artificial intelligence system in the IoT. The importance of data mining and management will be highlighted
in the paper. Also, the method used in the Artificial Intelligence like fuzzy logics and neural network also will
be discussed in this paper in conjunction with IoT network. The self-optimizing network and software defined
network are parts of the important parameters in the Artificial Intelligence IoT System.
3. IoT Solutions for Precision Farming and Food Manufacturing: Artificial Intelligence
Applications in Digital Food
Link: https://ieeexplore.ieee.org (Accessed on 01 July 2019)
Abstract:
In many respects, farming and food processing have lagged other industries when it comes to adoption of
innovative technology. Whilst bioengineering has brought about seeds with much higher yield and less need
for water and nutrients, it is only now with IoT that farmer can work on the intensive use of natural resources
to increase the sustainability of their operations. In the last ten years, high-end machinery has evolved pri-
marily to the benefit of larger corporations, with the introduction of satellite driven machines, sensors and all
components of precision farming. The most recent IoT advances bring about a level of simplification and cost
reduction that enable all farmers to benefit and a true adoption of prescription agriculture. In this conference
presentation, we will examine a practical case of a Malthouse, where careful modeling of how CO
2
, Tempera-
ture, Humidity and PH vary in the three steps of the malting process, enabled an artificial intelligence system
to prescribe different setting and schedules. The end result is malt with higher content of starch and proteins,
which in turn means higher alcohol in the downstream process. A second example on the cultivation of Medical
Marijuana, where similarly but in a more complex fashion (138 variables) the artificial intelligence supported
the tuning of many settings and schedules, is presented only in the conference.
4. Nonvolatile Circuits-Devices Interaction for Memory, Logic and Artificial Intelligence
Link: https://ieeexplore.ieee.org (Accessed on 01 July 2019)
Abstract:
Emerging nonvolatile memory (eNVM) has aroused extensive attention due to their low power and
high speed. Recent advances have further moved eNVM to the forefront as key enablers of nonvolatile logics
(nvLogics) for IoT devices and computing-in-memory (CIM) for AI chips. In this paper, we firstly examine
the circuit-device-interaction (CDI) issues to implement high-performance memory macro. Then we review
examples of emerging eNVM-based nvLogics for nonvolatile processors and CIM macro for AI chips with an
emphasis on the challenges required CDI.
5. In-Situ AI: Towards Autonomous and Incremental Deep Learning for IoT Systems
Link: https://ieeexplore.ieee.org (Accessed on 01 July 2019)
Abstract:
Recent years have seen an exploration of data volumes from a myriad of IoT devices, such as various sensors
and ubiquitous cameras. The deluge of IoT data creates enormous opportunities for us to explore the physical
world, especially with the help of deep learning techniques. Traditionally, the Cloud is the option for deploying
deep learning based applications. However, the challenges of Cloud-centric IoT systems are increasing due
to significant data movement overhead, escalating energy needs, and privacy issues. Rather than constantly
moving a tremendous amount of raw data to the Cloud, it would be beneficial to leverage the emerging powerful
IoT devices to perform the inference task. Nevertheless, the statically trained model could not efficiently handle
the dynamic data in the real in-situ environments, which leads to low accuracy. Moreover, the big raw IoT data
246 Internet of Things
Internet_of_Things_CH09_pp231-248.indd 246 9/3/2019 10:15:33 AM