Search

The increasing demand for hazelnut kernels is favoring an upsurge in hazelnut cultivation worldwide, but ongoing climate change threatens this crop, affecting yield decreases and subject to uncontrolled pathogen and parasite attacks. Technical advances in precision agriculture are expected to support farmers to more efficiently control the physio-pathological status of crops. Here, we report a straightforward approach to monitoring hazelnut trees in an open field, using aerial multispectral pictures taken by drones. A dataset of 4112 images, each having 2Mpixel resolution per tree and covering RGB, Red Edge, and near-infrared frequencies, was obtained from 185 hazelnut trees located in two different orchards of the Piedmont region (northern Italy). To increase accuracy, and especially to reduce false negatives, the image of each tree was divided into nine quadrants. For each quadrant, nine different vegetation indices (VIs) were computed, and in parallel, each tree quadrant was tagged as "healthy/unhealthy" by visual inspection. Three supervised binary classification algorithms were used to build models capable of predicting the status of the tree quadrant, using the VIs as predictors. Out of the nine VIs considered, only five (GNDVI, GCI, NDREI, NRI, and GI) were good predictors, while NDVI SAVI, RECI, and TCARI were not. Using them, a model accuracy of about 65%, with 13% false negatives was reached in a way that was rather independent of the algorithms, demonstrating that some VIs allow inferring the physio-pathological condition of these trees. These achievements support the use of drone-captured images for performing a rapid, non-destructive physiological characterization of hazelnut trees. This approach offers a sustainable strategy for supporting farmers in their decision-making process during agricultural practices.

This paper introduces a novel energy-efficient lightweight, void hole avoidance, localization, and trust-based scheme, termed as Energy-Efficient and Trust-based Autonomous Underwater Vehicle (EETAUV) protocol designed for 6G-enabled underwater acoustic sensor networks (UASNs). The proposed scheme addresses key challenges in UASNs, such as energy consumption, network stability, and data security. It integrates a trust management framework that enhances communication security through node identification and verification mechanisms utilizing normal and phantom nodes. Furthermore, a 6G communication module is deployed to reduce network delay and enhance packet delivery, contributing to more efficient data transmission. Leveraging Autonomous Underwater Vehicles (AUVs), the EETAUV protocol offers a lightweight approach for node discovery, identification, and verification while ensuring a high data transmission rate through a risk-aware strategy including at low computational cost. The protocol's performance is evaluated through extensive simulations and compared against state-of-the-art methods across various metrics, including network lifetime, throughput, residual energy, packet delivery ratio, mean square error, routing overhead, path loss, network delay, trust, distance, velocity, Computational Cost of Routing, and data security. The results demonstrate the superior cumulative performance of the proposed EETAUV scheme, making it a robust solution for secure, efficient, and reliable communication in UASNs.

Traffic flow prediction is a pivotal element in Intelligent Transportation Systems (ITSs) that provides significant opportunities for real-world applications. Capturing complex and dynamic spatio-temporal patterns within traffic data remains a significant challenge for traffic flow prediction. Different approaches to effectively modeling complex spatio-temporal correlations within traffic data have been proposed. These approaches often rely on a single model to capture temporal dependencies, which neglects the varying influences of different time periods on traffic flow. Additionally, these models frequently utilize either static or dynamic graphs to represent spatial dependencies, which limits their ability to address complex and overlapping spatial relationships. Moreover, some approaches struggle to fully capture spatio-temporal variations, leading to the exclusion of critical information and ultimately resulting in suboptimal prediction performance. Thus, this paper introduces the Adaptive Spatio-Temporal Attention-Based Multi-Model (ASTAM), an architecture designed to capture spatio-temporal dependencies within traffic data. The ASTAM employs multi-temporal gated convolution with multi-scale temporal input segments to model complex non-linear temporal correlations. It utilizes static and dynamic parallel multi-graphs to facilitate the modeling of complex spatial dependencies. Furthermore, this model incorporates a spatio-temporal self-attention mechanism to adaptively capture the dynamic and long-term spatio-temporal variations in traffic flow. Experiments conducted on four real-world datasets reveal that the proposed architecture outperformed 13 baseline approaches, achieving average reductions of 5.0% in MAE, 13.28% in RMSE, and 6.46% in MAPE across four datasets.

Algorithms for detecting point targets in hyperspectral imaging commonly employ the spectral inverse covariance matrix to whiten inherent image noise. Since data cubes often lack stationarity, segmentation appears to be an attractive preprocessing operation. Surprisingly, the literature reports both successful and unsuccessful segmentation cases, with no clear explanations for these divergent outcomes. This paper elucidates the conditions under which segmentation might improve detector performance. Focusing on a representative algorithm and assuming a target additive model, the study examines all influential factors through theoretical analysis and extensive simulations. The findings offer fundamental insights and practical guidelines for characterizing segmented datasets, enabling a thorough evaluation of segmentation's utility for detector performance. They outline the range of target scenarios and parameters where segmentation may prove beneficial and help assess the potential impact of proposed segmentation strategies on detection outcomes.

As modern vehicles continue to evolve, advanced technologies are integrated to enhance the driving experience. A key enabler of this advancement is the Controller Area Network (CAN) bus, which facilitates seamless communication between vehicle components. Despite its widespread adoption, the CAN bus was not designed with security as a priority, making it vulnerable to various attacks. In this paper, we propose CANGuard, an Intrusion Detection System (IDS) designed to detect attacks on the CAN network and identify the originating node in real time. Using a simulated CAN-enabled system with four nodes representing diverse vehicle components, we generated a dataset featuring Denial-of-Service (DoS) attacks by exploiting the arbitration feature of the CAN bus, which prioritizes high-criticality messages (e.g., engine control) over lower-criticality ones (e.g., infotainment). We trained and evaluated several machine learning models for their ability to detect attacks and pinpoint the responsible node. Results indicate that Gradient Boosting outperformed other models, achieving high accuracy in both attack detection and node identification. While the Multi-Layer Perceptron (MLP) model demonstrated strong attack detection performance, it struggled with node identification, achieving less than 50% accuracy. These findings underscore the potential of tree-based models for real-time IDS applications in CAN-enabled vehicles.

This paper addresses the increasing demand for efficient and scalable streaming service applications within the context of edge computing, utilizing NVIDIA Jetson Xavier NX hardware and Docker. The study evaluates the performance of DeepStream and Simple Realtime Server, demonstrating that containerized applications can achieve performance levels comparable to traditional physical machines. The results indicate that WebRTC provides superior low-latency capabilities, achieving delays of around 5 s, while HLS typically experiences delays exceeding 10 s. Performance tests reveal that CPU usage for WebRTC can exceed 40%, which is higher than that of HLS and RTMP, while memory usage remains relatively stable across different streaming protocols. Additionally, load testing shows that the system can support multiple simultaneous connections, but performance degrades significantly with more than three devices, highlighting the limitations of the current hardware setup. Overall, the findings contribute valuable insights into building efficient edge computing architectures that support real-time video processing and streaming.

