Search Results (221)

This paper aims to address the problem of the low success rate of seedling picking and throwing, and the high damage rate of pot seedling, caused by the unclear interaction and parameter mismatch between the seedling picking end effector and the pot seedling during the seedling picking and throwing process of automatic transplanters. An EDEM–RecurDyn coupled simulation was conducted, through which the disturbance of substrate particles in the bowl body during the inserting, extracting, and transporting processes by the seedling picking end effector was visualized and analyzed. The force and motion responses of the particles during their interaction with the seedling picking end effector were explored, and the working parameters of the seedling picking end effector were optimized. A seedling picking end effector using two fingers and four needles is taken as the research object, a kinematic mathematical model of the seedling picking end effector is established, and the dimensional parameters of each component of the end effector are determined. Physical characteristic tests are conducted on Shanghai bok choy pot seedlings to obtain relevant parameters. A discrete element model of the pot seedling is established in EDEM 2022 software, and a virtual prototype model of the seedling picking end effector is established in Recurdyn 2024 software. Through EDEM-Recurdyn coupled simulation, the force and movement of the substrate particles in the bowl body during the inserting, extracting, and transporting processes of the seedling picking end effector under different operating parameters were explored, providing a theoretical basis for optimizing the working parameters of the end effector. The inserting and extracting velocity, transporting velocity, and inserting depth of the seedling picking end effector were used as experimental factors, and the success rate of seedling picking and throwing, and the loss rate of substrate, were used as evaluation indicators; single-factor tests and three-factor, three-level Box–Behnken bench tests were conducted. Variance analysis, response surface methodology, and multi-objective optimization were performed using Design-Expert 13 software to obtain the optimal parameter combination: when the inserting and extracting velocity was 228 mm/s, the transporting velocity was 264 mm/s, the inserting depth was 37 mm, the success rate of seedling picking and throwing was 97.48%, and the loss rate of substrate was 2.12%. A verification experiment was conducted on the bench, and the success rate of seedling picking and throwing was 97.35%, and the loss rate of substrate was 2.34%, which was largely consistent with the optimized results, thereby confirming the rationality of the established model and optimized parameters. Field trial showed the success rate of seedling picking and throwing was 97.04%, and the loss rate of substrate was 2.41%. The error between the success rate of seedling picking and throwing and the optimized result was 0.45%, indicating that the seedling picking end effector has strong anti-interference ability, and verifying the feasibility and practicality of the established model and optimized parameters. Full article

With the rapid development of the power Internet of Things (IoT), the traditional manual inspection mode can no longer meet the growing demand for power equipment inspection. Unmanned aerial vehicle (UAV) intelligent inspection technology, with its efficient and flexible features, has become the mainstream solution. The rapid development of computer vision and deep learning (DL) has significantly improved the accuracy and efficiency of UAV intelligent inspection systems for power equipment. However, mainstream deep learning models have complex structures, and manual design is time-consuming and labor-intensive. In addition, the images collected during the power inspection process by UAVs have problems such as complex backgrounds, uneven lighting, and significant differences in object sizes, which require expert DL domain knowledge and many trial-and-error experiments to design models suitable for application scenarios involving power inspection with UAVs. In response to these difficult problems, evolutionary computation (EC) technology has demonstrated unique advantages in simulating the natural evolutionary process. This technology can independently design lightweight and high-precision deep learning models by automatically optimizing the network structure and hyperparameters. Therefore, this review summarizes the development of evolutionary deep learning (EDL) technology and provides a reference for applying EDL in object detection models used in UAV intelligent power inspection systems. First, the application status of DL-based object detection models in power inspection is reviewed. Then, how EDL technology improves the performance of the models in challenging scenarios such as complex terrain and extreme weather is analyzed by optimizing the network architecture. Finally, the challenges and future research directions of EDL technology in the field of UAV power inspection are discussed, including key issues such as improving the environmental adaptability of the model and reducing computing energy consumption, providing theoretical references for promoting the development of UAV power inspection technology to a higher level. Full article

