AU2020102437A4 - Quantum Machine Learning based Sensor Consolidation Approach for IIoT - Google Patents
Quantum Machine Learning based Sensor Consolidation Approach for IIoT Download PDFInfo
- Publication number
- AU2020102437A4 AU2020102437A4 AU2020102437A AU2020102437A AU2020102437A4 AU 2020102437 A4 AU2020102437 A4 AU 2020102437A4 AU 2020102437 A AU2020102437 A AU 2020102437A AU 2020102437 A AU2020102437 A AU 2020102437A AU 2020102437 A4 AU2020102437 A4 AU 2020102437A4
- Authority
- AU
- Australia
- Prior art keywords
- sensor
- quantum
- decision
- rate
- machine learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N10/00—Quantum computing, i.e. information processing based on quantum-mechanical phenomena
- G06N10/20—Models of quantum computing, e.g. quantum circuits or universal quantum computers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N10/00—Quantum computing, i.e. information processing based on quantum-mechanical phenomena
- G06N10/60—Quantum algorithms, e.g. based on quantum optimisation, quantum Fourier or Hadamard transforms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Quantum Machine Learning based Sensor Consolidation Approach
for HoT
Abstract
IoT devices are interconnected to grab data over a common platform from IoT
applications. Maintaining an immense data and making instant decision analysis by
selecting a feasible node, which should mandate a viable computation resources to meet
latency-constraints is a challenging task. It could be accomplished fundamentally with
accurate data generated by selecting a potential node of the environment. In this extension,
a quantum formalized node-specific parameters are essential. To streamline this issue, we
designed Quantum Machine Learning based Sensor Consolidation (QMLSC) approach
based on two phenomenal methods to select potentially satisfied sensors of the framework.
Those are
• Sensor contiguity rate
• Optimal knack rate of the sensor
The Q-bits have enabled with underline objective sub-parameters w.r.t to the
classical bits of that sub-parameter outcomes. Hence, an optimal quantum-based IoT
framework makes adaptive decision-making mechanism, which is essential to accomplish
reliable service. The quantum computing would streamline IoT edge computing issues by
selecting right device into the network. Therefore, the active devices could get high
equilibrium workload by offloading the tasks for computation service, which accumulates
adaptive reliable services to meet the latency constraint sensitive application entails being
satisfied by all sub-parameters.
- - Active Sensor
A ISensor Objective
(Q-1) no of q-bits
H or XOR gate
Fig 2: Quantum based sensor consolidation system
«Allow»
LLLLL 30 Sensor Contiguity Rate]
l«Modirate»
Optimal Knack Rate
«Reject»
Fig 3: Quantum Measured Decision-Making Model
2|Page
Description
adaptive reliable services to meet the latency constraint sensitive application entails being
satisfied by all sub-parameters.
- - Active Sensor
A ISensor Objective
(Q-1) no of q-bits
H or XOR gate
Fig 2: Quantum based sensor consolidation system
«Allow» LLLLL 30 Sensor Contiguity Rate]
l«Modirate» Optimal Knack Rate «Reject»
Fig 3: Quantum Measured Decision-Making Model
2|Page
Description
The quantum enabled machine learning (QML) would give more impact on computing the massive amount of data which have generate from multiple IoT domains. Why specifically, IoT, means: Nowadays everything wants to be automated, which ultimately generates immense data, but there is need of computation and analysis services to compute this data while making an automated decision. The data might be inaccurate (poor quality, redundant, loss data and mixed of all) and the data generate source points are industries, academic institutions, agriculture, transport, smart cities, smart grids etc. Therefore, controlling inaccurate data generation is possible by selecting potential sensor node into the network. In this extension, the QML enhances such abilities intelligently by building possibilities to analyze quantum states and its systems. It enables hybrid methods which are combined with quantum and classical processing, where deliberately computation subroutines are accommodated. These routines are complex and perform computation pretty faster with quantum devices support to accomplish the objective.
Sensor consolidation remains an important challenge in IoT and Cyber Physical Systems (CPS). Sensor consolidation plays a vital role to grab accurate data from various IoT frameworks. So, selecting a sensor, which should allow into the network and which should not base on decision system by evaluating all aspects. It ultimately generates unique valuable data by satisfying all entail aspects. This entire process would be carried out with our proposed QML approach.
Background and prior art of the invention: Billions of Internet of Things (IoT) sensor devices are interconnected to perceive data towards a unique platform to, where all sensor data to be analyzed and computed to make certain quality of service. To accomplish a maximizes data accuracy, there is an essentialneed to design and develop quantum-based reliable methods. The feasible node
1| P a g e must have to satisfy all sub-parameters such as data accuracy, linearity, repeat-ability, a span of window time, response time, occupation range, etc.
IoT has become a backbone for innovative application domains at present and also in forthcoming years. Some recent extant works are investigated to make a strong base of this research work. Those are listed below.
