← Back to Archives
VOLUME 10, ISSUE 12, DECEMBER 2022
REVIEW ON COMPRISION OF RESULT IN TRAPEZIODAL AND SIMPSON’S RULE OF NUMERICAL INTERGATION
Aditya Shivam, Ajit kumar, Vishal Mehtre
Review paper on Newtons Raphson method
Prachi Dhumal, Paramveer Dwivedi
EXAMINING THE EFFECTS OF LOW INTENSITY TREADMILL WORKOUTS ON CARDIOVASCULAR FITNESS IN SEDENTARY STUDENTS
Dr.Sinku Kumar Singh, Ramakant D. Bansode, Dr.AbdulWaheed
IOT BASED SMART PET CARE SYSTEM
Suvitha P S, Niniya VB, Sanjay Kumar B S, Shinassha VS, TR Devika
STUDY AND ANALYSIS OF IMPLEMENTATION OF ROBOTICS IN THE FIELD OF PHYSIOTHERAPY
Ajmal M Y, Ashin P M, Ashma K A, Benjamin Paul P, Ajeesh S
SURFACE WATER GARBAGE COLLECTOR AND QUALITY MONITORING SYSTEM
Shahaziya Parvez M, Naveen Kumar P S, Risana Salam V A, Rosemol P P, Varun P N
BRAIN STROKE THERAPY-EXOSKELETON
Ms. Aksa David*, Rasha Jalaludeen, Brijesh K Babu, Archana M, Gopi Krishnan MS
ISLANDING DETECTION USING ON GRID ACTIVE AND REACTIVE POWER
Ms. Twinkalben Rameshbhai Patel
MEDICINE DISPENSER AND REMINDER
Linu Babu P, Anupama Ajilesh, Athulkrishna V B, Fathima Abdul Rahim, Muhammed Nisam T
A Smart Shopping System for Visually Impaired
Anjali Rajan, Anusree Subran, Devika Narayanan, Marziya Moidennsha, Nazla CS
VOICE CONTROLLED ROBOT WITH SURVEILLENCE CAMERA USING LabVIEW
HAMSA REKHA S D, SEEMA BS, SHEETAL N
STUDY OF SOLAR POWERED VENDING MACHINE
Adarsh J, Aswin Balan k, Flamin Viju C, Nivedhya Biju, Bency Varghese A
A REVIEW PAPER ON RUNGE KUTTA 4TH ORDER METHOD
Karan Mane, Vishal V. Mehtre
AI in Healthcare Operations: Optimizing Hospital Resource Allocation via Cloud Platforms
Sai Teja Nuka
Cloud-Enabled AI Architectures for Personalized Financial Services and Payment Solutions
Jai Kiran Reddy Burugulla
Power-Efficient Semiconductors for AI at the Edge: Enabling Scalable Intelligence in Wireless Systems
Goutham Kumar Sheelam
Abstract
REVIEW ON COMPRISION OF RESULT IN TRAPEZIODAL AND SIMPSON’S RULE OF NUMERICAL INTERGATION
Aditya Shivam, Ajit kumar, Vishal Mehtre
DOI: 10.17148/IJIREEICE.2022.101201
Abstract: Many different methods are applied and used in an attempt to solve numerical integration. Trapezoidal and Simpson’s rule are widely used to solve numerical integration problems. Our paper mainly concentrates on identifying the method which provides more accurate result for numerical integration. with suitable example which solved by trapezoidal method and Simpson’s rule and compare its result and error.
Keywords: Trapezoidal rule, Simpson’s rule
Keywords: Trapezoidal rule, Simpson’s rule
Abstract
Review paper on Newtons Raphson method
Prachi Dhumal, Paramveer Dwivedi
DOI: 10.17148/IJIREEICE.2022.101202
Abstract: This method is used for solving algebraic equation. This method reduce the problem to solving a second degree polynomial equation . This x-intercept will typically be a enhanced approximation to the function's root than the original guess, and the method can be iterated Based on collinear scaling and local quadratic approximation, quasi-Newton methods have improved for function value is not fully used in the Hessian matrix.one of the most important thing is that these method is not applicable for equation which has complex rule . this deficiency,obtaining a third order polynomial equation which has always real root . The Advantages of using Newton's method to approximate a root rest primarily in its rate of convergence. When the method converges, it does so quadratically. Also, the method is very simple to apply and has great local convergence. And the disadvantages of using this method are numerous. First of all, it is not guaranteed that Newton's method will converge if we select an {\displaystyle \displaystyle x_{0}}{\displaystyle \displaystyle x_{0}} that is too far from the exact root. Likewise, if our tangent line becomes parallel or almost parallel to the x-axis, we are not guaranteed convergence with the use of this method. Also, because we have two functions to evaluate with each iteration ({\displaystyle f(x_{k})}{\displaystyle f(x_{k})} and {\displaystyle f'(x_{k})}{\displaystyle f'(x_{k})}, this method is computationally expensive. Another disadvantage is that we must have a functional representation of the derivative of our function, which is not always possible if we working only from given data.
Abstract
EXAMINING THE EFFECTS OF LOW INTENSITY TREADMILL WORKOUTS ON CARDIOVASCULAR FITNESS IN SEDENTARY STUDENTS
Dr.Sinku Kumar Singh, Ramakant D. Bansode, Dr.AbdulWaheed
DOI: 10.17148/IJIREEICE.2022.101203
Abstract:
Aims The primary aim of the study was to examining the effects of Low Intensity Treadmill Workouts on Cardiovascular Fitness in sedentary students.
Target population
Only one group was targeted as an experimental group, there was no control group. The 15 male participated in the study and their age ranged between 19-28 years. The all students are sedentary and not participation any sporting or physical activities Exclusion criteria were the presence of any chronic disease that would put the subjects at risk when performing the experimental tests.
Training program Experimental group participated in Low IntensityTreadmill Workouts Training program which was conducted for four- week, four days in a week and 15 minutes in a day. After the pre-test was over, the entire selected subjects were exposed to four-weekTreadmill Workouts.
Findings
The findings of the study showthat four-weekTreadmill Workoutsintervention programme. Diastolic blood pressure and heart was decrease due to Low IntensityTreadmill Workouts Training program.
Suggestion The findings of the study will be proposing a new conceptual model that may assist the government in framing new policies and strategies to manage the health related problem
Keywords: RHR, SBP, DBP
ORIGIN OF THE PROBLEM
Sedentary lifestyle is contributing factors for Heart diseases, including coronary artery disease and heart attack., diabetes , obesity, muscle weakening , High cholesterol, Stroke, Certain cancers, including colon, breast, and uterine cancers. A Sedentary lifestyle is a type of lifestyle in which one is not Participated in physical or sporting activity or life with exercise (Sassos 2020) A person living a sedentary lifestyle is often sitting or lying down while engaged in an activity like playing video games, reading or using a mobile phone or computer for much of the day, socializing and watching TV,. A sedentary lifestyle contributes to poor cardiovascular health, diseases as well as many preventable causes of death (Owen et.al 2020). Treadmill workout offers many benefits. Treadmill workout may boost stamina to
Aims The primary aim of the study was to examining the effects of Low Intensity Treadmill Workouts on Cardiovascular Fitness in sedentary students.
Target population
Only one group was targeted as an experimental group, there was no control group. The 15 male participated in the study and their age ranged between 19-28 years. The all students are sedentary and not participation any sporting or physical activities Exclusion criteria were the presence of any chronic disease that would put the subjects at risk when performing the experimental tests.
Training program Experimental group participated in Low IntensityTreadmill Workouts Training program which was conducted for four- week, four days in a week and 15 minutes in a day. After the pre-test was over, the entire selected subjects were exposed to four-weekTreadmill Workouts.
Findings
The findings of the study showthat four-weekTreadmill Workoutsintervention programme. Diastolic blood pressure and heart was decrease due to Low IntensityTreadmill Workouts Training program.
Suggestion The findings of the study will be proposing a new conceptual model that may assist the government in framing new policies and strategies to manage the health related problem
Keywords: RHR, SBP, DBP
ORIGIN OF THE PROBLEM
Sedentary lifestyle is contributing factors for Heart diseases, including coronary artery disease and heart attack., diabetes , obesity, muscle weakening , High cholesterol, Stroke, Certain cancers, including colon, breast, and uterine cancers. A Sedentary lifestyle is a type of lifestyle in which one is not Participated in physical or sporting activity or life with exercise (Sassos 2020) A person living a sedentary lifestyle is often sitting or lying down while engaged in an activity like playing video games, reading or using a mobile phone or computer for much of the day, socializing and watching TV,. A sedentary lifestyle contributes to poor cardiovascular health, diseases as well as many preventable causes of death (Owen et.al 2020). Treadmill workout offers many benefits. Treadmill workout may boost stamina to
Abstract
IOT BASED SMART PET CARE SYSTEM
Suvitha P S, Niniya VB, Sanjay Kumar B S, Shinassha VS, TR Devika
DOI: 10.17148/IJIREEICE.2022.101204
Abstract: Pet ownership is soaring each year. People love their pets and vice versa, but taking care of pets when you are not at home is a problematic issue .so the demand for high quality pet care products are increasing. In this paper we aim at designing a pet day-care robot that can monitor as well as feed the dogs or cats in a timely manner. The Robot is an IOT Based robot that is capable of taking care you your pets alone at home. The robot is integrated with a camera that allows for live streaming over IOT platform to get on demand footage of home. The robot dispenses appropriate amount of food and water in feeding tray as instructed by user online .This entire system is controlled by a raspberry pi controller that allows for efficient controlling of all robot functionalities .The data collected from each sensor are processed and displayed on a smart phone application .Thus, pet owners through only one single interface can obtain all the information regarding pets' food conception, water conception as well as defecation timing, duration and frequency .Additionally, a controlling function is also enabled in the application for pet owners to dispense food at any time and anywhere .The robot is also integrated with a speaker that speaks out to your dog’s/cats allowing you to warn them for any wrongdoings or call them when it is feeding time
Keywords: Android Application, Robot, Raspberry pi, Surveillance.
