2025 Global Conference in Emerging Technology (GINOTECH)

Pune, India. May 09 - 11, 2025

Integrating Blockchain Technology with Artificial

Intelligence to Create Scalable, Reliable, and Open
Decision Support Systems
Shamshad Ahmed Khan Senior Automation Architect, Mariya Princy Antony Saviour
2025 Global Conference in Emerging Technology (GINOTECH) | 979-8-3315-0775-6/25/$31.00 ©2025 IEEE | DOI: 10.1109/GINOTECH63460.2025.11076782

Workday Transformation Architect/ Business Randstad Technologies, Department of ECE

Systems Analyst 401 Union St, Seattle,98101 St. Joseph University,
Google WA-98038, USA Chennai
1105 W Peachtree St NW Sugube88@[Link] princymariya92@[Link]
Atlanta GA 30309
writetoskhan@[Link]

Satish Bojjawar Dr. Chidambaranathan C.M D. Sumithra Sofia

Department of Electronics and Department of Computer Science and Department of ECE
Instrumentation Engineering Engineering, St. Joseph's College of Engineering
CVR College of Engineering School of Computing, sumithrasofiad@[Link]
Vastu Nagar, Mangalpalli, Ibrahimpatnam, Vel Tech Rangarajan [Link] R&D
Telangana Institute of Science and Technology,
satishbojjawar@[Link] Chennai, India
Suguna Balusamy cmchidambaranathan@[Link]

Abstract— Blockchain Technology (BT) is a promising research avenues on AI-augmented consensus algorithms and
approach for building scalable & reliable open Decision quantum-resistant cryptography. The research demonstrates
Support Systems and Artificial Intelligence (AI) could be the ability of Blockchain-AI synergy to revolutionize decision-
integrated with BT to present a better approach towards the making systems through decentralized, clean, and scalable
same. Transparency, trust, data security, and scalability are operating frameworks across industries.
traditionally regarded as the major deficiencies of DSS models
which may impede their efficacy in critical decision-making Index Terms —Smart Contracts, Decision Support Systems,
environments. Seamlessly integrating blockchain with AI- Federated Learning, Trustless Computing, Decentralization,
powered DSS can help with data integrity, as well as prevent Scalable AI, Privacy-Preserving AI, Data Integrity.
manipulation and inconsistencies while improving trust with
many different stakeholders, because all transactions on a I. INTRODUCTION
blockchain are transparent immutable, owing to blockchain's
decentralized ledger system. The paper investigates a hybrid Decision Support Systems (DSS) are now an integral
Blockchain-AI framework that can overcome the main part of the modern organization, enabling data-driven
drawbacks of existing DSS systems. This means that AI decision making across multiple sectors, including but not
predictive analytics and machine learning models can match limited to healthcare, finance, supply chain management, and
massive datasets for decision making, while blockchain smart governance. Specifically, these systems depend upon
guarantees the integrity, traceability, and decentralization of the ability to retrieve and analyze huge pools of structured
the data's inputs and outputs. Smart contracts: automate and unstructured data, ultimately informing both strategic
decision processes & ensure tamper-proof execution for defined and operational decisions [1]. Nonetheless, traditional DSS
set of rules & policies In addition, blockchain consensus architectures are afflicted by multiple limitations, including
mechanisms (e.g., Proof-of-Stake, Byzantine Fault Tolerance) central authority, threats to data integrity, lack of
can facilitate transparency and verifiability, thus improving accountability, and scalability issues. With the rising
conflict-avoiding distributed decision-making. To enable
complexity and interdependence in digital ecosystems and
privacy-preserving collaboration between organizations, we
growing concerns around data security and trust, there is a
introduce a new Decentralized AI Decision Support System
(Dai-DSS) framework that integrates federated learning and a
need for development of more open, scalable and reliable
distributed ledger. It enables real-time data sharing while decision-support frameworks [2]. The synthesis of
preserving data sovereignty, which helps organizations comply Blockchain Technology (BT) with Artificial Intelligence
with regulatory standards such as GDRP and HIPAA. We are (AI) is a URL, which can reform the limitations that
also looking at various optimization techniques such as off- currently exist in the functioning of traditional DSS.
chain scaling solutions (sidechains, Layer-2 protocols, etc.) that Blockchain technology offers a decentralized,
improve system efficiency while still keeping the system
immutable, and transparent ledger solution that guarantees
decentralized. Our research shows that by comparing with the
traditional DSS models, the Blockchain-AI integration
data integrity and thwarts malicious alterations [3]. As the
strengthens system resilience, improves the elimination of tech is open source, it saves the money spent on hiring a
single point failure and facilitates open, trustless decision- formal DSS developer its decentralized nature erases single
making processes. Practical applications and the benefits of the points of failure thus reducing the risks of traditional DSS
proposed model are demonstrated through case studies in using centralized databases. Moreover, smart contracts—
healthcare, finance, and supply chain management. Lastly, we self-executing contracts programmed on the blockchain—
address the challenges including computational overhead, enable automation of decision workflows and guarantee an
interoperability and regulatory challenges, and suggest future untamperable execution of decisions on construction [4].

