Speed Precision Research Articles

Artificial intelligence in clinical genetics.

Artificial intelligence (AI) has been growing more powerful and accessible, and will increasingly impact many areas, including virtually all aspects of medicine and biomedical research. This review focuses on previous, current, and especially emerging applications of AI in clinical genetics. Topics covered include a brief explanation of different general categories of AI, including machine learning, deep learning, and generative AI. After introductory explanations and examples, the review discusses AI in clinical genetics in three main categories: clinical diagnostics; management and therapeutics; clinical support. The review concludes with short, medium, and long-term predictions about the ways that AI may affect the field of clinical genetics. Overall, while the precise speed at which AI will continue to change clinical genetics is unclear, as are the overall ramifications for patients, families, clinicians, researchers, and others, it is likely that AI will result in dramatic evolution in clinical genetics. It will be important for all those involved in clinical genetics to prepare accordingly in order to minimize the risks and maximize benefits related to the use of AI in the field.

Efeito da velocidade de semeadura e do lubrificante à base de grafite na plantabilidade da soja

ABSTRACT This study aimed to assess the efficiency of soybean seed distribution in the soil, which directly influences crop yield, using graphite as a solid lubricant, a common practice to improve seed dosing fluidity. The effect of sowing speed and seed chemical treatment on distribution in the furrow, final plant population, and yield was investigated. The experiment used Federer´s augmented block design with 10 treatments, five sowing speeds (4, 6, 8, 10, and 12 km h-1) and two seed treatments (with and without 4 g of graphite lubricant per kilogram of seeds). High sowing speeds increased uneven seed distribution, while graphite lubricant significantly improved plant spacing and crop yield. This study reinforces the importance of precise sowing speed adjustment and proper seed treatment to optimize soybean plant distribution in the field. Graphite lubricant proved to be effective at reducing spacing failures and increasing crop yield. These findings underscore the relevance of precision agriculture and the use of technology to ensure efficient and sustainable sowing operations.

Integrating Advanced Control Strategies for Enhanced Motor Efficiency in Robotics

Motor efficiency requires diversified paradigm integration to facilitate the advancement of robotics applications through precision, energy optimization, and reliability. Advanced control strategies like AI-driven predictive mechanisms, harmonic drive systems, and real-time feedback tools in motor performance underline the efficiency required in robotic technologies. As a collective role for robotic motors, the approaches enable precise torque and speed modulation, dynamic adaptability to environmental changes, and energy-efficient operation in controlled strategies. Understanding theoretical foundations in motor efficiency guides decisions on the selection and implementation of robotic technologies in the automation of industrial and manufacturing processes. Comparative robotic role analyses pinpoint optimization for the technology to harness dynamic responsiveness and energy utilization efficiency. The ways to implement advanced motor controls underscore the potential of combining intelligent algorithms with innovative motor designs to elevate robotics reliance in complex situations. The advanced control strategies showcase the need for efficiency, adaptability, and relevance of robotic solutions in trending technological applications.

Robust Formation Control for Unmanned Ground Vehicles Using Onboard Visual Sensors and Machine Learning

The performance of unmanned ground vehicle (UGV) formation is crucial for large-scale material transport. In a non-communicative environment, visual perception plays a central role in formation control. However, due to unstable lighting conditions, dust, fog, and visual occlusions, developing a high-precision visual formation control technology that does not rely on external markers remains a significant challenge in UGVs. This study developed a new UGV formation controller that relies solely on onboard visual sensors and proposed a teacher–student training method, TSTMIPI, combining the PPO algorithm with imitation learning, which significantly improves the control precision and convergence speed of the vision-based reinforcement learning formation controller. To further enhance formation control stability, we constructed a belief state encoder (BSE) based on convolutional neural networks, which effectively integrates visual perception and proprioceptive information. Simulation results show that the control strategy combining TSTMIPI and BSE not only eliminates the reliance on external markers but also significantly improves control precision under different noise levels and visual occlusion conditions, surpassing existing visual formation control methods in maintaining the desired distance and angular precision.

An Improved Pied Kingfisher Optimizer for Maritime UAV Path Planning

Maritime activities have become increasingly frequent with the deepening of economic globalization, highlighting the burgeoning significance of maritime rescue. However, in practical applications, UAVs for maritime rescue face numerous challenges, such as limited endurance and inadequate autonomous planning capabilities. To optimize flight routes and circumvent adverse sea conditions, an improved Pied Kingfisher Optimizer (IPKO) that incorporates refraction reverse learning, variable spiral search, and Cauchy mutation strategies was proposed. Comparative experiments conducted on CEC2005 and CEC2022 datasets with seven traditional algorithms demonstrate that the proposed algorithm exhibits superior precision and convergence speed. Subsequently, a path planning objective function was constructed based on trajectory cost and threat cost to simulate a 3D space for UAV maritime rescue missions, and the IPKO algorithm was applied to address the UAV path planning problem. The results showed that the total cost incurred by the IPKO algorithm decreased by 5.77% compared to the PKO algorithm and by 51.19% compared to the SCA algorithm. Finally, through UAV flight tests validating its practical applicability, it is ascertained that IPKO can enhance rescue efficiency in complex maritime rescue environments.

