Computational Intelligence for Sustainable Development
By Brojo Kishore Mishra, Editor
Nova Science Publishers
Brojo Kishore Mishra’s edited collection of research works, Computational Intelligence for Sustainable Development (2022), pulls from technology, engineering, and rigorous research traditions to advance sustainability efforts in India and other regions of the world. The focus places a premium on the future and the present and less so on the inherited past (“legacy” not as a map for the future).
Figure 1. Impressionistic Earth
This collection focuses on how to improve systems and processes. It highlights effective technologies. It considers where competitive advantages may be had in the promotion of “sustainable agriculture, good health, clean water and sanitation, affordable and clean energy, sustainable cities and communities, sustainable industrialization and innovation, and sustainable use of terrestrial ecosystems” (Mishra, Preface, 2022, p. ix). The north star points to the Sustainable Development Goals (SDC) that were arrived by a majority of national consensus and applies globally.
As to the “computational intelligence” in the title, that refers to the uses of “Artificial Neural Networks, Fuzzy Systems, and Evolutionary Computing” used to process data and acquire insights.
A core question is how people may thrive in the present while controlling for environmental harms from anthropocentric living.
Healthcare and AI
Sandeep Poddar’s “Sustainable Healthcare and Artificial Intelligence: Some Facts” (Ch. 1) describes the harnessing of a particular class of computational technologies to enhance healthcare through drug development, diagnostics, data analysis, and the provision of healthcare services in preclinical and clinical contexts. Computer technologies enable quicker response times for healthcare and ease “the burden on health workers” (Poddar, 2022, p. 1). Given the value of human health, there is a need for “proper ethical consideration” when using AI technologies in the healthcare space (Poddar, 2022, p. 1). AI outperforms humans in many healthcare and other tasks. This summary work provides a broad view of AI used in healthcare, as documented in a selection of the academic literature.
Preventing Rice Leaf Diseases with AI Approaches
Agriculture is critical for the survival of the human (and other) species. D. Akila, Kusum Yadav, Ranbir Singh Batth, Souvik Pal, and Jayakarthik’s “Rice Leaf Diseases Prediction using PSO Segmentation and Deep CNN Classification” (Ch. 2) focuses on the use of machine vision and AI algorithms to identify crop diseases and pestilence as soon as possible, in order to enable farmers to apply the most effective mitigations. The producing of rice “is the sole source of income for hundreds of millions of people” (Akila, Yadav, Batth, Pal, & Jayakarthik, 2022, p. 25). Rice is farmed in “over 100 countries in a variety of agroecological and socioeconomic settings” and is “one of the most significant human food crops” (p. 27). Rice covers a tenth of “all arable land on the planet” (p. 27).
At a macro level, agriculture has implications for a nation’s economy, its citizens’ health, its politics, and its social stability, among others. Mass hunger, for example, quickly turns to anger and destruction (and the overturning of governments and often loss of human life).
Figure 2: Rice Paddies in India (from a reference in CrAIyon)
In this work, Particle Swarm Optimization (PSO) and Deep Convolutional Neural Networks (DCNN) are applied to the analyzing of images of rice leaves. The research team explains: “In a broad field, automatic illness detection and identification is particularly helpful since it reduces the work, time, and cost associated with watching and analysing disease symptoms” (Akila, Yadav, Batth, Pal, & Jayakarthik, 2022, p. 25). The proposed method enables 98.43% accuracy based on testing with labeled image data. They write: “Farmers will be able to use a simple digital camera to detect early signs of rice illness using the deep convolutional networks model” (p. 29); the work also uses images from low-cost cell phones, which may be used for the capture of field imagery, to align with practical on-ground considerations.
This research work highlights some of the complexities in raising crops, considering “lighting, humidity, nutrients, fertilizer, water management, and farming conditions,” among others (Akila, Yadav, Batth, Pal, & Jayakarthik, 2022, p. 29). Some “42 of the 266 bug species” in rice habitats are pests (p. 27), which can destroy crops and / or limit yields. For computational intelligence to be applied effectively, multi-disciplinary information needs to be harnessed. Growing rice and other crops is complicated business, in the context also of global warming and climate change.