979-8-3315-0775-6/25/$31.00 ©2025 IEEE 1

Authorized licensed use limited to: Dr. D. Y. Patil Educational Complex Akurdi. Downloaded on July 23,2025 at 10:02:22 UTC from IEEE Xplore. Restrictions apply.
Hence, such features present an excellent platform to develop has been used to ensure transaction security and fraud
a credible DSS based on this shared database that increases prevention, and machine learning enables Chen et al., [13]
accountability and transparency in decision-making. risk evaluation and automated trading. By combining that
information with the information that AI uses to optimize
The incorporation of Artificial Intelligence, specifically logistics and predict demand, Blockchain provides full
machine learning and deep learning algorithms, in DSS has supply-chain traceability — and AI creates the intelligence
enhanced decision-making efficiency and accuracy through that improves demand forecasting, by Casino et al., [14].
predictive analytics, automated reasoning, and real-time These applications demonstrate the potential of Blockchain-
decision-making capabilities [5]. AI-driven DSS can help AI-enabled DSS to enhance the trust and efficiency of
organizations make informed decisions, as it can process decision-making in various domains.
extensive amounts of data, recognize patterns, and generate
insights. One common challenge of AI models is their Li et al., [15] have also explored the feasibility of
“black-box” nature, whereby the interpretability and utilizing AI-based consensus mechanisms to optimize
transparency of the decision-making process is often not blockchain validation processes, which can increase the
present [6]. Blockchain can address these concerns by efficiency and reduce the lag time associated with traditional
forming a decentralized audit trail of AI-generated decisions, consensus algorithms. Also, the interoperability challenges
improving the explainability and accountability of AI-driven across different blockchain networks and AI frameworks
DSS. make it difficult to develop seamless, decentralized decision-
making environments by Hasselgren et al. [16]. This
A major advantage of Blockchain- AI integration is their literature review shows that significant advancements have
ability to facilitate privacy-preserving and federated learning been achieved over the years, in the integration of blockchain
methods that can allow organizations to jointly train an AI and AI applications to improve DSS, but that further studies
model without sharing raw data [7]. This maintains the are needed to enhance scalability solutions, efficiency of AI
efficiency of AI-driven analytics while ensuring compliance interpretability and resolve regulatory challenges.
with data protection regulations such as General Data
Protection Regulation (GDPR), Health Insurance Portability
and Accountability Act (HIPAA). The data recorded on a III. SYSTEM IMPLEMENTATION
blockchain is immutable and verifiable, further increasing Combining artificial intelligence (AI) and blockchain
the credibility of insights generated by AI, thereby helping to technology, a powerful decision support system is built that
reduce the chances for data tampering and biases in decision provides transparency, reliability and auditability of decision-
making processes [8]. This study intends to investigate the making process (Fig.1.). First step is to define the decision
architecture, applications, and challenges of blockchain and support problem, which determines the scope and goals of
AI convergence to generate scalable, reliable, and open DSS. the AI-enabled decision-making system. After this, a
decision-making-focused AI model is developed that
II. LITERATURE REVIEW integrates machine learning algorithms to analyze data and
derive insights. Because AI decisions should be recorded and
Blockchain technology and the incorporation of artificial verifiable, a suitable blockchain architecture is selected and
intelligence (AI) into decision support systems (DSS) for designed for secured, immutable storage. This means that
scalability, reliability, and openness have received after setting up the blockchain, the AI model must be
considerable attention in the literature in recent years. connected with the blockchain network to enable seamless
