This paper addresses the challenges associated with drone formation and light shows, presenting an algorithm with a complexity of O(MNLO) tailored for drone light show applications. The problem has traditionally been addressed using vector methods in previous research; however, their application becomes challenging when dealing with the intricacies of UAV swarms. Therefore, the proposed UAV formation algorithm embraces the voxel data structure and maze-running methodology to effectively address the complexities inherent in UAV swarm scenarios. The algorithm comprises three integral components: task assignment, obstacle-avoidance path-planning, and fault tolerance. In the initial phase, task assignment elucidates the methodology for assigning starting points and unassigned end-points of UAV flights, with a time complexity of O(L3logL), where L represents the number of drones. The subsequent phase introduces two distinct methods, namely detour and stay-and-forward, to address the issue of obstacle-avoidance path-planning. Both methods exhibit time complexities of O(NL), with N denoting the number of voxels. The final phase proposes a fault-tolerant mechanism to ensure smooth performance of drone light shows in the event of a drone failure during formation. To ensure uninterrupted performance, the backup drones execute collision avoidance for each frame at the onset, with a complexity of O(NLO), where O signifies the number of backup drones. The aggregate time complexity of the main algorithm, encompassing the aforementioned three components, is O(MNLO), where M denotes the number of main frames. The proposed method may reduce time consumption by seamlessly integrating collision computation into Blender, thus obviating the need for manual adjustments and offering advancements in both algorithmic efficiency and fault-tolerant performance for drone light shows.

This paper presents an Internet of Things (IoT) application that utilizes an AI classifier for fast-object detection using the frame difference method. This method, with its shorter duration, is the most efficient and suitable for fast-object detection in IoT systems, which require energy-efficient applications compared to end-to-end methods. We have implemented this technique on three edge devices: AMD AlveoTMU50, Jetson Orin Nano, and Hailo-8TMAI Accelerator, and four models with artificial neural networks and transformer models. We examined various classes, including birds, cars, trains, and airplanes. Using the frame difference method, the MobileNet model consistently has high accuracy, low latency, and is highly energy-efficient. YOLOX consistently shows the lowest accuracy, lowest latency, and lowest efficiency. The experimental results show that the proposed algorithm has improved the average accuracy gain by 28.314%, the average efficiency gain by 3.6 times, and the average latency reduction by 39.305% compared to the end-to-end method. Of all these classes, the faster objects are trains and airplanes. Experiments show that the accuracy percentage for trains and airplanes is lower than other categories. So, in tasks that require fast detection and accurate results, end-to-end methods can be a disaster because they cannot handle fast object detection. To improve computational efficiency, we designed our proposed method as a lightweight detection algorithm. It is well suited for applications in IoT systems, especially those that require fast-moving object detection and higher accuracy.

Various optimization methods and network architectures are used by convolutional neural networks (CNNs). Each optimization method and network architecture style have their own advantages and representation abilities. To make the most of these advantages, evolutionary-fuzzy-integral-based convolutional neural networks (EFI-CNNs) are proposed in this paper. The proposed EFI-CNNs were verified by way of face classification of age and gender. The trained CNNs’ outputs were set as inputs of a fuzzy integral. The classification results were operated using either Sugeno or Choquet output rules. The conventional fuzzy density values of the fuzzy integral were decided by heuristic experiments. In this paper, particle swarm optimization (PSO) was used to adaptively find optimal fuzzy density values. To combine the advantages of each CNN type, the evaluation of each CNN type in EFI-CNNs is necessary. Three CNN structures, AlexNet, very deep convolutional neural network (VGG16), and GoogLeNet, and three databases, computational intelligence application laboratory (CIA), Morph, and cross-age celebrity dataset (CACD2000), were used in experiments to classify age and gender. The experimental results show that the proposed method achieved 5.95% and 3.1% higher accuracy, respectively, in classifying age and gender.

In the field of computer vision technology, deep learning of image processing has become an emerging research area. The semantic segmentation of an image is among the utmost essential and significant tasks in image-processing research, offering a wide range of application fields such as autonomous driving systems, medical diagnosis, surveillance security, etc. Thus far, many studies have suggested and developed neural network modules in deep learning. To the best of our knowledge, all existing neural networks for semantic segmentation have large parameter sizes and it is therefore unfeasible to implement those architectures in low-power and memory-limited embedded platforms such as FPGAs. Building an embedded platform with that architecture is possible after reducing the parameter size without affecting the module’s architecture. The quantization technique lowers the precision of the neural network parameters while mostly keeping the accuracy. In this paper, we propose a quantization algorithm for a semantic segmentation deep learning architecture, which reduces the parameter size by four to eight times with a negligible accuracy abatement. As long as the parameter size is reduced, the deep learning architecture is improved in terms of required storage, computational speed, and power efficiency.

Design strategies for parallel iterative algorithms are presented. In order to further study different tradeoff strategies in design criteria for integrated circuits, A 10 × 10 Jacobi Brent-Luk-EVD array with the simplified μ-CORDIC processor is used as an example. The experimental results show that using the μ-CORDIC processor is beneficial for the design criteria as it yields a smaller area, faster overall computation time, and less energy consumption than the regular CORDIC processor. It is worth to notice that the proposed parallel EVD method can be applied to real-time and low-power array signal processing algorithms performing beamforming or DOA estimation.