Low-Voltage Biological Electric Shock Fault Diagnosis Based on the Attention Mechanism Fusion Parallel Convolutional Neural Network/Bidirectional Long Short-Term Memory Model

Electric shock protection is critical for ensuring power safety in low-voltage grids, and robust fault diagnosis methods provide an essential foundation for the accurate operation of such protection devices. However, current low-voltage electric shock protection devices often suffer from limitations in operational precision and in their ability to effectively recognize electric shock types. To address these challenges, this paper proposes a fault diagnosis method for low-voltage electric shocks based on an attention-enhanced parallel CNN-BiLSTM model. The method first utilizes CNN to extract local spatial features of the electric shock signal and BiLSTM to capture temporal features. An attention mechanism is then introduced to fuse the local spatial and temporal features with weighted emphasis. Finally, a fully connected layer maps the fused features to the output layer, generating diagnostic results. Visualization through T-SNE analysis validates the improvement in model performance due to the attention mechanism. Comparative experiments show that the proposed model outperforms single models and other combined models in terms of accuracy, precision, recall, F1 score, and convergence speed. The results demonstrate that the proposed model achieves a fault diagnosis accuracy of 99.55%.

Multi-Class Sunflower Disease Detection by Integrating Enhanced Jellyfish Search Algorithm

Objectives: This research aims to classify diseases observed in sunflower flowers and leaves using deep learning algorithms. The goal is to enhance agricultural output by addressing the significant issue of plant diseases, which negatively affect the security of the food supply. Methods: The study utilizes a feature selection approach to identify multi-class sunflower diseases. The Enhanced Jellyfish Search (EJFSOA) algorithm is improved in three ways: (i) optimization capabilities and convergence speed are enhanced through sine and cosine learning variables during Type B motion in the swarm, (ii) a local escape operator is added to avoid the local optimization trap, improving the exploitability of the JS algorithm, and (iii) opposition-based learning and quasi-opposition learning strengthen the population distribution. A deep learning model, Multi-class Sunflower Network (MCSFNet), combines ResNets with TensorFlow for feature extraction, multi-label classification, and a multi-spectral stacking module. Findings: The proposed model is evaluated using several criteria, including accuracy, sensitivity, specificity, and F1-score. On a publicly available dataset, the algorithm achieves an average accuracy of 99.56%, outperforming state-of-the-art approaches with accuracies of 98.34% and 97.39%. Novelty: This work introduces improvements to the EJFSOA algorithm, significantly enhancing the precision and convergence speed of sunflower disease classification models. Combining deep learning with an optimized feature selection method leads to superior results in multi-class classification tasks. Keywords: Sunflower Leaves, Disease Detection, Enhanced jellyfish search, Local escape operator, Multi­class Sunflower Network, Residual Networks

Evaluating YOLO Models for Efficient Crack Detection in Concrete Structures Using Transfer Learning

The You Only Look Once (YOLO) network is considered highly suitable for real-time object detection tasks due to its characteristics, such as high speed, single-shot detection, global context awareness, scalability, and adaptability to real-world conditions. This work introduces a comprehensive analysis of various YOLO models for detecting cracks in concrete structures, aiming to assist in the selection of an optimal model for future detection and segmentation tasks. The YOLO models are initially trained on a dataset containing both images with and without cracks, producing a generalized model capable of extracting abstract features beneficial for crack detection. Subsequently, transfer learning is employed using a dataset that reflects real-world conditions, such as occlusions, varying crack sizes, and rotations, to further refine the model. Crack detection in concrete remains challenging due to the wide variation in crack sizes, aspect ratios, and complex backgrounds. To achieve optimal performance, we test different versions of YOLO, a state-of-the-art single-shot detector, and aim to balance inference speed and mean average precision (mAP). Our results indicate that YOLOv10 demonstrates superior performance, achieving a mean average precision (mAP) of 74.52% with an inference time of 19.5 milliseconds per image, making it the most effective among the models tested.

