profit of taxicabs.

Unmanned Aerial Vehicle (UAV)-type Quadrotors are highly nonlinear systems that are difficult to control and stabilize outdoors, especially in a windy environment. Many algorithms have been proposed to solve the problem of trajectory tracking using UAVs. However, current control systems face significant hurdles, such as parameter uncertainties, modeling errors, and challenges in windy environments. Sensitivity to parameter variations may lead to performance degradation or instability. Modeling errors arise from simplifications, causing disparities between assumed and actual behavior. Classical controls may lack adaptability to dynamic changes, necessitating adaptive strategies. Limited robustness in handling uncertainties can result in suboptimal performance. Windy environments introduce disturbances, impacting system dynamics and precision. The complexity of wind modeling demands advanced estimation and compensation strategies. Tuning challenges may necessitate frequent adjustments, posing practical limitations. Researchers have explored advanced control paradigms, including robust, adaptive, and predictive control, aiming to enhance system performance amidst uncertainties in a scientifically rigorous manner. Our approach does not require knowledge of UAVs and noise models. Furthermore, the use of the Type-2 controller makes our approach robust in the face of uncertainties. The effectiveness of the proposed approach is clear from the obtained results. In this paper, robust and optimal controllers are proposed, validated, and compared on a quadrotor navigating an outdoor environment. First, a Type-2 Fuzzy Logic Controller (FLC) combined with a PID is compared to a Type-1 FLC and Backstepping controller. Second, a Genetic Algorithm (GA) is proposed to provide the optimal PID-Type-2 FLC tuning. The Backstepping, PID-Type-1 FLC, and PID-Type-2 FLC with GA optimization are validated and evaluated with real scenarios in a windy environment. Deep robustness analysis, including error modeling, parameter uncertainties, and actuator faults, is considered. The obtained results clearly show the robustness of the optimal PID-Type-2 FLC compared to the Backstepping and PID-Type-1 FLC controllers. These results are confirmed by the numerical index of each controller compared to the PID-type-2 FLC, with 12% for the Backstepping controller and 51% for the PID-Type-1 FLC.

Low-power wide area network (LPWAN) technologies as part of IoT are gaining a lot of attention as they provide affordable communication over large areas. LoRa and Sigfox as part of LPWAN have emerged as highly effective and promising non-3GPP unlicensed band IoT technologies while challenging the supremacy of cellular technologies for machine-to-machine-(M2M)-based use cases. This paper presents the design goals of LoRa and Sigfox while throwing light on their suitability in congested environments. A practical traffic generator of both LoRa and Sigfox is introduced and further interpolated for understanding simultaneous operation of 100 to 10,000 such nodes in close vicinity while establishing deep understanding on effects of collision, re-transmissions, and link behaviour. Previous work in this field have overlooked simultaneous deployment, collision issues, effects of re-transmission, and propagation profile while arriving at a number of successful receptions. This work uses packet error rate (PER) and delivery ratio, which are correct metrics to calculate successful transmissions. The obtained results show that a maximum of 100 LoRa and 200 Sigfox nodes can be deployed in a fixed transmission use case over an area of up to 1 km. As part of the future scope, solutions have been suggested to increase the effectiveness of LoRa and Sigfox networks.

The distorted spots induced by atmospheric turbulence significantly degrade the spot position detection accuracy of the quadrant detector (QD). In this paper, we utilize angular measurement and homogenization characteristics of non-imaging microlens array (NI-MLA) systems, effectively reducing the distortion degree of the spots received on the QD target surface, thereby significantly enhancing the spot detection accuracy of the QD. First, based on the principles of geometric optics and Fourier optics, it is proved that the NI-MLA system possesses the angular measurement characteristic (AMC) within the paraxial region while deriving and verifying the focal length of the system. Then, the QD computation curve characteristics of the system under non-turbulence are explored. This study further elucidates the mathematical principle of the NI-MLA system for mitigating the spot position detection random error of QD (SPDRE-QD) and discusses in depth the relationship between the NI-MLA system's capability to mitigate the SPDRE-QD and the system's parameters under various turbulence intensities. Finally, it is experimentally verified that the root-mean-square error (RMSE) of the QD computation values using the NI-MLA system are reduced by a significant improvement of at least 2.44 times and up to 17.36 times compared with that of the conventional optical system of QD (COS-QD) under turbulence conditions ranging from weak to strong.

Accurate wind speed measurement in low-pressure conditions is crucial for the thermal performance validation and attitude control of stratospheric aircraft. As air density decreases, traditional wind speed measurement systems based on principles such as dynamic pressure, heat transfer, ultrasound, and particle velocimetry face significant challenges when applied in low-pressure environments, often failing to achieve the required measurement accuracy. This paper presents the development of a wind speed simulation system based on a rotation method designed to operate in low-pressure conditions, utilizing a space environment simulation chamber in conjunction with a high-precision turntable. The system was employed to conduct response tests on a constant heat flow thermal sphere anemometer within a stratospheric pressure range of 1 kPa to 30 kPa. The experimental results revealed that at extremely low Reynolds numbers, the probe signal exhibited increasing nonlinearity, significantly affecting the response curve at pressures below 15 kPa. While the sensitivity of the hot-sphere probe remained relatively stable at wind speeds above 5 m/s, it decreased nonlinearly as the pressure dropped when wind speeds fell below 5 m/s. Furthermore, this paper analyzes the impact of various interpolation methods on wind speed conversion errors, providing valuable data to support the future development and validation of stratospheric aircraft.