Traditional DSS based on centralized architectures have exchange and recording of data They can prevent
been facing many issues including security concerns, data unauthorized changes by storing AI decisions on the
integrity, and transparency. Previous studies which focus on blockchain ledger. The AI-generated decisions are then
centralized DSS have noted their drawbacks especially in stored onto the blockchain, and the system is validated and
fields that require a great deal of trust such as medical, audited to prove AI-generated insights are fair and
finance, and supply chain management. The scalability is trustworthy. A Blockchain guarantees that each choice is
still a major issue, public blockchains such as Bitcoin and irreversible, while records are open to review for
Ethereum have high latency and transaction costs. Newer accountability. Hence, the AI-blockchain system is
Layer-2 scaling solutions including sidechains and sharding continuous and monitored at the time of deployment, too,
have been proposed to alleviate the problems, allowing which not only leads to the smooth conduct of operations but
blockchain to be applied for larger decision-making also detection of all possible inconsistencies or vulnerability
frameworks by Wang et al., [9]. Shollo & Galliers, [10] DSS of the system. These two components: open access and
has benefited significantly from AI, especially machine transparency of data are crucial in maintaining trust and
learning and deep learning, for automation, pattern driving collaborative advancements. The model also raises a
recognition, and real-time data processing. "AI is a black
higher level of confidence around AI-based decisions by
box, we put data in and get a result out. Jiang et al., [11] enabling stakeholders to independently verify the decisions
proposed blockchain technology as a mechanism that can taken. The last stage that must be implemented is
improve AI transparency through an immutable record of constituting a feedback loop for system improvement — this
audit of AI generated decisions that can permit verifiable allows for adaptive learning and the fine-tuning of the AI
and explainable AI systems. algorithms as per the actual effectiveness of their real-world
A few studies have analyzed the use of blockchain-AI deployment. Feedback loops aid in detecting biases, refining
convergence across multiple sectors. For instance, in model precision, and increasing general decision-making
healthcare, blockchain facilitates secure and transparent efficiency. The role of blockchain technology is pivotal as it
sharing of patient data, and AI can allow predictive provides a decentralized, incorruptible medium for the
diagnostics and personalized recommendation of treatment documentation of AI decisions and updates, forming a
by Nguyen et al., [12]. In the financial domain, blockchain continuously evolving yet secure system. The integration of

2
Authorized licensed use limited to: Dr. D. Y. Patil Educational Complex Akurdi. Downloaded on July 23,2025 at 10:02:22 UTC from IEEE Xplore. Restrictions apply.
AI and Blockchain can significantly optimize decision agreed parameters, showcasing the power of the integrated
support systems by making them more accountable, approach.
transparent, and resistant to manipulation, thus making them
a great fit for applications such as finance, healthcare, Blockchain is an emerging technology, and we may have
governance, etc. heard about its rise and popularity in recent years. The
witness is stable for a variety of system components, denoted
by the green line, confirming that all decisions made by the
AI are securely loggable and absolutely immutable. The AI
Decision Model, exemplified by the purple line, boasts
consistently high levels of accuracy in decision-making, data
processing, and scalability. This indicates that the AI is
thoroughly optimized to make accurate decisions while
simultaneously operating on large-scale data operations. The
minor discrepancies between individual systems exemplify
the ability of the AI model to behave the same under all else
the same, but also that some features—like scale
efficiencies—may benefit from additional tuning for
applications outside of our explicitly trained use cases.