The artificial generation of text by computers has been a field of study in computer science since the beginning of the twentieth century, from Markov chains to Turing tests. This has evolved into automatic summarization and marketing chatbots. The generation of literary texts by Large Language Models (LLMs) has also been an area of scholarly inquiry for over six decades. The literary quality of AI-generated text can be evaluated with GrAImes, an evaluation protocol grounded in literary theory and inspired by the editorial process of book publishers. This evaluation can also be framed as part of broader editorial practices within publishing, emphasizing both theoretical grounding and applied assessment. This protocol necessitates the involvement of human judges to validate the texts generated, a process that is often resource-intensive in terms of both time and financial investment, primarily due to the specialized credentials and expertise required of these evaluators. In this paper, we propose an alternative approach by employing LLMs themselves as evaluators within the GrAImes framework. We apply this methodology to assess human-written and AI-generated microfictions in Spanish, to five PhD professors in literature and sixteen literary enthusiasts, and to short stories in both Spanish and English. By comparing the evaluations performed by LLMs with those of human judges, we examine the degree of alignment and divergence between both perspectives, thereby assessing the feasibility of LLMs as auxiliary literary evaluators. Our analysis focuses on the alignment of responses from LLMs with those of human evaluators, providing insights into the potential of LLMs in literary assessment. The conducted experiments reveal that while LLMs cannot be regarded as substitutes for human judges in the evaluation of literary microfictions and short stories, with a Krippendorff’a alpha reliability coefficient less than 0.66, they can serve as a valuable tool that offers an initial perspective on the editorial quality of the texts in question. Overall, this study contributes to the ongoing discourse on the role of artificial intelligence in literature, underlining both its methodological constraints and its potential as a complementary resource for literary evaluation. Full article

Accelerographs are essential instruments for quantifying strong ground motion, serving as the foundation of modern earthquake engineering. In Peru, the first accelerographic station was installed in Lima in 1944; since then, various institutions have promoted the expansion of the national network. However, this network’s spatial coverage and instrumentation remain insufficient to properly characterize strong motion and support seismic risk reduction policies. In this context, the KUYUY accelerograph is presented as a low-cost, low-noise device equipped with real-time telemetry and high-performance MEMS sensors. Its interoperability with the Intelligent Automatic Processing System (SIPA) enables real-time monitoring and automated signal analysis for seismic microzonation studies and rapid damage assessment, contributing to seismic risk reduction in Peru. The validation process included static gravity calibration, field comparison with a reference accelerograph, and an initial deployment in Lima and Yurimaguas. The results demonstrate the proposed accelerograph’s linear response, temporal stability, and amplitude consistency with respect to high-end instruments, with differences below 5–10%. Full article

To address the challenges of low automatic leveling efficiency and insufficient control precision for small tracked operation chassis navigating uneven terrain in hilly and mountainous areas, this study proposes a leveling control system that integrates a dual-layer threshold strategy with a BP neural network algorithm. The system is developed based on a four-point lifting leveling mechanism. Building upon this foundation, the conventional single-threshold angle error compensation control strategy was optimized to meet the specific leveling demands of chassis operating in such complex environments. A co-simulation platform was established using Matlab/Simulink-AMEsim for subsequent simulation and comparative analysis. Simulation results demonstrate that the proposed method achieves a 15.6% improvement in leveling response speed and a 21.3% enhancement in leveling accuracy compared to the classical single-threshold PID control algorithm. Static test results reveal a smooth leveling process devoid of significant overshoot or hysteresis, with the leveling error consistently maintained within 0.5°. Field tests further indicate that at a travel speed of 3 km/h under a 50 kg load, the platform stabilization time is reduced by an average of 1.3 s, while the leveling angle error remains within 0.5°. The proposed system not only improves leveling response speed and precision but also effectively enhances the overall leveling efficiency of the tracked chassis system. Full article

Labor shortages and reliance on manual seedling transplanting constrain pepper production from meeting market demand. To address this mechanization gap, the development of new agricultural machinery is an urgent priority. This study presented kinematic modeling and field validation of an automatic link-driven hopper planting unit for a 3.4 kW walking-type pepper transplanter under development. Kinematic behavior of the hopper was analyzed through mathematical modeling and dynamic simulation and validated under actual transplanting conditions under ridge-patterned field. The optimal design (crank length: 75 mm; 60 rpm) achieved a stable elliptical trajectory that enabled synchronized seedling pickup, tray release, and soil deposition while maintaining vertical alignment. Under this setup, the hopper followed a stable elliptical trajectory (166.88 mm × 318.81 mm), with supply and deposition coordinates of approximately (321 mm, −322 mm) and (293 mm, −617 mm), and peak velocities and accelerations within 0.47 m/s and 1.68 m/s², respectively. Field results showed that the proposed mechanism enabled reliable transplanting performance, achieving a mean planting depth of 27.06 ± 8.18 mm and an uprightness angle of 80.03 ± 7.56°, which fall within agronomic requirements for early pepper establishment. The overall defect rate was low (7.17 ± 3.73%), leading to a 92.83 ± 3.73% success rate at a throughput of 24 seedlings min⁻¹. Variety-dependent responses were observed: Kaltan seedlings exhibited lower defect rates and greater stability than Shinhung seedlings, highlighting the importance of plug strength and stem rigidity in automated systems. These results demonstrate that the mechanism supports fully automated transplanting with acceptable agronomic quality and provides practical design guidance for advancing mechanized pepper production. Full article

