
Artificial Intelligence in Instrumentation, Control and Automation
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
Revolutionize your industrial practice with this essential book, which provides a comprehensive overview of how artificial intelligence can be integrated into instrumentation and control systems to achieve unprecedented precision, efficiency, and autonomous optimization.
Artificial Intelligence is increasingly becoming a game-changer in the fields of instrumentation, control, and automation, offering unprecedented capabilities to optimize processes, enhance efficiency, and drive innovation. AI algorithms and techniques could be integrated into traditional control systems to create smart and adaptive solutions capable of learning from data and making autonomous decisions for dynamic real-world environments. From predictive maintenance in manufacturing plants to navigation of autonomous vehicles in complex roadways, AI empowers instrumentation and control systems to operate with heightened precision and agility, revolutionizing industries across the board. This book will present the power of AI to optimize processes, enhance efficiency, and achieve unparalleled precision in instrumentation, control, and automation applications. It provides a comprehensive overview of these emerging technologies and their role in optimizing the instrumentation, control, and automation, covering topics such as neural networks and deep learning in control systems, data-driven modeling and prediction in automation, and optimization and decision-making in instrumentation using AI.
More details
Other editions
Additional editions

Persons
B. Jaganatha Pandian, PhD is an Associate Professor and the Head of the Control and Automation Department in the School of Electrical Engineering at the Vellore Institute of Technology with more than 20 years of experience. He has published more than 20 journal papers and more than 15 conference papers. His research interests span machine learning, process control, and intelligent systems.
N. Amutha Prabha, PhD is a Professor in the Department of Instrumentation in the School of Electrical Engineering at the Vellore Institute of Technology with more than 25 years of teaching experience. She has published more than 20 journal papers and more than 15 conference papers. Her research includes wireless LAN networks and discrete-time linear systems.
Abhishek Gudipalli, PhD is an Associate Professor in the Department of Instrumentation in the School of Electrical Engineering at the Vellore Institute of Technology with more than 15 years of teaching experience. He has published more than 40 journal papers and more than 15 conference papers. His research interests include image processing, machine learning, IoT, and electric vehicles.
V. Indragandhi, PhD is a Professor in the Department of Energy and Power Electronics in the School of Electrical Engineering at the Vellore Institute of Technology. She has authored 100 research articles in leading peer-reviewed international journals, one book, and three patents. Her research interests include power generation, inverters, and photovoltaics.
Content
Preface xxv
1 One-Shot Learning for Inertial Measurement Unit-Based Phone Gesture Recognition 1 Subramaniyaswamy Vairavasundaram, Indragandhi V., Arnav Jain, Pavan Dheeraj, Pragun Gurkhi Chetan and Srinath Chitrala
2 Optimizing Hydrogen Consumption from Fuel Cell in DC Microgrid Energy Management Using Efficient State Machine-Fractional Order PID Control 17 Shashi Bhushan Mohanty, Satyajit Mohanty, Mrutunjaya Panda, Sandeep S. D. and Soumya Ranjan Mahapatro
3 Forecasting of Electromagnetic Relay Epoch Using Artificial Intelligence 31 T. Maris Murugan, E. Sathish, C. Jayabharathi and A. Malligarjun
4 Cancer Prediction Using Machine Learning 51 Anuprabha S.S., Abinaya P., Pooja Nandhini N., Satyanarayan G.D., Revathi S. and N.S. Raghavee
5 Parkinson's Disease Prediction Using Convolutional Neural Network (CNN) 65 Sheeba Rachel S., J. Godwin Ponsam, Bharath S. and Saiganesh V.
6 Crop Yield Prediction Using Machine Learning and Deep Learning Techniques 77 Angulakshmi Maruthamuthu, Balasingam B. and Khushi K. S.
7 A Deep Learning Approach for Signature Recognition 89 Jasmine Pemeena Priyadarsini M., Viswa Brahmana Nanda Kishore, Dhavileswarapu Meher Anand, Murra Anil Kumar Reddy, Tamizharasi R., Ganesan Subramanian, Ernest Bravin Clinton S. and G.K. Rajini
8 Modeling Efficient Deep Learning Network on Imbalanced Data for Pest Prediction 113 D. Lakshmi Sreenivasa Reddy, S. Siva Priyanka, C. Venkata Narasimhulu and Dhana Lakshmi N.
9 PPG as a Biometric: A Study on the Effectiveness of Statistical Input-Based ML Algorithms in Disadvantageous Scenarios 123 Sathvik Rajampalli, Kaviya Dharshini A. S., Nithillen Jayaseelan and Jeeva J. B.
10 Classification of Physical Fitness Using Neural Networks 135 Shovan Sahoo, Piyush Kumar Sinha, T. Shankar, Ravi S. and Marimuthu R.