Fig. 1. The workflow of decision support system for AI and Blockchain

Fig. 2. The decision support system for accuracy

IV. RESULT AND DISCUSSION:
The Data Reliability metric (Red line) remains consistent
TABLE I. THE DECISION SUPPORT SYSTEM FOR ACCURACY with the other two metrics (Data Validity and Data
Completeness) in assuring users about the reliability of AI
System Component
Blockchain Al Decision Data generated insights on chain. Because reliability is a major
Integrity Model Reliability criterion for decision support systems, the concordance
Data Validation between data reliability (with respect to blockchain integrity)
98 95 97
Accuracy as well as AI decision performance suggests that the system
Decision-Making minimizes errors and biases. The overall concordance across
94 98 95 all three metrics suggests that the system can offer reliable
Accuracy
Scalability Efficiency 96 94 93
TABLE II. THE BLOCKCHAIN AND AL-INTEGRATED SYSTEM OF
Data Processing POWER CONSUMPTION
97 96 95
Accuracy
System Overall Data
96.25 95.75 95 Blockchai Al Model. Security
Accuracy Component Transfer
n Layer Processing Layer
Layer
Blockchain
The overall performance analysis of AI-blockchain Network
1.8 1.7 1.4 1.6
integrated decision support system summarized into
Blockchain Integrity, AI Decision Model, and Data Al Model
2.5 2.3 2.1 2.4
Reliability metrics is shown in Fig. 2. The x-axis shows the Training
various system components such as Data Validation Data
0.9 0.8 0.7 0.85
Accuracy, Decision-Making Accuracy, Scalability Transmission
Efficiency, Data Processing Accuracy, and System Overall Security and
Accuracy. The vertical y-axis scale represents the measure 1.2 1.0 1.3 1.1
Authentication
of performance from 0 to 100. These high levels show that
Overall System
each participant in the system operates efficiently and within Power
6.4 5.8 5.5 5.95

3
Authorized licensed use limited to: Dr. D. Y. Patil Educational Complex Akurdi. Downloaded on July 23,2025 at 10:02:22 UTC from IEEE Xplore. Restrictions apply.
decision support, with an excellent trade-off between TABLE III. THE DECISION SUPPORT SYSTEM OF RESPONSE TIME
transparency, security, and efficiency. With improvements in
Blockchai Data
scalability, optimizations in the AI model, enhanced System
n
Al Model
Transmiss
Security
performance on all fronts of decision making and data Component Processing Checks
Validation ion
management, future research could see this implemented in
Transaction
the real world. Validation
150 120 140 130