The distributed nature of IoT systems and new trends focusing on fog computing enforce the need for reliable communication that ensures the required quality of service for various scenarios. Due to the direct interaction with the real world, failure to deliver the required QoS level can introduce system failures and lead to further negative consequences for users. This paper introduces a prediction-based resource allocation method for Multi-Access Edge Computing-capable networks, aimed at assurance of the required QoS and optimization of resource utilization for various types of IoT use cases featuring adaptability to changes in users' requests. The method considers the current resource load and predicted changes in resource utilization based on historical request data, which are then utilized to adjust the resource allocation optimization criteria for upcoming requests. The proposed method was developed for scenarios utilizing edge computing, e.g., autonomous vehicle data exchange, which can be susceptible to periodic resource demand fluctuations related to typical rush hours, predictable with the proposed approach. The results indicate that the proposed approach can increase the reliability of processes conducted in IoT systems.

Conventional endoscopy is limited in its ability to examine the small bowel and perform long-term monitoring due to the risk of infection and tissue perforation. Wireless Capsule Endoscopy (WCE) is a painless and non-invasive method of examining the body's internal organs using a small camera that is swallowed like a pill. The existing active locomotion technologies do not have a practical localization system to control the capsule's movement within the body. A robust localization system is essential for safely guiding the WCE device through the complex gastrointestinal (GI) tract. Moreover, having access to the capsule's trajectory data is highly desirable for drug delivery and surgery, as well as for creating accurate user profiles for diagnosis and future reference. Therefore, a robust, real-time, and practical localization system is imperative to advance the field of WCE and make it desirable for clinical trials. In this work, we have identified salient features of different localization techniques and categorized studies in comprehensive tables. This study is self-contained as it offers a comprehensive overview of emerging localization techniques based on magnetic field, radio frequency (RF), video, and hybrid methods. A summary at the end of each method is provided to point out the potential gaps and give directions for future research. The main point of this work is to present an in-depth review of the most recent localization techniques published in the past five years. This will assist researchers in comprehending current techniques and pinpointing potential areas for further investigation. This review can be a significant reference and guide for future research on WCE localization.

Impedance-based biosensing has emerged as a critical technology for high-sensitivity biomolecular detection, yet traditional approaches often rely on bulky, costly impedance analyzers, limiting their portability and usability in point-of-care applications. Addressing these limitations, this paper proposes an advanced biosensing system integrating a Silicon Nanowire Field-Effect Transistor (SiNW-FET) biosensor with a high-gain amplification circuit and a 1D Convolutional Neural Network (CNN) implemented on FPGA hardware. This attempt combines SiNW-FET biosensing technology with FPGA-implemented deep learning noise reduction, creating a compact system capable of real-time viral detection with minimal computational latency. The integration of a 1D CNN model on FPGA hardware for adaptive, non-linear noise filtering sets this design apart from conventional filtering approaches by achieving high accuracy and low power consumption in a portable format. This integration of SiNW-FET with FPGA-based CNN noise reduction offers a unique approach, as prior noise reduction techniques for biosensors typically rely on linear filtering or digital smoothing, which lack adaptive capabilities for complex, non-linear noise patterns. By introducing the 1D CNN on FPGA, this architecture enables real-time, high-fidelity noise reduction, preserving critical signal characteristics without compromising processing speed. Notably, the findings presented in this work are based exclusively on comprehensive simulations using COMSOL and MATLAB, as no physical prototypes or biomarker detection experiments were conducted. The SiNW-FET biosensor, functionalized with antibodies specific to viral antigens, detects impedance shifts caused by antibody-antigen interactions, providing a highly sensitive platform for viral detection. A high-gain folded-cascade amplifier enhances the Signal-to-Noise Ratio (SNR) to approximately 70 dB, verified through COMSOL and MATLAB simulations. Additionally, a 1D CNN model is employed for adaptive noise reduction, filtering out non-linear noise patterns and achieving an approximate 75% noise reduction across a broad frequency range. The CNN model, implemented on an Altera DE2 FPGA, enables high-throughput, low-latency signal processing, making the system viable for real-time applications. Performance evaluations confirmed the proposed system's capability to enhance the SNR significantly while maintaining a compact and energy-efficient design suitable for portable diagnostics. This integrated architecture thus provides a powerful solution for high-precision, real-time viral detection, and continuous health monitoring, advancing the role of biosensors in accessible point-of-care diagnostics.

The proliferation of the Internet of Things (IoT) has worsened the challenge of maintaining data and user privacy. IoT end devices, often deployed in unsupervised environments and connected to open networks, are susceptible to physical tampering and various other security attacks. Thus, robust, efficient authentication and key agreement (AKA) protocols are essential to protect data privacy during exchanges between end devices and servers. The previous work in "Provably Secure ECC-Based Anonymous Authentication and Key Agreement for IoT" proposed a novel AKA scheme for secure IoT environments. They claimed their protocol offers comprehensive security features, guarding against numerous potential flaws while achieving session key security. However, this paper demonstrates through logical and mathematical analyses that the previous work is vulnerable to various attacks. We conducted a security analysis using the extended Canetti and Krawczyk (eCK) model, which is widely employed in security evaluations. This model considers scenarios where an attacker has complete control over the network, including the ability to intercept, modify, and delete messages, while also accounting for the potential exposure of ephemeral private keys. Furthermore, we show that their scheme fails to meet critical security requirements and relies on flawed security assumptions. We prove our findings using the automated validation of internet security protocols and applications, a widely recognized formal verification tool. To strengthen attack resilience, we propose several recommendations for the advancement of more robust and efficient AKA protocols specifically designed for IoT environments.

This paper provides the complete details of current challenges and solutions in the cybersecurity of cyber-physical systems (CPS) within the context of the IIoT and its integration with edge computing (IIoT-edge computing). We systematically collected and analyzed the relevant literature from the past five years, applying a rigorous methodology to identify key sources. Our study highlights the prevalent IIoT layer attacks, common intrusion methods, and critical threats facing IIoT-edge computing environments. Additionally, we examine various types of cyberattacks targeting CPS, outlining their significant impact on industrial operations. A detailed taxonomy of primary security mechanisms for CPS within IIoT-edge computing is developed, followed by a comparative analysis of our approach against existing research. The findings underscore the widespread vulnerabilities across the IIoT architecture, particularly in relation to DoS, ransomware, malware, and MITM attacks. The review emphasizes the integration of advanced security technologies, including machine learning (ML), federated learning (FL), blockchain, blockchain-ML, deep learning (DL), encryption, cryptography, IT/OT convergence, and digital twins, as essential for enhancing the security and real-time data protection of CPS in IIoT-edge computing. Finally, the paper outlines potential future research directions aimed at advancing cybersecurity in this rapidly evolving domain.