This work provides a solid review of the literature. There are descriptions of AI processing techniques. From this, a process is engineered and tested against a known dataset of images to see the actual performance. A general sequence goes as follows: image acquisition, image preprocessing (and encoding), feature extraction, PSO segmentation, and DCNN classification (Akila, Yadav, Batth, Pal, & Jayakarthik, 2022, p. 36). For this study, images were taken at dawn and dusk “between 6:30 a.m. and 9:30 a.m., as well as 4 p.m. and 5:30 p.m.” (so in times when the light is not so defining or bright or flattening). The researchers used a Canon Powershot SX530HS, Gionee mobile phones, and LYF mobile phones. [It was not clear how they ensure focal depth to ensure consistency. Back in the day, researchers in the field would bring a measure to help capture the size of the plant leaf against a known size.] The backgrounds were removed using a black fill to reduce image complexity and save on computational processing expense. The researchers note that this work is the “first time a huge dataset of rice illnesses from the Indian farming industry has been gathered” (p. 38). The 979 collected images were separated into four disease categories: Brown Spot, Leaf Blight, Leaf Blast, Leaf Smut, and then the general category of Healthy Leaves. The images was transcoded to capture various visual aspects, from RGB (red-green-blue) to HSV (hue-saturation-value), and then to a hue-based version, and then a saturated version. Each visual type highlights particular visual aspects of the plant leaf.
The research team describes some of the digital image pre-processing to heighten the learning from the two main processes:
Image samples may contain noise and are not suited for direct processing, thus preprocessing processes are utilized instead. In this category are operations such as cropping, enhancing, filtering, smoothing, and changing the colour of an image. This stage enhances the optimal evaluation of the picture samples. To sharpen the photos, Auzi et al. (2013) used Laplacian filters after converting the images to HSV colour space, extracting the S (saturation) component, and then using histogram equalization. Pictures of a diseased area were removed after which the photos were changed to their suitable grey levels and the image was enhanced with the Laplacian filter. The collected picture data was changed to HIS (sic) colour space since some infected portions of plant leaves have higher intensity values than others. Cropped photos were used to increase CPU efficiency, decrease processing time, and increase disc storage. (Akila, Yadav, Batth, Pal, & Jayakarthik, 2022, p. 39)
[In the above block-quoted paragraph, the “HIS” probably is “HSI” for “hue, saturation, intensity”.] Segmentation involves the extraction of image features (of interest, and of relevance)
Particle Swarm Optimization is used to identify locational areas of interest:
Because of the complexity and variety of images, image segmentation is a difficult procedure. Lighting, contrast, interference, and other factors all have an impact on segmentation results. Using segmentation, you can pinpoint trouble spots and narrow down the condition. (Akila, Yadav, Batth, Pal, & Jayakarthik, 2022, p. 41)
The researchers include the code for the PSO segmentation algorithm (pp. 42-43).
For More about PSOs…
Ali Mirjalili’s video “Learn Particle Swarm Optimization (PSO) in 20 Minutes” includes some evocative explanatory visualizations.
A Particle Swarm Optimization algorithm has swarms of dots that converge on areas of interest. These areas carry more information than other parts of the 2d space.
Figure 3. Particle Swarm Optimization (from Deep Dream Generator)
The images are then processed for classifying. Convolutional neural networks or CNNs “can learn complicated problems extremely quickly due to weight sharing and more complex models utilized, which enable huge parallelization. Deep Convolutional neural networks can improve their chances of proper classification if big enough data sets (hundreds to thousands of measurements, depending on the complexity of the subject under study) are available to describe the problem. Convolutional, pooling, and / or completely linked layers make up these layers” (Akila, Yadav, Batth, Pal, & Jayakarthik, 2022, p. 43).