• An amended network has designed with active mobile devices to estimate
the human body temperate status with a cloud-enabled framework. It operates based on event-function-model. They measured the performance of the system w.r.t standard bench-mark systems. • Cross-layer intruder repellent protocol has designed for moderate communication purpose. The main objective is to resolve time-constraint sensitive decision-making issues. • Many application frameworks have used quantum models for qualitative services. Such as, A quantum-based data distribution method has designed to diminish traffic issues to avoid privacy and security attacks.
Summary of the invention:
In this invention, we designed Quantum Machine Learning based Sensor Consolidation (QMLSC) approach based on two phenomenal methods to select potentially satisfied sensors of the framework. Those methods are Sensor contiguity rate, Optimal knack rate of the sensor. Each Q-bit has enabled with underline objective of sub-parameters w.r.t to the classical bits of that sub-parameter outcomes. Hence, an optimal quantum-based IoT framework makes adaptive decision-making mechanism, which is essential to accomplish reliable service.The proposed system has different components to evaluate like the sensor repeatability, sensing radio range, sensor span, linearity, reproducibility etc. It ultimately generates accurate data which helps to make accurate decision-making system.
Objective of the invention: The primary objective of this invention is to bring a new system for reliable service through Quantum Machine Learning approach and to accomplish this objective, we have
21 P a g e designed two novel computational techniqueswhich applies on active mobile sensor nodes to assess the feasible sensor, which became a target sensor to accommodate computation and analysis service. Ultimately, we called this process is by the sensor, for the sensor. Statement of the invention:
Resource scheduling among fog environment nodes has become a challenging task to meet time-sensitive latency constraints. Most of the cases the classical bit-based decision has been considered. It may lead to making false declaration because 0 or 1 two combinations, wherein quantum mechanisms, the traditional binary bits count, remain decided how many combinations have to be considered to make an accurate decision. In this extension, a quantum formalized node-specific parameter is essential. To streamline this issue, we designed a Quantum Machine Learning based Sensor Consolidation (QMLSC) approach based on two phenomenal methods to select potentially satisfied sensors of the framework. Those are Sensor contiguity rate and Optimal knack rate of the sensor. The Q-bits have enabled with underline objective sub-parameters w.r.t to the classical bits of that sub-parameter outcomes. Hence, an optimal quantum-based IoT framework makes adaptive decision-making mechanism, which is essential to accomplish reliable service. In addition to this, Quantum Neural Network system remains designed with the above-described models to determine thefeasible computational node to achieve real-time service delivery with a reliable quality objective.
Brief description of the proposed architecture:
The proposed invention proves
1. Q-bit Measurement • As per the demand to scrutinize the node, the respective parameters are to be considered. • The beauty of quantum computing is, all three states of probability models have conceded to finalize the outcome with esteem gate adaptability. 2. Quantum Analysis
31Page
• As the individual demands of sub-parameters, the q-bit register will amend all entails. • It makes a scope to minimize the number of parameters; which shows more impact on time complexity. 3. Quantum Measurement index for Spatial and Temporal Analysis w.r.t time • The underlying sensor objective has formulate by considering iterative values which come under the limited amount of window time. • Designing a measurement index by considering high priority values is a challenging task; which comes under this iterative step. 4. Optimal decision making • Segmenting the measurement index outcome and designing a decision making system is a phenomenal concept. The extension of this concept, I have been demonstrated with bellow framework. • Selection of feasible node comes under the comparative analysis of the adaptive measurement index.
Fig. 2 describes the sensor node consolidation mechanism by a bottom to top approach. Here, the (q-1) bits are considered to evaluate each parameter. For instance, the 9 parameters are listed then, at each time window, the respective values will be esteemed with q-bit registered, and outcomes are to be estimated with H or XOR or Q-gate.
The outcome to be compared with an actual object value.
41Page
• If iteratively, the parameter has inadequate value, then the sensor has to remove from the active sensors list. • In this section, might be the sensor remain to continue, but the last section would discontinue if and only if, the sensor remains to fail to meet the objective. • The sensors are consolidated by assessing
* Sensor contiguity rate * Optimal knack rate of the sensor • Actually, the q-bits remains used to evaluate low number of sensors as per above considerations. • Quantifying and satisfying threshold values are the essential parameters during this approach. • The Machine Learning approaches are considered to avoid haphazard mapping and migrations. It purely increases performance of the system compare to the existing systems.
Fig 3, illustrates the Quantum measured decision-making system, where the sensor contiguity rate (SCR) and optimal knack rate (OKR) of the sensor are estimated to identify the available sensor. Here, the tentative Equation 1, which is used to determine
OKR value. Where E
j=1
¶ojrefers sub-parameter value, zujrefers normalized weight of the corresponding sub
parameter.
Subsequently, the novel segmentation system segments the outcomes of the measurement index into three sub-segments to identify decision and notification based on sub-segment outcome value based on its bounded range.
51Page
Claims (9)
1. The proposed approach provides accurate data by consolidating potential sensor to make accurate decision in terms of computation and analysis to meet latency sensitive constraints.