Hybrid Detection Model Combining an Advanced Q-Learning Network (AQN) and Attention-Enriched Transfer Learning Approach for DDoS Detection

Modern network systems are seriously threatened by distributed denial of service (DDoS) attacks, which call for sophisticated mitigation strategies. The proposed Advanced Q-learning network(AQN) [1] with an Attention-Enriched Transfer Learning (AETL) [2] is designed to integrate MixNet, Recurrent Neural Network (RNN), and MobileNetV3 with the aid of insights from an advanced classifier. The comprehensive methodology includes data collection, advanced normalization using Recursive Feature Elimination (RFE)[3], anomaly detection-driven data cleaning, and Deep Packet Inspection (DPI) [4]. To improve feature representation, temporal dependencies are captured using Long Short-Term Memory (LSTM) [5] networks and attention mechanisms Adding an attention mechanism, Q-Learning and transfer learning to improve previously trained models allows the suggested method to concentrate on important network traffic features that indicate possible DDoS attacks. The current analysis shows that low false rate in accuracy, precision, and detection speed in finding the mitigation strategies. The proposed model is tested on various datasets and in real-world network environments to confirm its scalability and resilience.

STGPT2UGAN: Spatio-Temporal GPT-2 United Generative Adversarial Network for Wind Speed Prediction in Turbine Network

In a turbine network, an accurate wind speed prediction plays a key role in improving the efficiency of turbine operations. At present, Large Language Models (LLMs) have shown their strong capabilities in time sequence forecasting. Unfortunately, the existing LLM-based models face the following two difficulties in precise wind speed prediction: (1) These models fail to capture spatio-temporal correlations. (2) These models rely exclusively on supervised learning to train. Supervised learning updates parameters by optimizing a loss function, which focuses solely on improving accuracy on a specific regression or classification task rather than understanding the true data distribution. To tackle these difficulties, we devise a novel wind speed prediction architecture entitled Spatio-Temporal GPT-2 United Generative Adversarial Network (STGPT2UGAN). In particular, in order to model spatio-temporal correlations, we first design a Spatio-Temporal GPT-2 (STGPT-2), which comprises a Spatio-Temporal Block and the variant of GPT-2. Second, to improve the training of STGPT-2, a Generative Adversarial Network (GAN) is introduced to develop an adversarial training strategy. The strategy combines unsupervised training and supervised training in a complementary fashion. The unsupervised training promotes STGPT-2 to learn the distribution of true data through minimizing the adversarial loss. The supervised training intends to align the true values and the predicted values. We conduct the experiments on one real-world wind speed dataset. The experimental results verify that STGPT2UGAN outperforms the state-of-the-art benchmarks in terms of prediction precision.

DEVELOPMENT AND APPLICATION OF STEER-BY-WIRE (SBW) WITH LINEAR SENSORS TO A SMALL ELECTRIC VEHICLE

A steer-by-wire (SBW) system with linear sensors has been developed and implemented on a small electric vehicle (EV). This system comprises a steering wheel, an angle and torque sensor, a wheel angle feedback sensor, an electric motor actuator, linkages, and a controller. It is specifically designed to electrically control the wheel angles without utilizing a conventional steering gearbox. The electric actuator motor is mounted on the steering mechanism and directly connected to the left and right wheel knuckles via linkages. Two linear sensors are employed: one located on the steering wheel to generate steering wheel angle signal , and the other installed on the wheel knuckle mechanism to produce front wheel angle feedback signal . When the driver rotates the steering wheel, the controller calculates the pitch error based on inputs from the two linear sensors and subsequently adjusts the wheel angles by powering the electric motor actuator. Experimental testing revealed a response time of 0.3 seconds, with the pitch error maintained within an angle of less than 3° during straight-motion tests. During cornering motion tests, the measured backlash was approximately 0.06 rad, demonstrating the system's responsive performance. This SBW technology with linear sensors is anticipated to reduce system complexity while enhancing precision, accuracy, and response speed of wheel angle adjustments to steering inputs, effectively meeting driving requirements.

Full-field dynamic strain reconstruction of rotating compressor blades based on FBG sensors

Abstract Rotating compressor blades experience complex alternating loads during service, altering their stress–strain distributions and peak stress positions over time. Accurate measurement of these strains is crucial for identifying the areas of stress concentration. This paper presents a structural health monitoring system using fiber Bragg grating (FBG) sensors to record dynamic strains on laboratory-scale rotating blades, and a tailored full-field strain reconstruction methodology, which successfully identifies the magnitude of the strains and the areas of stress concentration of the blades at different rotational speeds. First, dynamic strain at selected blade points was monitored using FBG sensors, with raw signal data enhanced by the empirical wavelet transform method to reduce noise and clarify signals. An analytical framework was developed to relate blade rotational velocity to signal period, enabling precise speed calculation and accurate strain analysis. The improved-Kriging interpolation technique was then used to reconstruct comprehensive strain profiles. A comparative analysis showed an average strain relative error of 7.4% between predicted and actual values, demonstrating the methodology’s robustness and precision.