Urban railway bridges are critical components of modern transportation networks. Dynamic loads and harsh environments put urban railway bridges at high risk of damage. Conventional vibration-based damage detection approaches often fail to provide sufficient accuracy and robustness under complex urban conditions. To address this limitation, this study introduces a hybrid deep learning framework that integrates a one-dimensional convolutional neural network (1D-CNN) and a recurrent neural network (RNN) for automatic damage detection using Linear Variable Differential Transformer (LVDT) displacement data. Start with the calibration of a finite element model (FEM) of the target bridge, achieved through updating the model parameters to align with field-acquired LVDT data, thereby establishing a robust and reliable baseline representation of the structure’s behaviour. Subsequently, a series of failure and damage scenarios is introduced within the FEM, and the associated dynamic displacement responses are generated to construct a comprehensive synthetic training dataset. These time-series responses serve as input for training a hybrid deep learning architecture, which integrates a one-dimensional convolutional neural network (1D-CNN) for automated feature extraction with a recurrent neural network (RNN) designed to capture the temporal dependencies inherent in the structural response data. Results show rapid convergence and minimal error in single-damage cases, and robust performance in multi-damage conditions on a dataset exceeding 5 million samples; the model attains a mean absolute error of ≈3.2% for damage severity and an average localisation error of <0.7 m. The findings highlight the effectiveness of combining numerical simulation with advanced data-driven approaches to provide a practical, data-efficient, and scalable solution for structural health monitoring in the urban railway context. Full article

To address the issues of high labor intensity, high missed harvest rates, and high damage rates associated with traditional subsurface crop harvesters, this paper takes carrots as the research object and designs an automatic row-following device based on collaborative perception and intelligent control. Firstly, the physical characteristic parameters and planting agronomic requirements of carrots in a harvest period were systematically measured and analyzed, and a collaborative control architecture with ‘lateral row-following and longitudinal profiling’ as the core was established. The architecture was composed of a lateral detection mechanism and a ridge surface floating detection mechanism. Building on this, this paper designed a control system with a STC12C5A60S2 single-chip microcomputer as the control core and a fusion fuzzy PID algorithm. By collaboratively driving the lateral and vertical stepper motors, the system achieved a precise control of the digging device’s position and posture, significantly improving the response speed and control stability under complex ridge conditions. Through the simulation of SolidWorks (2019) and RecurDyn (2023), the structural reliability and dynamic profiling effect of key components were validated from both static and dynamic perspectives, respectively. The parameter optimization results based on the response surface method show that the lateral motor speed and the forward speed are the dominant factors affecting the lateral accuracy and the vertical accuracy, respectively. Under the optimal parameter combination, the mean lateral deviation of the device measured in the field test was 1.118 cm, and the standard deviation was 0.257 cm. The mean vertical deviation is 0.986 cm, and the standard deviation is 0.016 cm. This study provides a feasible technical solution for the mechanized agronomic operation of carrots and other subsurface crops. Full article

Modern companies often rely on integrating an extensive network of suppliers to organize and produce industrial artifacts. Within this process, it is critical to maintain sustainability and flexibility by analyzing and managing information from the supply chain. In particular, there is a continuous demand to automatically analyze and infer information from extensive datasets structured in various forms, such as natural language and domain-specific models. The advancement of Large Language Models (LLM) presents a promising solution to address this challenge. By leveraging prompts that contain the necessary information provided by humans, LLM can generate insightful responses through analysis and reasoning over the provided content. However, the quality of these responses is still affected by the inherent opaqueness of LLM, stemming from their complex architectures, thus weakening their trustworthiness and limiting their applicability across different fields. To address this issue, this work presents a framework to leverage the graph-based LLM to support the analysis of supply chain information by combining the LLM and domain knowledge. Specifically, this work proposes an integration of LLM and domain knowledge to support an analysis of the supply chain as follows: (1) constructing a graph-based knowledge base to describe and model the domain knowledge; (2) creating prompts to support the retrieval of the graph-based models and guide the generation of LLM; (3) generating responses via LLM to support the analysis and reason about information across the supply chain. We demonstrate the proposed framework in the tasks of entity classification, link prediction, and reasoning across entities. Compared to the average performance of the best methods in the comparative studies, the proposed framework achieves a significant improvement of 59%, increasing the ROUGE-1 F1 score from 0.42 to 0.67. Full article