2. Sensor contiguity rate model remain used to assess the surrounding coverage rate by tracking and meeting the objective of area.
3. Optimal knack rate of the sensor model remains used to assess the sensor ability and its potential rate, which plays important role while making active and inactive mode decision.
4. Our proposed approach provides absolute accurate data with minimal data cost during the entire span of each sensor.
5. This invention uses machine learning approaches for analysis purpose while designing adaptive decision-making system.
6. In second invention uses Quantum based Convolution Neural Network system to streamline sensor selection and decision-making issues.
7. The underlying sensor objective has to formulate by considering iterative values which come under the limited amount of window time.
8. The Machine Learning approaches are considered to avoid haphazard mapping and migrations. It purely increases performance of the system compare to the existing systems.
9. Subsequently, the novel segmentation system segments the outcomes of the measurement index into three sub-segments to identify decision and notification based on sub-segment outcome value based on its bounded range.
1 Pag e
Quantum Machine Learning based Sensor Consolidation Approach Sep 2020
for IIoT
Diagram 2020102437
Fig 1: :Proposed Q-SC Model
1|Page
Fig 2: Quantum based sensor consolidation system
Fig 3: Quantum Measured Decision-Making Model
2|Page
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2020102437A AU2020102437A4 (en) | 2020-09-25 | 2020-09-25 | Quantum Machine Learning based Sensor Consolidation Approach for IIoT |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2020102437A AU2020102437A4 (en) | 2020-09-25 | 2020-09-25 | Quantum Machine Learning based Sensor Consolidation Approach for IIoT |
Publications (1)
Publication Number | Publication Date |
---|---|
AU2020102437A4 true AU2020102437A4 (en) | 2020-11-12 |
Family
ID=73048430
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
AU2020102437A Ceased AU2020102437A4 (en) | 2020-09-25 | 2020-09-25 | Quantum Machine Learning based Sensor Consolidation Approach for IIoT |
Country Status (1)
Country | Link |
---|---|
AU (1) | AU2020102437A4 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112286666A (en) * | 2020-11-17 | 2021-01-29 | 重庆邮电大学 | Fine-grained data flow reliable unloading method based on callback mechanism |
-
2020
- 2020-09-25 AU AU2020102437A patent/AU2020102437A4/en not_active Ceased
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112286666A (en) * | 2020-11-17 | 2021-01-29 | 重庆邮电大学 | Fine-grained data flow reliable unloading method based on callback mechanism |
CN112286666B (en) * | 2020-11-17 | 2022-07-15 | 重庆邮电大学 | Fine-grained data stream reliable unloading method based on callback mechanism |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11132608B2 (en) | Learning-based service migration in mobile edge computing | |
US20230024501A1 (en) | System and Method for Throughput Prediction for Cellular Networks | |
Ashok et al. | Vehicular cloud computing through dynamic computation offloading | |
US10803186B2 (en) | Systems and methods for dynamic application management | |
AU2020104133A4 (en) | Expected conditional clustered regressive deep multilayer precepted neural learning for iot based cellular network traffic prediction with big data | |
WO2023016159A1 (en) | Method and system for predicting network traffic of smart city | |
WO2020098016A1 (en) | Network traffic prediction method, device, and electronic device | |
Fiandrino et al. | Toward native explainable and robust AI in 6G networks: Current state, challenges and road ahead | |
AU2020102437A4 (en) | Quantum Machine Learning based Sensor Consolidation Approach for IIoT | |
US10432477B2 (en) | Performance monitoring at edge of communication networks using hybrid multi-granular computation with learning feedback | |
US20220156658A1 (en) | System and method for managing resources | |
WO2021169478A1 (en) | Fusion training method and apparatus for neural network model | |
da Silva et al. | Online machine learning for auto-scaling in the edge computing | |
Yamamoto et al. | Prediction of traffic congestion on wired and wireless networks using RNN | |
CN117573477A (en) | Abnormal data monitoring method, device, equipment, medium and program product | |
Kasuluru et al. | On the use of Probabilistic Forecasting for Network Analysis in Open RAN | |
Shukla et al. | Analysis and detection of outliers due to data falsification attacks in vehicular traffic prediction application | |
CN102282824A (en) | A method, device and computer program product for service balancing in an electronic communications system | |
Xue et al. | CoMap: Proactive Provision for Crowdsourcing Map in Automotive Edge Computing | |
Li et al. | An Empirical Study on GAN‐Based Traffic Congestion Attack Analysis: A Visualized Method | |
KR20210076928A (en) | Fast and efficient sorting system | |
Liu et al. | Glee: Gpr-based latent effect elimination for performance prediction of big data transfer | |
da Silva et al. | Online Machine Learning for Auto-Scaling Processing Services in the Edge Computing Environment | |
US20240073716A1 (en) | Anomaly Prediction in OpenRAN Mobile Networks Using Spatio-Temporal Correlation | |
Yang et al. | Discovering spatial contexts for traffic flow prediction with sparse representation based variable selection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FGI | Letters patent sealed or granted (innovation patent) | ||
MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |