Available via license: CC BY 4.0
Content may be subject to copyright.
Month Published by the IEEE Computer Society Publication Name 1
AI in Industry: Real-World Applications and Case
Studies
Wahyu Rahmaniar, Institute of Innovative Research, Tokyo Institute of Technology, Kanagawa, 226-8503,
Japan
Alfian Ma’arif, Department of Electrical Engineering, Universitas Ahmad Dahlan, Yogyakarta, 55166, Indonesia
Qazi Mazhar ul Haq, International Bachelor Program in Informatics and Computer Science, Yuan Ze University,
Taoyuan, 320315, Taiwan
Muchammad Edo Iskandar, Ezy Industries, Jakarta, Indonesia
Abstract— Artificial intelligence (AI) has advanced rapidly and is becoming a cornerstone
technology that drives innovation and efficiency in various industries. This paper examines
the real-world application of AI in multiple sectors, including healthcare, finance,
agriculture, retail, energy, and automotive. Several case studies are described to
understand better the practical applications, results, and challenges of implementing AI.
While many industries have reaped enormous benefits from AI, inherent challenges include
data privacy, the potential for bias, and the continuing demand for skilled labor. This
comprehensive review aims to provide AI application insights to professionals and
researchers. Thus, as AI grows, there may be challenges and avenues for future research.
he Artificial Intelligence (AI) began in the mid-
20th century when scientists first imagined
machines that could simulate human intelligence
[1]. Over the decades, AI has progressed from basic
algorithms to more complex models. Currently, AI can
simulate and surpass human capabilities in specific tasks.
In the digital era, AI stands as a transformative force in
various global industries, as shown in Fig. 1.
In healthcare, technology has evolved in diagnostic
procedures with AI tools that can detect diseases with
accurate results [2]. In finance, there is no more manual
fraud detection. Instead, sophisticated algorithms
examine millions of transactions in real-time, flagging
suspicious activity with high accuracy [3]. Traditionally
driven by intuition and human experience, the retail
sector relies on AI models to tailor personalized shopping
experiences and transform business interactions [4].
Farmers are leveraging AI-based predictive analytics to
make informed decisions about growing, harvesting, and
irrigating crops in the agricultural domain, bridging the
gap between traditional practices and technological
innovation [5]. AI has also been used in the energy and
automotive sectors, facilitating monitoring and
automation. Table 1 summarizes the main AI applications
in the industry.
Although it looks promising, the road to integrating
AI is not smooth. The industry is grappling with challenges
such as ensuring data privacy, navigating the complexities
of potential biases in AI models, and coping with the
growing demand for a skilled workforce proficient in these
new technologies [6]. Furthermore, the rapid proliferation
of AI applications underscores the need for systematic
documentation and understanding of real-world
implementation. This review seeks for an in-depth
exploration of the practical implementation, challenges,
and successes associated with AI in various sectors. Thus,
this paper can provide a broader perspective to guide
professionals, researchers, and stakeholders in AI
technology.
FEATURE ARTICLE: AI IN INDUSTRY
THEME/FEATURE/DEPARTMENT
2
Publication Title
Month Year
FIGURE 1. AI applications in industry.
TABLE 1. AI in industry.
Industry
Key AI Application
Brief Description
Healthcare
Diagnosing diseases using medical imaging
Use of neural networks to analyze medical images
and detect anomalies.
Finance
Fraud detection and risk assessment
Machine learning models to identify unusual
transactions and assess creditworthiness.
Agriculture
Predictive analytics for crop yield
AI algorithms predict crop yields based on
environmental data and historical trends.
Retail
Personalized customer experiences and
recommendations
Algorithms analyze customer data for personalized
shopping experiences and product suggestions.
Energy
Renewable energy forecasting
Predictive models for forecasting energy production,
especially from renewable sources like wind and
solar.
Automotive
Autonomous vehicles
Complex AI systems interpret sensor data, make
navigational decisions, and safely operate vehicles
without human intervention.
HEAD
Month Year
Publication Title
3
HEALTHCARE
The integration of AI in healthcare has resulted in
expedited diagnosis, personalized care, and predictive
analytics. In particular, medical imaging has witnessed a
revolutionary shift due to AI capabilities in image
recognition and interpretation.