11 Performance Evaluation of Convolution Neural Network Architectures for Deepfake Detection 153 Anitha Julian, Hariharan E., Ramyadevi R. and Lingasri P.
12 Structural Defect Detection in Walls Using Convolutional Neural Networks 167 Anitha Julian, Thanga Deepika R., Naveenaa V. R. and Pradeepasri S.
13 Non-Invasive Temperature Monitoring for Testicular Health 181 P. Sinthia, Madesh M. and Suriyaprakash K.
14 Driver Sleep Detection and Emergency Word Spotting Using Similarity Map and Bi-LSTM 195 Arun S. L., Tarun Raj R. and Vijayapriya R.
15 A System Theoretic Stochastic Adaptive Model of Neuron with Probability of Firing 213 Chittotosh Ganguly
16 An Overview of Capacitor-Diode Voltage Multiplier-Based High Voltage Pulse Generators 227 Shanmuga Sundari A. and Vijayakumar D.
17 Optimal Tuning of PI Parameters for Speed Control of BLDC Motor 247 P.V.S.K. Kousik, Namra Nadem and Bagyaveereswaran V.
18 Tracking Control of a Robotic Arm Using Model-Based Neural Control Approach 259 K. Jaswanth, B. Jaganatha Pandian and Nohaidda Sariff
19 Design of Static Output Feedback Controller for Positive Systems: An LMI Approach 277 Jitendra Kumar Goyal, Adithya Suresh, Adhiraj Kaushik, Mathew Santosh, Amutha Prabha N., Ankit Sachan, Sandeep Kumar Soni and Chockalingam Aravind
20 Model Free Robust Controller Design for Half Quad Rotor Aero System: An Experimental Study 289 Jitendra Kumar Goyal, Jonnada Harshavardhan, Yashwant Ramesh Dhote, Partha P. Katkar, Amutha Prabha N., Ankit Sachan, Sandeep Kumar Soni and Swee King Phang
21 The Design and Control of Grid-Connected PWM Rectifiers Using a Soft Switching Control Strategy 307 S. Suba, M. Malukannan, R. Uthirasamy, M. Dinesh, P. C. Sivakumar and S. Dinesh
22 Software Defect Prediction by Exploiting Semantic and Syntax Information 319 M. Senthil, Arunkumar C. and Sabarish B.A.
23 Evolutionary Interfaces: Unleashing Creativity in UI Design with Generative AI 333 M. Ravi Teja, Sabarish B.A. and Arunkumar C.
24 Hybrid PV and Supercapacitor-Powered UAVs for Optimized SWIPT in IoT Networks Using DDPG and Game Theory Model 349 P. Keerthana and A. Vijayalakshmi
25 Design of a Smart Restaurant Ordering System Utilizing Human Activity Recognition and Machine Learning in a Digital Infrastructure 371 Gundumalle Ashlin Joel, Navamani T.M., Archita Sharma, Vansh Harkut, Mansi Saxena and Arnav Goenka
26 IoT-Based Smart Electricity Energy Meter 387 Hariny A., R. Resmi and Ashwini K.
27 IoT-Enabled Framework for OpenViBE-Based Online BCI with an OSC-Driven Somatosensory Stimulator and Unity Animation Control 399 Vadivelan Ramu and Kishor Lakshminarayanan
28 Design of Low-Cost Durable System Using IoT Technology for Signal Violated Vehicle Detection 409 Sujatha Canavoy Narahari, Abhishek Gudipalli, K. Saiteja, K. Hemchandra, K. Sudhamsh and Wei Jen Chew
29 IoT in an E-Bike with Theft Detection and Accident Alert 423 Rajesh Kannan Megalingam, Puppala Gautham Prasad, Sreehari Sahadevan, Bhupathiraju Mohan Varma and Kummara Anand Dileep
30 IoT-Based Soil Fertilizer Dispensing System for Smart Agriculture 443 Karthikeyan A., Manmeet Singha, Abhiansh Wadegaonkara and Rajalakshmi S.
31 Deep Reinforcement Learning for Autonomous Vehicle and Surface Vessel Navigation Using Unreal Engine 455 Mukund Pareek, Muthunagai S. U., Ramya G. and Nivitha K.
