Deep Analytics: Technologies for Humanity, AI & Security by Sumit Chakraborty, Suryashis Chakraborty, Kusumita - HTML preview

PLEASE NOTE: This is an HTML preview only and some elements such as links or page numbers may be incorrect.
Download the book in PDF, ePub, Kindle for a complete version.

1. SCOPE

 

Scope Analytics

 

Agents: Earth scientists, engineers;

Moves : Requirements management, threat analytics;

Disasters: call threat analytics –> assess threats (drought, flood, heavy rainfall, snowfall, storm, sand storm, cyclone, earthquake, volcano, bushfire, woodfire, epidemic, pandemic, astronomical hazards, environmental pollution (air, water, soil, sound, sunlight), (attacks of wild beasts and pastes);

 

Prof. Nick Jones and Mr. Lin are exploring the scope of emerging technologies against natural disaster. Natural disaster is a critical causal factor of poverty of human society globally. Can emerging technologies be used to fight against natural calamities effectively? How can we assess and mitigate risks of various types of natural disaster such as flood, drught, storm, earthquake, volcano, woodfire, snowfall, epidemic and pandemic outbreak, astronomical hazards, environmental pollution and attack of malicious pastes and wild animals effectively?

Can You recall the tune of ‘The rain must fall’ by Yanni? This session is analyzing the technological innovation associated with the problem of water security through artificial rainfall and rational, fair and correct resource allocation and sharing among multiple entities. Such type of technological innovation is essential to fight against natural calamities such as drought and flood. It is an emerging technology for humanity. We have analyzed the technological innovation through seven elements of the deep analytics i.e. scope, system, structure, security, strategy, staff- resources and skill-style support of the deep analytics. We have shown various strategic moves of artificial rainfall such as weather modification and rain enhancement through cloud seeding, glaciogenic seeding, hygroscopic seeding and laser induced rainfall. At present, the technology is at emergence phase of technological life-cycle. We have shown SWOT analysis on various methods of artificial rainfall. This work also outlines a water sharing mechanism (WSM) based on collaborative intelligence. However, the efficiency of the resource sharing mechanism is associated with several critical success factors such as good governance, corporate social responsibilities, law and order, rational positive thinking and political goodwill. An intelligent broadcast protocol is expected to enhance public awareness of rational usage of water by the common people and restrict wastage of water in swimming pools, water amusement parks, luxurious use of air conditioners and air coolers by the rich and super rich classes of our society; tap at roadside and construction works and leakage from pipelines, saving water bodies and conservation of water. Academic institutes and government are expected to play responsible and rational role in regional urban and rural development planning globally. Finally, this work outlines the innovation, diffusion and adoption on emerging laser induced artificial rainfall technology, very large scale integrated smart water grid and water sharing mechanisms based on collaborative planning, forecasting and replenishment.

The expert panel are considering the problem of water security. The people in today’s world are facing with significant challenges in this utility sector such as shortage of water, high cost of generation, storage and distribution, wastage or loss and pollution. We must set an efficient national and global utility policy to promote the development of a sustainable system which should be viable environmentally, socially and economically. The sustainability in such resource management not only requires a balanced approach between natural and artificial rainfall but also encourages rational and efficient use of water by minimizing wastage and pollution. There are many strategic moves of efficient water resource management. This work is focused on two specific strategic moves to fight against flood and drought: artificial rainfall and multi-agent collaborative resource sharing. Can we dream of a collaborative enterprise model in this context?

This session is also also exploring the problem of private search and presents three private search algorithms for three test cases – (a) real-time moving target search to detect astronomical hazards; (b) Real time private moving target search for robot navigation and (c) Private Light Beam Search. The basic objective of a search is to identify an object and the position of the target. The target’s position may be uncertain or there may be complete or incomplete information about its location in terms of a probability distribution. The target may be stationary or in motion. The target distribution is associated with discrete or continuous search space. The problem of optimal search is to maximize the probability of detecting a target subject to the constraints of resources, effort and time. Adaptive security and dynamic data management (DDM) is an essential part of space technology that can monitor the space in real-time to detect any anomalies, vulnerabilities or malicious traffic congestion. If a threat is detected, the technology should be able to mitigate the risks through a set of preventive, detective, retrospective and predictive capabilities and measures. This session also presents Real-time Probabilistic Search Mechanism (RPSM). The probabilistic search approach addresses the incomplete information on the target location by location probability. The problem is probabilistic from the perspectives of the location, size, distance and timing of the moving target(s) and distribution of the search efforts. The effectiveness of probabilistic search procedure can be verified on the basis of various properties of adaptive secure multiparty computation such as correctness, privacy, transparency, reliability and consistency. The search space can be divided into a set of private blocks; adequate number of sensors should be assigned to each private block; each block is monitored independently. This work highlights the complexity analysis of RPSM from the perspectives of computational cost and security intelligence. It also exercises case based reasoning on a test case of astronomical hazards and explores the scope of RPSM to assess and mitigate those threats. The universe is basically a computer, its history is being computed continuously. The astronomical hazards may be really dangerous threats against the sustainability of today’s human civilization and the existence of a safe earth. This type of probabilistic search problem is really hard to solve, it is not a trivial problem. It is also challenging to deploy automated real-time search in reality and seeks extensive support, coordination, planning and corporate social responsibilities from various space research organizations and earth science institutes globally. Today, we have been dreaming of the moon and Mars voyage in space research. It may be a hard target. But, the sustainability of our earth from the dangerous astronomical hazards should be a top priority in space research globally: isn’t it rational?