More on neural networks may be explored here:
“But what is a neural network? | Chapter 1, Deep learning:
There were 8 groups in the training data and 1 in the test dataset (Akila, Yadav, Batth, Pal, & Jayakarthik, 2022, p. 47). The researchers used common metrics for the assessment of the classifier: accuracy (A), precision (P), recall (R), and F1-score. They found some slight variances in differentiating between the various conditions, along the various measured dimensions (p. 49). It is beyond the purview of this work what the application design might look like.
An app that farmers would use would benefit from an awareness of the app’s strengths and weaknesses. Perhaps direct and clear advisement would also be helpful given inputs, for clarity, particularly for farmers who may struggle with literacy and numeracy, among others.
This chapter is very readable even for those who may not be as familiar with the technologies but are comfortable with technology terminology.
Sustainable Smart Cities with the Support of AI
S. Meenakshi Sundaram, Tajaswini R. Murgod, and M. Sowmya’s “Computational Intelligence for Sustainable Smart Cities and Communities” (Ch. 3) highlights the importance of global cities turning “smart” in order to attract youthful talent to enhance business development and growth and people’s quality of life and wellbeing. The floods of constant and big data are to be used for enhancing infrastructure and shaping the built environment. Cities will have to have “access to an open data platform and relevant information” (p. 57). In this vision, it is not only officials who have responsibility for benefitting the city and its running but all its informed and aware citizens. City data will also be needed to enable the building of “sustainable urban development” to adapt to climate change (p. 57), in a world where more than half the people live in urban areas and ”by 2050 more than two-thirds (of the global) population will live in cities” (p. 58).
Smart cities have existed for many years, but the concept itself may be fairly new depending on where a person lives and how much they have traveled. Over a hundred billion has been spent on smart cities since 2021 (Sundaram, Murgod, & Sowmya, 2022, p. 58). Urbanization is itself “a non-ending phenomenon” (p. 58). Smart cities are wired, with sensors and other connected devices, to enable continuous data collection and awareness. They write: “Smart cities utilize technology to improve access to public transport, manage traffic, optimize water, power supply (sic) and to improve law enforcement services, schools, hospitals to name a few” (p. 58). Ideally, traffic flows more smoothly and safely. There is less crime. Natural resources are used more tactically, with less wastage. Buildings are more energy efficient. Energy is renewable. A city then has less of an environmental footprint and is ultimately carbon neutral. There are green spaces for livability. There is high walkability. There is efficient public transportation. There is broad access to education, and there is available work for all. Healthcare is also available. A sustainable city involves a broad basket of goods.
Figure 4. Servers
The role of technology is seen as all-pervasive. There are AI supports for managing traffic, managing waste, anticipating energy consumption, identifying crimes occurring in real time (and tracking individuals as they move, from camera coverage-to-camera coverage), analyzing roads and predicting the need for repairs, predicting pollution levels, parking enforcement, coordinating public transportation, management of recycling, reducing traffic by redirecting drivers, analyzing “business and citizen energy usage,” assessing pollution emissions from a city, and others (Sundaram, Murgod, & Sowmya, 2022, pp. 64-65). Citizens may be notified of where to charge their electronic vehicles. Street lighting is smart and can brighten and dim responsively to environmental conditions. Some of the descriptions are idealized, but there has been progress on many of these endeavors.
One-Stop Dairy Product Management
Subrata Paul and Anirban Mitra’s “DairyShop: A Machine Learning-Based Platform for One-Stop Dairy Product Management” (Ch. 4) suggests that there are ways to set up an online system to ensure smooth operations around the selling of dairy products. They write:
For rationalizing the entire data, there is a requirement for a web-based gateway that would generate and reinforce dairy assets or infrastructure by entire dairy processors belonging to cooperatives as well as the private dairy sector. The author has tried to develop an online marketplace for the procurement of dairy products with the aim of covering the entire system’s objectives. (Paul & Mitra, 2022, p. 90)
The system is conceptualized as including some of the more cutting-edge capabilities, such as artificial intelligence and machine learning capabilities. They offer a flowchart of the proposed system from the perspectives of the users, the administrators of the system, and the merchant (in terms of common functionalities). The model reads like a description of simple extant systems more than for something that is highly cutting-edge, however. The specifications are fairly general. The actual focus on dairy is minimal.
