Interest in anti-UAV detection systems has increased due to growing concerns about the security and privacy issues associated with unmanned aerial vehicles (UAVs). Achieving real-time detection with high accuracy, while accommodating the limited resources of edge-computing devices poses a significant challenge for anti-UAV detection. Existing deep learning-based models for anti-UAV detection often cannot balance accuracy, processing speed, model size, and computational efficiency. To address these limitations, a lightweight and efficient anti-UAV detection model, DRBD-YOLOv8, is proposed in this paper. The model integrates several innovations, including the application of a Re-parameterization Cross-Stage Efficient Layered Attention Network (RCELAN) and a Bidirectional Feature Pyramid Network (BiFPN), to enhance feature processing capabilities while maintaining a lightweight design. Furthermore, DN-ShapeIoU, a novel loss function, has been established to enhance detection accuracy, and depthwise separable convolutions have been included to decrease computational complexity. The experimental results showed that the proposed model outperformed YOLOV8n in terms of mAP50, mAP95, precision, and FPS while reducing GFLOPs and parameter count. The DRBD-YOLOv8 model is almost half the size of the YOLOv8n model, measuring 3.25 M. Its small size, fast speed, and high accuracy combine to provide a lightweight, accurate device that is excellent for real-time anti-UAV detection on edge-computing devices.

Traditional deep learning methods struggle to simultaneously segment, recognize, and forecast human activities from sensor data. This limits their usefulness in many fields, such as healthcare and assisted living, where real-time understanding of ongoing and upcoming activities is crucial. This article introduces P2LHAP, a novel Patch-to-Label Seq2Seq framework that tackles all three tasks in an efficient single-task model. P2LHAP divides sensor data streams into a sequence of “patches,” served as input tokens, and outputs a sequence of patch-level activity labels, including the predicted future activities. A unique smoothing technique based on surrounding patch labels, is proposed to identify activity boundaries accurately. Additionally, P2LHAP learns patch-level representation by sensor signal channel-independent Transformer encoders and decoders. All channels share embedding and Transformer weights across all sequences. Evaluated on the three public datasets, P2LHAP significantly outperforms the state-of-the-art in all three tasks, demonstrating its effectiveness and potential for real-world applications.

NURBS interpolation is superior to traditional linear or circular interpolation in terms of code size, surface quality, and machining efficiency. However, with the increasing demands for high-accuracy and efficient machining, NURBS interpolation has faced a growing number of challenges. Many researchers are actively involved in this field with great interest. Due to the special form of NURBS curve, there is a nonlinear relationship between its curve and arc length; feed fluctuations and mechanical shocks which are caused during the interpolation process will seriously affect the surface accuracy and quality of machined parts. To solve these problems, a real-time NURBS interpolation is proposed under multiple constraints (RNIC) in this paper. First, the formulas of the constrained feedrate under geometric errors, kinematic constraints, drive constraints, and contour errors are given. Then, the two stages for the proposed interpolation are established. The former stage is offline preprocessing stage, which aims to quickly find feedrate sensitive areas (FSAs), while the latter online stage is the real-time interpolation, which is responsible for smoothing the velocity. In the preprocessing stage, we utilized FSA scan module and feedrate adjustment module to detect the FSAs and adjust the feedrate at the start/end of each subsegment by a bidirectional scanning algorithm. Each segment contains acceleration and deceleration (some contains uniform speed) stages, which can be well matched with the processing process of acceleration and deceleration. Finally, according to the proposed method and the adaptive speed adjustment method, the simulation of a “butterfly-shaped” NURBS curve using the S-shaped ACC/DEC algorithm is carried out, which verifies the reliability and effectiveness of the proposed algorithm.

This paper introduces a novel approach for enhancing human activity recognition through the integration of LoRa wireless RF signal preprocessing and deep learning. We tackle the challenge of extracting features from intricate LoRa signals by scrutinizing the unique propagation process of linearly modulated LoRa signals—a critical aspect for effective feature extraction. Our preprocessing technique involves converting intricate data into real numbers, utilizing Short-Time Fourier Transform (STFT) to generate spectrograms, and incorporating differential signal processing (DSP) techniques to augment activity recognition accuracy. Additionally, we employ frequency-to-image conversion for the purpose of intuitive interpretation. In comprehensive experiments covering activity classification, identity recognition, room identification, and presence detection, our carefully selected deep learning models exhibit outstanding accuracy. Notably, ConvNext attains 96.7% accuracy in activity classification, 97.9% in identity recognition, and 97.3% in room identification. The Vision TF model excels with 98.5% accuracy in presence detection. Through leveraging LoRa signal characteristics and sophisticated preprocessing techniques, our transformative approach significantly enhances feature extraction, ensuring heightened accuracy and reliability in human activity recognition.

Feedrate scheduling is one of the most critical technologies in CNC machining, requiring a reasonable balance between efficiency and quality. This paper proposes a jerk-continuous feedrate smoothing (JCFS) method to generate a low-vibration and smooth feedrate profile for non-uniform rational B-spline (NURBS) interpolation. Firstly, the segmentation concept is introduced to subdivide the entire trajectory into segments to accommodate curvature changes of the NURBS curve, accelerating the acceleration/deceleration process. Secondly, a length threshold-based curve segment classification method is proposed to overcome the complexity of the traditional acceleration and deceleration algorithms. The curve segments are divided into long, medium, and short types, and the length threshold calculation model is derived. Next, to avoid computational complexity for engineering applications, a model is established for the first time to calculate the actual maximum feedrate for different types of segments. Finally, the horizontal-8-shaped and butterfly-shaped NURBS curves are simulated and analyzed. The simulation results indicate that the machining quality is steadily improved while several key indicators remain within the given tolerances. Compared with the traditional method, the proposed method reduces the computational and interpolation time by 17.2% and 22.8%, respectively, demonstrating the feasibility and effectiveness of the method.

Multiobjective clustering algorithm using particle swarm optimization has been applied successfully in some applications. However, existing algorithms are implemented on a single machine and cannot be directly parallelized on a cluster, which makes it difficult for existing algorithms to handle large-scale data. With the development of distributed parallel computing framework, data parallelism was proposed. However, the increase in parallelism will lead to the problem of unbalanced data distribution affecting the clustering effect. In this paper, we propose a parallel multiobjective PSO weighted average clustering algorithm based on apache Spark (Spark-MOPSO-Avg). First, the entire data set is divided into multiple partitions and cached in memory using the distributed parallel and memory-based computing of Apache Spark. The local fitness value of the particle is calculated in parallel according to the data in the partition. After the calculation is completed, only particle information is transmitted, and there is no need to transmit a large number of data objects between each node, reducing the communication of data in the network and thus effectively reducing the algorithm’s running time. Second, a weighted average calculation of the local fitness values is performed to improve the problem of unbalanced data distribution affecting the results. Experimental results show that the Spark-MOPSO-Avg algorithm achieves lower information loss under data parallelism, losing about 1% to 9% accuracy, but can effectively reduce the algorithm time overhead. It shows good execution efficiency and parallel computing capability under the Spark distributed cluster.