Early Detection of Adolescent Idiopathic
Scoliosis
AI and deep learning based on convolutional neural
networks (CNN) have been used to help doctors analyze
scoliosis patients [7]. The CNN architecture was proposed
to detect the location of spinal vertebrae from X-ray
images to evaluate the Cobb angle automatically. The
proposed method can measure Cobb angles with up to
93.6% accuracy and has excellent reliability compared to
manual clinician measurements, making it usable in real-
world clinical settings. The method also reduces
diagnostic time, leading to faster interventions to treat
patients better. Successful integration may encourage
other healthcare institutions to explore similar AI-based
diagnostic solutions.
Diagnosis of Breast Cancer on Mammograms
Breast cancer is a significant health problem for
women globally. Early detection is essential for effective
prevention and treatment. A traditional mammogram, an
X-ray image of the breast, helps spot the early signs of this
cancer. AI can be applied to segmenting areas detected as
cancer on mammograms [8]. AI can also help improve
image quality and find anomalous patterns. AI is changing
the way breast cancer is detected, making the process
faster and often more precise. However, AI in medicine
can be a tool, not a substitute for human expertise. A
doctor and radiologist can do it for further detection and
decision-making.
Drug Discovery and Development
Drug discovery and development is a long and
expensive process. With AI, this process gets a significant
boost. AI algorithms analyze extensive data sets to
identify potential drug candidates by predicting how
different compounds might interact with biological
pathways [9]. So, instead of the traditional trial and error
method, researchers can now start by focusing only on the
most promising compounds. In addition, AI can help
predict potential side effects, making the drug
development process safer. AI streamlines and optimizes
the journey from the lab to the pharmacy shelf,
potentially getting effective drugs to patients faster and
more affordably.
Natural Language Processing (NLP) for
Medical Records
Medical records often contain large amounts of
unstructured text, ranging from doctor's notes to patient
histories. NLP, a branch of AI, is designed to understand,
interpret, and extract meaningful information from such
texts. In the context of medical records, NLP algorithms
sift through data, identifying important details such as
diagnosis, treatment, and patient outcomes [10]. NLP
helps in efficient patient management and research,
which provides information for medical studies and
strategies. NLP transforms seas of text in medical records
into actionable information, improving patient care and
healthcare research.
FINANCE
AI has played a critical role in tackling complex challenges
in finance, such as fraud detection and risk assessment.
The high volume of financial transactions every day makes
manual fraud detection nearly impossible. Financial
institutions face a constant battle against ever-evolving
fraud techniques. Traditional systems are often reactive,
identifying fraud after it has occurred. Financial entities
can proactively detect and deter suspicious activity with
AI predictive analytics.
Fraud Detection in Real-Time Payment
Systems
In a real-time payment system, fraud detection
must be instantaneous. Traditional approaches often fail
to keep up with this speed and transaction volume. AI
methods, such as deep learning, are trained on millions of
transactions [3]. These models can detect patterns and
anomalies faster than humans. The AI model can mark
high-value transactions from countries where users have
never transacted as suspicious. Several financial
institutions that integrated AI-based real-time fraud
detection observed a reduction in fraudulent transactions
of up to 40% while also reducing false positives.
THEME/FEATURE/DEPARTMENT
4
Publication Title
Month Year
Predicting Credit Card Default Risks
Credit card companies must predict the probability
of a default user to decide on credit limits and reduce
losses. By training historical data, including past
transactions, payment histories, and social factors, AI
models can provide more accurate predictions about the
likelihood of users defaulting [11]. More advanced models
even consider non-traditional data, such as social media
activity. Credit card companies using AI-based risk
assessment tools can reduce bad loans compared to
traditional methods.
Automated Trading and Risk Management
The stock market is notoriously unpredictable.
Manual trading strategies cannot always keep up with
rapid fluctuations. AI algorithms, trained on large datasets
of years of market data, can make real-time trading
decisions [12]. By analyzing patterns, AI can predict short-
term price changes with greater accuracy. In addition, AI
assists portfolio managers in risk assessment by
forecasting potential market downturns based on global
news and events. Trading companies using AI-based
trading strategies consistently outperform traditional
methods, some reporting an increase in annual returns of
up to 15%.
