Volume 8, Issue 11, November 2023 International Journal of Innovative Science and Research Technology

ISSN No:-2456-2165

Artificial Intelligence: A Computational and Linear

Programming Approach
Emmanuel ADEDIRAN1, Adewale SALAMI2, Taiwo OGUNYINKA3, Wilson SAKPERE4
1
Department of Computer Science, Lead City University Ibadan, Nigeria
2
Bluescripts I.T Institute, Ibadan, Nigeria
*Corresponding Author

Abstract:- Artificial intelligence (AI) has become a potent problem-solving capabilities. The objective of this systematic
tool for resolving complicated issues in a variety of fields. review is to comprehensively analyze the existing literature at
This study investigates how computational and linear the intersection of computational and linear programming with
programming approaches, in particular, may be used to AI. Through synthesizing and evaluating the findings from
solve practical problems. The computational side of AI relevant studies, this review aims to shed light on the
includes creating models and algorithms that replicate effectiveness, challenges, and implications of adopting
human reasoning and decision-making processes. A branch computational and linear programming approaches in the
of mathematical optimization known as "linear development and enhancement of AI systems (Abdallah et al.,
programming" tries to maximize or minimize a linear 2020; Letaief et.al, 2022). The realm of computational and
objective function while taking into account a number of linear programming in AI encompasses a wide range of
linear constraints. Combining these strategies will enable us applications. One such application is within the healthcare
to maximize efficiency, increase decision-making, and better industry. AI systems equipped with computational and linear
allocate resources across a variety of industries, including programming techniques can analyze patient data, optimize
banking, logistics, healthcare, and manufacturing. The treatment plans, and predict disease outcomes with remarkable
theoretical underpinnings of computational and linear precision and efficiency. By utilizing mathematical models,
programming approaches are examined in this study, and these systems can facilitate more accurate diagnoses,
case studies showing how they have been successfully used personalized therapies, and improved patient outcomes.
in practical scenarios. The results highlight the effectiveness Moreover, the finance industry has also witnessed significant
of AI-driven computational and linear programming advancements through the integration of computational and
approaches in tackling complex problems, ultimately linear programming with AI (Wetzstein et al., 2020).
leading to improved outcomes and increased productivity.
As AI continues to advance, further research and Financial institutions are leveraging these techniques to
innovation in these areas hold great promise for solving enhance portfolio management, risk assessment, and investment
even more intricate challenges in the future. strategies. AI systems equipped with computational intelligence
can process vast amounts of financial data in real-time, identify
Keywords:- Computational, Linear Programming, Artificial patterns, and make informed decisions to optimize investment
Intelligence. returns and minimize risks. In addition to healthcare and
finance, computational and linear programming can play a vital
I. INTRODUCTION role in optimizing manufacturing processes. AI systems
embedded with these techniques can enhance production
Artificial Intelligence (AI) has emerged as a revolutionary efficiency, minimize downtime, and optimize resource
field, transforming various industries such as healthcare, allocation (Ullah et al., 2020). By modeling and optimizing
finance, manufacturing, and entertainment (Ning et al., 2021). complex production scenarios, manufacturers can maximize
Researchers have been driven to explore different productivity while minimizing costs and errors. The
methodologies, including computational and linear entertainment industry has not been left behind in the realm of
programming techniques, in order to enhance the performance, computational and linear programming in AI. These
efficiency, and robustness of AI systems. These systematic and methodologies enable intelligent systems to recommend
mathematical approaches have proven to be invaluable tools for personalized and engaging content to users based on their
optimizing AI systems in diverse domains. Computational and preferences and behavior. Content platforms, such as streaming
linear programming involve converting real-world problems services and social media, utilize computational intelligence to
into mathematical models, which can then be optimized to analyze vast amounts of user data and deliver tailored
achieve specific objectives (Singh et al., 2020). When recommendations, effectively enhancing user experience and
integrated with AI systems, these methods have the potential to satisfaction. While the integration of computational and linear
significantly improve decision-making, resource allocation, and programming with AI holds great promise, there are challenges

