Neuromorphic hardware-based IoT edge services allow intelligent processing on end devices, which makes them suitable for IoT edge computing. However, Comprehending the complex operating processes of Spiking Neural Networks (SNNs) used in neuromorphic hardware can be challenging for IoT developers. In this paper, we propose an efficient SNN generation method to simplify the process for IoT developers. Our proposed method generates SNN models considering the constraints of FPGA devices and neuromorphic hardware, while meeting user performance requirements. We utilize trained model by extracting the set of effective cost data through the pre-processing. Additionally, we focus on minimizing the size of the network model using the set of effective cost data to enhance efficiency.
Deep excavation in urban areas has the potential to cause significant economic and human losses by damaging adjacent structures. Prior to such damage, deformation may occur in the sidewalk or road nearest to the construction site. Accurate measurement of deformation levels is crucial for assessing stability in such scenarios, but existing techniques face challenges in achieving precise measurements. In this paper, we propose a novel approach for detecting and measuring block joints using laser sensor data. Our method consists of two key steps: detection and measurement based on laser sensor data. In the detection stage, the proposed method constructs dynamic frames from line data from laser sensor that contain depth information and utilizes these frames to detect block objects. Furthermore, in the measurement stage, it employs a clustering based measurement, called CPLF (Clustered Piecewise Linear Fitting). We built its prototype implementation on an Unmanned Ground Vehicle (UGV) equipped with a laser sensor and performed measurements to quantify its run-time performance. The implementation results show that our proposed approach yields more accurate results within a 1 mm of error.1