Smartphones are intricately connected to the modern society. The two widely used mobile phone operating systems, iOS and Android, profoundly affect the lives of millions of people. Android presently holds a market share of close to 71% among these two. As a result, if personal information is not securely protected, it is at tremendous risk. On the other hand, mobile malware has seen a year-on-year increase of more than 42% globally in 2022 mid-year. Any group of human professionals would have a very tough time detecting and removing all of this malware. For this reason, deep learning in particular has been used recently to overcome this problem. Deep learning models, however, were primarily created for picture analysis. Despite the fact that these models have shown promising findings in the field of vision, it has been challenging to fully comprehend what the characteristics recovered by deep learning models are in the area of malware. Furthermore, the actual potential of deep learning for malware analysis has not yet been fully realized due to the translation invariance trait of well-known models based on CNN. In this paper, we present ViTDroid, a novel model based on vision transformers for the deep learning-based analysis of opcode sequences of Android malware samples from large real-world datasets. We have been able to achieve a false positive rate of 0.0019 as compared to the previous best of 0.0021. However, this incremental improvement is not the major contribution of our work. Our model aims to make explainable predictions, i.e., it not only performs the classification of malware with high accuracy, but it also provides insights into the reasons for this classification. The model is able to pinpoint the malicious behavior-causing instructions in the malware samples. This means that our model can actually aid in the field of malware analysis itself by providing insights to human experts, thus leading to further improvements in this field.

A major concern in data-driven deep learning (DL) is how to maximize the capability of a model for limited datasets. The lack of high-performance datasets limits intelligent agriculture development. Recent studies have shown that image enhancement techniques can alleviate the limitations of datasets on model performance. Existing image enhancement algorithms mainly perform in the same category and generate highly correlated samples. Directly using authentic images to expand the dataset, the environmental noise in the image will seriously affect the model's accuracy. Hence, this paper designs an automatic leaf segmentation algorithm (AISG) based on the EISeg segmentation method, separating the leaf information with disease spot characteristics from the background noise in the picture. This algorithm enhances the network model's ability to extract disease features. In addition, the Cycle-GAN network is used for minor sample data enhancement to realize cross-category image transformation. Then, MobileNet was trained by transfer learning on an enhanced dataset. The experimental results reveal that the proposed method achieves a classification accuracy of 98.61% for the ten types of tomato diseases, surpassing the performance of other existing methods. Our method is beneficial in solving the problems of low accuracy and insufficient training data in tomato disease detection. This method can also provide a reference for the detection of other types of plant diseases.

The purpose of this paper is to introduce a method of measuring spatiotemporal gait patterns, tibial accelerations, and heart rate that are matched with high resolution geographical terrain features using publicly available data. These methods were demonstrated using data from 218 Marines, who completed loaded outdoor ruck hikes between 5-20 km over varying terrain. Each participant was instrumented with two inertial measurement units (IMUs) and a GPS watch. Custom code synchronized accelerometer and positional data without a priori sensor synchronization, calibrated orientation of the IMUs in the tibial reference frame, detected and separated only periods of walking or running, and computed acceleration and spatiotemporal outcomes. GPS positional data were georeferenced with geographic information system (GIS) maps to extract terrain features such as slope, altitude, and surface conditions. This paper reveals the ease at which similar data can be gathered among relatively large groups of people with minimal setup and automated data processing. The methods described here can be adapted to other populations and similar ground-based activities such as skiing or trail running.

This paper reports the successful application of a self-developed, miniaturized, low-power nano-star tracker for precise attitude measurement of a 5-m-long satellite extension boom. Such extension booms are widely used in space science missions to extend and support payloads like magnetometers. The nano-star tracker, based on a CMOS image sensor, weighs 150 g (including the baffle), has a total power consumption of approximately 0.85 W, and achieves a pointing accuracy of about 5 arcseconds. It is paired with a low-cost, commercial lens and utilizes automated calibration techniques for measurement correction of the collected data. This system has been successfully applied to the precise attitude measurement of the 5-m magnetometer boom on the Chinese Advanced Space Technology Demonstration Satellite (SATech-01). Analysis of the in-orbit measurement data shows that within shadowed regions, the extension boom remains stable relative to the satellite, with a standard deviation of 30'' (1σ). The average Euler angles for the "X-Y-Z" rotation sequence from the extension boom to the satellite are [-89.49°, 0.08°, 90.11°]. In the transition zone from shadow to sunlight, influenced by vibrations and thermal factors during satellite attitude adjustments, the maximum angular fluctuation of the extension boom relative to the satellite is approximately ±2°. These data and the accuracy of the measurements can effectively correct magnetic field vector measurements.

Currently, underwater sensor networks are extensively applied for environmental monitoring, disaster prediction, etc. Nevertheless, owing to the complicacy of the underwater environment, the limited energy of underwater sensor nodes, and the high latency of hydroacoustic channels, the energy-efficient operation of underwater sensor networks has become an important challenge. In this paper, a high-efficiency clustering routing protocol in AUV-assisted underwater sensor networks (HECRA) is proposed to address the energy limitations and low data transmission reliability in underwater sensor networks. The protocol optimizes the cluster head selection strategy of the traditional low-energy adaptive clustering hierarchy (LEACH) protocol by introducing the residual energy and node degree in the cluster head selection phase and performs some optimizations in the cluster formation and data transmission phases, including selecting clusters for joining by ordinary nodes based on the residual energy of the cluster head nodes and weight computation based on the depth and residual energy of the cluster head nodes to select the optimal message forwarding nodes. In addition, this paper introduces an autonomous underwater vehicle (AUV) as a dynamic relay node to improve network transmission efficiency. According to the simulation results, compared with the existing LEACH, the energy efficient routing protocol based on layers and unequal clusters in underwater wireless sensor networks (EERBLC) and energy-efficient clustering multi-hop routing protocol in a UWSN (EECMR), the HECRA significantly improves network lifetime, the residual node energy, and the number of successfully transmitted packets, which can effectively prolong network lifetime and ensure efficient data transmission.

The application of deep neural networks for the semantic segmentation of remote sensing images is a significant research area within the field of the intelligent interpretation of remote sensing data. The semantic segmentation of remote sensing images holds great practical value in urban planning, disaster assessment, the estimation of carbon sinks, and other related fields. With the continuous advancement of remote sensing technology, the spatial resolution of remote sensing images is gradually increasing. This increase in resolution brings about challenges such as significant changes in the scale of ground objects, redundant information, and irregular shapes within remote sensing images. Current methods leverage Transformers to capture global long-range dependencies. However, the use of Transformers introduces higher computational complexity and is prone to losing local details. In this paper, we propose UNeXt (UNet+ConvNeXt+Transformer), a real-time semantic segmentation model tailored for high-resolution remote sensing images. To achieve efficient segmentation, UNeXt uses the lightweight ConvNeXt-T as the encoder and a lightweight decoder, Transnext, which combines a Transformer and CNN (Convolutional Neural Networks) to capture global information while avoiding the loss of local details. Furthermore, in order to more effectively utilize spatial and channel information, we propose a SCFB (SC Feature Fuse Block) to reduce computational complexity while enhancing the model's recognition of complex scenes. A series of ablation experiments and comprehensive comparative experiments demonstrate that our method not only runs faster than state-of-the-art (SOTA) lightweight models but also achieves higher accuracy. Specifically, our proposed UNeXt achieves 85.2% and 82.9% mIoUs on the Vaihingen and Gaofen5 (GID5) datasets, respectively, while maintaining 97 fps for 512 × 512 inputs on a single NVIDIA GTX 4090 GPU, outperforming other SOTA methods.

Measurements monitoring the inductive coupling between oscillating radio-frequency magnetic fields and objects of interest create versatile platforms for non-destructive testing. The benefits of ultra-low-frequency measurements, i.e., below 3 kHz, are sometimes outweighed by the fundamental and technical difficulties related to operating pick-up coils or other field sensors in this frequency range. Inductive measurements with the detection based on a two-photon interaction in rf atomic magnetometers address some of these issues as the sensor gains an uplift in its operational frequency. The developments reported here integrate the fundamental and applied aspects of the two-photon process in magnetic induction measurements. In this paper, all the spectral components of the two-photon process are identified, which result from the non-linear interactions between the rf fields and atoms. For the first time, a method for the retrieval of the two-photon phase information, which is critical for inductive measurements, is also demonstrated. Furthermore, a self-compensation configuration is introduced, whereby high-contrast measurements of defects can be obtained due to its insensitivity to the primary field, including using simplified instrumentation for this configuration by producing two rf fields with a single rf coil.

In the context of rapid advancements in AI, the accuracies and speeds among various AI models and methods are often compared. However, a basic question is rarely asked: is AI better than humans, and if so, under what conditions? This paper investigates human ability to detect distant landmark targets under cluttered surroundings such as buildings, trees, and clouds in NIR and LWIR images, aiming to facilitate AI object detection performance analysis. Our investigation employs perception tests and a human performance model to analyze object detection capabilities. The results reveal distinctive differences in NIR and LWIR detectability, showing that although LWIR performs less effectively at range, it offers superior robustness across various environmental conditions. Our findings suggest that AI could be particularly advantageous for object detection in LWIR as it outperform humans in terms of detection accuracy at a long range.

Simultaneous localization and mapping, a critical technology for enabling the autonomous driving of vehicles and mobile robots, increasingly incorporates multi-sensor configurations. Inertial measurement units (IMUs), known for their ability to measure acceleration and angular velocity, are widely utilized for motion estimation due to their cost efficiency. However, the inherent noise in IMU measurements necessitates the integration of additional sensors to facilitate spatial understanding for mapping. Visual-inertial odometry (VIO) is a prominent approach that combines cameras with IMUs, offering high spatial resolution while maintaining cost-effectiveness. In this paper, we introduce our uncertainty-aware depth network (UD-Net), which is designed to estimate both depth and uncertainty maps. We propose a novel loss function for the training of UD-Net, and unreliable depth values are filtered out to improve VIO performance based on the uncertainty maps. Experiments were conducted on the KITTI dataset and our custom dataset acquired from various driving scenarios. Experimental results demonstrated that the proposed VIO algorithm based on UD-Net outperforms previous methods with a significant margin.