AI-based educational chatbots can expand access to learning, but many remain limited to text-only interfaces and fixed infrastructures, while purely generative responses raise concerns of reliability and consistency. In this context, we present ROboMC, a portable and multimodal system that combines a validated knowledge base with generative responses (OpenAI) and voice–text interaction, designed to enable both text and voice interaction, ensuring reliability and flexibility in diverse educational scenarios. The system, developed in Django, integrates two response pipelines: local search using normalized keywords and fuzzy matching in the LocalQuestion database, and fallback to the generative model GPT-3.5-Turbo (OpenAI, San Francisco, CA, USA) with a prompt adapted exclusively for Romanian and an explicit disclaimer. All interactions are logged in AutomaticQuestion for later analysis, supported by a semantic encoder (SentenceTransformer—paraphrase-multilingual-MiniLM-L12-v2’, Hugging Face Inc., New York, NY, USA) that ensures search tolerance to variations in phrasing. Voice interaction is managed through gTTS (Google LLC, Mountain View, CA, USA) with integrated audio playback, while portability is achieved through deployment on a Raspberry Pi 4B (Raspberry Pi Foundation, Cambridge, UK) with microphone, speaker, and battery power. Voice input is enabled through a cloud-based speech-to-text component (Google Web Speech API accessed via the Python SpeechRecognition library, (Anthony Zhang, open-source project, USA) using the Google Web Speech API (Google LLC, Mountain View, CA, USA; language = “ro-RO”)), allowing users to interact by speaking. Preliminary tests showed average latencies of 120–180 ms for validated responses on laptop and 250–350 ms on Raspberry Pi, respectively, 2.5–3.5 s on laptop and 4–6 s on Raspberry Pi for generative responses, timings considered acceptable for real educational scenarios. A small-scale usability study (N ≈ 35) indicated good acceptability (SUS ~80/100), with participants valuing the balance between validated and generative responses, the voice integration, and the hardware portability. Although system validation was carried out in the eHealth context, its architecture allows extension to any educational field: depending on the content introduced into the validated database, ROboMC can be adapted to medicine, engineering, social sciences, or other disciplines, relying on ChatGPT only when no clear match is found in the local base, making it a scalable and interdisciplinary solution. Full article

Natural disasters occur continuously across the globe, posing severe threats to human life and property. Remote sensing technology has provided powerful technical means for large-scale and rapid disaster monitoring. However, the deep integration of remote sensing observations with sector-specific disaster statistical data to construct a knowledge system that supports early warning decision-making remains a significant challenge. This study aims to address the bottleneck in the “data-information-knowledge-service” transformation process by constructing an integrated natural disaster early warning knowledge graph that incorporates multi-source heterogeneous data. We first designed an ontological schema layer comprising six core elements: disaster type, event, anomaly information, impact information, warning information, and decision information. Subsequently, multi-source data were integrated from various sources, including the Emergency Events Database (EM-DAT), sector-specific websites, encyclopedic pages, and remote sensing imagery such as Gaofen-2 (GF-2) and Sentinel-1. A Bidirectional Encoder Representations from Transformers with a Conditional Random Field layer (BERT-CRF) model was employed for entity and relation extraction, and the knowledge was stored and visualized using the Neo4j graph database. The core innovation of this research lies in proposing a quantitative methodology for assessing disaster intensity, impact, and trends based on remote sensing evaluation, establishing a knowledge conversion mechanism with sector-specific warning levels, and designing explicit warning issuance rules. A case study on a specific wildfire event (2017-0417-PRT, Coimbra, Portugal) demonstrates that the knowledge graph not only achieves organic integration and visual querying of multi-source disaster knowledge but also facilitates warning decision-making driven by remote sensing assessment indicators. For this event, quantitative analysis of Gaofen-2 imagery yielded intensity, impact, and trend levels of 4, 3, and 3, respectively, which, when applied to our warning rule (intensity ≥ 1 or impact ≥ 1 or trend ≥ 3), automatically triggered an early warning, thereby validating the rule’s practicality. A preliminary performance evaluation on 50 historical wildfire events demonstrated promising results, with an F1-score of 74.3% and an average query response time of 128 ms, confirming the system’s practical responsiveness and detection capability. In conclusion, this study offers a novel and operational technical pathway for the deep interdisciplinary integration of remote sensing and disaster science, effectively bridging the gap between data silos and actionable warning knowledge. Full article