RETAIL
Physical and digital retailers have turned to AI to enhance
the customer shopping experience, offering personalized
product recommendations based on individual
preferences and browsing history. Modern consumers
expect a personalized shopping experience.
Real-Time Personalized Online Shopping
Experience
Online shoppers often face many choices, leading to
potential shopping cart abandonment. The AI model is
trained on users' browsing patterns, purchase history, and
click-through rates, dynamically adjusting the online
shopping interface [4]. This personalization can range
from visual layout adjustments to specific product
highlights. E-commerce platforms that have integrated AI
personalization tools have reported a 20% increase in
conversion rates and a 15% increase in average order
value.
In-Store Personalized Recommendations
through Augmented Reality (AR)
Brick-and-mortar stores aim to replicate a
personalized online experience for in-store customers.
Augmented Reality (AR) devices, powered by AI
algorithms, analyze a customer's purchase history and
store interactions [13]. The AR device then overlays real-
time product information and recommendations onto the
customer's view. Stores using AR and AI for personalized
recommendations have increased in-store sales by 10-
15% and increased customer return rates by 20%.
Virtual Try-Ons and Personalized Styling
Suggestions
The challenge of choosing the right size and style is
familiar to both online and in-store shoppers. With AI and
AR, virtual test tools allow customers to wear clothes,
accessories, or make-up virtually [13]. AI suggests sizes,
colors, and complementary products based on virtual
experiences and past purchases. Retailers offering virtual
trials and AI-driven style advice saw a 20-40% decrease in
product returns and a 3% increase in sales of
complementary products.
AGRICULTURE
Modern agriculture seeks to combine traditional wisdom
with technological advances. AI has emerged as a vital
tool, providing farmers with data-driven insights that
were previously inaccessible. Predictive analytics with AI
offers solutions to optimize crop yield predictions based
on various parameters.
Predicting Yield Based on Weather Patterns
Weather fluctuations have a direct impact on crop
yields. Traditional predictive models often lack real-time
response to sudden weather changes. Machine learning
models, which are trained on historical weather data, crop
yields, and satellite imagery, can predict crop yields based
on predicted weather patterns [5]. Farms using AI models
report yield increases of up to 20% due to timely
interventions, optimizing irrigation, and predictive pest
control.
HEAD
Month Year
Publication Title
5
Soil Health Analysis and Crop Yield
Soil health, including nutrient content and moisture
levels, is a major factor in crop yields. Sophisticated
sensors and AI algorithms can analyze soil samples,
predicting which plants grow best in certain soil types and
conditions [5]. These predictions can also be extended to
specific fertilizer or treatment recommendations. By
aligning crop planting with soil health recommendations,
the farm recorded a 15% increase in crop yields and a 10%
reduction in fertilizer and maintenance costs.
Drone-based Crop Surveillance and Yield
Prediction
Regular crop monitoring can detect early signs of
disease or pest infestation that can affect yields. Drones
equipped with AI-based cameras can capture high-
resolution images of plants [14]. Then, deep learning
models analyze the images to detect abnormalities,
predict the potential impact of outcomes, and suggest
interventions. Early detection and intervention can
reduce crop losses, ensuring more consistent and higher
yields.
ENERGY
The energy sector is currently undergoing a
transformative AI-driven evolution. As global energy
demand increases and the urgent need for sustainable
solutions increases, AI delivers innovation, promising
efficiency, adaptability, and foresight in diverse energy
production, distribution, and consumption fields.
Renewable Energy Forecasting
Renewable energy sources, such as wind and solar,
are affected by unpredictable natural factors. AI is used
to improve energy production forecasting from these
sources [15]. AI models can more accurately predict
energy output by analyzing large amounts of data,
including weather patterns, historical energy production,
and satellite imagery. Thus, the energy network can
effectively integrate renewable sources, optimize energy
distribution, and reduce dependence on non-renewable
reserves. AI-powered forecasting helps maximize the
efficiency and reliability of renewable energy, making it a
more viable alternative to traditional energy sources.