In this paper, a conductor-backed coplanar waveguide with sine edges (CBCPW-SE), consisting of a conductor-backed coplanar with periodic sine edges supported by a dielectric substrate, is proposed as a promising new transmission line (TL) at millimeter-wave and terahertz frequencies. This configuration offers a distinct advantage by maintaining a constant input impedance of 50 Ω across a broad frequency spectrum, eliminating the necessity for any additional impedance matching transitions, thereby enhancing the overall efficiency and simplicity of the transmission system. To verify the design, the CBCPW-SE was fabricated and measured. The measurement results demonstrate that, from 10 MHz to 100 GHz, the insertion loss is less than 0.1 dB/mm and the reflection coefficient is better than -10 dB. The measured S21 (dB) for a 50 mm-long CBCPW-SE section is less than -5 dB from 10 MHz to 100 GHz. The measured group delay per unit length of the trace is 3.4-5 ps, ranging from 10 MHz to 100 GHz. Moreover, the measured group velocity dispersion (GVD) approaches zero, signifying the minimal temporal spreading of the signal components, a crucial aspect for maintaining signal integrity and facilitating high-speed data transmission.

Optical communications providing huge capacity and low latency remain vulnerable to a range of attacks. In consequence, encryption at the optical layer is needed to ensure secure data transmission. In our previous work, we proposed LightPath SECurity (LPSec), a secure cryptographic solution for optical transmission that leverages stream ciphers and Diffie-Hellman (DH) key exchange for high-speed optical encryption. Still, LPSec faces limitations related to key generation and key distribution. To address these limitations, in this paper, we rely on Quantum Random Number Generators (QRNG) and Quantum Key Distribution (QKD) networks. Specifically, we focus on three meaningful scenarios: In Scenario A, the two optical transponders (Tp) involved in the optical transmission are within the security perimeter of the QKD network. In Scenario B, only one Tp is within the QKD network, so keys are retrieved from a QRNG and distributed using LPSec. Finally, Scenario C extends Scenario B by employing Post-Quantum Cryptography (PQC) by implementing a Key Encapsulation Mechanism (KEM) to secure key exchanges. The scenarios are analyzed based on their security, efficiency, and applicability, demonstrating the potential of quantum-enhanced LPSec to provide secure, low-latency encryption for current optical communications. The experimental assessment, conducted on the Madrid Quantum Infrastructure, validates the feasibility of the proposed solutions.

Human-robot collaboration will play an important role in the fourth industrial revolution in applications related to hostile environments, mining, industry, forestry, education, natural disaster and defense. Effective collaboration requires robots to understand human intentions and tasks, which involves advanced user profiling. Voice-based communication, rich in complex information, is key to this. Beamforming, a technology that enhances speech signals, can help robots extract semantic, emotional, or health-related information from speech. This paper describes the implementation of a system that provides substantially improved signal-to-noise ratio (SNR) and speech recognition accuracy to a moving robotic platform for use in human-robot interaction (HRI) applications in static and dynamic contexts. This study focuses on training deep learning-based beamformers using acoustic model-based multi-style training with measured room impulse responses (RIRs). The results show that this approach outperforms training with simulated RIRs or matched measured RIRs, especially in dynamic conditions involving robot motion. The findings suggest that training with a broad range of measured RIRs is sufficient for effective HRI in various environments, making additional data recording or augmentation unnecessary. This research demonstrates that deep learning-based beamforming can significantly improve HRI performance, particularly in challenging acoustic environments, surpassing traditional beamforming methods.

The cost of hyperspectral image (HSI) classification primarily stems from the annotation of image pixels. In real-world classification scenarios, the measurement and annotation process is both time-consuming and labor-intensive. Therefore, reducing the number of labeled pixels while maintaining classification accuracy is a key research focus in HSI classification. This paper introduces a multi-strategy triple network classifier (MSTNC) to address the issue of limited labeled data in HSI classification by improving learning strategies. First, we use the contrast learning strategy to design a lightweight triple network classifier (TNC) with low sample dependence. Due to the construction of triple sample pairs, the number of labeled samples can be increased, which is beneficial for extracting intra-class and inter-class features of pixels. Second, an active learning strategy is used to label the most valuable pixels, improving the quality of the labeled data. To address the difficulty of sampling effectively under extremely limited labeling budgets, we propose a new feature-mixed active learning (FMAL) method to query valuable samples. Fine-tuning is then used to help the MSTNC learn a more comprehensive feature distribution, reducing the model's dependence on accuracy when querying samples. Therefore, the sample quality is improved. Finally, we propose an innovative dual-threshold pseudo-active learning (DSPAL) strategy, filtering out pseudo-label samples with both high confidence and uncertainty. Extending the training set without increasing the labeling cost further improves the classification accuracy of the model. Extensive experiments are conducted on three benchmark HSI datasets. Across various labeling ratios, the MSTNC outperforms several state-of-the-art methods. In particular, under extreme small-sample conditions (five samples per class), the overall accuracy reaches 82.97% (IP), 87.94% (PU), and 86.57% (WHU).