IJISRT23NOV184 www.ijisrt.com 184

Volume 8, Issue 11, November 2023 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
that need to be addressed (Zhou et al., 2019). One of the main machine learning. This domain entails employing complex
challenges is the complexity of formulating real-world algorithms to process extensive data sets, recognize patterns,
problems into mathematical models. and make predictions. Linear Programming (LP) emerges as a
mathematical optimization technique that addresses the search
This process requires a deep understanding of the problem for the optimal solution to a problem governed by linear
domain and expertise in computational and linear programming relationships. LP finds widespread application in operations
techniques. Furthermore, the optimization process itself may be research, economics, and engineering for optimizing resource
computationally expensive and time-consuming, requiring allocation and decision-making processes. Within the domain
efficient algorithms and powerful computing infrastructure. of AI, the integration of linear programming techniques can
Another challenge lies in the interpretability and explainability provide a structured methodology for resolving specific
of AI systems. Computational and linear programming optimization problems that arise in AI applications (Stepin et
techniques may produce complex solutions that are difficult to al., 2021). The amalgamation of AI and linear programming
interpret and explain to stakeholders. This can hinder the entails harnessing the optimization capabilities of linear
adoption and trust in AI systems, particularly in domains where programming to enhance AI algorithms. One example is the
accountability and transparency are crucial, such as healthcare utilization of linear programming to determine optimal
and finance. Researchers must strive to develop methodologies parameters or configurations for AI models, thus yielding more
that balance performance and interpretability, ensuring that AI efficient and effective outcomes (Ahmad et al., 2021).
systems' decisions can be understood and justified. Despite Conversely, AI techniques empower linear programming by
these challenges, the integration of computational and linear introducing sophisticated problem-solving strategies and
programming with AI has immense implications for the future improved decision-making based on data patterns. By
of problem-solving and optimization. This review aims to integrating linear programming into AI, we can unlock a
provide insights and recommendations based on the existing multitude of innovative possibilities. The application of AI and
literature to guide future research and development in this linear programming convergence showcases the potential for
rapidly evolving field (Stepin et a.l, 2021). Through advancements in various domains, such as healthcare, finance,
comprehensive analysis and evaluation, the review intends to manufacturing, and entertainment. The synthesis of these
highlight the potential benefits of adopting computational and powerful disciplines fosters the creation of cutting-edge
linear programming approaches in AI systems, while also solutions that optimize resource allocation, decision-making,
addressing the challenges and limitations that need to be and overall system performance. In the domain of healthcare,
overcome. In conclusion, the integration of computational and the integration of AI and linear programming can revolutionize
linear programming with AI holds tremendous potential for patient care. By employing AI algorithms, patient data can be
optimizing decision-making, resource allocation, and problem- efficiently processed, providing real-time insights and
solving capabilities across various domains. This systematic personalized treatment plans. Linear programming techniques
review endeavors to shed light on the effectiveness, challenges, can further enhance this process by optimizing resource
and implications of adopting these methodologies. By allocation within healthcare facilities, ensuring optimal
synthesizing and evaluating the existing literature, this review utilization of equipment, staff, and beds. Thus, the combination
aims to provide valuable insights for researchers, developers, of AI and linear programming promotes improved patient
and practitioners in their quest to enhance AI systems through outcomes and efficient utilization of resources. The finance
computational and linear programming approaches (Gauthier et industry also reaps significant benefits from the synergy
al., 2021). between AI and linear programming (Stepin et al., 2021). AI
algorithms can monitor financial markets, identifying patterns
II. LITERATURE REVIEW and making predictions to inform investment decisions (Ahmad
et al., 2021). Leveraging linear programming, this process can
Artificial Intelligence (AI) has revolutionized our be further enhanced by optimizing investment portfolios,
interactions with technology and has become prominent in balancing risk and return to achieve the best possible financial
diverse fields, spanning from healthcare and finance to outcomes. The integration of AI and linear programming in
manufacturing and entertainment. By developing algorithms finance empowers institutions to make informed decisions
and systems, AI enables computers to accomplish tasks backed by comprehensive data analysis and optimization
typically requiring human intelligence (Ahmad et al., 2021). techniques. In the realm of manufacturing, AI and linear
This encompasses understanding natural language, identifying programming can streamline production processes, enhancing
patterns in data, making predictions, and even decision-making. efficiency and productivity. AI algorithms can analyze data
An intriguing aspect of AI lies in its capacity to learn from data, streams from sensors and machines, enabling predictive
continuously adapting and improving performance over time. maintenance and proactive intervention to prevent breakdowns.
Fundamentally, AI can be viewed as a computational pursuit, By optimizing production schedules and resource allocation
involving the creation of mathematical models and algorithms through linear programming, manufacturing facilities can
that allow machines to process information and execute tasks achieve maximum output while minimizing costs and
akin to human cognitive processes. Computational approaches downtime. The collaboration of AI and linear programming in
are particularly vital in the realm of AI, most notably in manufacturing ensures seamless operations and improved