Energy Efficiency in Buildings
Buildings, such as homes and office spaces, consume
much energy. AI plays an essential role in increasing the
energy efficiency of these structures. AI algorithms can
optimize heating, cooling, and lighting systems in real-
time by analyzing data from sensors, past energy usage,
weather forecasts and occupancy patterns [16]. AI can
ensure that energy is only used when and where needed
to prevent wastage. Additionally, AI can predict when a
system may need maintenance, avoiding energy
inefficiencies due to wear and tear. Therefore, AI is an
intelligent manager for building systems, ensuring optimal
energy consumption and significantly reducing costs.
Predictive Maintenance in Energy
Infrastructure
Energy infrastructure, such as power plants, turbines,
and transmission lines, are important assets that require
regular maintenance. Traditional maintenance strategies
often rely on scheduled inspections or waiting for
equipment to fail. The predictive maintenance approach
can be applied with AI. AI can analyze data from sensors
placed on equipment, identifying patterns and anomalies
that hint at potential failure or wear and tear [17].
Foreseeing these problems before they cause damage,
operations can continue without interruption, and costly
emergency repairs can be avoided. AI ensures energy
infrastructure stays in peak condition, reduces downtime,
and maximizes efficiency.
AUTOMOTIVE
The automotive field is undergoing a radical
metamorphosis powered by AI. As ancient vehicle
mechanics are entwined with digital AI prowess, the
horizon of automotive possibilities is expanding, ushering
in an era of enhanced safety, unprecedented efficiency
and reimagined driving experiences.
Autonomous Vehicles
Autonomous vehicles, often referred to as self-driving
cars, rely heavily on AI to navigate and make decisions.
Using a variety of sensors, cameras and radar, the vehicle
is constantly gathering data about its environment. AI
processes this data in real-time, helping vehicles
THEME/FEATURE/DEPARTMENT
6
Publication Title
Month Year
recognize obstacles, read traffic signs, and understand
road conditions [18]. Additionally, AI algorithms can
predict the actions of pedestrians and other vehicles to
make driving decisions, such as when to brake or change
lanes. AI, such as deep learning, enables these vehicles to
learn from large amounts of driving data and continuously
improve their performance. Thus, AI functions as the brain
of autonomous vehicles, allowing them to navigate
complex urban environments safely and efficiently.
Predictive Maintenance
The automotive industry has applied AI to predict
and prevent vehicle breakdowns before they occur. The
vehicle continuously delivers performance data by
integrating on-board sensors and diagnostics. AI
algorithms analyze this data, detecting subtle patterns
and irregularities that might indicate potential damage or
wear on some parts [19]. Instead of following a fixed
service schedule or waiting for a breakdown, car owners
are forewarned about which components need attention.
This predictive approach increases vehicle life, ensures
safer driving conditions, and can reduce unforeseen repair
costs. AI turns vehicles into self-diagnosis systems,
offering timely maintenance insights to keep them
running optimally.
Intelligent Voice Assistants
Modern vehicles are equipped with AI voice
assistants that go beyond basic speech recognition. AI can
understand context, preferences and even adapt to
individual user voices. Drivers can use voice commands to
control navigation, play music, send messages, or get real-
time updates on vehicle performance, all without taking
their hands off the wheel. AI processes these commands
quickly and accurately, ensuring smooth interactions [20].
Over time, these assistants learn from user behavior and
can proactively provide suggestions, such as finding a gas
station on a long trip or suggesting a faster route. This AI-
TABLE 2. Advantages and limitations of AI applications.
Aspect
Advantages
Limitations
Efficiency
- Automation of repetitive tasks.
- Faster data processing and decision-making.
- Over-reliance on automation can lead to decreased
human oversight.
- AI algorithms can sometimes make erroneous
decisions if trained on flawed data.
Accuracy
- Enhanced precision in tasks like medical
imaging.
- Reduction in human errors.
- Algorithms might be overfit to training data, leading to
poor generalization in real-world scenarios.
- AI can amplify biases present in training data, leading
to unfair or skewed outcomes.
Scalability
- Ability to handle large datasets efficiently.
- Can manage tasks that scale beyond human
capacity.
- Needs extensive computational resources for training
complex models.