In chromatic confocal line sensors, calibration is usually divided into peak extraction and wavelength calibration. In previous research, the focus was mainly on peak extraction. In this paper, a kernel-based algorithm is proposed to deal with wavelength calibration, which corresponds to the mapping relationship between peaks (i.e., the wavelengths) in image space and profiles in physical space. The primary component of the mapping function is depicted using polynomial basis functions, which are distinguished along various dispersion axes. Considering the unknown distortions resulting from field curvature, sensor fabrication and assembly, and even the inherent complexity of dispersion, a typical kernel trick-based nonparametric function element is introduced here, predicated on the notion that similar processes conducted on the same sensor yield comparable distortions.To ascertain the performance with and without the kernel trick, we carried out wavelength calibration and groove fitting on a standard groove sample processed via glass grinding and with a reference depth of 66.14 μm. The experimental results show that depths calculated by the kernel-based calibration algorithm have higher accuracy and lower uncertainty than those ascertained using the conventional polynomial algorithm. As such, this indicates that the proposed algorithm provides effective improvements.

One basic limitation of using the periodogram as a frequency estimator is that any of its significant peaks may result from a diffuse (or spread) frequency component rather than a pure one. Diffuse components are common in applications such as channel estimation, in which a given periodogram peak reveals the presence of a complex multipath distribution (unresolvable propagation paths or diffuse scattering, for example). We present a method to detect the presence of a diffuse component in a given peak based on analyzing the projection of the data vector onto the span of the signature's derivatives up to a given order. Fundamentally, a diffuse component is detected if the energy in the derivatives' subspace is too high at the peak's frequency, and its spread is estimated as the ratio between this last energy and the peak's energy. The method is based on exploiting the signature's Vandermonde structure through the properties of discrete Chebyshev polynomials. We also present an efficient numerical procedure for computing the data component in the derivatives' span based on barycentric interpolation. The paper contains a numerical assessment of the proposed estimator and detector.

When wind turbines contribute to system frequency support using virtual synchronous generator (VSG) control, conventional VSG methods often fall short of meeting operational demands, particularly in terms of inertia and frequency support. In this study, considering both the frequency regulation and dynamic performance of VSG, a novel parameter design method that enhances frequency modulation capabilities is proposed in this paper. Initially, VSG control is integrated into the grid-side converter of a direct-drive permanent magnet synchronous generator (D-DPMSG) wind turbine. A small-signal model of the D-DPMSG-VSG active power is then formulated to analyze how the moment of inertia and damping coefficient impact system stability. Subsequently, ensuring that system parameter constraints are met, the key parameters of VSG are adaptively designed to dynamically adjust the system's frequency and output power during transient responses. Finally, simulation results based on D-DPMSG-VSG in MATLAB/Simulink validated the feasibility, effectiveness, and advantages of the proposed parameter-adaptive VSG control strategy for enhancing the frequency modulation (FM) performance of wind turbines.

In clinical settings, computed tomography (CT), magnetic resonance imaging (MRI), or positron emission tomography (PET) are commonly employed in brain imaging to assist clinicians in determining the type of stroke in patients. However, these modalities are associated with potential hazards or limitations. In contrast, microwave imaging emerges as a promising technique, offering advantages such as non-ionizing radiation, low cost, lightweight, and portability. The primary challenges faced by microwave tomography include the severe ill-posedness of the electromagnetic inverse scattering problem and the time-consuming nature and unsatisfactory resolution of iterative quantitative algorithms. This paper proposes a learning electric field enhancement imaging method (LEFEIM) to achieve quantitative brain imaging based on a microwave tomography system. LEFEIM comprises two cascaded networks. The first, based on a convolutional neural network, utilizes the electric field from the receiving antenna to predict the electric field distribution within the imaging domain. The second network employs the electric field distribution as input to learn the dielectric constant distribution, thereby realizing quantitative brain imaging. Compared to the Born Iterative Method (BIM), LEFEIM significantly improves imaging time, while enhancing imaging quality and goodness-of-fit to a certain extent. Simultaneously, LEFEIM exhibits anti-noise capabilities.

Flexible and stretchable electronics have emerged as a groundbreaking technology with wide-ranging applications, including wearable devices, medical implants, and environmental monitoring systems. Among their numerous applications, hydrogen sensing represents a critical area of research, particularly due to hydrogen's role as a clean energy carrier and its explosive nature at high concentrations. This review paper provides a comprehensive overview of the recent advancements in flexible and stretchable electronics tailored for resistive hydrogen sensing applications. It begins by introducing the fundamental principles underlying the operation of flexible and stretchable resistive sensors, highlighting the innovative materials and fabrication techniques that enable their exceptional mechanical resilience and adaptability. Following this, the paper delves into the specific strategies employed in the integration of these resistive sensors into hydrogen detection systems, discussing the merits and limitations of various sensor designs, from nanoscale transducers to fully integrated wearable devices. Special attention is paid to the sensitivity, selectivity, and operational stability of these resistive sensors, as well as their performance under real-world conditions. Furthermore, the review explores the challenges and opportunities in this rapidly evolving field, including the scalability of manufacturing processes, the integration of resistive sensor networks, and the development of standards for safety and performance. Finally, the review concludes with a forward-looking perspective on the potential impacts of flexible and stretchable resistive electronics in hydrogen energy systems and safety applications, underscoring the need for interdisciplinary collaboration to realize the full potential of this innovative technology.