32 Design of a Smart Bin System for Efficient Waste Management 467 Yi Wen Tan, Wai Leong Pang, Hui Hwang Goh, Kah Yoong Chan, Gwo Chin Chung and N. Amutha Prabha
33 Enhancing Energy Efficiency in Cooling Systems: Benchmarking Machine Learning Algorithms for Cooler Energy Consumption Prediction 479 Mayeesha Bashar, Chockalingam Aravind Vaithilingam, Manee Sangaran Diagarajan, Jitendra Kumar Goyal and Nagentrau Muniandy
34 Enhanced Fault Detection for Solar Panels with YOLOv7 on RGB Images Using Augmentation Strategies and an Early Stopper 503 Weng Ti Wong, Swee King Phang, Nohaidda Sariff, Husna Sarirah Husin and B. Jaganatha Pandian
35 Automated Plaque Identification in Arterial Walls Using MATLAB 521 Nazarkar Pravalika, Jabeena A., Vetriveeran Rajamani, Jasmin Pemeena Priyadarisini M. and Nazarkar Archana
36 Hybrid PSO-SA Algorithm for Efficient 3D Path Planning of UAVs 535 Shankar Thangavelu, Lavanya Nagarajan, Akshay Narendran, Samarth Begari A. and Marimuthu R.
37 Voice-Activated Alert System for the Hearing-Impaired 557 Dinesh N., Harshavardhan J. and M. Manimozhi
38 Energy Efficient Cluster Using Floyd Warshall Shortest Path with Artificial Bee Colony Optimization for Data Transmission in MANET 569 S. Usha Devi and K. Preetha
39 ADAS for Improving Road Safety: YOLOv10-Based Detection of Cows, Potholes, and Traffic Signboards 585 Jayakrishnan P, Sunsitha Varshini Pugalaendhi and Sanaputur Sai Charan
40 Design, Development, Implementation and Optimization of a Low-Cost CNC Pen Plotter Using GRBL 599 Jibesh Mahanta and Sankardoss Varadhan
Bibliography 609 About the Editors 611 Index 613
1
One-Shot Learning for Inertial Measurement Unit-Based Phone Gesture Recognition
Subramaniyaswamy Vairavasundaram1*, Indragandhi V.2, Arnav Jain1, Pavan Dheeraj1, Pragun Gurkhi Chetan1 and Srinath Chitrala1
1School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India
2School of Electrical Engineering, Vellore Institute of Technology, Vellore, India
Abstract
With the use of Inertial Measurement Unit (IMU) data, a method for mobile gesture recognition is presented in this work. By allowing users to design and use their own custom gestures, we overcome the limitations of current mobile apps that provide pre-defined gestures. This user-centric approach supports a wider range of personalized interactions and promotes a more natural mobile experience. We use a modified Siamese Neural Network, which is traditionally used for image classification, to accomplish this. In order to independently process the IMU data sequences recorded for a user-defined gesture and a live gesture recording, this network uses two identical 1D Convolutional Neural Networks (CNNs). The CNN creates an embedding that encodes the properties of the gesture by efficiently extracting the required features from the input data. Next, we test three potential similarity checking mechanisms to see how well they perform, a Dense Network, Euclidean Distance, and Cosine similarity. Our evaluation found Cosine similarity to be the most promising. This similarity function is used to compare the embedded user's customized gesture and the live recording. The system is able to classify live gestures in real time thanks to this efficient comparison of embedded gestures. Achieving real-time performance on mobile platforms is a key focus of our work. This is especially important for mobile deployment because it minimizes battery drain and ensures responsiveness.1D CNNs' low computational requirements and effectiveness in feature extraction achieved better results.
Keywords: Gesture recognition, one shot learning, similarity measures, embedding, convolutional neural network, siamese networks
1.1 Introduction
In today's world of increased human-computer interaction, user input methods for mobile computers have primarily focused on touchscreens and buttons. In this regard, we aimed to explore alternative input methods by leveraging the capabilities of Inertial Measurement Units embedded in modern smartphones. IMUs offer data on motion and orientation, which is commonly used for gesture recognition. This particular aspect has been explored by various smartphone brands that offer IMU-based gesture-based control for certain functions, such as turning on the flashlight or opening the camera app on a device [1].
Despite this potential, there aren't many applications specifically designed to record and classify custom IMU gestures and perform actions from them. In this work, we present a system that bridges this gap. Our objective is to develop a system that enables users to create personalized gesture-based controls for various uses on a device. Ideally, the system we developed should classify gestures even with minimal training data or setup from the user; this requires a One-Shot or Few-Shot approach. Next the gesture recognition should occur with minimal latency, to ensure a seamless user experience. Finally the system should achieve sufficient accuracy for everyday use.
1.2 Related Works
Device elements utilizing Inertial Measurement Unit (IMU) have already enabled gesture recognition operations [1]. However, despite the advantages they provide, conventional methods are only successful given they are fitted into large datasets, and this specific ability restrains usage when little information is available [3]. These one-shot learning techniques promise hope for how these challenges can be addressed.
Image datasets have been used to investigate the concept of one-shot learning in image recognition applications. Siamese Neural Networks were proposed by Koch et al. [2] for the case, but there were issues with the limited amounts of data that could be used to train these networks and their capacity for generalization. Prototypical networks [4] and matching networks [6], two other techniques that have been the subject of other recent research, appear to be promising; however, they may have issues with noise-related uncertainties in the real inertial measurement unit (IMU) input streams.