- Scalability might be limited by infrastructure or data
storage constraints.
Customization
- Personalized experiences in sectors like retail.
- Tailored recommendations based on user
behavior.
- Personalization might lead to privacy concerns if not
handled with discretion.
- Over-personalization can create a "filter bubble,"
limiting exposure to diverse information.
Cost
- Potential for cost savings in the long run.
- Reduction in manual labor costs.
- High initial investment required for setting up AI
systems, training, and infrastructure.
- Continuous maintenance, updates, and potential need
for retraining models can be expensive.
Innovation
- Introduction of novel solutions and capabilities.
- Facilitates research and development.
- Rapid advancements can lead to issues of tech
redundancy and require frequent updates to stay current.
- Dependence on AI might stifle human creativity and
innovation in some scenarios.
HEAD
Month Year
Publication Title
7
driven voice assistant enhances the driving experience,
making it more intuitive, safe, and enjoyable.
CHALLENGE
Implementing AI in real-world applications across various
industries has several advantages and limitations, as
summarized in Table 2. Data quality and quantity emerge
as important factors, as AI models, especially deep
learning, demand large amounts of high-quality data. The
process of collecting, cleaning, and managing such data
presents considerable difficulties.
Another significant challenge lies in the ethical
considerations of implementing AI. AI decisions, especially
when they are made based on data that biases or
influences human life, can have substantial ethical
implications. The challenge is particularly relevant in
critical sectors such as health or finance, where decisions
can directly affect an individual's life or wealth.
The integration and scalability of AI solutions pose
another hurdle. It is a complex task to adapt AI solutions
to suit existing industrial systems while ensuring they can
scale to accommodate growing data and demand. Lack of
efficient integration or scalability can lead to system
failure and inability to process larger data sets.
On top of that, the AI black box issue adds to the
complexity. Deep learning architectures lack
transparency, making decision-making processes difficult
to interpret. Thus, there is a lack of confidence in AI
decisions, and troubleshooting or perfecting the model is
complex. These challenges demonstrate the complexities
of transitioning from AI research to real-world
applications in various industries. Navigating this
complexity successfully is the key to unlocking AI's full
potential.
DISCUSSION AND FUTURE
DIRECTIONS
As AI continues to evolve, the industry is witnessing the
tremendous potential it brings and the challenges it
brings. From healthcare predictive diagnostics to financial
fraud detection mechanisms and agricultural predictive
analytics for crop yields, the impact of AI is evident.
However, infrastructure constraints, data generalization
issues, a rigorous regulatory landscape, and a prominent
skills gap underscore the complexity of embedding AI in
real-world scenarios.
One thing that stands out is the dichotomy between
the theoretical promise of AI and its practical application.
While AI models in controlled environments, such as
research labs, can achieve remarkable accuracy, applying
them to unpredictable real-world scenarios often yields
variable results. Factors such as changing environmental
conditions, diverse user behavior, and evolving data
patterns play an essential role. Additionally, the ethical
implications of AI decisions, especially in sectors such as
healthcare and justice, cannot be overstated. As AI
systems increasingly make decisions that affect human
life, building trust, ensuring fairness, and maintaining
transparency is paramount.
As industries globally continue to harness the power
of AI, a multi-pronged approach that balances innovation
with ethical considerations and technical prowess with
human-centric design will be critical. The transformation
of AI from the laboratory to real-world applications is
fraught with challenges, but its potential to reshape
industries offers an exciting vision for the future as
follows:
1) Industry-specific AI solutions: In the future, it is
likely to develop AI solutions that are more
adapted to industry-specific challenges and
environments. For example, a healthcare AI tool
might prioritize patient data privacy and
diagnostic accuracy, while a retail solution might
focus on personalization and inventory
management.
2) Human-AI collaboration: AI cannot replace the
human touch in many industries. The focus may
turn to building systems that complement
human skills, leading to a collaborative human-
AI workforce.
3) AI ethical frameworks: As the social implications
of AI become more apparent, the industry may
adopt standard ethical frameworks to guide the
development and deployment of AI systems,
ensuring fairness, transparency, and
accountability.