Sensitivity Analysis of a Stator Current-based MRAS Estimator for Sensorless Induction Motor Drives

The sensitivity of speed estimators for parameter variations presents a significant challenge for sensorless Induction Motor (IM) drives, particularly at very low speeds. This paper examines the impact of parameter variations and the PI adaptation mechanism on the stator current-based Model Reference Adaptive System (MRAS). In contrast to the estimation of rotor flux, the MRAS method uses the observed stator current and the stator current estimate error within the adjustable IM model. The stability analysis for changes in machine parameters and PI controller gains is examined using small-signal perturbation. Additionally, a sensitivity analysis of stator and rotor resistance changes is included. A complete simulation using MATLAB/Simulink and experimental validation using a laboratory prototype based on the DSP-DS1103 are provided. The analytical, modeling, and measurement results reveal that the suggested observer responds well and provides precise speed estimation in all four quadrants of operation.

Medical Image Classification Using DL-based Feature Extraction in IoMT

Aim:: Recent advances in Artificial Intelligence (AI) and the addition of Deep Learning (DL) have made it possible to analyse both real-time and historical data from the Internet of Things (IoT). Recently, IoT technology has been implemented in healthcare schemes as IoMT to aid in medical diagnoses. Medical image classification is useful for predicting and identifying serious diseases at an early stage, which is crucial in the diagnostic process. Background:: When it comes to managing, treating, and preventing illness, medical photographs are an essential element of a patient’s health record. However, it is a difficult issue in computer-based diagnostics to classify images using efficient characteristics. Objective:: The study aimed to develop a deep learning-based classification model for feature extraction. Methods:: Levy flight optimization is employed to pick the weight for the classification model optimally. At the end of the day, the optimal weight led to a better classification result and a higher degree of precision when analyzing medical photos for disease. Result:: We tested the proposed results in MATLAB and compared them with conventional methods of classification. The suggested model’s best results include 97.71% accuracy on a brain dataset and 97.2% accuracy on an Alzheimer’s disease dataset. Conclusion:: The proposed algorithm’s high rate of convergence proves that it can successfully balance the exploration and exploitation phases by avoiding capturing in local optimization and classifying thresholds rapidly. In light of the need for improved accuracy, precision, and computational speed in clinical picture classification, a novel approach based on soft sets has been presented.

Computation of the Damping Loss Factor of Heterogeneous Meta-structure using the Wave Finite Element-based Methodology

Abstract Existing methodologies employed for the computation of vibroacoustic indicators of heterogeneous structures with high contrasting properties have limitations in terms of precision and computational speed. The present study, focuses on estimating the composite Damping Loss Factor (DLF) of these structures. It presents a Wave Finite Element-based methodology that uses the forced response of a Unit Cell (UC) representative of the periodic meta-structure to calculate the DLF through a power balance. Various configurations, ranging from a simple plate to complex laminated configurations, are presented to highlight the advantages and limitations of the presented methodology.

Correlation between Leg Muscle Power And Agility On Football Skills Of Psap Sigli Players In 2024, Indonesia

Football is played by two squads, each of eleven players. The game can be done with all limbs except the hands (arms) in good physical condition. Physical condition has components: endurance, strength, speed, power, flexibility, agility, coordination, balance, precision, and reaction speed. Leg muscle power is necessary when soccer players kick, especially when shooting. Agility is also important to achieve success in football. Agility is indispensable when dribbling because it will affect the speed of grinding. This study aims to determine the correlation between leg muscle power and agility with the football skills of PSAP Sigli players in 2024. This study uses quantitative research. The sampling technique was carried out through total sampling or samples from the entire population of PSAP Sigli players, totalling 20 athletes. Furthermore, the data was processed by calculating the mean value, percentage, and correlation between variables. The hypothesis test results show that the correlation coefficient between X1 and X2 with Y is (1). A significant relationship exists between leg muscle power football skills in PSAP Sigli players in 2024. (2) a significant relationship exists between agility and football skills in PSAP Sigli players in 2024. (3) a significant relationship exists between leg muscle power and agility with football skills in PSAP Sigli players in 2024.