The effects of mechanical vibrations on control system stability could be significant in control systems designed on the assumption of rigid-body dynamics, such as launch vehicles. Vibrational loads can also cause damage to launch vehicles due to fatigue or excitation of structural resonances. This paper investigates a method to control structural vibrations in real time using a finite number of strain measurements from a fiber Bragg grating (FBG) sensor array. A scaled test article representative of the structural dynamics associated with an actual launch vehicle was designed and built. The main modal frequencies of the test specimen are extracted from finite element analysis. A model of the test article is developed, including frequency response, thruster dynamics, and sensor conversion matrices. A model-based robust controller is presented to minimize vibrations in the test article by using FBG measurements to calculate the required thrust in two cold gas actuators. Controller performance is validated both in simulation and on experiments with the proposed test article. The proposed controller achieves a 94% reduction in peak-peak vibration in the first mode, and 80% reduction in peak-peak vibration in the second mode, compared to the open loop response under continuously excited base motion.

Android malware detection remains a critical issue for mobile security. Cybercriminals target Android since it is the most popular smartphone operating system (OS). Malware detection, analysis, and classification have become diverse research areas. This paper presents a smart sensing model based on large language models (LLMs) for developing and classifying network traffic-based Android malware. The network traffic that constantly connects Android apps may contain harmful components that may damage these apps. However, one of the main challenges in developing smart sensing systems for malware analysis is the scarcity of traffic data due to privacy concerns. To overcome this, a two-step smart sensing model Syn-detect is proposed. The first step involves generating synthetic TCP malware traffic data with malicious content using GPT-2. These data are then preprocessed and used in the second step, which focuses on malware classification. This phase leverages a fine-tuned LLM, Bidirectional Encoder Representations from Transformers (BERT), with classification layers. BERT is responsible for tokenization, generating word embeddings, and classifying malware. The Syn-detect model was tested on two Android malware datasets: CIC-AndMal2017 and CIC-AAGM2017. The model achieved an accuracy of 99.8% on CIC-AndMal2017 and 99.3% on CIC-AAGM2017. The Matthew's Correlation Coefficient (MCC) values for the predictions were 99% for CIC-AndMal2017 and 98% for CIC-AAGM2017. These results demonstrate the strong performance of the Syn-detect smart sensing model. Compared to the latest research in Android malware classification, the model outperformed other approaches, delivering promising results.

In recent years, significant progress has been achieved in understanding and processing tabular data. However, existing approaches often rely on task-specific features and model architectures, posing challenges in accurately extracting table structures amidst diverse layouts, styles, and noise contamination. This study introduces a comprehensive deep learning methodology that is tailored for the precise identification and extraction of rows and columns from document images that contain tables. The proposed model employs table detection and structure recognition to delineate table and column areas, followed by semantic rule-based approaches for row extraction within tabular sub-regions. The evaluation was performed on the publicly available Marmot data table datasets and demonstrates state-of-the-art performance. Additionally, transfer learning using VGG-19 is employed for fine-tuning the model, enhancing its capability further. Furthermore, this project fills a void in the Marmot dataset by providing it with extra annotations for table structure, expanding its scope to encompass column detection in addition to table identification.

Over recent years, automated Human Activity Recognition (HAR) has been an area of concern for many researchers due to its widespread application in surveillance systems, healthcare environments, and many more. This has led researchers to develop coherent and robust systems that efficiently perform HAR. Although there have been many efficient systems developed to date, still, there are many issues to be addressed. There are several elements that contribute to the complexity of the task, making it more challenging to detect human activities, i.e., (i) poor lightning conditions; (ii) different viewing angles; (iii) intricate clothing styles; (iv) diverse activities with similar gestures; and (v) limited availability of large datasets. However, through effective feature extraction, we can develop resilient systems for higher accuracies. During feature extraction, we aim to extract unique key body points and full-body features that exhibit distinct attributes for each activity. Our proposed system introduces an innovative approach for the identification of human activity in outdoor and indoor settings by extracting effective spatio-temporal features, along with a Multi-Class Support Vector Machine, which enhances the model's performance to accurately identify the activity classes. The experimental findings show that our model outperforms others in terms of classification, accuracy, and generalization, indicating its efficient analysis on benchmark datasets. Various performance metrics, including mean recognition accuracy, precision, F1 score, and recall assess the effectiveness of our model. The assessment findings show a remarkable recognition rate of around 88.61%, 87.33, 86.5%, and 81.25% on the BIT-Interaction dataset, UT-Interaction dataset, NTU RGB + D 120 dataset, and PKUMMD dataset, respectively., Competing Interests: The authors declare no conflicts of interest.

Future 7G/8G networks are expected to integrate both terrestrial Internet and space-based networks. Space networks, including inter-planetary Internet such as cislunar and deep-space networks, will become an integral part of future 7G/8G networks. Vehicle-to-everything (V2X) communication networks will also be a significant component of 7G/8G networks. Therefore, space networks will eventually integrate with V2X communication networks, with both space vehicles (or spacecrafts) and terrestrial vehicles involved. DTN is the only candidate networking technology for future heterogeneous space communication networks. In this work, we study possible concatenations of different DTN convergence layer protocol adapters (CLAs) over a cislunar relay communication architecture. We present a performance characterization of the concatenations of different CLAs and the associated data transport protocols in an experimental manner. The performance of different concatenations is compared over a typical primary and secondary cislunar relay architecture. The intent is to find out which network relay path and DTN protocol configuration has the best performance over the end-to-end cislunar path.

Recently, computer vision methods have been widely applied to agricultural tasks, such as robotic harvesting. In particular, fruit harvesting robots often rely on object detection or segmentation to identify and localize target fruits. During the model selection process for object detection, the average precision (AP) score typically provides the de facto standard. However, AP is not intuitive for determining which model is most efficient for robotic harvesting. It is based on the intersection-over-union (IoU) of bounding boxes, which reflects only regional overlap. IoU alone cannot reliably predict the success of robotic gripping, as identical IoU scores may yield different results depending on the overlapping shape of the boxes. In this paper, we propose a novel evaluation metric for robotic harvesting. To assess gripping success, our metric uses the center coordinates of bounding boxes and a margin hyperparameter that accounts for the gripper's specifications. We conducted evaluation about popular object detection models on peach and apple datasets. The experimental results showed that the proposed gripping success metric is much more intuitive and helpful in interpreting the performance data., Competing Interests: The authors declare no conflicts of interest.

In mission-critical environments such as industrial and military settings, the use of unmanned vehicles is on the rise. These scenarios typically involve a ground control system (GCS) and nodes such as unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs). The GCS and nodes exchange different types of information, including control data that direct unmanned vehicle movements and sensor data that capture real-world environmental conditions. The GCS and nodes communicate wirelessly, leading to loss or delays in control and sensor data. Minimizing these issues is crucial to ensure nodes operate as intended over wireless links. In dynamic networks, distributed path calculation methods lead to increased network traffic, as each node independently exchanges control messages to discover new routes. This heightened traffic results in internal interference, causing communication delays and data loss. In contrast, software-defined networking (SDN) offers a centralized approach by calculating paths for all nodes from a single point, reducing network traffic. However, shifting from a distributed to a centralized approach with SDN does not inherently guarantee faster route creation. The speed of generating new routes remains independent of whether the approach is centralized, so SDN does not always lead to faster results. Therefore, a key challenge remains: determining how to create new routes as quickly as possible even within an SDN framework. This paper introduces a caching technique for forwarding rules based on predicted link states in SDN, which was named the CRIMSON (Cashing Routing Information in Mobile SDN Network) algorithm. The CRIMSON algorithm detects network link state changes caused by node mobility and caches new forwarding rules based on predicted topology changes. We validated that the CRIMSON algorithm consistently reduces end-to-end latency by an average of 88.96% and 59.49% compared to conventional reactive and proactive modes, respectively.