4) Continuous learning systems: To address the
challenge of data generalization, future AI
systems in the industry may be designed for
continuous learning, enabling AI to seamlessly
THEME/FEATURE/DEPARTMENT
8
Publication Title
Month Year
adapt to changing data patterns and
environments.
5) Bridging the skills gap: With the proliferation of
AI, there is an urgent need for training programs
that upskill today's workforce. Industry-
academic collaboration can pave the way for
curricula aligned with industry needs.
CONCLUSION
The application of AI technology in various industries
represents a paradigm shift in the way businesses operate
and innovate. AI has the potential to help with everything
from increasing operational efficiency to pioneering
unprecedented solutions. With industry-specific AI
solutions, increased emphasis on human-AI collaboration,
ethical AI frameworks, continuous learning systems, and
initiatives to bridge the skills gap, industries can address
the complexities of AI applications. Moreover, the future
directions of AI promise a more customized, ethical, and
human-centric approach, with equal emphasis on
innovation and societal well-being.
Although the transformation of AI from a
conceptual model to real-world application is complex, its
potential is undeniable. By tackling challenges head-on
and continuously evolving with technology, industries can
harness the full potential of AI, charting a course for a
technologically advanced, human-centric future.
REFERENCES
[1] Z. Shao, R. Zhao, S. Yuan, M. Ding, and Y. Wang, “Tracing
the evolution of AI in the past decade and forecasting
the emerging trends,” Expert Syst Appl, vol. 209, p.
118221, Dec. 2022.
[2] A. Parfett, S. Townley, and K. Allerfeldt, “AI-based
healthcare: a new dawn or apartheid revisited?,” AI Soc,
vol. 36, no. 3, pp. 983–999, Sep. 2021.
[3] A. Ali et al., “Financial fraud detection based on machine
learning: A systematic literature review,” Applied
Sciences,vol. 12, no. 19, p. 9637, Sep. 2022.
[4] A. S. Riegger, J. F. Klein, K. Merfeld, and S. Henkel,
“Technology-enabled personalization in retail stores:
Understanding drivers and barriers,” J Bus Res, vol. 123,
pp. 140–155, Feb. 2021.
[5] M. Javaid, A. Haleem, I. H. Khan, and R. Suman,
“Understanding the potential applications of artificial
intelligence in agriculture sector,” Advanced Agrochem,
vol. 2, no. 1, pp. 15–30, Mar. 2023.
[6] U. Wilkens, “Artificial intelligence in the workplace – A
double-edged sword,” International Journal of
Information and Learning Technology, vol. 37, no. 5, pp.
253–265, Nov. 2020.
[7] W. Caesarendra, W. Rahmaniar, J. Mathew, and A.
Thien, “Automated Cobb angle measurement for
adolescent idiopathic scoliosis using convolutional
neural network,” Diagnostics, vol. 12, no. 2, p. 396, Feb.
2022.
[8] I. Sechopoulos, J. Teuwen, and R. Mann, “Artificial
intelligence for breast cancer detection in
mammography and digital breast tomosynthesis: State
of the art,” Semin Cancer Biol, vol. 72, pp. 214–225, Jul.
2021.
[9] D. Paul, G. Sanap, S. Shenoy, D. Kalyane, K. Kalia, and R.
K. Tekade, “Artificial intelligence in drug discovery and
development,” Drug Discov Today, vol. 26, no. 1, p. 80,
Jan. 2021.
[10] C. J. Harrison and C. J. Sidey-Gibbons, “Machine learning
in medicine: A practical introduction to natural language
processing,” BMC Med Res Methodol, vol. 21, no. 1, pp.
1–11, Dec. 2021.
[11] J. Gao, W. Sun, and X. Sui, “Research on default
prediction for credit card users based on XGBoost-LSTM
model,” Discrete Dyn Nat Soc, vol. 2021, 2021.
[12] R. Michaela Denise Gonzales and C. A. Hargreaves, “How
can we use artificial intelligence for stock
recommendation and risk management? A proposed
decision support system,” International Journal of
Information Management Data Insights, vol. 2, no. 2, p.
100130, Nov. 2022.