IJISRT23NOV184 www.ijisrt.com 185

 Volume 8, Issue 11, November 2023 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
performance. Entertainment is another domain that benefits sea of pixels, or even navigate through the streets with the
from the integration of AI and linear programming. AI acumen needed for autonomous vehicles(Zhou et.al, 2019).
algorithms can personalize user experiences, recommending This serves as the foundation for a myriad of applications that
tailored content based on preferences and behavior patterns. revolutionize industries, from security systems to smart cities,
This can be further optimized using linear programming and from healthcare to self-driving cars.
techniques to ensure efficient content delivery and resource
allocation for streaming platforms. By merging AI and linear D. Robotics
programming, the entertainment industry can deliver highly Combines the ingenuity of AI with the practical
engaging and personalized experiences to consumers. In accomplishments of mechanical engineering to create
summary, the convergence of AI and linear programming autonomous or semi-autonomous machines that undertake a
presents a wealth of opportunities across diverse domains wide array of tasks. From powering industrial automation,
(Stepin et al., 2021). By harnessing the optimization vastly increasing efficiency and precision, to assisting surgeons
capabilities of linear programming, AI algorithms can be in delicate and complex procedures, robots are revolutionizing
enhanced to achieve more efficient and effective results. our world. This fusion of intelligence and mechanics is
Conversely, AI empowers linear programming by introducing continuously pushing the boundaries of what machines can
sophisticated problem-solving strategies based on data patterns. achieve, vastly reshaping industries and propelling us into a
The collaboration of these disciplines unlocks new dimensions future filled with possibilities.
of optimization, resource allocation, and decision-making.
Through the integration of AI and linear programming, E. Linear Programming (LP)
industries such as healthcare, finance, manufacturing, and A mathematical optimization technique that reshapes
entertainment can explore unprecedented levels of efficiency, models with linear relationships into their ultimate form.
productivity, and personalized experiences. Widely employed in the fields of operations research and
management science, LP extracts the optimal outcome within
III. AI, AS A PIONEERING FIELD OF INNOVATION mathematical frameworks, paving the way for enhanced
problem-solving. By skillfully allocating resources or
This can be subcategorized into several specialized streamlining production schedules, LP facilitates efficient
domains that collectively push the boundaries of human resource management and optimal utilization of time and
technological capabilities. Let us embark on an enlightening energy (Gauthier et al., 2021).
journey through these multifarious subfields, each with its
distinct purpose and applications. F. How does Linear Programming find a home within the
world of AI?
A. Machine Learning Machine learning enthusiasts may marvel at the potential
This is an enthralling subset of AI, unveils the secrets of uses of LP in training models to reach their true potential.
pattern extraction from vast troves of data. Emerging at the Within the realm of linear regression, LP emerges as a valuable
intersection of computer science and statistics, it gifts tool, navigating the vast landscape of possible weight
computers with the ability to learn and adapt independently configurations to find the optimal set that unlocks superior
(Zhou et al., 2019). Within this realm, we encounter various model performance. Moreover, AI applications arise in
techniques, such as supervised learning, where models are numerous domains with inherent optimization problems,
trained using labeled data, unsupervised learning, where including resource allocation in distributed systems and
patterns are discerned without human guidance, and transportation optimization. LP steps in as a guiding beacon,
reinforcement learning, which imitates the concept of rewards orchestrating the delicate balance between computational
and punishments to teach machines to make decisions in an complexity and operational efficiency(Gauthier et al., 2021).
autonomous setting.
IV. INTERSECTION OF AI AND LP
B. Natural Language Processing (NLP)
This empowers machines to comprehend, interpret, and The intersection of AI and LP involves applying AI
even generate human language. As we delve into the depths of techniques to enhance the solution of optimization problems
NLP, we unlock a world of groundbreaking applications formulated using linear programming.
ranging from chatbots that simulate conversations and language
translation tools that transcend boundaries, to sentiment A. Optimization with AI
analysis systems that decipher emotions expressed through text. AI techniques, such as machine learning algorithms, can
be used to optimize parameters in linear programming models.
C. Computer Vision This can lead to better solutions and improved efficiency in
This manifests itself in the wondrous ability of computers finding optimal solutions.
to decipher and make sense of visual information from the
world around us. By analyzing images and videos, computers
can identify faces through facial recognition, detect objects in a