Data Science and its Affordances
S. Kannadhasan, R. Nagarajan, G. Ramya, and C. Jisha Chandra’s “Recent Developments in Data Science and its Challenges” (Ch. 5) offers a general bridge to the topic of data science. “Big data,” they note, is used to refer to “data that has a high velocity, diversity, and volume” (p. 109). Various types of computer analytics are possible from structured (data tables) and semi-structured data (text, imagery, video), and others, in real time. Big data is seen to enable various applications and affordances.
Protecting Lightning Networks in Blockchain
Rajdeep Chakraborty, Sohini Roy, and Arun Sarkar’s “Intuistic Fuzzy Stream Cipher for Protecting Second Layer Lightning Network Transactions in Blockchain” (Ch. 6) introduces a method to protect “the lightning network in Blockchain in (a) stream cipher system where intuitionistic fuzzy logic is used to generate pseudorandom digits” (p. 121). They write:
Stream Cipher encrypts and decrypts data, producing a cipher text by combining the binary digits with pseudorandom digits, one at a time. The lightning network solves the scaling problem of blockchain cryptocurrency by introducing an additional second layer to the already existing blockchain where there exist multiple transaction channels between users. Security is needed to mitigate the risk of cyber-attacks and deceit. (p. 121)
The novelty of their system lies in “the fuzzification of stream cipher” for use in lightning networks that are part of blockchain platforms. Blockchain security is already protected using modern ciphers, but there are extant research questions about security in lightning networks. “Stream Cipher is one of the most secure manners to protect data if it becomes a one-time pad which decides by the randomness of the output bits in each clock cycle covering the whole plaintext,” they write (Chakraborty, Roy, & Sarkar, 2022, pp. 122-123).
So how is blockchain as a sustainable development technology? It enables the storing of data in distributed ways based on consensus mechanisms enabling trusted nodes to participate.
The researchers describe their system, and then they implement it and run it through a series of tests for data leakage. They use frequency tests, entropy tests, floating frequency tests, histograms, n-grams, autocorrelations, periodicity, and other approaches (to defend against known hacking methods), and they report the findings. They write with clarity about how the respective tests demonstrate the security aspects of their approach.
Making Bio-Fertilizers from Organic Matter for Agricultural Application
Rakesh Kumar Yadav and Shivram Krishna Chandrakar’s “Synthesis of Bio-Fertilizers with Nutrients (NPK) for Agricultural Use from Organic Matters” (Ch. 7) is not about “computational intelligence” leading to improved sustainability per se. The focus here is on how to make biofertilizers as a “a synthetic organic substance that contains live microorganisms” and is seen to be a powerful intervention in agricultural usage by providing nutrients to plants (p. 155). Some common approaches involve composting and landfilling. This work highlights local resources that may be used in the India context. This chapter reads like a solid work for sustainability.
Security for IoT Systems
Payal Bansal, Rajeev Kumar, Brojo Kishore Mishra, and Devendra Somwanshi’s “IoT-Based Security System using ESP-32 and Lasers and its Various Applications” (Ch. 8) has contents which do not seem to align with the title. There are challenges with writing clarity, image resolution, and word choices. The work reads as mostly descriptive of various microcontroller boards and their capabilities. Some of the phrasing is a little unclear, such as, “Arduino can be used to make free instinctive things or can be related to programming on your PC” (Bansal, Kumar, Mishra, & Somwanshi, 2022, p. 196). There are some schematics, but these are too small to be legible. This work offers a selective mashup of information but without the necessary structure or firsthand insight to serve as a guide for others.