[13] R. Zimmermann et al., “Enhancing brick-and-mortar
store shopping experience with an augmented reality
shopping assistant application using personalized
recommendations and explainable artificial
intelligence,” Journal of Research in Interactive
Marketing, vol. 17, no. 2, pp. 273–298, Mar. 2023.
[14] B. D. S. Barbosa, G. A. e. S. Ferraz, L. Costa, Y. Ampatzidis,
V. Vijayakumar, and L. M. dos Santos, “UAV-based
coffee yield prediction utilizing feature selection and
deep learning,” Smart Agricultural Technology, vol. 1, p.
100010, Dec. 2021.
[15] C. Ying, W. Wang, J. Yu, Q. Li, D. Yu, and J. Liu, “Deep
learning for renewable energy forecasting: A taxonomy,
and systematic literature review,” J Clean Prod, vol. 384,
p. 135414, Jan. 2023.
[16] M. U. Mehmood, D. Chun, Zeeshan, H. Han, G. Jeon, and
K. Chen, “A review of the applications of artificial
intelligence and big data to buildings for energy-
efficiency and a comfortable indoor living
environment,” Energy Build, vol. 202, p. 109383, Nov.
2019.
HEAD
Month Year
Publication Title
9
[17] W. Shin, J. Han, and W. Rhee, “AI-assistance for
predictive maintenance of renewable energy systems,”
Energy, vol. 221, p. 119775, Apr. 2021.
[18] B. Ben Elallid, N. Benamar, A. S. Hafid, T. Rachidi, and N.
Mrani, “A comprehensive survey on the application of
deep and reinforcement learning approaches in
autonomous driving,” Journal of King Saud University -
Computer and Information Sciences, vol. 34, no. 9, pp.
7366–7390, Oct. 2022.
[19] A. Theissler, J. Pérez-Velázquez, M. Kettelgerdes, and G.
Elger, “Predictive maintenance enabled by machine
learning: Use cases and challenges in the automotive
industry,” Reliab Eng Syst Saf, vol. 215, p. 107864, Nov.
2021.
[20] U. Gulati, Ishaan, and R. Dass, “Intelligent car with voice
assistance and obstacle detector to aid the disabled,”
Procedia Comput Sci, vol. 167, pp. 1732–1738, Jan.
2020.
Wahyu Rahmaniar received a B.S. in Electronics and
Instrumentation from Universitas Gadjah Mada, Yogyakarta,
Indonesia, and a Ph.D. in Electrical Engineering from the
National Central University, Taiwan. She was a Computer
Vision Engineer at Issa Technology and a Postdoctoral
Researcher at the National Taipei University of Technology in
Taiwan. She is currently an Assistant Professor (specially
appointed) at the Institute of Innovative Research, Tokyo
Institute of Technology, Japan. Her research interests include
Artificial Intelligence, Medical Imaging, Computer Vision,
and Robotics. Contact her at rahmaniar.w.aa@m.titech.ac.jp.
Alfian Ma’arif received the bachelor’s degree from the
Department of Electrical Engineering, Universitas Islam
Indonesia, in 2014 and the master’s degree from the
Department of Electrical Engineering, Universitas Gadjah
Mada, in 2017. In 2023, he began his doctoral study in the
Department of Electrical Engineering, Universitas Gadjah
Mada. Since 2018, he has been a Lecturer with the Department
of Electrical Engineering, Universitas Ahmad Dahlan. His
research interest includes Control Systems. He is the Editor in
Chief of the International Journal of Robotics and Control
Systems. Contact him at alfianmaarif@ee.uad.ac.id.
Qazi Mazhar ul Haq is currently working as Assistant
Professor at Yuan Ze University, Taiwan. His research area
includes Autonomous Vehicles, Object Detection, Medical
Image Processing, and Incremental Learning. Contact him at
qazi@saturn.yzu.edu.tw.
Muchammad Edo Iskandar is the President Commissioner
of Ezy Industries, Indonesia, a leading holding company that
strategically leverages Artificial Intelligence (AI) to improve
its various businesses. With visionary leadership, he drives the
deployment of cutting-edge AI solutions, aligning technology
with company goals. He has a free online school, Utter
Academy, to study coding, marketing, accounting, and
business. Contact him at edo@utter.academy.