IJISRT23NOV184 www.ijisrt.com 186

 Volume 8, Issue 11, November 2023 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
B. Solving Complex Problems with remarkable accuracy, allowing organizations to optimize
AI can be used to solve complex optimization problems inventory levels and minimize costs associated with excess
that might have non-linear or dynamic constraints. This stock. Additionally, these advanced algorithms can discern
involves using advanced optimization algorithms inspired by subtle yet vital factors such as seasonality, market trends, and
AI, like genetic algorithms, particle swarm optimization, or consumer behavior, further fortifying the organization's ability
simulated annealing. to adapt to evolving market dynamics (Gauthier et al., 2021).

C. Decision Making B. Production scheduling,

AI can assist in decision-making based on LP solutions. Production scheduling, another crucial aspect of supply
For example, AI algorithms can analyze LP output to make chain management, is likewise benefiting immensely from the
real-time decisions in dynamic environments. Resource amalgamation of AI and linear programming. By leveraging
Allocation: AI can aid in the allocation of resources in LP this powerful duo, companies can optimize their production
problems, such as distribution of goods, staff scheduling, or processes by factoring in a multitude of variables, such as
project management. machine availability, labor capacity, and material constraints.
Through the integration of machine learning algorithms,
D. AI Techniques in Linear Programming organizations can even predict potential production bottlenecks,
The integration of AI techniques into linear programming empowering them to take proactive measures to maximize
opens up new horizons for optimization and lays the foundation efficiency and meet customer demands more effectively
for tackling increasingly complex real-world problems. Neural (Gauthier et al., 2021). Distribution, the final piece in the
networks, genetic algorithms, and reinforcement learning have supply chain puzzle, is an area that has substantially
demonstrated their potential to enhance the efficiency, transformed through the application of AI and linear
effectiveness, and robustness of linear programming solutions. programming. Traditionally, companies relied on manual and
While there is still much research to be done and challenges to intuition-based planning for transportation routes, vehicle
be overcome, the combination of AI techniques and linear scheduling, and logistics. However, with the advent of AI-
programming holds immense promise for industries and sectors driven linear programming, organizations can now plan and
where optimization is crucial(Gauthier et al., 2021).. As optimize these elements with unprecedented precision (Tong et
technology advances and algorithms improve, we can look al., 2019). By considering factors like traffic patterns, fuel
forward to a future where AI-powered linear programming consumption, and delivery time windows, businesses can
becomes the de facto approach to solving optimization minimize wasted resources, reduce costs, and enhance overall
problems. delivery efficiency. These advancements are particularly
advantageous when dealing with complex delivery networks or
V. APPLICATIONS OF INTEGRATION OF CP AND last-mile logistics, where even minor improvements can have a
LP IN AI substantial impact on customer satisfaction and profitability
(Gauthier et al., 2021).
A. Supply chain optimization
Supply chain optimization is a critical aspect of successful C. Financial industry,
business operations, encompassing diverse elements such as Financial industry more specifically in the domain of
inventory control, production scheduling, and distribution. In portfolio management. Traditional models for asset allocation,
recent years, a groundbreaking innovation has emerged, risk management, and portfolio diversification often fail to
combining the prowess of artificial intelligence (AI) techniques, account for the intricate dynamics and volatility of the financial
specifically machine learning algorithms and genetic markets. By introducing AI algorithms into the mix,
algorithms, with the power of linear programming. This organizations can optimize asset allocation strategies based on
ingenious union has transformed the landscape of supply chain factors such as historical performance, market trends, and risk
management, unlocking unprecedented potential for efficiency, appetite(Tong et.al, 2019). Furthermore, the integration of
cost reduction, and overall optimization(Tong et.al, 2019).By machine learning techniques enables continuous learning and
delving into the symbiotic relationship between AI and linear adaptation, empowering organizations to refine their portfolio
programming, we can unearth the vast benefits and management strategies in real-time and adapt to ever-changing
opportunities awaiting organizations in streamlining their market conditions(Zhou et.al, 2019).
supply chain processes. This article aims to explore the
fascinating applications of this merger, analyzing how it Transportation planning, a fundamental aspect of various
revolutionizes inventory control, production scheduling, and industries, has also witnessed dramatic improvements thanks to
distribution within supply chain management (Zhou et al., the fusion of AI and linear programming. Optimizing
2019). One of the most impactful applications of AI-driven transportation routes, vehicle scheduling, and logistics has
linear programming in supply chain optimization lies within traditionally been a complex and time-consuming task, often
inventory control(Tong et al., 2019). The intricate dance resulting in suboptimal allocation of resources and higher costs
between demand and supply can make or break a company's (Tong et al., 2019). However, with the application of AI-driven
profitability. AI algorithms can now predict demand patterns linear programming, organizations can now plan, forecast, and

