Summary
TensorFlow for IoT is an effective tool to enable deep learning on IoT devices. By leveraging existing IoT infrastructures, deep learning models can be trained on huge datasets to interpret and react to user and environmental events. These models can be used to create intelligent applications such as smart parking models, distributed analytics in fog computing platforms, smart home automation, and flash flood detection alerts. For example, the smart parking model uses TensorFlow for IoT to identify and predict available parking spots, allowing users to quickly find available parking spaces and navigate to them. In addition, distributed analytics in fog computing platforms can be used to enable voice commands on IoT devices, such as Amazon Echo. Finally, TensorFlow can be used to create an intelligent flood detection and alert system to ensure that cities can rapidly respond to flash floods and minimize the financial damage caused by these events.
Consensus Meter
Our model aims to save people's time by allocating them a free parking space in a nearby parking area and help them to navigate that place. This paper first provides a complete model to provide a free parking space, how to reserve or book the place and help them to navigate in the indoor parking area.
Published By:
MO Hasan, MM Islam, Y Alsaawy - 2019 7th International …, 2019 - ieeexplore.ieee.org
Cited By:
14
Deep learning can enable Internet of Things (IoT) devices to interpret unstructured multimedia data and intelligently react to both user and environmental events but has ... Deep learning can enable Internet of Things (IoT) devices to interpret unstructured multimedia data and intelligently react to both user and environmental events but has demanding performance and power requirements.
Published By:
J Tang, D Sun, S Liu, JL Gaudiot - Computer, 2017 - ieeexplore.ieee.org
Cited By:
149
For example, Echo [1] is a new IoT application manufactured by Amazon, which connects humans to other IoT devices via voice commands. With the growing IoT market, a forecast from Gartner says that 8.4 billion IoT devices will be in use worldwide in 2017, which is 31% more than that in 2016; and the number will increase to 20.4 billion by 2020 [2].
Published By:
PH Tsai, HJ Hong, AC Cheng… - 2017 19th Asia-Pacific …, 2017 - ieeexplore.ieee.org
Cited By:
54
In: IEEE Region 10 Symposium, pp 184–187 Google Scholar Garcia CG, Meana-Llorian D, Pelayo G-Bustelo BC, Cueva Lovelle JM, Garcia-Fernandez N (2017) Midgar: detection of people through computer vision in the Internet of Things scenarios to improve the security in Smart Cities, Smart Towns, and Smart Homes. In: IEEE 9th international conference on computational intelligence and communication networks (CICN), pp 108–112 Google Scholar Sefat MS, Khan AAM, Shahjahan M (2014) Implementation of vision based intelligent home automation and security system.
Published By:
R Sarawale, A Deshpande, P Arora - Data Science and Security …, 2021 - Springer
Cited By:
1
I. Introduction For an urban area, the most common type of flood is flash flood heavy rainfall exceeds the ability of the ground to absorb it and drainage to divert it [1]. The impact of flash flood to urban population is huge, in Malaysia shop owner around Kajang needs to bare average RM4,510.07 of financial loss due to flash flood occurring on the area [2]. Meanwhile, globally flooding has caused 40 billion in damage financially [3]. Based on research conducted by [4], the impact of flooding is more severe in a developed country and will cause greater loss. Thus, proficient flood assessments, detection and alert system should be designed to ensure that the city can adapt to flooding and mitigate damage quickly [5].
Published By:
A Abd Rashid, MAM Ariffin… - 2021 11th IEEE …, 2021 - ieeexplore.ieee.org
Cited By:
1