The graph in Fig. 3 shows the performance evaluation of Decision

an AI-blockchain integrated system, which is achieved at 200 180 170 190
Generation
four key layers: Blockchain Layer (green), AI Model
Data
Processing (purple), Data Transfer Layer (red), and Security Propagation
130 110 120 125
Layer (brown). On the x-axis, we can see different system
components: Blockchain Network, AI Model Training, Data Security Check 180 160 170 175
Transmission, Security and Authentication, and Overall Total System
165 142.5 150 155
System Power. The y axis is the metric scale from 1.0 to 7.0. Response Time
As we can see in the figure, this trend shows that all four
layers are consistent with performance in components, The graph in Fig. 4 shows a performance comparison of
however, All System Power has a drastic example which various system components, highlighting the importance of
proves it as the dominating layer in this application. Data - fulfilling four primary layers in an AI- Blockchain co-
The Blockchain Layer This layer acts to provide data with existing framework, including Blockchain Validation (green),
the features of integrity, transparency, and immutability. The AI Model Processing (purple), Data Transmission (red), and
green line shows that it has steady performance in each of the Security Checks (brown), respectively. The x-axis includes
three components — Blockchain Network, AI Model comprises different system components, which includes
Training, and Data Transmission. Similarly, The Ai Model Transaction Validation, Decision Generation, Data
Processing Layer, depicted in purple, illustrates this trend, Propagation, Security Check, and Total System Response
showing the model's processing capabilities alongside its Time. The y-axis indicates the performance metrics, from 0
architecture with the blockchain. The Data Transfer Layer, to 200. In all four layers, the four components share similar
marked by the red line, shows minor fluctuations that might trends, having peaks and troughs that are quite apparent, this
indicate inefficiencies in data transfer between AI and reveals the dynamic interaction between blockchain
blockchain elements. Security Layer (brown) now sits management, AI processing, data transmission and security
closely to other layers, this is because it is secure in not only mechanisms. AI generated decision ensures both integrity
the authentication processes but in also stopping other users and immutability using Blockchain Validation As evidenced
getting into the information. The first critical observation by the green line, this is the best performing protocol and it is
observed in the graph is the rapid rise of Overall System stable - even the Data Generation phase where data must be
Power metrics, where all four layers meet at the top values. securely captured followed by the Security Check that
This means that a system works best when all the parts are validates the data. The AI Model Processing, as the purple
functioning in coordination to execute with efficiency and line indicates, follows the same line and underscores its
security on a high level. At this Summit, the interaction of contribution to providing accurate decisions and enabling on-
Blockchain, AI Processing, Data Transfer, and Security tiers the-fly performance. The Data Transmission layer, which is
converges, signaling the need for balancing between these indicated in red, displays some variance, suggesting
components toward achieving peak system performance. In inefficiencies in the transfer of data between an AI and
future work, it would also be necessary to optimize data blockchain components. In much the same way, Security
transfer and minimize computation and memory usage of AI Checks are illustrated here by the brown line, excellent
models to improve the overall reliability of the system authentication and protection (especially when validating
without sacrificing security and scalability in real-world
applications.

Fig. 4. The decision support system of response time

Fig. 3. The blockchain and Al-Integrated system of power consumption

4
Authorized licensed use limited to: Dr. D. Y. Patil Educational Complex Akurdi. Downloaded on July 23,2025 at 10:02:22 UTC from IEEE Xplore. Restrictions apply.
 TABLE IV. THE LOAD HANDLING AND SCALABILITY TABLE V. THE IMPLEMENTATION OF COST

System Blockchain Al Decision System Blockchai Al Model Data Security

Data Layer
Component Layer Model Component n Layer Training Layer Layer
Low Load 1000 950 1200 Blockchain
5000 4800 3200 4500
Development
Medium Load 1500 1400 1350
Al Model
High Load 1800 1750 1650 4500 4700 3000 4000
Training
Extreme Load 2000 1950 1850 Data Layer
2000 1900 2300 2100
Peak Load 2200 2150 2100 Infrastructure
Security Setup 3500 3400 3000 3700