IJISRT23NOV184 www.ijisrt.com 187

Volume 8, Issue 11, November 2023 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
adjust their transportation operations dynamically, taking into optimization techniques that pave the path to efficient problem-
account factors such as traffic congestion, weather conditions, solving, the possibilities offered by AI are boundless. As we
and customer demands (Gauthier et al., 2021). continue to push the limits of technology, AI will undoubtedly
stay at the forefront of progress, shaping the world and
VI. SUMMARY propelling humanity into a brighter future.As organizations
continue to explore these cutting-edge technologies, unleashing
The introduction sets the context, emphasizing the their power in unlocking hidden opportunities, we can expect
increasing role of AI in solving real-world issues. The significant advancements in the field of supply chain
methodology section outlines the systematic approach, from management and related industries. With each passing day, AI-
search strategy to article selection, ensuring transparency and driven linear programming will continue to reshape the way we
rigor. The review reveals how AI techniques such as neural approach complex decision-making, propelling businesses
networks, genetic algorithms, and reinforcement learning towards a future of unparalleled success.
enhance traditional LP. Diverse applications are showcased,
spanning supply chain optimization, resource allocation, and REFERENCES
more. Each application's challenges and benefits are elucidated.
Challenges, including computational demands and [1]. Ning, Z., Zhang, K., Wang, X., Guo, L., Hu, X., Huang,
interpretability concerns, are discussed. Promising avenues for J., Hu, B. & Ricky (2021). Intelligent Edge Computing in
future research are identified, such as refining hybrid Internet of Vehicles: A Joint Computation Offloading and
algorithms and exploring new application domains (Gauthier et Caching Solution. IEEE Transactions on Intelligent
al., 2021).In conclusion, the review underscores the Transportation Systems, 22(4), 2212–2225, 2021.
significance of AI-LP fusion, offering insights for both AI and https://doi.org/10.1109/tits.2020.2997832
operations research communities. It emphasizes the need for [2]. Singh, A.V., Ansari, M.H.D., Rosenkranz, D., Maharjan,
continued collaborative research to advance this R.S., Kriegel, F.L., Gandhi, K., Kanase, A., Singh, R.,
multidisciplinary field. Laux, P. & Luch, A. (2020).. Artificial Intelligence and
Machine Learning in Computational Nanotoxicology:
A. Suggestions Unlocking and Empowering Nanomedicine. Advanced
 Hybrid Algorithm Development: Investigating the Healthcare Materials, 9(17), 1901862,
development of novel hybrid algorithms that effectively https://doi.org/10.1002/adhm.201901862
combine AI techniques (e.g., deep learning, swarm [3]. Abdallah, M., Abu Talib, M., Feroz, S., Nasir, Q.,
intelligence) with linear programming to achieve improved Abdalla, H., & Mahfood, B. (2020). Artificial intelligence
optimization results. Focusingon creating algorithms that applications in solid waste management: A systematic
leverage the strengths of both approaches while mitigating research review. Waste Management, 109, 231–246.