Notably, 6D pose estimation is a critical technology that enables robotics to perceive and interact with their operational environment. However, occlusion causes a loss of local features, which, in turn, restricts the estimation accuracy. To address these challenges, this paper proposes an end-to-end pose-estimation network based on a multi-channel attention mechanism, DA2Net. Firstly, a multi-channel attention mechanism, designated as "DA2Net", was devised using A 2 -Nets as its foundation. This mechanism is constructed in two steps. In the first step, the essential characteristics are extracted from the global feature space through the second-order attention pool. In the second step, a feature map is generated by the integration of position and channel attention. Subsequently, the extracted key features are assigned to each position of the feature map, enhancing both the feature representation capacity and the overall performance. Secondly, the designed attention mechanism is introduced into both the feature fusion and pose iterative refinement networks to enhance the network's capacity to acquire local features thus improving its overall performance. The experimental results demonstrated that the estimation accuracy of DenseFusion-DA2 on the LineMOD dataset was approximately 3.4% higher than that of DenseFusion. Furthermore, the estimation accuracy surpassed that of PoseCNN, PVNet, SSD6D, and PointFusion by 8.3%, 11.1%, 20.3%, and 23.8%, respectively. The estimation accuracy also shows a significant advantage on the Occluded LineMOD and HR-Vision datasets. This research not only presents a more efficient solution for robot perception but also introduces novel ideas and methods for technological advancements and applications in related fields.

This paper focuses on the direction-of-arrival (DOA) estimation for noncircular coherently distributed (CD) sources with nested arrays. Usually, for point sources, sparse arrays have the potential to improve the estimation performance of algorithms by obtaining more degrees of freedom. However, algorithms have to be reconsidered for CD sources with sparse arrays and many problems arise. One thorny problem is the disappearance of displacement invariance of the virtual array manifold constructed by the virtualization technique. To deal with this issue, a nested array processing method for CD sources transmitting noncircular signals is proposed in this paper. Firstly, we construct the virtual sum-and-difference co-array by leveraging the noncircular quality of signals with a nested array. Then, an approximation is made to degrade CD sources into point sources. In this way, spatial smoothing techniques can be applied to restore the rank. Finally, in order to reduce the complexity, we modify the reduced-dimension MUSIC to estimate DOAs through a one-dimensional peak-searching procedure. The simulation results prove the superiority of our algorithm against other competitors.

This research paper describes the development of a low-cost device for measuring wastewater flow rates in open channels, a significant advancement enabled by the evolution of microcomputers and processing techniques. A laboratory setup was constructed to validate the device's accuracy against a standard flow measurement method, optimizing key parameters to achieve a linear relationship between detected and set flow rates, while considering hardware limitations and energy efficiency. The central focus of the research was developing a method to measure the velocity of contaminated fluid using ultrasonic signals, employing the cross-correlation method for signal delay analysis in a stochastic environment. This was complemented by a procedure to measure fluid levels, also based on ultrasonic signals. The device's reliability was assessed through repeatability and uncertainty measurements, confirming its accuracy with an extended uncertainty not exceeding an average of 3.47% for flows above 40 L/min. The device has potential to provide valuable data on the operational dynamics of sanitary networks, crucial for developing and calibrating simulation models.

This paper introduces a novel capacitive sensor array designed for tactile perception applications. Utilizing an all-in-one inkjet deposition printing process, the sensor array exhibited exceptional flexibility and accuracy. With a resolution of up to 32.7 dpi, the sensor array was capable of capturing the fine details of touch inputs, making it suitable for applications requiring high spatial resolution. The design incorporates two multiplexers to achieve a scanning rate of 100 Hz, ensuring the rapid and responsive data acquisition that is essential for real-time feedback in interactive applications, such as gesture recognition and haptic interfaces. To evaluate the performance of the capacitive sensor array, an experiment that involved handwritten number recognition was conducted. The results demonstrated that the sensor accurately captured fingertip inputs with a high precision. When combined with an Auxiliary Classifier Generative Adversarial Network (ACGAN) algorithm, the sensor system achieved a recognition accuracy of 98% for various handwritten numbers from "0" to "9". These results show the potential of the capacitive sensor array for advanced human-computer interaction applications.

This paper analyzes the quantitative quality parameters of a mobile communication network in a controlled drone logistic use-case scenario. Based on the analysis of standards and recommendations, the values of key performance indicators (KPIs) are set. As the main network-impacting parameters, reference signal received power (RSRP), reference signal received quality (RSRQ), and signal to interference and noise ratio (SINR) were selected. Uplink (UL), downlink (DL), and ping parameters were chosen as the secondary ones, as they indicate the quality of the link depending on primary parameters. The analysis is based on experimental measurements performed using a Latvian mobile operator's "LMT" JSC infrastructure in a real-life scenario. To evaluate the altitude impact on the selected network parameters, the measurements were performed using a drone as transport for the following altitude values: 40, 60, 90, and 110 m. Network parameter measurements were implemented in automatic mode, allowing switching between LTE4-LTE2 standards, providing the opportunity for more complex analysis. Based on the analysis made, the recommendations for the future mobile networks employed in controlled drone flights should correspond to the following KPI and their values: -100 dBm for RSRP, -16 dB for RSRQ, -5 dB for SINR, 4096 kbps for downlink, 4096 kbps for uplink, and 50 ms for ping. Lastly, recommendations for a network coverage digital twin (DT) model with integrated KPIs are also provided.

