This paper presents an adaptive control scheme for streetlights by optimizing the energy consumed using deep learning during late hours at night. A city’s infrastructure is not complete without a proper lightening system for streets and roads. The streetlight systems often consume up to 50% of the electricity utilized by the city. Due to this reason, it has a huge financial impact on the electricity generation of the city. Furthermore, continuous luminosity of the streetlights contributes to the environmental pollution as well. Economists and ecologists around the globe are working hard to reduce the global impact of continued utilization of streetlights at night. In regard to a developing country which is already struggling to produce enough electrical energy to fulfill its industry requirements, proposing a system to lessen the load of the energy utilization by the streetlights should be beneficial. Therefore, an innovative and novel energy efficient streetlight control system is presented based on embedded video processing. The proposed system uses deep learning for the optimization of energy consumption during the later hours. Conventional street lighting systems consume enormous amounts of electricity, even when there is no need for the light, i.e., during off-peak hours and late at night when there is reduced or no traffic on the roads. The proposed system was designed, and implemented and tested at two different sites in Karachi, Pakistan. The system is capable of detecting vehicles and pedestrians and is able to track their movements. The YOLOv5 deep-learning based algorithm was trained according to the local requirements and implemented on the NVIDIA standalone multimedia processing unit “Jetson Nano”. The output of the YOLOv5 is then used to control the intensity of the streetlights through intensity control unit. This intensity control unit also considers the area, object and time for the switching of streetlights. The experimental results are promising, and the proposed system significantly reduces the energy consumption of streetlights.

The nerves in the skin surface of the foot are comprised of unmyelinated smaller somatic nerves and larger myelinated sensory nerves. Current diagnostic methods are unable to evaluate combined nerve conduction velocity (NCV) from both unmyelinated smaller somatic nerve (USSN) and myelinated larger nerves (MLN) respectively. Computational models may provide an alternative tool to determine the NCV of the combined nerve. Therefore, a combined functional dorsal nerve model (CFDNM) of the various dorsal nerves along with its associated nerve ending of the human foot is proposed and constructed. The combined dorsal nerve model consists of synthetic USSN (SUSSN) and dorsal MLN of the foot. The unmyelinated as well as myelinated electrophysiological nerve models were used to simulate selected SUSSN and MLN of the foot by injecting an external stimulus at the most distal part of SUSSN of the foot through the use of bidomain model. Results from our work demonstrated that the action potential propagated from the most distal part to proximal part of distinct dorsal nerves of the foot, e.g., the simulated NCV of the combined intermediate dorsal cutaneous nerve (IDCN) of the foot was 28.4 m s^-1. The CFDNM will provide a vital tool for diagnosis initially small fibre neuropathy (SFN) by computing NCV in the prospective studies.

The nerves in the foot offer a significant role in controlling the movement and correct loading of the foot by providing continuous feedback to the central nervous system. The health importance in the anatomical variations of nerves, such as the locations, the lengths, the communicating branches, and the distance between the adjacent nerve terminals between individuals have given prominence to anatomists as well as physiologists. A previously developed one-dimensional (1D) model of the nerve was extended to determine different anatomical variations in the nerves of the foot, as a realistic anatomical-based variant nerve model of the human foot is not available. The model was verified against experimental data from the literature for communicating branches and distances of various area of the human foot. For instance, the simulated distances of the communicating branches of the plantar nerves and medial dorsal cutaneous nerve (MDCN) division proximal to the first digital space were found to be 43.3 mm and 112.3 mm, respectively, which was in general agreement with the experimental distances of 8-56 mm and 96-116.74 mm, respectively. The developed nerve variant model provides a platform for future studies of the various geometrical and efficient concerns of neurovascular diseases such as diabetic neuropathies by determining the parameters of nerve conduction studies.