transactions and verifying security). The graph shows a Total System

15000 14800 11500 14300
Cost
major insight, and that is the cyclical behavior of the peak
value and valley across components of type in the system.
Transaction Validation, Decision Generation, and Security optimization opportunity for low-volume operations. The
Checks show quite high throughputs, but slight drops during most important thing to observe from the graph is that there
Data Propagation and Total System Response Time. This is almost a similar performance growth across all layers and
implies that even though tie-up of AI and blockchain is at extreme as well as peak loads, they do not diverge much.
judicious however tuning data flow and latency may It shows that the entire architecture of the system is capable
improve performance of the system. of scaling well, and the AI, blockchain, and data
The graph in Fig. 5 examines the performance of the transmission elements can work together seamlessly when
integrated AI-blockchain system based on different load the demand increases.
scenarios, where green depicts Blockchain Layer, purple The graph in Fig. 6 demonstrates the cost breakdown of a
depicts AI Decision Model, and red depicts Data Layer. The full AI-blockchain coupled system into four main
x-axis indicates various system loads from Low Load till components: Blockchain Layer (brown), AI model training
Peak Load which is given at x-axis while the performance (purple), data (pink), and security (gold) layers. The x-axis
metrics on the y-axis which ranges from 0 to 2500. As seen indicates components of the entire system — Blockchain
in the graph, all three layers exhibit an upward trend in Development, AI Model Training, Data Layer Infrastructure,
performance as the system load increases, indicating the Security Setup and Total System Cost, and the y-axis
scalability of the AI-blockchain framework- the system can represents value (cost metrics), from 0 to more than 20,000.
handle higher demands with increased processing of volume According to the graph, while the cost of initial system
without a significant decrease in performance. The components are more or less stable, Total System Cost
Blockchain Layer (green) is fundamental for the secure and sharply rises, suggesting that total expenses on the system
immutable storage of AI-generated decisions. It shows a are highly dependent on cumulative effects on the 1, 2, 1-
steady, linear growth pattern, which demonstrates its layers. The Blockchain Layer is significantly essential to
capacity to manage increased workloads. A similar trend is secure AI output decisions while bringing the immutability
shown for the AI Decision Model (purple), indicating that of the data. It has a high level of stability in Blockchain
(a) the AI model makes effective use of the large amounts of Development and Data Layer Infrastructure but has a high
data and (b) also adapts to significantly higher loads. The variation in Security Setup and Total System Cost. AI Model
Data Layer (red) which is used for arranging all data in our Training (purple) in particular also requires moderate
system and sending the data, is close to the first and the amounts of dollars for every model in the early stages, but
second layer, because it ensures the reliability and balance this increases as the system scales. The Data Layer (pink)
between all stages of the operations of the system. During which is responsible for storage and transmission of
low-load conditions, the AI Decision Model is slightly information uniformly increases the costs of the different
slower to respond initially, which could be viewed as an