Column Test Methodology in Geo-Environmental Engineering
J. Sumalatha’s “Column Test Methodology and its Versatile Applications in Geo-Environmental Engineering” (Ch. 9) is a solid chapter about a soil testing methodology that has wide application. The author writes:
The outcomes of column tests can be used to calculate the rates of contaminant transport in soil, which are required to determine the thickness of the soil barrier system to prevent the migration of contaminants with a view to design appropriate soil type and its thickness. Further, the results of column test can be used to select appropriate fluid to remediate contaminated soil by soil washing, efficiency of selected fluid, duration of washing and to estimate the volume of fluid required for washing the field soil. Contaminate transport parameters (diffusion coefficient and retardation factor) are commonly determined through column tests which are useful for the calculation of transport parameters. The transport parameters are predicted by comparing the experimental breakthrough curve with the theoretical curve generated using an advection dispersion model and with assumed transport parameters. The transport parameters, thus obtained are taken as the parameters for any given contaminant and for the given medium. (Sumalatha, 2022, p. 207)
Specifically, such testing enables informed design of clay liner for landfills, the “appropriate flushing fluid for the remediation of contaminated soil by washing and suitable amendment to immobilize the contaminants in the soil” (Sumalatha, 2022, p. 208). Soil itself is threatened by erosion, metals contamination, nano-plastics contamination, veterinary antibiotics contamination, chemical seepage, and other risks (p. 208). “The processes involved in contaminant transport through a soil liner includes advection, dispersion and are affected by retardation of solute mass” (p. 209). This work uses a diagram showing the apparatus for the column test and offers in-depth computational assessments of collected data in a clear, rigorous, and evocative way.
Detecting Physical Distancing with Arduino Ultrasonic and Passive Infrared Receivers
Rita Dwi Pratiwi, Fenita Purnama Sari Indah, Sandeep Poddar, Tukimin Bin Sansuwito, Faridah Mohd Said, and Riris Andriati’s “The Effectiveness of Arduino Ultrasonic and Passive Infrared Receivers on the Perception of Physical Distancing” (Ch. 10) is a work that evokes the SARS-CoV-2 / COVID-19 pandemic, as a product of that time. The use case involves helping people stay aware of their proximity to others to lower or limit the air-to-air transmission of the dangerous pathogen. The idea is that the two device types may be worn by people, and if others get too close, an auditory warning is sounded. This study explored which of the two device approaches (the Arduino Ultrasonic or Passive Infrared Receivers / PIRs) were more effective for this purpose, in a study in Villa Pamulang, in Depok City, Indonesia, among a small group of participants. They found that the Arduino ultrasonic sensors had “a higher effectiveness” than passive infrared receiver sensor necklaces (p. 229). This work suggests that wearables may be an effective intervention during some phases of a global pandemic (and even an epidemic). Such a work is commendable since it was achieved during the pandemic with so much of the world on lockdown.
Orifice as a Flow Measurement Device
Santosh Kumar Panda, Kali Charan Rath, and Balaji Kumar Choudhury’s “Analytical Model for Orifice as a Flow Measurement Device” (Ch. 11) focuses on a fluid flow measurement tool and how the data from this device may be analyzed for insights. Such devices are used in various industrial applications, including gas and oil, food production, and others. They set the stage:
The orifice works on the theory of Bernoulli’s equation which gives the relation between pressure and velocity as an energy head of a fluid flow…The principle of orifice meters is applied to the mining, chemical processes, oil, energy, nuclear, refrigerant devices, electricity production systems, oil pits pipeline, and food industries, where the fluid flows as a single-phase and multi-phase flow, which plays an essential role. (Panda, Rath, & Choudhury, 2022, p. 257)
This work defines the terms in this space, such as various nozzles, tubes, flow meters, and probes, and this defines their respective functions. The researchers define the equations applied to the data for practical analytics.
