3 Data Analytics: Classification
There are other ways in which analytics can be used than for prediction, from
understanding customers to optimising a business process. In machine learning
and statistics, classification is the problem of identifying which category a new
observation belongs, on the basis of a training set of data containing observations
(or instances) whose category membership is known (hence described as supervised
learning). An example would be assigning a given pipe to a high-risk or low-risk
category for water quality issues based on asset characteristics (pipe material,
age, diameter, etc.). Classification can be viewed as a special case of function
approximation using some type of discriminant for the decision.
3.1 Internet of Things and Edge Computing
Internet of Things (IoT) objects and sensors can be connected to the Internet (via the
cloud) giving rise to the concept of ‘smartness’ and the development of ‘smart cities’
and ‘smart water’. By definition they have an IP address. It seems clear that in the
future, the whole water sector is going to be completely penetrated by ICT and
Internet-like technologies. It is estimated that 50 billion devices in all industries
will be connected in this way by 2020 (with an estimated 6.1 billion smartphones)
and as many as 75 billion by 2025. In a decade, tens or even hundreds of petabytes
of data may be routinely available. The sensing of data that could not be gathered
in the past and collecting them on IoT platforms is expected to create new value.
As these technological capabilities advance, so does the ability to collect information
from remote devices and correlate that information across diverse systems.
Standards will be required to manage this level of interconnectivity which may
ultimately lead to the unification of information management for the industry.
An infrastructure that can connect the monitoring and control systems to an IoT
platform allows the effective use of the operational information the systems hold
and help achieve near real-time situational awareness. Demands for solutions
and tools will become more urgent to meet the aspiration for intelligent water
networks, proactively managed through access to timely information.
In recent years, the UK water industry has been making increasing use of
advances in sensor technology for monitoring parameters of water systems to
identify performance shortfalls in order to improve asset management and
hence provide better customer service, value and regulatory performance. For
example, in supply systems sensors for flow and pressure have become more
widely used, especially on trunk mains and at district metered area (DMA) level,
to facilitate zone-based asset management. The monitoring of sewerage systems
has not progressed as far; however there is an increasing interest and deployment
of instrumentation, for example, for CSO (combined sewer overflows) level
measurement and pump station flows. Water quality data (parameters such as
10
S. R. Mounce
There are other ways in which analytics can be used than for prediction, from
understanding customers to optimising a business process. In machine learning
and statistics, classification is the problem of identifying which category a new
observation belongs, on the basis of a training set of data containing observations
(or instances) whose category membership is known (hence described as supervised
learning). An example would be assigning a given pipe to a high-risk or low-risk
category for water quality issues based on asset characteristics (pipe material,
age, diameter, etc.). Classification can be viewed as a special case of function
approximation using some type of discriminant for the decision.
3.1 Internet of Things and Edge Computing
Internet of Things (IoT) objects and sensors can be connected to the Internet (via the
cloud) giving rise to the concept of ‘smartness’ and the development of ‘smart cities’
and ‘smart water’. By definition they have an IP address. It seems clear that in the
future, the whole water sector is going to be completely penetrated by ICT and
Internet-like technologies. It is estimated that 50 billion devices in all industries
will be connected in this way by 2020 (with an estimated 6.1 billion smartphones)
and as many as 75 billion by 2025. In a decade, tens or even hundreds of petabytes
of data may be routinely available. The sensing of data that could not be gathered
in the past and collecting them on IoT platforms is expected to create new value.
As these technological capabilities advance, so does the ability to collect information
from remote devices and correlate that information across diverse systems.
Standards will be required to manage this level of interconnectivity which may
ultimately lead to the unification of information management for the industry.
An infrastructure that can connect the monitoring and control systems to an IoT
platform allows the effective use of the operational information the systems hold
and help achieve near real-time situational awareness. Demands for solutions
and tools will become more urgent to meet the aspiration for intelligent water
networks, proactively managed through access to timely information.
In recent years, the UK water industry has been making increasing use of
advances in sensor technology for monitoring parameters of water systems to
identify performance shortfalls in order to improve asset management and
hence provide better customer service, value and regulatory performance. For
example, in supply systems sensors for flow and pressure have become more
widely used, especially on trunk mains and at district metered area (DMA) level,
to facilitate zone-based asset management. The monitoring of sewerage systems
has not progressed as far; however there is an increasing interest and deployment
of instrumentation, for example, for CSO (combined sewer overflows) level
measurement and pump station flows. Water quality data (parameters such as
10
S. R. Mounce