Keywords: Android Application, Robot, Raspberry pi, Surveillance.
Abstract
STUDY AND ANALYSIS OF IMPLEMENTATION OF ROBOTICS IN THE FIELD OF PHYSIOTHERAPY
Ajmal M Y, Ashin P M, Ashma K A, Benjamin Paul P, Ajeesh S
DOI: 10.17148/IJIREEICE.2022.101205
Abstract: Physical therapy is used to improve a patient physical functions through physical examination , diagnosis , prognosis , patient education , and health promotion. It is practiced by physical therapists, usually at a clinic or at the patient suitable place . Even though physiotherapists are efficient and effective, there are some difficulties faced by patients like travel distance , works in rural areas Robotic technology designed to assist physiotherapy can potentially increase the efficiency of and accessibility to therapy. It helps to assist therapists to provide consistent training for extended periods of time, and collecting data to assess progress. Robotic devices also offer flexibility in their operation, as feedback of the user's performance based on the data from the sensors can be used to provide appropriate movements and forces during training . It enables consistent training of the prescribed intensity for extended periods of time. It has the potential to completely change the way physiotherapists deliver treatment to patients in the future.
Keywords: Physiotherapy,Robotics,Sensors.
Keywords: Physiotherapy,Robotics,Sensors.
Abstract
SURFACE WATER GARBAGE COLLECTOR AND QUALITY MONITORING SYSTEM
Shahaziya Parvez M, Naveen Kumar P S, Risana Salam V A, Rosemol P P, Varun P N
DOI: 10.17148/IJIREEICE.2022.101206
Abstract: Waste disposal in water effect the water quantity and leads to water pollution. In this article, an intelligent robotic system for water surface cleaning is developed to collect the garbage also to monitor the quality of water is proposed. The system can detect and track the floating garbage and move towards it to collect them. For collecting the garbage, a specialized arm structure is used. This work deals with, not completely cleaning an entirely polluted water resource but to prevent it from further polluted after being cleaned once. The garbage material is dumped into the tub placed behind it. Raspberry pi microprocessor is used to perform the required process. Additionally, the water quality can also be monitored in real time through web server. System movement is operated through motor driver and further controlled by propeller unit. Water environment parameters that are, Turbidity, conductivity, temperature are measured real time using turbidity sensor, Conductivity sensor temperature sensor, Respectively. And it is monitored in real time through a web server.
Keywords: Arm structure, Motor driver, Propeller unit, Turbidity sensor, Conductivity sensor, Temperature sensor, Raspberry pi, Web server.
Keywords: Arm structure, Motor driver, Propeller unit, Turbidity sensor, Conductivity sensor, Temperature sensor, Raspberry pi, Web server.
Abstract
BRAIN STROKE THERAPY-EXOSKELETON
Ms. Aksa David*, Rasha Jalaludeen, Brijesh K Babu, Archana M, Gopi Krishnan MS
DOI: 10.17148/IJIREEICE.2022.101207
Abstract: Stroke is usually the sudden death of brain cells due to lack of oxygen, caused by blockage of blood flow or rupture of an artery to the brain. A stroke occurs when part of the brain loses its blood supply and stops working. This causes the part of the body that it controls to stop working as well.Wearable exoskeleton that need to be portable,lightweight, safe.. Most current hand exoskeletons have been designed specifically for rehabilitation, assistive or haptic applications to simplify the design requirements. There are several treatments for the stroke like endovascular treatments, surgical treatments etc. but the best treatment for the paralysis, strokes, is the physiotherapy. Usually, the therapy is done manually with an assistant. We propose a method in which the physiotherapy is done automatically with the help of simple mechanisms.