Using AI for Quantum Error Correction
Seema Verma, Rakesh Kumar Sheoran, and Savita Kumari Sheoran’s “Research Hotspots in Quantum Error Correction using Artificial Intelligence Techniques” (Ch. 12) provides a summary work on an important issue: How can people try to control for “faults occurring due to interaction of (the quantum) system with environment” to ultimately enable applied quantum computing? (p. 281) They explain:
The realization of a versatile quantum computer requires the implementation of a universal set of gates (a set of unitary transformations) at the logical level which is highly prone to error due to its interaction with the environment, noise, and other undesired interference. The temporal drifting of error in the quantum circuit operations may cause a higher error rate at the later stage and destroy the computing environment. To sustain a scalable and robust quantum computing environment and achieve high fidelity in operations it is necessary to keep the error below the desired threshold. (Verma, Sheoran, & Sheoran, 2022, p. 283)
This is a problem that is apparently still being worked by scientists. This chapter offers a summary of the state of play in quantum computing efforts. At core, they suggest that algorithms based on AI techniques, “machine learning, reinforcement learning, deep learning, artificial neural network, genetic algorithms, support vector machine, and natural language processing” have been “found effective in mitigating the quantum error which is an entirely different paradigm from classical error correction” (p. 281). They elaborate on their findings about efforts at the Quantum Error Correct (QEC) to enhance fault tolerance in quantum computing.
Figure 5. Quantum Computing (from Deep Dream Generator)
This work lists various big companies vying to set up quantum computing and striving for “quantum supremacy” (p. 297). There are apparently quantum simulators to enable study of quantum systems.
Crop Disease Detection Using AI
Goutam Sahu, Rutuparnna Mishra, Sujata Chakravarty, and Mamata Garanayak’s “Crop Disease Detection Using Image Processing and Convolutional Neural Network” (Ch. 13) opens with the suggestion that Indian farmers have an “insufficient awareness about the infection, pesticides and insecticides at hand to control the infections” (p. 305), and they propose an app to address this challenge. Their focus is on rice crops and the uses of various photos of rice leaves in situ in four categories (classifications): healthy leaf, bacterial leaf blight, brown spot, and Hispa. Their model has an accuracy of 98.81% and “the performance of leaf disease in paddy class like bacterial leaf blight and brown spot have achieved an overall 100% accuracy” (p. 305).
In their flow diagram, the process begins with loading a dataset of visuals, augmenting the image in the dataset, splitting the dataset into a 70% training set and a 30% testing set, training the dataset, building the convolutional neural network (CNN) model, testing the dataset, calculating the loss function, selecting the Adam optimizer, training the CNN with a specific number of epochs (iterations or cycles), classifying the paddy disease in the image into four categories (healthy leaf, Hispa, bacterial leaf blight, and brown spot) (Sahu, Mishra, Chakravarty, and Garanayak, 2022, p. 319). This is a strong chapter for understanding terms and the processes of convolutional neural networks (CNNs).
Face Detection for Learner Attendance
The next chapter deals with various ways that “attendance” may be taken in workplaces and schools, in Ritu Maity and Shamaun Alam’s “Automatic Face Detection Attendance System” (Ch. 14). Current systems use RFID cards (which can be spoofed), manual attendance which takes up time, and other approaches which can be improved on. This research team suggests that a better approach involves the use of the VGG face model. In their approach, they use a Raspberry Pi camera for image capture, LCD and LED, ultrasonic sensors, a buzzer; deep learning for face detection (a form of biometric), and GUI web pages “to maintain an attendance database” for the attendance (pp. 331 and 334). This work requires three facial images with different emotions to be captured prior, and then from that, face embeddings may be captured. The threshold is .8 for an accurate identification. They write:
Every facial embedding dataset consists of three triplets images. The set consists of one-class triplets, two-class triplets, and three-class triplets. In one class of triplets, all images are of the same expression let’s say happiness, in two-class triplets two face images will be of happiness and one will be of anger it will be a combination of emotions but at least two faces will be of the same type, in three-class triplets all three images will be of different type(s) of emotions. (Maity & Alam, 2022, p. 338)
The data was maintained on a SQL Lite platform. They tested their setup and identified persons with “more than 95% accuracy” (Maity & Alam, 2022, p. 346).