Today, huge amounts of time series data are sensed continuously by AIoT devices, transmitted to edge nodes, and to data centers. It costs a lot of energy to transmit these data, store them, and process them. Data compression technologies are commonly used to reduce the data size and thus save energy. When a certain level of data accuracy is sacrificed, lossy compression technologies can achieve better compression ratios. However, different applications may have different requirements for data accuracy. Instead of keeping multiple compressed versions of a time series w.r.t. different error bounds, HIRE hierarchically maintains a tree, where the root records a constant function to approximate the whole time series, and each other node records a constant function to approximate a part of the residual function of its parent for a particular time period. To retrieve data w.r.t. a specific error bound, it traverses the tree from the root down to certain levels according to the requested error bound and aggregates the constant functions on the visited nodes to generate a new bounded error compressed version dynamically. However, the number of nodes to be visited is unknown before the tree traversal completes, and thus the data size of the new version. In this paper, a time series is progressively decomposed into multiple piecewise linear functions. The first function is an approximation of the original time series w.r.t. the largest error bound. The second function is an approximation of the residual function between the original time series and the first function w.r.t. the second largest error bound, and so forth. The sum of the first, second, …, and m -th functions is an approximation of the original time series w.r.t. the m -th error bound. For each iteration, Swing-RR is used to generate a Bounded Error Piecewise Linear Approximation (BEPLA). Resolution Reduction (RR) plays an important role. Eight real-world datasets are used to evaluate the proposed method. For each dataset, approximations w.r.t. three typical error bounds, 5%, 1%, and 0.5%, are requested. Three BEPLAs are generated accordingly, which can be summed up to form three approximations w.r.t. the three error bounds. For all datasets, the total data size of the three BEPLAs is almost the same with the size used to store just one version w.r.t. the smallest error bound and significantly smaller than the size used to keep three independent versions. The experiment result shows that the proposed method, referred to as PBEPLA-RR, can achieve very good compression ratios and provide multiple approximations w.r.t. different error bounds.

In the current era of advanced IoT technology, human occupancy monitoring and positioning technology is widely used in various scenarios. For example, it can optimize passenger flow in public transportation systems, enhance safety in large shopping malls, and adjust smart home devices based on the location and number of occupants for energy savings. Additionally, in homes requiring special care, it can provide timely assistance. However, this technology faces limitations such as privacy concerns, environmental factors, and costs. Traditional cameras may not effectively address these issues, but infrared thermal sensors can offer similar applications while overcoming these challenges. Infrared thermal sensors detect the infrared heat emitted by the human body, protecting privacy and functioning effectively day and night with low power consumption, making them ideal for continuous monitoring scenarios like security systems or elderly care. In this study, we propose a system using the AMG8833, an 8 × 8 Infrared Thermal Array Sensor. The sensor data are processed through interpolation, adaptive thresholding, and blob detection, and the merged human heat signatures are separated. To enhance stability in human position estimation, a dynamic sliding window adjusts its size based on movement speed, effectively handling environmental changes and uncertainties.

The major task of a wireless sensor network (WSN) is data collection. Key predistribution (KP) is to establish pairwise keys for secure communication in a WSN, such that all collected data could be securely sent to a backend database. Most research on KP-like schemes is dedicated to enhancing resiliency against node capture attack (NA) and retaining the link connectivity in the meantime. For large-scale wireless sensor networks, a more common approach is to use a multiple-sink WSN (MWSN) to support a large number of sensor nodes. In MWSNs, there are different clusters (referred to as groups). We took the lead in studying KP in the MWSN environment. Based on the new MWSN environment, we present intragroup and intergroup KP (I 2 KP) to fulfill both requirements of security and energy efficiency when gathering data via various sink nodes in a large-scale WSN. Three types of I 2 KP with respective pros and cons are proposed. Theoretical analysis and numerical simulation demonstrate their effectiveness.

The Internet of Things (IoT) has seen remarkable advancements in recent years, leading to a paradigm shift in the digital landscape. However, these technological strides have introduced new challenges, particularly in cybersecurity. IoT devices, inherently connected to the internet, are susceptible to various forms of attacks. Moreover, IoT services often handle sensitive user data, which could be exploited by malicious actors or unauthorized service providers. As IoT ecosystems expand, the convergence of traditional and cloud-based systems presents unique security threats in the absence of uniform regulations. Cloud-based IoT systems, enabled by Platform-as-a-Service (PaaS) and Infrastructure-as-a-Service (IaaS) models, offer flexibility and scalability but also pose additional security risks. The intricate interaction between these systems and traditional IoT devices demands comprehensive strategies to protect data integrity and user privacy. This paper highlights the pressing security concerns associated with the widespread adoption of IoT devices and services. We propose viable solutions to bridge the existing security gaps while anticipating and preparing for future challenges. This paper provides a detailed survey of the key security challenges that IoT services are currently facing. We also suggest proactive strategies to mitigate these risks, thereby strengthening the overall security of IoT devices and services.

Precision depth estimation plays a key role in many applications, including 3D scene reconstruction, virtual reality, autonomous driving and human-computer interaction. Through recent advancements in deep learning technologies, monocular depth estimation, with its simplicity, has surpassed the traditional stereo camera systems, bringing new possibilities in 3D sensing. In this paper, by using a single camera, we propose an end-to-end supervised monocular depth estimation autoencoder, which contains an encoder with a structure with a mixed convolution neural network and vision transformers and an effective adaptive fusion decoder to obtain high-precision depth maps. In the encoder, we construct a multi-scale feature extractor by mixing residual configurations of vision transformers to enhance both local and global information. In the adaptive fusion decoder, we introduce adaptive fusion modules to effectively merge the features of the encoder and the decoder together. Lastly, the model is trained using a loss function that aligns with human perception to enable it to focus on the depth values of foreground objects. The experimental results demonstrate the effective prediction of the depth map from a single-view color image by the proposed autoencoder, which increases the first accuracy rate about 28% and reduces the root mean square error about 27% compared to an existing method in the NYU dataset.