Exoskeleton robots were designed to increase strength and endurance of human limbs. This kind of robots could be used to increase the physical ability of either disabled or ordinary people for executing motion or manipulation tasks. The important point is to design such a shape that could be used safely, and accurately. This function could assist in walking, running, jumping or lifting objects that are beyond the human abilities to carry. In this paper, an upper body exoskeleton robot for rehabilitation applications is presented. This exoskeleton could be used for physiotherapy of whole arm of a patient, when the physiotherapist wears the armband device and performs predefined actions. The manufacturing points including 3D printing of the main parts and prototype of the robot with control instruments and designed mobile application for controlled over IoT.
Keyword: stroke, rupture, exoskeleton, physiotherapists, manufacturing,3D printing
Exoskeleton robots were designed to increase strength and endurance of human limbs. This kind of robots could be used to increase the physical ability of either disabled or ordinary people for executing motion or manipulation tasks. The important point is to design such a shape that could be used safely, and accurately. This function could assist in walking, running, jumping or lifting objects that are beyond the human abilities to carry. In this paper, an upper body exoskeleton robot for rehabilitation applications is presented. This exoskeleton could be used for physiotherapy of whole arm of a patient, when the physiotherapist wears the armband device and performs predefined actions. The manufacturing points including 3D printing of the main parts and prototype of the robot with control instruments and designed mobile application for controlled over IoT.
Keyword: stroke, rupture, exoskeleton, physiotherapists, manufacturing,3D printing
Abstract
ISLANDING DETECTION USING ON GRID ACTIVE AND REACTIVE POWER
Ms. Twinkalben Rameshbhai Patel
DOI: 10.17148/IJIREEICE.2022.101208
Abstract: In increasing development of world, the “electricity or electrical power” plays main role. For this delivering the continuous power is necessary. In this report we will discuss about situation of islanding in which local load disconnected from main grid or micro grid and connected with source of distributed power generation. Distributed generations like PV cells, wind turbines etc. gives the continuous power supply to the load and protect it from the interruption. When load disconnected from grid and connect with DG set, for this some islanding detection methods are used which is active method, passive method and utility based method and some advanced detection method for islanding.
Keywords: Distributed Generator ,Islanding Condition , Islanding Detection Methods , Advance Anti-Islanding Protection , Wind Farm , Local Load , STATCOM , Grid Connecting Transformer,B25 Bus Data Acquisition
Keywords: Distributed Generator ,Islanding Condition , Islanding Detection Methods , Advance Anti-Islanding Protection , Wind Farm , Local Load , STATCOM , Grid Connecting Transformer,B25 Bus Data Acquisition
Abstract
MEDICINE DISPENSER AND REMINDER
Linu Babu P, Anupama Ajilesh, Athulkrishna V B, Fathima Abdul Rahim, Muhammed Nisam T
DOI: 10.17148/IJIREEICE.2022.101209
Abstract: Many medical errors are due to the fact that people in charge of patient or elder's medication have to deal with sorting huge amounts of pills each day. This paper consists on the conception, design and creation of a pillbox prototype intended to solve this deficiency in the medical area as it has the ability of sorting out the pills by itself as well as many other advanced features, with this device being intended to be used by hospitals or retirement homes.
This medication pill box is focused on patients who frequently take medications or vitamin supplements, or attendants who deal with the more seasoned or patients. Our smart pill box is programmable that enables medical caretakers or clients to determine the pill amount and timing to take pills, and the service times for every day. Our shrewd pills box contains nine separate sub-boxes. At the point when the pill time has been set, the pillbox will remind clients or patients to take pills utilizing sound and light. Contrasted and the conventional pill box that requires clients or attendants to stack the crate each day or consistently. Our shrewd pill box would essentially discharge medical attendants or clients' weight on much of the time preloading pills for patients or clients and overlook the measurements which must be taken.
This medication pill box is focused on patients who frequently take medications or vitamin supplements, or attendants who deal with the more seasoned or patients. Our smart pill box is programmable that enables medical caretakers or clients to determine the pill amount and timing to take pills, and the service times for every day. Our shrewd pills box contains nine separate sub-boxes. At the point when the pill time has been set, the pillbox will remind clients or patients to take pills utilizing sound and light. Contrasted and the conventional pill box that requires clients or attendants to stack the crate each day or consistently. Our shrewd pill box would essentially discharge medical attendants or clients' weight on much of the time preloading pills for patients or clients and overlook the measurements which must be taken.