Collecting crop growth data in field environments is crucial for breeding research. The team’s current autonomous soybean phenotyping system requires manual control to start and stop data collection. To address the aforementioned issues, this study innovatively proposes an elliptical calibration rotating geofencing technique. Preprocess coordinates using Z-scores and mean fitting perform global error calibration via weighted least squares, calculate the inclination angle between the row direction and the relative standard direction by fitting a straight line to the same row of data, and establish a rotation model based on geometric feature alignment. Results show that the system achieves an average response time of 0.115 s for geofence entry, with perfect accuracy and Recall rates of 1, meeting the requirements for starting and stopping geographic fencing in soybean ridge trial plots. This technology provides the critical theoretical foundation for enabling a dynamic, on-demand automatic start–stop functionality in smart data collection devices for soybean field trial zones within precision agriculture. Full article

The high spatiotemporal resolution of optically pumped magnetometers (OPMs) makes them an essential tool for functional brain imaging, enabling accurate recordings of neuronal activity. However, physiological signals such as eye blinks and cardiac activity overlap with neural magnetic signals in the frequency domain, resulting in contamination and creating challenges for the observation of brain activity and the study of neurological disorders. To address this problem, an automatic physiological artifact removal method based on OPM magnetic reference signals and a channel attention mechanism is proposed. The randomized dependence coefficient (RDC) is employed to evaluate the correlation between independent components and reference signals, enabling reliable recognition of artifact components and the construction of training and testing datasets. A channel attention mechanism is subsequently introduced, which fuses features from global average pooling (GAP) and global max pooling (GMP) layers through convolution to establish a data-driven automatic recognition model. The backbone network is further optimized to enhance performance. Experimental results demonstrate a strong correlation between the magnetic reference signals and artifact components, confirming the reliability of magnetic signals as artifact references for OPM-MEG. The proposed model achieves an artifact recognition accuracy of 98.52% and a macro-average score of 98.15%. After artifact removal, both the event-related field (ERF) responses and the signal-to-noise ratio (SNR) are significantly improved. Leveraging the flexible and modular characteristics of OPM-MEG, this study introduces an artifact recognition framework that integrates magnetic reference signals with an attention mechanism. This approach enables highly accurate automatic recognition and removal of OPM-MEG artifacts, paving the way for real-time, automated data analysis in both scientific research and clinical applications. Full article

In field exploration, disaster rescue, and complex terrain operations, the accuracy of ground type recognition directly affects the walking stability and task execution efficiency of legged robots. To address the problem of terrain recognition in complex ground environments, this paper proposes a high-precision classification method based on single-leg triaxial force signals. The method first employs a one-dimensional convolutional neural network (1D-CNN) module to extract local temporal features, then introduces a long short-term memory (LSTM) network to model long-term and short-term dependencies during ground contact, and incorporates a convolutional block attention module (CBAM) to adaptively enhance the feature responses of critical channels and time steps, thereby improving discriminative capability. In addition, an improved whale optimization algorithm (iBWOA) is adopted to automatically perform global search and optimization of key hyperparameters, including the number of convolution kernels, the number of LSTM units, and the dropout rate, to achieve the optimal training configuration. Experimental results demonstrate that the proposed method achieves excellent classification performance on five typical ground types—grass, cement, gravel, soil, and sand—under varying slope and force conditions, with an overall classification accuracy of 96.94%. Notably, it maintains high recognition accuracy even between ground types with similar contact mechanical properties, such as soil vs. grass and gravel vs. sand. This study provides a reliable perception foundation and technical support for terrain-adaptive control and motion strategy optimization of legged robots in real-world environments. Full article

It is widely recognized that mosquitoes are attracted to ultraviolet (UV) light traps in field and semi-field trials. However, the specific characteristics of mosquito behavioral responses to UV light remain poorly defined. Moreover, the molecular mechanisms underlying their phototactic behavior remain unexplored. Here, we characterized mosquito photobehavior under UV light in a laboratory setting using three experimental apparatuses. Our findings indicate that mosquitoes exhibit strong attraction to low-intensity UV light, yet show no preference between high-intensity UV light and darkness. Video recordings and automatic analyses of photobehavior under low-intensity UV light revealed that mosquitoes preferred the window illuminated by UV light over an unilluminated window and were more active when exposed to UV light. Through RNA interference (RNAi)-mediated knockdown of opsins highly expressed in the adult stage of Culex quinquefasciatus, we identified CqOpsin3, CqOpsin5, and CqOpsin6 as crucial mediators of UV phototaxis. This study provides methods for characterizing mosquito photobehavior under UV light in the laboratory, and represents the first mechanistic investigation into UV light-mediated attractive behavior in mosquitoes. Full article