Reconfigurable Intelligent Surface (RIS) panels have garnered significant attention with the emergence of next-generation network technologies. This paper proposes a novel data-driven approach that leverages Light Detecting and Ranging (LiDAR) sensors to enhance user localization and beamforming in RIS-assisted networks. Integrating LiDAR sensors into the network will be instrumental, offering high-speed and precise 3D mapping capabilities, even in low light or adverse weather conditions. LiDAR data facilitate user localization, enabling the determination of optimal RIS coefficients. Our approach extends a Graph Neural Network (GNN) by integrating LiDAR-captured user locations as inputs. This extension enables the GNN to effectively learn the mapping from received pilots to optimal beamformers and reflection coefficients to maximize the RIS-assisted sumrate among multiple users. The permutation-equivariant and -invariant properties of the GNN proved advantageous in efficiently handling the LiDAR data. Our simulation results demonstrated significant improvements in sum rates compared with conventional methods. Specifically, including locations improved on excluding locations by up to 25% and outperformed the Linear Minimum Mean Squared Error (LMMSE) channel estimation by up to 85% with varying downlink power and 98% with varying pilot lengths, and showed a remarkable 190% increase with varying downlink power compared with scenarios excluding the RIS.

In this paper, we propose a method for applying the p -ary m-sequence as a channel-searching pattern for rendezvous in the asymmetric channel model of cognitive radio. We mathematically analyzed and calculated the ETTR when the m-sequence is applied to the conventional scheme, and our simulation results demonstrated that the ETTR performance is significantly better than that of the JS algorithm. Furthermore, we introduced a new channel-searching scheme that maximizes the benefits of the m-sequence and proposed a method to adapt the generation of the m-sequence for use in the newly proposed scheme. We also derived the ETTR mathematically for the new scheme with the m-sequence and showed through simulations that the performance of the new scheme with the m-sequence is superior to that of the conventional scheme with the m-sequence. Notably, when there is only one common channel, the new scheme with the m-sequence achieved approximately four times the improvement in the ETTR compared to the conventional scheme.

Distributed fiber optic sensors (DFOSs) have become increasingly popular for intrusion detection, particularly in outdoor and restricted zones. Enhancing DFOS performance through advanced signal processing and deep learning techniques is crucial. While effective, conventional neural networks often involve high complexity and significant computational demands. Additionally, the backscattering method requires the signal to travel twice the normal distance, which can be inefficient. We propose an innovative interferometric sensing approach utilizing a Mach-Zehnder interferometer (MZI) combined with a time forest neural network (TFNN) for intrusion detection based on signal patterns. This method leverages advanced sensor characterization techniques and deep learning to improve accuracy and efficiency. Compared to the conventional one-dimensional convolutional neural network (1D-CNN), our proposed approach achieves an 8.43% higher accuracy, demonstrating the significant potential for real-time signal processing applications in smart environments.

With the fast-fashion trend, an increasing number of discarded clothing items are being eliminated at the stages of both pre-consumer and post-consumer each year. The linear economy produces large volumes of waste, which harm environmental sustainability. This study addresses the pressing need for efficient textile recycling in the circular economy (CE). We developed a highly accurate Raman-spectroscopy-based textile-sorting technology, which overcomes the challenge of diverse fiber combinations in waste textiles. By categorizing textiles into six groups based on their fiber compositions, the sorter improves the quality of recycled fibers. Our study demonstrates the potential of Raman spectroscopy in providing detailed molecular compositional information, which is crucial for effective textile sorting. Furthermore, AI technologies, including PCA, KNN, SVM, RF, ANN, and CNN, are integrated into the sorting process, further enhancing the efficiency to 1 piece per second with a precision of over 95% in grouping textiles based on the fiber compositional analysis. This interdisciplinary approach offers a promising solution for sustainable textile recycling, contributing to the objectives of the CE.

The Internet of Things (IoT) contains many devices that can compute and communicate, creating large networks. Industrial Internet of Things (IIoT) represents a developed application of IoT, connecting with embedded technologies in production in industrial operational settings to offer sophisticated automation and real-time decisions. Still, IIoT compels significant cybersecurity threats beyond jamming and spoofing, which could ruin the critical infrastructure. Developing a robust Intrusion Detection System (IDS) addresses the challenges and vulnerabilities present in these systems. Traditional IDS methods have achieved high detection accuracy but need improved scalability and privacy issues from large datasets. This paper proposes a Fog-enabled Federated Learning-based Intrusion Detection System (FFL-IDS) utilizing Convolutional Neural Network (CNN) that mitigates these limitations. This framework allows multiple parties in IIoT networks to train deep learning models with data privacy preserved and low-latency detection ensured using fog computing. The proposed FFL-IDS is validated on two datasets, namely the Edge-IIoTset, explicitly tailored to environments with IIoT, and CIC-IDS2017, comprising various network scenarios. On the Edge-IIoTset dataset, it achieved 93.4% accuracy, 91.6% recall, 88% precision, 87% F1 score, and 87% specificity for jamming and spoofing attacks. The system showed better robustness on the CIC-IDS2017 dataset, achieving 95.8% accuracy, 94.9% precision, 94% recall, 93% F1 score, and 93% specificity. These results establish the proposed framework as a scalable, privacy-preserving, high-performance solution for securing IIoT networks against sophisticated cyber threats across diverse environments.

The analysis of running gait has conventionally taken place within an expensive and restricted laboratory space, with wearable technology offering a practical, cost-effective, and unobtrusive way to examine running gait in more natural environments. This pilot study presents a wearable inertial measurement unit (IMU) setup for the continuous analysis of running gait during an outdoor parkrun (i.e., 5 km). The study aimed to (1) provide analytical validation of running gait measures compared to time- and age-graded performance and (2) explore performance validation. Ten healthy adults (7 females, 3 males, mean age 37.2 ± 11.7 years) participated. The participants wore Axivity AX6 IMUs on the talus joint of each foot, recording tri-axial accelerometer and gyroscope data at 200 Hz. Temporal gait characteristics-gait cycle, ground contact time, swing time, and duty factor-were extracted using zero-crossing algorithms. The data were analyzed for correlations between the running performance, foot strike type, and fatigue-induced changes in temporal gait characteristics. Strong correlations were found between the performance time and both the gait cycle and ground contact time, with weak correlations for foot strike types. The analysis of asymmetry and fatigue highlighted modest changes in gait as fatigue increased, but no significant gender differences were found. This setup demonstrates potential for in-field gait analysis for running, providing insights for performance and injury prevention strategies.

This research work presents an integrated method leveraging Convolutional Neural Networks and Recurrent Neural Networks (CNN-RNN) to enhance the accuracy of predictive maintenance and fault detection in DC motor drives of industrial robots. We propose a new hybrid deep learning framework that combines CNNs with RNNs to improve the accuracy of fault prediction that may occur on a DC motor drive during task processing. The CNN-RNN model determines the optimal maintenance strategy based on data collected from sensors, such as air temperature, process temperature, rotational speed, and so forth. The proposed AI model has the capacity to make highly accurate predictions and detect faults in DC motor drives, thus helping to ensure timely maintenance and reduce operational breakdowns. As a result, comparative analysis reveals that the proposed framework can achieve higher accuracy than the current existing method of combining CNN with Long Short-Term Memory networks (CNN-LSTM) as well as other CNNs, LSTMs, and traditional methods. The proposed CNN-RNN model can provide early fault detection for motor drives of industrial robots with a simpler architecture and lower complexity of the model compared to CNN-LSTM methods, which can enable the model to process faster than CNN-LSTM. It effectively extracts dynamic features and processes sequential data, achieving superior accuracy and precision in fault diagnosis, which can make it a practical and efficient solution for real-time fault detection in motor drive control systems of industrial robots.

Epilepsy, as a common brain disease, causes great pain and stress to patients around the world. At present, the main treatment methods are drug, surgical, and electrical stimulation therapies. Electrical stimulation has recently emerged as an alternative treatment for reducing symptomatic seizures. This study proposes a novel closed-loop epilepsy detection system and stimulation control chip. A time-domain detection algorithm based on amplitude, slope, line length, and signal energy characteristics is introduced. A new threshold calculation method is proposed; that is, the threshold is updated by means of the mean and standard deviation of four consecutive eigenvalues through parameter combination. Once a seizure is detected, the system begins to control the stimulation of a two-phase pulse current with an amplitude and frequency of 34 μA and 200 Hz, respectively. The system is physically designed on the basis of the UMC 55 nm process and verified by a field programmable gate array verification board. This research is conducted through innovative algorithms to reduce power consumption and the area of the circuit. It can maintain a high accuracy of more than 90% and perform seizure detection every 64 ms. It is expected to provide a new treatment for patients with epilepsy.

This paper introduces a novel methodology for evaluating communication performance in rotating electric machines using Received Signal Strength Indication (RSSI) measurements coupled with artificial intelligence. The proposed approach focuses on assessing the quality of wireless signals in the complex, dynamic environment inside these machines, where factors like reflections, metallic surfaces, and rotational movements can significantly impact communication. RSSI is used as a key parameter to monitor real-time signal behavior, enabling a detailed analysis of communication reliability. The methodology comprises several stages, including data collection, preprocessing, feature extraction, and model training. Various machine learning models are implemented and evaluated. Among these, the SVM model with a Radial Basis Function (RBF) kernel outperforms others, achieving an accuracy of 97%, with high precision and recall scores, confirming its robustness in classifying RSSI data and handling complex signal behavior. The confusion matrix further supports the SVM model's accuracy, showing minimal misclassification.

Multi-modal systems extract information about the environment using specialized sensors that are optimized based on the wavelength of the phenomenology and material interactions. To maximize the entropy, complementary systems operating in regions of non-overlapping wavelengths are optimal. VIS-IR (Visible-Infrared) systems have been at the forefront of multi-modal fusion research and are used extensively to represent information in all-day all-weather applications. Prior to image fusion, the image pairs have to be properly registered and mapped to a common resolution palette. However, due to differences in the device physics of image capture, information from VIS-IR sensors cannot be directly correlated, which is a major bottleneck for this area of research. In the absence of camera metadata, image registration is performed manually, which is not practical for large datasets. Most of the work published in this area assumes calibrated sensors and the availability of camera metadata providing registered image pairs, which limits the generalization capability of these systems. In this work, we propose a novel end-to-end pipeline termed DeepFusion for image registration and fusion. Firstly, we design a recursive crop and scale wavelet spectral decomposition (WSD) algorithm for automatically extracting the patch of visible data representing the thermal information. After data extraction, both the images are registered to a common resolution palette and forwarded to the DNN for image fusion. The fusion performance of the proposed pipeline is compared and quantified with state-of-the-art classical and DNN architectures for open-source and custom datasets demonstrating the efficacy of the pipeline. Furthermore, we also propose a novel keypoint-based metric for quantifying the quality of fused output.

Climate change caused by greenhouse gas (GHG) emissions is an escalating global issue, with the transportation sector being a significant contributor, accounting for approximately a quarter of all energy-related GHG emissions. In the transportation sector, vehicle emissions testing is a key part of ensuring compliance with environmental regulations. The Vehicle Certification Agency (VCA) of the UK plays a pivotal role in certifying vehicles for compliance with emissions and safety standards. One of the primary methods employed by the VCA to measure vehicle emissions for light-duty vehicles is the Worldwide Harmonized Light Vehicles Test Procedure (WLTP). The WLTP is a global standard for testing vehicle emissions and fuel consumption, and sensors are crucial in ensuring accurate, real-time data collection in laboratories. Using the data collected by the VCA, regression machine learning models were trained to predict CO 2 emissions in light-duty vehicles. Among six regression models tested, the Decision Tree Regression model achieved the highest accuracy, with a Mean Absolute Error (MAE) of 2.20 and a Mean Absolute Percentage Error (MAPE) of 1.69%. It was then deployed as a web application that provides users with accurate CO 2 emission estimates for vehicles, enabling informed decisions to reduce GHG emissions. This research demonstrates the efficacy of machine learning and AI-driven approaches in fostering sustainability within the transportation sector., Competing Interests: The authors declare no conflict of interest.

Unmanned aerial vehicle (UAV)-enabled vehicular communications in the sixth generation (6G) are characterized by line-of-sight (LoS) and dynamically varying channel conditions. However, the presence of obstacles in the LoS path leads to shadowed fading environments. In UAV-assisted cellular vehicle-to-everything (C-V2X) communication, vehicle and UAV mobility and shadowing adversely impact latency and throughput. Moreover, 6G vehicular communications comprise data-intensive applications such as augmented reality, mixed reality, virtual reality, intelligent transportation, and autonomous vehicles. Since vehicles' sensors generate immense amount of data, the latency in processing these applications also increases, particularly when the data are not independently identically distributed (non-i.i.d.). Furthermore, when the sensors' data are heterogeneous in size and distribution, the incoming packets demand substantial computing resources, energy efficiency at the UAV servers and intelligent mechanisms to queue the incoming packets. Due to the limited battery power and coverage range of UAV, the quality of service (QoS) requirements such as coverage rate, UAV flying time, and fairness of vehicle selection are adversely impacted. Controlling the UAV trajectory so that it serves a maximum number of vehicles while maximizing battery power usage is a potential solution to enhance QoS. This paper investigates the system performance and communication disruption between vehicles and UAV due to Doppler effect in the orthogonal time-frequency space (OTFS) modulated channel. Moreover, a low-complexity UAV trajectory prediction and vehicle selection method is proposed using federated learning, which exploits related information from past trajectories. The weighted total energy consumption of a UAV is minimized by jointly optimizing the transmission window (Lw), transmit power and UAV trajectory considering Doppler spread. The simulation results reveal that the weighted total energy consumption of the OTFS-based system decreases up to 10% when combined with federated learning to locally process the sensor data at the vehicles and communicate the processed local models to the UAV. The weighted total energy consumption of the proposed federated learning algorithm decreases by 10-15% compared with convex optimization, heuristic, and meta-heuristic algorithms.