Deep learning methods have been applied to recognize gestures using IMU data. In their study, Suri et al. [3] attained accuracy by employing Deep Neural Networks (DNNs) although their emphasis was on refining the classifier rather than delving into one shot learning strategies. Another study by Kim et al. [1] introduced an LSTM centered method, which faced challenges, with overfitting owing to a scarcity of data. Other modalities such as surface electromyography (sEMG) have also been investigated. Ding et al. [5] achieved high accuracy using CNNs with sEMG signals, but their method requires high computational resources, limiting real-time applications on mobile devices like smartphones. While multimodal approaches combining different data sources like IMU and camera data have shown success, this research focuses solely on IMU data due to its prevalence in smartphones [7].
One-Shot Learning for EMG-based Gestures: The recent work by [8] demonstrates the feasibility of applying one-shot learning to gesture recognition using EMG data. However, their work does not address domain adaptation for IMU data and lacks ablation studies to analyze the contribution of each component in their proposed method. In conclusion, while deep learning approaches have shown promise for IMU-based gesture recognition, limited research has explored one-shot learning techniques in this domain. This research aims to bridge this gap by investigating the application of one-shot learning for hand gesture recognition using IMU data collected from smartphones.
1.3 Siamese Architecture
For our one-shot learning task, we chose 1D convolutional neural networks (CNNs) after carefully reviewing various literature. Although recurrent architectures such as LSTMs and GRUs are very good at identifying long-term dependencies in sequential data, the lack of gesture recordings per action class restricts the applicability of these architectures. These intricate models with many parameters tend to overfit this limited set of data, which results in mediocre performance on unseen gestures. Furthermore, the training of LSTMs and GRUs necessitates a large number of computational resources, which increases power consumption and latency on mobile devices with limited processing power. However, 1D CNNs are a good alternative since they can effectively extract relevant features from short clips, which is similar to how features are obtained from single gesture recordings. They are ideal for real-time gesture recognition on mobile devices because of their simpler architecture and fewer parameters, which also make them computationally efficient to run on a mobile GPU.
1.3.1 Design
Our system will work based on the Siamese Architecture inspired by Koch et al. [2]. The gestures will be recorded with a rotation vector sensor on an android device. This recording will be converted into an embedding of lower dimensionality, which will be saved during the user's recording of gestures.
During runtime, live input from the sensor will be embedded and compared with the saved gesture embeddings to check for similarity using cosine distance. This will be done iteratively for all the gestures to check for a close match. When this occurs, a corresponding user defined command will be executed (Figure 1.1).
Figure 1.1 Siamese network block diagram.
1.3.2 Architecture Modules
1.3.2.1 Input
We gather input from the composite rotation vector sensor defined in the Android Open-Source Project (AOSP). This gives us the rotation in the form of a unit quaternion (w,x,y,z), a 4D representation of absolute rotation. We sample this sensor arbitrarily at 100 Hz to later reduce if needed and set the duration for the gestures to be of 3 seconds, as longer gestures are impractical from a usage standpoint. This makes the array or matrix of floating-point values of shape (301,4) for a single gesture.
1.3.2.2 Dataset
We recorded 18 unique gestures at least 20 times each to create a dataset of 366 gesture recordings. Each recording is sampled at 100 Hz for 3.01s, which makes the dataset shape (366,301,4). We then created 2 pairs of recordings (one positive and one negative) for each of the 366 recordings, the positive pair contains recordings from the same class, and the negative pair contains recordings from different classes. This gives us our final dataset of shape (732,2,301,4) 732 instances of a pair of recordings of shape (301,3).
Table 1.1 Implemented embedder architecture.
Layer (type) Output shape Param # embedder_input (InputLayer) [(None, 301, 4)] 0 embedder_conv1 (Conv1D) (None, 299, 18) 234 max_pooling1d (MaxPooling1D) (None, 149, 18) 0 dropout (Dropout) (None, 149,...System requirements
File format: ePUB
Copy protection: Adobe-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Install the free reader Adobe Digital Editions prior to download (see eBook Help).
- Tablet/smartphone (Android; iOS): Install the free app Adobe Digital Editions or the app PocketBook before downloading (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (not Kindle).
The file format ePub works well for novels and non-fiction books – i.e., „flowing” text without complex layout. On an e-reader or smartphone, line and page breaks automatically adjust to fit the small displays.
This eBook uses Adobe-DRM, a „hard” copy protection. If the necessary requirements are not met, unfortunately you will not be able to open the eBook. You will therefore need to prepare your reading hardware before downloading.
Please note: We strongly recommend that you authorise using your personal Adobe ID after installation of any reading software.
For more information, see our ebook Help page.