Abstract
A Smart Shopping System for Visually Impaired
Anjali Rajan, Anusree Subran, Devika Narayanan, Marziya Moidennsha, Nazla CS
DOI: 10.17148/IJIREEICE.2022.101210
Abstract: Life of an individual depends on basic five senses in which ability of vision is probably the most important one. Fulfilling the daily tasks of life becomes extremely hard for them. This can lead to difficulties which can only be temporarily subdued by some assisting personal and cases exist where certain situations might be fatal, not only for the individual but also anyone in the surrounding environment. The World health organization (WHO) statistics indicate that a large amount of people experience vision losses because of which they encounter many difficulties in everyday jobs. To date numerous method have been processed to enhance the lifestyle of visually impaired and blind people.Here,our goal is to structure a modest, secure shopping trolley for blind people, which assist them in grocery shopping. It provides guidance to identify and purchase their products. Which contains a Raspberry Pi, as well as an RFID reader, a headset and motors. The person’s speech is used as input, through Raspberry pi, input will drive the motors to the desired direction. RFID tags are provided for product identification and the detailed information of the item is send to the person via headset. All things in the trolley are logged in the IoT and printed at the bill section.
Keywords: RFID, Ultra sonic sensor, DC servo motor and Bluetooth.
Keywords: RFID, Ultra sonic sensor, DC servo motor and Bluetooth.
Abstract
VOICE CONTROLLED ROBOT WITH SURVEILLENCE CAMERA USING LabVIEW
HAMSA REKHA S D, SEEMA BS, SHEETAL N
DOI: 10.17148/IJIREEICE.2022.101211
Abstract: In the digital world it would be cool to make a robot which obeys human speech commands and perform tasks. It will be very much fun if we can control robot with our speech. There are movies like iron man where he makes himself a totally different network for himself which is overrated. The idea of making this came from a movie called I robot, here the people uses robots for the help just by giving commands. The reason we chose voice was there are robots which work on gestures and line robots. But the voice control we used overcomes the flaws in these other ones. Voice recognition technology is made possible for the computer to analyze and follow the voice command and to understand human languages. Although there are many robots designed on touch and other devices aiding on control, the control over voice with ease of operation is left untouched. The main intention is to make a gateway for simple operation for the automation in voice controlled robot. As a solution, the robot with voice control is designed in the paper by combining the speech recognition technique with the help of LABVIEW programming concepts. The appropriate control signal for the robot will be provided by the LABVIEW. The usage of LABVIEW for the interpretation of voice signals makes the research easier compared to other sound-based robot control system.
Keywords: Speech command, Voice control, Voice recognition, LABVIEW.
Keywords: Speech command, Voice control, Voice recognition, LABVIEW.
Abstract
STUDY OF SOLAR POWERED VENDING MACHINE
Adarsh J, Aswin Balan k, Flamin Viju C, Nivedhya Biju, Bency Varghese A
DOI: 10.17148/IJIREEICE.2022.101212
Abstract: In past decades, many vending machines have been made which provide different types of products within different numbers of selections. They are divided into Medic vending machines, Food vending machines, chocolate vending machines and many other forms of drinks vending machines. In the concern of medical field, up till this 21st century, we are not able to provide first aid kits at all over places like schools, stations, and many more areas which are still under up-gradation. In those circumstances we are implementing a Medic vending machine, so people can easily dispense first aid items as well as all the necessary medicines for the person who needs immediate attention. If looking to the food and beverage sector many more vending machines are there to dispense chocolate, drinks and any type of food items. Food vending machines do not include any vending machine dispensing only canned or bottled soft drinks or prepackaged food that does not require temperature control for safety. And presently, most of the vending machines started to become Automatic and Solar powered. For automatic vending machines, there is no need for manual controls. So, people can easily dispense products from these machines while working. Talking about solar powered vending machine there is not only solar energy but also electricity is used on demand.
Abstract
A REVIEW PAPER ON RUNGE KUTTA 4TH ORDER METHOD
Karan Mane, Vishal V. Mehtre
DOI: 10.17148/IJIREEICE.2022.101213
Abstract: This is achieved by using the SIR model to solve the system, two numerical methods are used, namely 4th order Runge-Kutta. In this paper, we study the performance and comparison of both methods in solving the model. The result in this paper that in the running process of solving it turns out that using the euler method is faster than using the 4th order Runge-Kutta method and the differences of solutions between the two methods are large.
Keywords: Fourth order Runge Kutta Method, Derivation, Stability Analysis
Keywords: Fourth order Runge Kutta Method, Derivation, Stability Analysis
Abstract
Data-driven insights for community investment through mortgage-backed securities
Someshwar Mashetty
DOI: 10.17148/IJIREEICE.2022.101214
Abstract: Unconventional mortgage-backed securities (MBS) present an opportunity for the capital markets to support community investment on behalf of issuers interested in less-distant stakeholders with their investors. Such instruments seek to link offers-of-capital to on-the-ground housing finance provision that helps build community identity, which can be expressed through local economic linkages, participatory governance mechanisms and the creation of tangible assets that build personal equity. These securities can be differentiated from conventional MBS by the sectors of the economy they support, the connections they maintain with community actors, and their potential for piquing the interest of market investors through risk-return enhancements. An innovative aspect of the securities is that, through a designated capital flows mechanism, they can recirculate capital within a defined region, creating direct and indirect effects through a filtering process. By bringing together a range of institutions from diverse sectors, the paper aims to provide a stepping stone to the innovative finance communities. The paper discusses the theory behind the securities and their capital flows, gives examples of community reinvestment assistance programs, describes possible roles that different stakeholders can take on, and details the type of support socially responsible investors seek. The results clearly show that financing the housing recovery efforts in high-vacancy areas poses unique risks, and there is a widespread concern that the downside risks could be compounded through demand for low-cost, high-volume investments.
In this context, the motivation for community groups is to bring visibility to the housing market in which they operate, and to identify specific instruments that suit their investment philosophy. At present, there are very few, if any, housing rehabilitation mortgage-backed securities the investment community could focus on. These securities would not be about the issuance of collateralized mortgage obligations that operatively bundle the best assets in the market and re-label them to fit an investor-defined credit quality; the securities would rather be about the capital that operates at a local level, where default risk can be better realized, and the product sold delivers what the investor would expect: a return of their values, along with their expected return.
Keywords: Unconventional MBS, Community Investment, Capital Markets, Housing Finance, Community Identity, Economic Linkages, Participatory Governance, Tangible Assets, Personal Equity, Capital Flow Mechanism, Regional Recirculation, Innovative Finance, Reinvestment Programs, Socially Responsible Investors, Housing Recovery, High- Vacancy Areas, Investment Philosophy, Local Capital, Default Risk, Values-Based Returns.
In this context, the motivation for community groups is to bring visibility to the housing market in which they operate, and to identify specific instruments that suit their investment philosophy. At present, there are very few, if any, housing rehabilitation mortgage-backed securities the investment community could focus on. These securities would not be about the issuance of collateralized mortgage obligations that operatively bundle the best assets in the market and re-label them to fit an investor-defined credit quality; the securities would rather be about the capital that operates at a local level, where default risk can be better realized, and the product sold delivers what the investor would expect: a return of their values, along with their expected return.
Keywords: Unconventional MBS, Community Investment, Capital Markets, Housing Finance, Community Identity, Economic Linkages, Participatory Governance, Tangible Assets, Personal Equity, Capital Flow Mechanism, Regional Recirculation, Innovative Finance, Reinvestment Programs, Socially Responsible Investors, Housing Recovery, High- Vacancy Areas, Investment Philosophy, Local Capital, Default Risk, Values-Based Returns.
Abstract
AI in Healthcare Operations: Optimizing Hospital Resource Allocation via Cloud Platforms
Sai Teja Nuka
DOI: 10.17148/IJIREEICE.2022.101215
Abstract: In recent decades, modern healthcare systems need to respond to the challenges of constantly increasing patient demand, a growing number of complex diseases, and patients with multimorbidity. This results in constrained hospital resources and limited financing from governments to effectively deliver care to patients. For operational decision-making, the timely forecasting of patient arrivals and resource demand is of utmost importance. Although the importance of forecasting has been recognized, analysing, monitoring, and forecasting multivariate time series in healthcare delivery systems remain challenging. Experts must become involved in system key performance measurement, resulting in significant resources being allocated to analyse and monitor processes but ultimately missing the timely nature of forecasting. This work develops a new hierarchical recurrent neural network (RNN) model to provide forecasts for a comprehensive resource allocation problem. First, a monitoring framework is developed to provide insightful analyses of operational difficulties. Also, a new deep learning framework is designed to leverage the derived univariate time series distributions and capture correlations at multiple aggregation levels using a hierarchical RNN framework to produce simultaneous forecasts of the timing and magnitudes of resource distribution.