The proposed protocol features reliable and fast image transmission while periodically transmitting scalar data without interruption by allowing two networks, a LoRa network and a wireless sensor network, with different transmission characteristics to cooperate. It adopts the RT-LoRa protocol for periodic scalar data transmission and uses a WSN-based pipelined transmission method that leverages single-hop message transmission of a LoRa network for image transmission. Thus, it can not only eliminate the control message overhead for time synchronization, slot scheduling, and path establishment for pipelined image transmission in WSNs but also eliminate interferences within WSNs, such as data collisions and data and message collisions, during pipelined image transmission, thereby enabling high reliability and fast transmission. According to experimental results obtained inside a university building, the proposed protocol achieved an image transfer rate of approximately 96% without packet loss, transmitted one 24 KB image in approximately 0.3 s, and achieved an image transfer rate of 100% under the tolerance of one image packet loss. These results indicate a speedup of about 25% compared to a recent pipelined protocol while ensuring near-perfect image transmission quality.

Simultaneous localization and mapping (SLAM) techniques can be used to navigate the visually impaired, but the development of robust SLAM solutions for crowded spaces is limited by the lack of realistic datasets. To address this, we introduce InCrowd-VI, a novel visual-inertial dataset specifically designed for human navigation in indoor pedestrian-rich environments. Recorded using Meta Aria Project glasses, it captures realistic scenarios without environmental control. InCrowd-VI features 58 sequences totaling a 5 km trajectory length and 1.5 h of recording time, including RGB, stereo images, and IMU measurements. The dataset captures important challenges such as pedestrian occlusions, varying crowd densities, complex layouts, and lighting changes. Ground-truth trajectories, accurate to approximately 2 cm, are provided in the dataset, originating from the Meta Aria project machine perception SLAM service. In addition, a semi-dense 3D point cloud of scenes is provided for each sequence. The evaluation of state-of-the-art visual odometry (VO) and SLAM algorithms on InCrowd-VI revealed severe performance limitations in these realistic scenarios. Under challenging conditions, systems exceeded the required localization accuracy of 0.5 m and the 1% drift threshold, with classical methods showing drift up to 5-10%. While deep learning-based approaches maintained high pose estimation coverage (>90%), they failed to achieve real-time processing speeds necessary for walking pace navigation. These results demonstrate the need and value of a new dataset to advance SLAM research for visually impaired navigation in complex indoor environments.

Freezing of wind turbines causes loss of wind-generated power. Forecasting or prediction of icing on wind turbine blades based on SCADA sensor data allows taking appropriate actions before icing occurs. This paper presents a newly developed deep learning network model named PCTG (Parallel CNN-TCN GRU) for the purpose of high-accuracy and long-term prediction of icing on wind turbine blades. This model combines three networks, the CNN, TCN, and GRU, in order to incorporate both the temporal aspect of SCADA time-series data as well as the dependencies of SCADA variables. The experimentations conducted by using this model and SCADA data from three wind turbines in a wind farm have generated average prediction accuracies of about 97% for prediction horizons of up to 2 days ahead. The developed model is shown to maintain at least 95% prediction accuracy for long prediction horizons of up to 22 days ahead. Furthermore, for another wind farm SCADA dataset, it is shown that the developed PCTG model achieves over 99% icing prediction accuracy 10 days ahead.

This systematic review examines EEG-based imagined speech classification, emphasizing directional words essential for development in the brain-computer interface (BCI). This study employed a structured methodology to analyze approaches using public datasets, ensuring systematic evaluation and validation of results. This review highlights the feature extraction techniques that are pivotal to classification performance. These include deep learning, adaptive optimization, and frequency-specific decomposition, which enhance accuracy and robustness. Classification methods were explored by comparing traditional machine learning with deep learning and emphasizing the role of brain lateralization in imagined speech for effective recognition and classification. This study discusses the challenges of generalizability and scalability in imagined speech recognition, focusing on subject-independent approaches and multiclass scalability. Performance benchmarking across various datasets and methodologies revealed varied classification accuracies, reflecting the complexity and variability of EEG signals. This review concludes that challenges remain despite progress, particularly in classifying directional words. Future research directions include improved signal processing techniques, advanced neural network architectures, and more personalized, adaptive BCI systems. This review is critical for future efforts to develop practical communication tools for individuals with speech and motor impairments using EEG-based BCIs.

Several approaches have been developed to generate synthetic object points using real LiDAR point cloud data for advanced driver-assistance system (ADAS) applications. The synthetic object points generated from a scene (both the near and distant objects) are essential for several ADAS tasks. However, generating points from distant objects using sparse LiDAR data with precision is still a challenging task. Although there are a few state-of-the-art techniques to generate points from synthetic objects using LiDAR point clouds, limitations such as the need for intense compute power still persist in most cases. This paper suggests a new framework to address these limitations in the existing literature. The proposed framework contains three major modules, namely position determination, object generation, and synthetic annotation. The proposed framework uses a spherical point-tracing method that augments 3D LiDAR distant objects using point cloud object projection with point-wall generation. Also, the pose determination module facilitates scenarios such as platooning carried out by the synthetic object points. Furthermore, the proposed framework improves the ability to describe distant points from synthetic object points using multiple LiDAR systems. The performance of the proposed framework is evaluated on various 3D detection models such as PointPillars, PV-RCNN, and Voxel R-CNN for the KITTI dataset. The results indicate an increase in mAP (mean average precision) by 1.97%, 1.3%, and 0.46% from the original dataset values of 82.23%, 86.72%, and 87.05%, respectively.

This study investigated the relationship between stepping-defined daily activity levels, time spent in different postures, and the patterns and intensities of stepping behaviour. Using a thigh-mounted triaxial accelerometer, physical activity data from 3547 participants with seven days of valid data were analysed. We classified days based on step count and quantified posture and stepping behaviour, distinguishing between indoor, community, and recreation stepping. The results indicated significant differences in time spent in upright (2.5 to 8.9 h, p < 0.05), lying (8.0 to 9.1 h, p < 0.05), and sedentary (7.0 to 13.0 h, p < 0.05) postures across activity levels. At higher daily activity levels (10,000-15,000 steps), individuals tended to spend approximately equal time in each posture (8 h lying, 8 h sitting, and 8 h upright). The study found that at lower stepping-defined activity levels, step volumes were driven primarily by indoor stepping, while at higher activity levels, outdoor and recreation stepping were larger contributors. Additionally, stepping classified as indoor had significantly slower cadences compared to outdoor stepping. These findings suggest that the composition and intensity of stepping behaviours vary significantly with daily activity volumes, providing insights that could enhance public health messaging and interventions aimed at promoting physical activity.

Early identification of concrete cracks and multi-class detection can help to avoid future deformation or collapse in concrete structures. Available traditional detection and methodologies require enormous effort and time. To overcome such difficulties, current vision-based deep learning models can effectively detect and classify various concrete cracks. This study introduces a novel multi-stage deep learning framework for crack detection and type classification. First, the recently developed YOLOV10 model is trained to detect possible defective regions in concrete images. After that, a modified vision transformer (ViT) model is trained to classify concrete images into three main types: normal, simple cracks, and multi-branched cracks. The evaluation process includes feeding concrete test images into the trained YOLOV10 model, identifying the possible defect regions, and finally delivering the detected regions into the trained ViT model, which decides the appropriate crack type of those detected regions. Experiments are conducted using the individual ViT model and the proposed multi-stage framework. To improve the generation ability, multi-source datasets of concrete structures are used. For the classification part, a concrete crack dataset consisting of 12,000 images of three classes is utilized, while for the detection part, a dataset composed of various materials from historical buildings containing 1116 concrete images with their corresponding bounding boxes, is utilized. Results prove that the proposed multi-stage model accurately classifies crack types with 90.67% precision, 90.03% recall, and 90.34% F1-score. The results also show that the proposed model outperforms the individual classification model by 10.9%, 19.99%, and 19.2% for precision, recall, and F1-score, respectively. The proposed multi-stage YOLOV10-ViT model can be integrated into the construction systems which are based on crack materials to obtain early warning of possible future deformation in concrete structures.