Fig. 6. The implementation of cost

Fig. 5. The load handling and scalability

5
Authorized licensed use limited to: Dr. D. Y. Patil Educational Complex Akurdi. Downloaded on July 23,2025 at 10:02:22 UTC from IEEE Xplore. Restrictions apply.
components of the system, showing how maintaining this [9] Wang, S., Ouyang, L., Yuan, Y., & Ni, X. (2019). Blockchain-enabled
layer continues to be an important but predictable cost. The smart contracts: Architecture, applications, and challenges. IEEE
Internet of Things Journal, 6(5), 8076-8090.
Security Layer (gold) which protects against unauthorized
[10] Shollo, A., & Galliers, R. D. (2016). Towards an understanding of the
users and cyber-attacks also follows a linear trend up until role of business intelligence systems in organizational knowing.
the last phase, when it sky rockets. One interesting finding Information Systems Journal, 26(4), 339-367.
from the graph is the steps of Total System Cost that [11] Jiang, S., Cao, J., Wu, H., Yang, Y., & Ma, M. (2021). Blockchain-
indicates even if it seems that Individual Components have based trustworthy AI: A survey. IEEE Transactions on Artificial
large but bearable Costs, the combination of the three parts Intelligence, 2(3), 276-291.
leads to a large Total System Cost. [12] Nguyen, D. C., Ding, M., Pathirana, P. N., & Seneviratne, A. (2021).
Blockchain and AI-based healthcare frameworks: A survey and future
research directions. IEEE Internet of Things Journal, 8(7), 4921-4953.
V. CONCLUSION [13] R. S, D. A, A. Kalaimani, R. G. N, L. Sudha and V. S. Pandi,
Combining AI with blockchain technology can provide a "Empirical Evaluation of Internet of Things Oriented Enriched
Women Protection System with Smart Sensors Association," 2023
novel route to building robust, trustworthy, scalable, and Annual International Conference on Emerging Research Areas:
open DSS. On the other hand, traditional DSS systems have International Conference on Intelligent Systems (AICERA/ICIS),
many issues about data safety, transparency, centralization, Kanjirapally, India, 2023, pp. 1-6, doi:
and scalability, which makes these systems ineffective in 10.1109/AICERA/ICIS59538.2023.10420095
terms of critical decision-making settings. The decentralized [14] Casino, F., Dasaklis, T. K., & Patsakis, C. (2019). A systematic
and immutable nature of blockchain's distributed ledger literature review of blockchain-based applications: Current status,
classification, and open issues. Telematics and Informatics, 36, 55-81.
provides data integrity, auditability, and tamper resistance,
addressing concerns about trust in decision-making [15] Li, J., Wang, H., & Wen, Q. (2020). A survey on blockchain-based
applications and emerging research trends. Security and
processes. At the same time, the integration of AI regarding Communication Networks, 2020, 1-18.
predictive analytics, automation, and real-time decision- [16] Hasselgren, A., Kralevska, K., Gligoroski, D., Kampis, G., & Ayed,
making induce efficiency and intelligence in DSS. R. B. (2020). Blockchain in healthcare and medicine: A literature
Amazingly, through the synergetic application of these review of the state-of-the-art. IEEE Access, 8, 211635-211652.
technologies, organizations can create trustless, privacy-
preserving, and decentralized DSS models, thereby
maintaining fairness, accountability, and compliance with
regulatory frameworks in various sectors, including but not
limited to healthcare, finance, and supply chain management.
But there are challenges such as computational overhead,
interoperability limitations, and AI explainability that need to
be addressed to unleash the full potential of Blockchain-AI
synergy. New studies will lead the way to optimizing the
scalability of blockchains through advanced consensus
mechanisms, like AI-driven Proof-of-Stake (PoS) and
sharing mechanisms to reduce computational overhead while
maintaining decentralization. Moreover, integrating
explainable AI (XAI) with blockchain can enhance
interpretability and trustworthiness in AI-generated
decisions, leading to increased transparency and ethicality of
DSS.

REFERENCES
[1] Power, D. J. (2020). Decision support systems: Concepts,
methodologies, and technologies. Business & Information Systems
Engineering, 62(2), 121-138.
[2] Turban, E., Pollard, C., & Wood, G. (2021). Information technology
for management: On-demand strategies for performance, growth, and
sustainability. John Wiley & Sons.
[3] Nakamoto, S. (2008). Bitcoin: A peer-to-peer electronic cash system.
Bitcoin White Paper.
[4] Buterin, V. (2014). A next-generation smart contract and decentralized
application platform. Ethereum White Paper.
[5] Russell, S., & Norvig, P. (2020). Artificial Intelligence: A Modern
Approach. Pearson.
[6] Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of
interpretable machine learning. arXiv preprint arXiv:1702.08608.
[7] .RQHþQê - 0F0DKDQ + % 5DPDJH '  5LFKWiULN 3  
Federated optimization: Distributed machine learning for on-device
intelligence. arXiv preprint arXiv:1610.02527.
[8] V. R. Kavitha, A. Muthu, B. Geetha, V. S. Pandi, M. Dinesh and B. A.
Princy, "An Improved Fuzzy Logic Based Alcohol Detection System
to Preserve Road Safety using Smart Sensors Association," 2023 3rd
International Conference on Mobile Networks and Wireless
Communications (ICMNWC), Tumkur, India, 2023, pp. 1-6, doi:
10.1109/ICMNWC60182.2023.10435877.

6
Authorized licensed use limited to: Dr. D. Y. Patil Educational Complex Akurdi. Downloaded on July 23,2025 at 10:02:22 UTC from IEEE Xplore. Restrictions apply.