The basic objective of a search is to identify an object and the position of the target. The target’s position may be uncertain or there may be complete or incomplete information about its location in terms of a probability distribution. The target may be stationary or in motion. The target distribution is associated with discrete or continuous search space. Search is conducted with various types of sensors such as CCTVs, cameras, telescopes, satellites and eyes of human agents. A detection function gives the probability of detection for a search as a function of effort (e.g. swept area, time). The detection function evaluates the effectiveness of search efforts in terms of probability of detecting the target object. The problem of optimal search is to maximize the probability of detecting a target subject to the constraints of resources, effort and time. The search space can be divided into a set of private blocks; adequate number of resources (sensors) can be assigned to each private block; each block is monitored independently.

In a search problem, a searching agent tries to find a hidden object by screening a certain defined area. The search space may be either discrete or continuous. In a continuous space, the target may move in various ways such as random, Markovian or Brownian moves. If the location of the target is known, then it may be complete- information tractable search problem and it may detect the target with a minimal number of search moves. The exact location of the target is generally unknown to the searching agent in incomplete information search and the problem is addressed using the concepts of fuzzy logic or probability theory. The probabilistic search approach addresses the incomplete information on the target location by location probability. The problem is probabilistic from the perspectives of the location of the target and distribution of the search efforts. The effectiveness of probabilistic search procedure can be verified on the basis of various properties of secure multiparty computation: correctness (i.e. correct identification of the targets), privacy, transparency, reliability and consistency.

The problem of optimal search for a moving target in both discrete and continuous space has been investigated extensively in various research articles on operations research and artificial intelligence. This work is an attempt to extend the study on the basis of related literature review and case based reasoning. This work is organized as follows. Section 1 is focused on scope; it defines the problem of probabilistic search of moving targets in discrete and continuous space.

This session also explores the scope of other natural disasters including epidemic and pandemic outbreak and bushfire and suggests a set of intelligent strategic moves as countermeasures. It is rational to adopt an efficient system; an optimal mix of e-governance (e.g. online grievance management system), broadcast communication protocol and artificial immune mechansism to fight against natural disaster, epidemic and pandemic outbreak. There is threat of bio-terrorism on the soft targets (e.g. life-science supply chain and healthcare service chain). Is the conflict between security intelligence and business intelligence inevitable? It is an interesting observations that technologies for humanity can be effectively applied to fight against disasters. Pandemic is more dangerous than epidemic. When an epidemic spreads globally, it is called pandemic. In case of epidemic, a disease spreads at very fast rate witin a particular period among one or more communities. For example, WHO has recently declared the outbreak of novel Corona virus as Pandemic, but it is controllable. There are other various types of threats of epidemic globally due to environmental pollution such as air, water, soil, light and sound pollution.

a) Epidemic due to air pollution like dust at construction sites and industrial plants; smoke from vehicles; paste control problem (e.g. mosquitoes, flies), malnutrition in slum areas, improper cleaning of garbages and stool of street animals?

b) Epidemic due to water pollution in supply of dirty drinking tap water caused by leakage in pipelines, contamination and jerms in water storage system, malfunctioning of tube wells, water filtering problem, mixing of water from drainage system and tap water pipeline, unprotected selling of unhealthy food (e.g. oily spicy biriyani) and beverages at retail outlets and by hawkers being contaminated by flies; risks of diahorrea, stomach upset and loose motion.

c) Epidemic due to soil pollution and earthquake caused by random digging of soil for construction projects, erosion of soil at riverbeds; jamming in drains due to plastics, improper cleaning of drainage and sewage system;

d) Epidemic due to light pollution in slum areas, unplanned urban development planning, blockage of sufficient sunlight into residential areas (e.g. houses, flats, multi-storied buildings)

e) Epidemic due to sound pollution caused by playing loud and wild music, fireworks, activities at construction sites and industrial belts.

The key focus areas of this session are artificial rainfall, cloud  seeding, collaborative intelligence, resource sharing mechanism, water sharing, compensation, collaborative planning, forecasting & replenishment, political will, power play, conspiracy for war, corporate social responsibilities, artificial intelligence, probabilistic light beam search, predictive threat analytics, astronomical hazards, reactive and proactive security, private search, adaptive security, dynamic data management, natural disaster, epidemic control, pandemic

outbreak, intelligent broadcast, online grievance management system, articial immune mechanism, self-Nonself classification, danger signal, clonal selection, hotspot, cluster, social distancing, security intelligence, business intelligence, bio- terrorism, life science supply chain and healthcare service chain.