The selection of a target when training deep neural networks for speech enhancement is an important consideration. Different masks have been shown to exhibit different performance characteristics depending on the application and the conditions. This paper presents a comprehensive comparison of several different masks for noise reduction in cochlear implants. The study incorporated three well-known masks, namely the Ideal Binary Mask (IBM), Ideal Ratio Mask (IRM) and the Fast Fourier Transform Mask (FFTM), as well as two newly proposed masks, based on existing masks, called the Quantized Mask (QM) and the Phase-Sensitive plus Ideal Ratio Mask (PSM+). These five masks are used to train networks to estimate masks for the purpose of separating speech from noisy mixtures. A vocoder was used to simulate the behavior of a cochlear implant. Short-time Objective Intelligibility (STOI) and Perceptual Evaluation of Speech Quality (PESQ) scores indicate that the two new masks proposed in this study (QM and PSM+) perform best for normal speech intelligibility and quality in the presence of stationary and non-stationary noise over a range of signal-to-noise ratios (SNRs). The Normalized Covariance Measure (NCM) and similarity scores indicate that they also perform best for speech intelligibility/gauging the similarity of vocoded speech. The Quantized Mask performs better than the Ideal Binary Mask due to its better resolution as it approximates the Wiener Gain Function. The PSM+ performs better than the three existing benchmark masks (IBM, IRM, and FFTM) as it incorporates both magnitude and phase information.

This paper presents a single-input multiple-output (SIMO) cascode low-noise amplifier with inductive degeneration for inter- and intra-band carrier aggregation. The proposed low-noise amplifier has two output ports for flexible operation in carrier aggregation combinations for band 30 and band 7. However, during inter- and intra-band operation, gain variation occurs depending on the output mode. To compensate for this, a switching circuit is proposed to adjust the degeneration inductor, optimizing gain performance for both modes. The switching operation can minimize the control for the dynamic range in the receiver system to support carrier aggregation. The designed low-noise amplifier was fabricated using a 65 nm CMOS process, occupying an area of 2.1 mm 2 . In inter-band operation, the small-signal gain was measured by 18.9 dB for band 30 and 18.6 dB for band 7, with the noise figures of 1.03 dB and 1.07 dB, respectively. For intra-band operation, the small-signal gain was 17.3 dB and 17.2 dB, with the noise figures of 1.3 dB and 1.41 dB. The IIP 3 values were measured by -7.6 dBm and -6.7 dBm for inter-band, and -6.3 dBm and -6.2 dBm for intra-band. Power consumption was 8.04 mW and 7.68 mW in inter-band, and 17.04 mW and 17.64 mW in intra-band depending on the output configuration.

The paper discusses the results of the concentrations of atmospheric particulate matter, in the PM 2.5 and PM 10 fractions, acquired by two low-cost sensors. The research was carried out from 1 July 2023 to 30 June 2024, in Palermo, Sicily. The results obtained from two systems equipped with the same sensor model were compared. Excellent linear correlation was observed between the results, with differences in measurements falling within instrumental accuracy. Two instruments equipped with different sensors, models Novasense SDS011 and Plantower PMSA003, were placed at the same site. These were complemented by a weather station to measure meteorological parameters. Upon comparing the atmospheric particulate matter concentrations measured by the two instruments, it was observed that there was a good linear correlation for PM 2.5 and a poor linear correlation for PM 10 . Additionally, the PMSA003 sensor appeared to consistently record higher concentrations than the SDS011 sensor. During periods influenced by natural sources and/or anthropogenic activities at the regional and/or local scale, i.e., the dispersal of Saharan sands, forest fires, and local events using fireworks, abnormal concentrations of atmospheric particulate matter were detected. Despite the inherent limitations in precision and accuracy, both low-cost instruments were able to identify periods with abnormal concentrations of atmospheric particulate matter, regardless of their source or type.

Photodetectors play a critical role in space lidars designed for scientific investigations from orbit around planetary bodies. The detectors must be highly sensitive due to the long range of measurements and tight constraints on the size, weight, and power of the instrument. The detectors must also be space radiation tolerant over multi-year mission lifetimes with no significant performance degradation. Early space lidars used diode-pumped Nd:YAG lasers with a single beam for range and atmospheric backscattering measurements at 1064 nm or its frequency harmonics. The photodetectors used were single-element photomultiplier tubes and infrared performance-enhanced silicon avalanche photodiodes. Space lidars have advanced to multiple beams for surface topographic mapping and active infrared spectroscopic measurements of atmospheric species and surface composition, which demand increased performance and new capabilities for lidar detectors. Higher sensitivity detectors are required so that multi-beam and multi-wavelength measurements can be performed without increasing the laser and instrument power. Pixelated photodetectors are needed so that a single detector assembly can be used for simultaneous multi-channel measurements. Photon-counting photodetectors are needed for active spectroscopy measurements from short-wave infrared to mid-wave infrared. HgCdTe avalanche photodiode arrays have emerged recently as a promising technology to fill these needs. This paper gives a review of the photodetectors used in past and present lidars and the development and outlook of HgCdTe APD arrays for future space lidars.