In healthcare operations, resource allocation significantly influences healthcare delivery efficiency and patient wait-time, for which cloud computing platforms have been adopted and developed in hospitals. This review first identifies cloud- based AI techniques to aid healthcare operations literature and then uses a systematic dual-faceted framework to systematically review cloud-based AI applications in healthcare operations literature from three perspectives: type of AI techniques and methods, applications of AI in healthcare operations, and dimensions used to separate healthcare operations research problems. The findings reveal that (i) the cloud platform has been mainly adopted in healthcare as a cost-effective and efficient data storage and sharing solution, (ii) few studies have investigated the cloud platform’s value in AI-based decision-making optimization, (iii) cloud-based AI techniques are ignition-infrastructure to drive healthcare transformation, which justifies the need of more studies that develop and deploy cloud-based AI techniques to address healthcare operations optimization problems.
Keywords: AI in healthcare operations, Hospital resource optimization, Cloud-based hospital management, Predictive analytics in healthcare, Healthcare cloud computing, AI hospital resource planning, Smart hospital infrastructure, Machine learning in operations management, Cloud-enabled healthcare analytics, Real-time hospital data management, AI-powered patient flow optimization, Dynamic bed allocation system, Intelligent staff scheduling, Healthcare logistics AI, Operational efficiency in hospitals.
In healthcare operations, resource allocation significantly influences healthcare delivery efficiency and patient wait-time, for which cloud computing platforms have been adopted and developed in hospitals. This review first identifies cloud- based AI techniques to aid healthcare operations literature and then uses a systematic dual-faceted framework to systematically review cloud-based AI applications in healthcare operations literature from three perspectives: type of AI techniques and methods, applications of AI in healthcare operations, and dimensions used to separate healthcare operations research problems. The findings reveal that (i) the cloud platform has been mainly adopted in healthcare as a cost-effective and efficient data storage and sharing solution, (ii) few studies have investigated the cloud platform’s value in AI-based decision-making optimization, (iii) cloud-based AI techniques are ignition-infrastructure to drive healthcare transformation, which justifies the need of more studies that develop and deploy cloud-based AI techniques to address healthcare operations optimization problems.
Keywords: AI in healthcare operations, Hospital resource optimization, Cloud-based hospital management, Predictive analytics in healthcare, Healthcare cloud computing, AI hospital resource planning, Smart hospital infrastructure, Machine learning in operations management, Cloud-enabled healthcare analytics, Real-time hospital data management, AI-powered patient flow optimization, Dynamic bed allocation system, Intelligent staff scheduling, Healthcare logistics AI, Operational efficiency in hospitals.
Abstract
MLOps at Scale: Bridging Cloud Infrastructure and AI Lifecycle Management
Phanish Lakkarasu
DOI: 10.17148/IJIREEICE.2022.101216
Abstract: To successfully manage the development and deployment of machine learning models (ML models), organizations require a platform that provides the necessary tools, standardized settings, and workflows for ML teams to easily build, monitor, and leverage ML models’ intelligence and insights at scale. This introduction section highlights the challenges organizations face in building robust, automated, reliable, and production-ready machine learning solutions. These challenges include managing changes across multiple tools, monitoring components throughout the AI lifecycle, and enabling collaboration among all teams involved in this lifecycle. Organizations need a hybrid cloud infrastructure that allows them to connect MLOps tools hosted on different clouds and vendors while enabling low-maintenance integration and a simplified, extensible developer experience. Traditionally, data scientists and AI developers performed data and model storage, training, and predictions on the organizations' infrastructure, whether on-premise or cloud- hosted. These systems allowed the development of ML solutions at scale through clustering hardware or distributed training techniques. These solutions were typically written as self-contained batch programs scheduled and monitored with existing data processing schedulers. The majority of ML workloads were still too simple for the engineering and deployment work needed to develop a robust and efficient solution, which allowed for other approaches to be followed. Once models were defined and trained, they were typically saved to disk, logged into a version control system, or manually documented in the source code or ticketing system. Existing systems, which in general were made for more traditional software, did not efficiently address the needs of an ML development team, which had very different tooling and priorities. This introduction focuses on vendor-neutral and cloud-agnostic approaches to the MLOps platform that empowers organizations to choose or easily integrate multiple open-source or proprietary tools into their workflows and pipelines while abstracting them with a streamlined API. The proposed platform addresses the aforementioned challenges faced by organizations by offering a set of deployment-ready components, giving them more freedom for customizing their MLOps and AI infrastructure management. Finally, the achievements of the MLOps works mentioned above and expected contributions to the literature are discussed.
Keywords: Data Science Platform; Data Lifecycle Management; Deployment & Monitoring; Machine Learning Platforms; MLOps. MLOps, MLOps system; ML; Ai; AIops; AIOps; Development process.