Application of PID Control Technology in Unmanned Aerial Vehicles

Abstract. The rapid advancement of unmanned aerial vehicle (UAV) technology underscores the essential role of PID (proportional-integral-derivative) control in ensuring flight stability, particularly through precise motor speed adjustments. Thus, this paper systematically analyzes the fundamental principles and limitations of traditional PID control, further highlighting its insufficient adaptability to dynamic external conditions, which includes load fluctuations and wind disturbances. In response to these challenges, it explores adaptive control strategies such as self-tuning PID and fuzzy logic PID, points out how these advanced methods can effectively improve flight stability by dynamically adjusting control parameters, and demonstrates their superiority over traditional PID through comparative analysis. In addition, the paper anticipates future developments in UAV control systems, thereby emphasizing the integration of artificial intelligence and machine learning technologies into PID control. And this integration seeks to optimize control strategies and markedly enhance the autonomous decision-making capabilities and adaptability of UAVs. Meanwhile, the paper also predicts the development trend of hybrid control systems, that is, combining PID with other advanced control methods (such as linear quadratic control) to enhance the overall control capabilities of UAVs. In short, it underscores the necessity for continuous innovation and in-depth research in response to the dynamic flight environment and the diverse mission requirements.

Numerical analysis of All-Optical universal NAND and NOR photonic crystal logic gates by creating holes in silicon material

All-optical NAND and NOR logical gates based on two-dimensional photonic crystals have been designed and analyzed in this research. A hole in the silicon substrate was created to design the desired gates, and the light emission analysis was performed using the FDTD numerical method. Most of the circuits that have been designed so far based on photonic crystals have included dielectric rods in the airfield. This research uses a hole in the silicon substrate, which is more suitable for fabrication. The proposed structure is created symmetrically using a small photonic crystal. The simulation results show that this small structure can be used as two NAND and NOR gates, which have a suitable power difference in the upper and lower logic states. Therefore, the proposed structure is suitable for precise logic circuits and high transmission speed. Due to the simplicity of structure and small size, the output stable time for NAND and NOR gates are 0.9 ps and 0.67 ps, respectively, indicating the gates’ low delay time. Also, the value of the contrast ratio for NAND and NOR gates is 7.26 dB and 6.35 dB, respectively, which indicates the appropriate power difference in the upper and lower logic states.

Whole-cell multi-target single-molecule super-resolution imaging in 3D with microfluidics and a single-objective tilted light sheet

Multi-target single-molecule super-resolution fluorescence microscopy offers a powerful means of understanding the distributions and interplay between multiple subcellular structures at the nanoscale. However, single-molecule super-resolution imaging of whole mammalian cells is often hampered by high fluorescence background and slow acquisition speeds, especially when imaging multiple targets in 3D. In this work, we have mitigated these issues by developing a steerable, dithered, single-objective tilted light sheet for optical sectioning to reduce fluorescence background and a pipeline for 3D nanoprinting microfluidic systems for reflection of the light sheet into the sample. This easily adaptable microfluidic fabrication pipeline allows for the incorporation of reflective optics into microfluidic channels without disrupting efficient and automated solution exchange. We combine these innovations with point spread function engineering for nanoscale localization of individual molecules in 3D, deep learning for analysis of overlapping emitters, active 3D stabilization for drift correction and long-term imaging, and Exchange-PAINT for sequential multi-target imaging without chromatic offsets. We then demonstrate that this platform, termed soTILT3D, enables whole-cell multi-target 3D single-molecule super-resolution imaging with improved precision and imaging speed.

An online open circuit faults diagnosis method for converter using the lightweight two-channel deep network

Online diagnostic technology is crucial for ensuring the reliable operation of power converters in industrial applications. However, quickly diagnosing the faults of a power converter using intelligent algorithms is challenging due to the redundancy and noise of the sensor measurement signal. Hence, this paper proposes a lightweight two-channel deep network (LTCDN) to overcome it and achieve rapid fault diagnosis. It consists of a quadratic mean preprocessing layer (QMPL), a two-channel convolutional layer (TCCL), and a bidirectional gated recurrent unit (BGRU). The QMPL is designed to achieve denoising and lightening of output currents. Then, the TCCL is proposed to extract edge features and internal key information for improving diagnostic accuracy. Finally, the BGRU classifier completes the online fault diagnosis with a fast detection speed and high precision. It is evaluated through experiments with real-time open circuit faults for multiple switches of a four-level active neutral point clamped (4L-ANPC) converter, demonstrating superior performance with a false diagnosis rate of less than 1% and a diagnosis time of under 8ms. The method combines a novel data preprocessing layer with an efficient neural network to provide an effective fault detection method for a 4L-ANPC converter, which not only has high accuracy but also has significant computational efficiency. Its scalability for more complex multilevel converters is also verified.