Fuzzy Systems in Image Processing
Aradhana Behura and Sheya’s “Role of Fuzzy Systems in the Field of Image Processing and VANET” (Ch. 15) describes the use of fuzzy logic to create a computational system to “identify the types of disease in pomegranate leaves” using the Support Vector Machines (SVM) classification technique (p. 362). VANET refers to a “Vehicular Ad Hoc Network” designed for smart transportation and other technologies, but repurposed here for a classification problem in agriculture. Fuzzy systems enable the representation with inexactness, through “partial truth” and “many-valued logic.”
The imagery is segmented here using c-means clustering (Behura & Shreya, 2022, p. 365). It is refreshing to see extant algorithms harnessed in fresh ways to solve human challenges.
“Cognitive IoT” for Effective Data-Driven Problem Solving for Human Wellbeing
“Cognitive IoT” combines “cognitive computing” (problem solving using computers but emulating human cognition) and the Internet of Things (uses of sensors in an interconnected way for ambient awareness). What emerges is a sensing system with some automated decision-making. Gurpreet Singh Chhabra, Umashankar Ghugar, B. N. V. Rajareddy, and Buddhadeb Pradhan’s “Applications of Cognitive IoT for the Wellbeing of Human Life: An Empirical Study” (Ch. 16) explain the context this way: “IoT management algorithms are incredibly complicated, necessitating human thinking and automated cognition processes for quick and precise decision-making” (p. 377). Cognitive IoT is used for “smart health, smart city, chatbots, real-time analytics, smart living, social monitoring, and driverless car(s),” among others (p. 379). Sensor data may be processed in real-time or post-events.
About Hyperledger Fabric
Priyanka Gaba, Urvashi Sugandh, Manju Khari, and Arvind Panwar’s “A Blockchain Network Simulation Tool – Hyperledger Fabric: Detailed Overview on its Features, Process, and Implementation Steps (Ch. 17) focuses on the open-source platform Hyperledger Fabric, created in 2015 by the Linux Foundation. The researchers write:
Hyperledger offers features like scalability, secrecy, complexity, vital security necessities, and compliance; along with other features like distributed ledgers, smart contracts, and responsive interfaces (Ranjan et al, 2019, as cited in Gaba, Sugandh, Khari, & Panwar, 2022, p. 392).
Blockchains can be public, private, or hybrid. They have been applied in areas like “financial, healthcare, agriculture, IoT, cloud, supply chain” and others (p. 387). This work summarizes the various aspects of Hyperledger Fabric and summarizes how to set this up. Technology tools can be intimidating, so having a work attest to the effectiveness of setup is helpful.
Figure 6. Computational Intel
Dr. Brojo Kishore Mishra, Editor, is a professor in the Department of Computer Science & Engineering at GIET University in Gunupur, Odisha, India. Computational Intelligence for Sustainable Development (2022) is an engaging collection of works showing various applications of algorithms to solve real-world problems.
About the Author
Shalin Hai-Jew works as an instructional designer / researcher at Kansas State University. Her email is firstname.lastname@example.org.
This page has paths:
This page has tags:
This page references:
- Rice Paddies in India (from a reference in CrAIyon)
- Learn Particle Swarm Optimization (PSO) in 20 Minutes
- But what is a neural network? | Chapter 1, Deep learning
- Quantum Computing (by Deep Dream Generator)
- Computational Intelligence for Sustainable Development (cover)
- Particle Swarm Optimization (from Deep Dream Generator)
- Impressionistic Earth
- Computational Intel