In the field of muscle fatigue models (MFMs), the prior research has demonstrated success in fitting data in specific contexts, but it falls short in addressing the diverse efforts and rapid changes in exertion typical of soccer matches. This study builds upon the existing model, aiming to enhance its applicability and robustness to dynamic demand shifts. The objective is to encapsulate the complexities of soccer dynamics with a streamlined set of parameters. Our refined model achieved a slight improvement in the R2 score in the maximum hand-grip test, increasing from 0.87 to 0.89 compared to the existing model. It also demonstrated dynamic change robustness in a soccer-specific 1 min drill and 15 min treadmill protocol extracted from the literature. Through individualized fitting on a 10-repetition 80 m sprint test for a soccer player, the model exhibited R2 scores between 0.62 and 0.80. Furthermore, when tested with actual soccer match data, it maintained a robust performance, with the average R2 scores ranging from 0.70 to 0.72. The proposed approach holds the potential to advance the understanding of tactical decisions by correlating them with real-time physical performance, offering opportunities for more informed strategies and ultimately enhancing team performance.

Contemporary environmental challenges are increasingly significant. The primary cause is the drastic changes in climates. The prediction of solar radiation is a crucial aspect of solar energy applications and meteorological forecasting. The amount of solar radiation reaching Earth's surface (Global Horizontal Irradiance, GHI) varies with atmospheric conditions, geographical location, and temporal factors. This paper presents a novel methodology for estimating surface sun exposure using advanced deep learning techniques. The proposed method is tested and validated using the data obtained from NASA's Goddard Earth Sciences Data and Information Services Centre (GES DISC) named the SORCE (Solar Radiation and Climate Experiment) dataset. For analyzing and predicting accurate data, features are extracted using a deep learning method, Deep-FS. The method extracted and provided the selected features that are most appropriate for predicting the surface exposure. Time series analysis was conducted using Convolutional Neural Networks (CNNs), with results demonstrating superior performance compared to traditional methodologies across standard performance metrics. The proposed Deep-FS model is validated and compared with the traditional approaches and models through the standard performance metrics. The experimental results concluded that the proposed model outperforms the traditional models.

This paper presents a lens-free imaging approach utilizing an array of light sources, capable of measuring the dielectric properties of many particles simultaneously. This method employs coplanar electrodes to induce velocity changes in flowing particles through dielectrophoretic forces, allowing the inference of individual particle properties from differential velocity changes. Both positive and negative forces are detectable. The light source utilized in this system is composed of LEDs with a wavelength of 470 nm, while detection is performed using a 256-element optical array detector. Measurements with 10 μm polystyrene beads demonstrate this method can resolve changes equivalent to a Clausius-Mossotti factor of 0.18. Simulations in this work, using values from the literature, predict that Clausius-Mossotti factor differences of 0.18 are sufficient to differentiate viable from nonviable cells and cancerous from multidrug-resistant cancerous cells. We demonstrate that for Chinese hamster ovary (CHO) cells, the method can collect a dielectric response spectrum for a large number of cells in several minutes. We demonstrate that for CHO cells, Clausius-Mossotti factor differences of 0.18 can be discriminated. Due to its simple detection apparatus and the utilization of high-throughput, wide, clog-resistant channels, this method holds promise for a wide range of applications.

In this paper, a sub-1dB Low Noise Amplifier (LNA) with several gain modes, including amplification and attenuation modes required for the fifth and fourth generations (5G/4G) of mobile network applications, is proposed. Its current consumption is adaptive for every gain mode and varies to lower currents for lower amplifications due to the importance of current consumption for mobile network applications. The proposed LNA features an innovative architecture with a three-core input structure supporting multi-gain modes, achieving high gain and ultra-low noise performance. Additionally, the design integrates a cascade switching mechanism to ensure fast transitions between the gain modes and maintain operational stability. A reconfigurable input structure is introduced to support multiple input stages, enabling the proposed LNA to be compatible with both 5G and 4G applications. The proposed design demonstrates the implementation of seven distinct gain modes with a maximum current consumption of 11.68 mA, achieving proper input matching in each gain mode. The LNA delivers a maximum gain of 20.4 dB with a noise figure of 0.73 dB. Moreover, the most stringent mode switching condition achieved, the ON time, is as short as 1.295 µs, and the gain mode transition speed is an impressive 0.874 µs, ensuring extremely fast mode transitions. The proposed LNA occupies an area of 700 µm × 500 µm and is fabricated using a 65 nm FD-SOI process., Competing Interests: Authors KyungDuk Choi, Sung Hwan Paik, KyungJin Lee, DongMin Kim, SangSun Yoo and KangYoon Lee were employed by the company SKAIChips. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

This paper presents a comprehensive review of path planning in dynamic environments. This review covers the entire process, starting from obstacle detection techniques, through path-planning strategies, and also extending to formation control and communication styles. The review discusses the key trends, challenges, and gaps in current methods to emphasize the need for more efficient and robust algorithms that can handle complex and unpredictable dynamic environments. Moreover, it discusses the importance of collaborative decision making and communication between robots to optimize path planning in dynamic scenarios. This work serves as a valuable resource for advancing research and practical applications in dynamic obstacle navigation.

As proximity-aware services among devices such as sensors, IoT devices, and user equipment are expected to facilitate a wide range of new applications in the beyond 5G and 6G era, managing heterogeneous environments with diverse node capabilities becomes essential. This paper analytically models and characterizes the performance of heterogeneous random access-based wireless mutual broadcast (RA-WMB) with distinct transmit (Tx) power levels, leveraging a marked Poisson point process to account for nodes' various Tx power. In particular, this study enables the performance of RA-WMB with heterogeneous Tx power to be represented in terms of the performance of RA-WMB with a common Tx power by deriving an equivalent Tx power based on the probability distribution of heterogeneous Tx power and the path loss exponent. This approach allows for an analytical and quantitative comparison of heterogeneous RA-WMB performance with the common Tx power configuration. Further, the study derives performance ratios among node groups with distinct Tx power levels and formulates an optimization problem to design a heterogeneous Tx power configuration that balances individual node group performance improvements with overall network performance, yielding the optimal Tx power configuration. A closed-form suboptimal transmission probability (TxPr) is also proposed to improve heterogeneous RA-WMB performance, providing an efficient alternative to iterative methods for the optimal TxPr. Numerical results demonstrate the accuracy of performance analysis and highlight the effectiveness of the proposed designs.