Traditional object counting systems use object detection methods to count objects. However, when objects are small, crowded, and dense, object detection may fail, leading to inaccuracies in counting. To address this issue, we propose a crowded object counting system based on density map estimation. While most density map estimation models employ encoder-decoder or multi-branch approaches to generate feature maps at different scales for obtaining an accurate density map, improving the accuracy of crowded object counting remains a challenge. In this paper, we propose a novel model that can generate more accurate density maps, utilizing the context-aware network as the primary structure and integrating the self-attention mechanism. There are three main contributions in this paper. Firstly, the self-attention mechanism is employed to improve the accuracy of density map estimation. Secondly, the missing vehicle labels in the TRANCOS database are relabeled, ensuring that the ground truth data are more complete than the original TRANCOS database, thus enabling the proposed novel model to have higher crowded object counting accuracy. Thirdly, the parameters of the self-attention mechanism are analyzed to obtain the optimum parameter combination. The experimental results demonstrate that the accuracy of crowded object counting can reach 85.9%, 90.0%, 83.4%, and 92.6% for the TRANCOS, relabeled TRANCOS, ShanghaiTech Part A, and Part B datasets, respectively. Furthermore, the ablation study for the context-aware network with self-attention mechanism analyzes the optimum parameter combination.

This paper presents a dual-purpose LED driver system that functions as both a lighting source and a Visible Light Communication (VLC) transmitter integrated with a Powerline Communication (PLC) network under the PRIME G3 standard. The system decodes PLC messages from the powerline grid and transmits the information via LED light to an optical receiver under a binary phase shift keying (BPSK) modulation. The load design targets a light flux of 800 lumens, suitable for LED light bulb applications up to 10 watts, ensuring practicality and energy efficiency. The Universal Asynchronous Receiver-Transmitter (UART) module enables communication between the PLC and VLC systems, allowing for an LED driver with dynamic control and real-time operation. Key signal processing stages are commented and developed, including a hybrid buck converter with modulation capabilities and a nonlinear optical receiver to regenerate the BPSK reference signal for VLC. Results show a successful prototype working under a laboratory environment. Experimental validation shows successful transmission of bit streams from the PLC grid to the VLC setup. A design guideline is presented in order to dictate the design of the electronic devices involved in the experiment. Finally, this research highlights the feasibility of integrating PLC and VLC technologies, offering an efficient and cost-effective solution for data transmission over existing infrastructure.

This paper presents the design of a strawberry fruit head gripper unit, together with the concept of a control system for the operation of its mechanisms and vision system. The developed design consists of three specialised mechanisms: positioning, grasping, and cutting off of the fruit. A Finite Element Method (FEM) model was developed for the described design. Next, calculations were carried out, based on which the construction materials were selected. The key performance parameters of the functional model, built on the basis of the developed design concept, were verified under laboratory conditions. In tests carried out on the possible hematoma caused by exceeding the breaking stress induced by the pressure of the encompassing jaws on the fruit, it was found that none of the fruit tested suffered mechanical damage as a result of the sensor triggering force, and the average length of the trimmed stalk was approximately 14 mm. The designed head gripper, together with the proposed automation system, will contribute to improving harvesting precision, and this will favour a reduction in the quantitative and qualitative losses of the harvested crop. The experimental tests conducted under harvesting conditions showed a high efficiency of 95% in identifying ripe fruit, and the harvesting efficiency of the robotic arm was 90%.

Long-range networks, renowned for their long-range, low-power communication capabilities, form the backbone of many Internet of Things systems, enabling efficient and reliable data transmission. However, detecting tampered frequency signals poses a considerable challenge due to the vulnerability of LoRa devices to radio-frequency interference and signal manipulation, which can undermine both data integrity and security. This paper presents an innovative method for identifying tampered radio frequency transmissions by employing five sophisticated anomaly detection algorithms-Local Outlier Factor, Isolation Forest, Variational Autoencoder, traditional Autoencoder, and Principal Component Analysis within the framework of a LoRa-based Internet of Things network structure. The novelty of this work lies in applying image-based tampered frequency techniques with these algorithms, offering a new perspective on securing LoRa transmissions. We generated a dataset of over 26,000 images derived from real-world experiments with both normal and manipulated frequency signals by splitting video recordings of LoRa transmissions into frames to thoroughly assess the performance of each algorithm. Our results demonstrate that Local Outlier Factor achieved the highest accuracy of 97.78%, followed by Variational Autoencoder, traditional Autoencoder and Principal Component Analysis at 97.27%, and Isolation Forest at 84.49%. These findings highlight the effectiveness of these methods in detecting tampered frequencies, underscoring their potential for enhancing the reliability and security of LoRa networks.

This paper explores an application of 3D printing technology on the food industry. Since its inception in the 1980s, 3D printing has experienced a huge rise in popularity. This study uses cost-effective, flexible, and sustainable components that enable specific features of certain gas chromatography. This study aims to optimize the process of gas detection using a 3D printed separation column and the MiCS-6814 sensor. The principle of the entire device is based on the idea of utilizing a simple capillary chromatographic column manufactured by 3D printing for the separation of samples into components prior to their measurement using inexpensive chemiresistive sensors. An optimization of a system with a 3D printed PLA block containing a capillary, a mixing chamber, and a measuring chamber with a MiCS-6814 sensor was performed. The optimization distributed the sensor output signal in the time domain so that it was possible to distinguish the peak for the two most common alcohols, ethanol and methanol. The paper further describes some optimization types and their possibilities.