their individual limitations. https://doi.org/10.1016/j.wasman.2020.04.057
 Explain ability and Interpretability: Address the challenge [4]. Letaief, K.B., Shi, Y., Lu, J. and Lu, J. (2022). Edge
of explaining and interpreting the results obtained from AI- Artificial Intelligence for 6G: Vision, Enabling
enhanced linear programming models. Research methods Technologies, and Applications. IEEE Journal on Selected
for providing transparent insights into the decision-making Areas in Communications, 40(1), pp.5–36.
process of hybrid models, which is crucial for gaining trust doi:https://doi.org/10.1109/jsac.2021.3126076.
and acceptance in real-world applications. [5]. Wetzstein, G., Ozcan, A., Gigan, S., Fan, S., Englund, D.,
 Scalability and Efficiency: By exploring techniques to Soljačić, M., Denz, C., Miller, D. A. B., & Psaltis, D.
enhance the scalability and computational efficiency of AI- (2020). Inference in artificial intelligence with deep optics
integrated linear programming algorithms. distributed and photonics. Nature, 588(7836), 39–47.
computing, parallel processing, and other strategies to https://doi.org/10.1038/s41586-020-2973-6
handle large-scale optimization problems in various [6]. Ullah, Z., Al-Turjman, F., Mostarda, L., & Gagliardi, R.
industries could be investigated. (2020). Applications of Artificial Intelligence and
Machine Learning in Smart Cities. Computer
VII. CONCLUSION Communications, 154, 313–323.
https://doi.org/10.1016/j.comcom.2020.02.069
In conclusion, the fascinating world of AI is comprised of [7]. Stepin, I., Alonso, J. M., Catala, A., & Pereira-Farina, M.
various subfields, each with its unique purpose and (2021). A Survey of Contrastive and Counterfactual
contributions. As we journey through the landscapes of Explanation Generation Methods for Explainable
Machine Learning, Natural Language Processing, Computer Artificial Intelligence. IEEE Access, 9, 11974–12001.
Vision, Robotics, and Linear Programming, we witness the https://doi.org/10.1109/access.2021.3051315
transformative power of intelligence and innovation. From
machines capable of independent learning, comprehension of
human language, and analysis of visual information, to
autonomous robots that revolutionize industries and

IJISRT23NOV184 www.ijisrt.com 188

Volume 8, Issue 11, November 2023 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
[8]. Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J.
(2019). Edge Intelligence: Paving the Last Mile of
Artificial Intelligence With Edge Computing. Proceedings
of the IEEE, 107(8), 1738–1762.
https://doi.org/10.1109/jproc.2019.2918951
[9]. Ahmad, T., Zhang, D., Huang, C., Zhang, H., Dai, N.,
Song, Y., & Chen, H. (2021). Artificial intelligence in
sustainable energy industry: Status Quo, challenges and
opportunities. Journal of Cleaner Production, 289(289),
125834. https://doi.org/10.1016/j.jclepro.2021.125834
[10]. Gauthier, D. J., Bollt, E., Griffith, A., & Barbosa, W. A. S.
(2021). Next generation reservoir computing. Nature
Communications, 12(1). https://doi.org/10.1038/s41467-
021-25801-2
[11]. Tong, W., Hussain, A., Bo, W. X., & Maharjan, S. (2019).
Artificial Intelligence for Vehicle-to-Everything: A
Survey. IEEE Access, 7, 10823–10843.
https://doi.org/10.1109/ACCESS.2019.2891073

IJISRT23NOV184 www.ijisrt.com 189