Keywords: Data Science Platform; Data Lifecycle Management; Deployment & Monitoring; Machine Learning Platforms; MLOps. MLOps, MLOps system; ML; Ai; AIops; AIOps; Development process.
Abstract
A Secure and Scalable IT Infrastructure Model for AI-Powered Banking Services
Bharath Somu
DOI: 10.17148/IJIREEICE.2022.101217
Abstract: In the rapidly evolving landscape of financial services, the integration of artificial intelligence (AI) has become imperative for maintaining competitiveness and ensuring customer satisfaction. This abstract presents a comprehensive overview of a secure and scalable IT infrastructure model tailored for AI-powered banking services. The model addresses the dual challenges of safeguarding sensitive financial data while supporting the computational demands of AI systems. The traditional banking IT infrastructure is no longer sufficient; it must transition to a robust architecture that embraces cloud computing and advanced security protocols. At the core of the proposed model lies a multi-layered architecture designed to balance performance and security. The infrastructure incorporates advanced encryption algorithms and robust firewalls alongside machine learning algorithms that detect anomalies in real-time, thereby enhancing threat detection capabilities. Seamless integration of these technologies enables financial institutions to process large volumes of data efficiently while ensuring compliance with regulatory frameworks. Additionally, the adoption of containerization and microservices architecture supports the modular deployment of AI applications, allowing for rapid scaling in response to fluctuating user demands. This infrastructure not only prioritizes security but also ensures scalability, allowing banks to adapt to the increasing complexities associated with AI-driven analytics. As AI continues to reshape customer interactions and operational processes, organizations must reconsider their infrastructure strategies. The proposed model provides a strategic blueprint that not only meets current demands but also anticipates future advancements in AI technologies. Through a thorough examination of security measures, deployment strategies, and performance optimization, this abstract sets the groundwork for a detailed exploration of how a secure and scalable IT infrastructure can catalyze the effective implementation of AI in banking services. This synthesis of security, scalability, and efficiency is essential for leveraging AI's transformative potential in the financial sector, ensuring that institutions can thrive in an increasingly digital economy.
Keywords: Secure IT infrastructure, scalable architecture, AI-powered banking, cybersecurity, data protection, cloud computing, microservices, containerization, identity management, encryption protocols, multi-factor authentication, intrusion detection systems, compliance automation, load balancing, high availability, disaster recovery, zero trust model, network segmentation, system hardening, virtualization, API security, continuous monitoring, infrastructure as code, data governance, AI integration, secure data lakes, orchestration platforms, secure DevOps, fault tolerance, regulatory compliance.
Keywords: Secure IT infrastructure, scalable architecture, AI-powered banking, cybersecurity, data protection, cloud computing, microservices, containerization, identity management, encryption protocols, multi-factor authentication, intrusion detection systems, compliance automation, load balancing, high availability, disaster recovery, zero trust model, network segmentation, system hardening, virtualization, API security, continuous monitoring, infrastructure as code, data governance, AI integration, secure data lakes, orchestration platforms, secure DevOps, fault tolerance, regulatory compliance.
Abstract
Enabling Sustainable Manufacturing Through AI-Optimized Supply Chains
Raviteja Meda
DOI: 10.17148/IJIREEICE.2022.101218
Abstract: Rapid digital transformations in every aspect of life, work, and society are aided by quickly developing technologies like artificial intelligence (AI) and the Internet of Things (IoT). The sophisticated data-driven decision- making environment that they inspire enables the implementation of smart manufacturing, in which every aspect of manufacturing is monitored using sensors that continuously record and analyze data streams in real-time. The focus is on monitoring the real-time state of affairs within the ecosystem of machines, processes, and resources. This shift in paradigm can increase productivity, efficiency, and profitability in a significantly disruptive manner by enhancing the transparency of operations and automating data-driven decision-making processes. This transformation needs to embrace many technological and systematic alterations that require aligned collective efforts from stakeholders. The design, development, and interoperation are essential for the successful implementation of smart manufacturing systems. Mass customization, lower energy consumption, retrofitting and reusability of assets, lower environmental impact, and a more sustainable production process are desirable manufacturing efficiencies that will drive up the acceptance of smart manufacturing systems.
A supply chain (SC) must be designed to allow for efficient management of all aspects of supply chain planning, analysis, modeling, monitoring, and control with the support of data-driven business intelligence (BI) systems. The smart manufacturing system architecture that is detailed in this context. Singularity of the suggested system architecture shields processes, operations, systems, subsystems, and their interactions from external environment factors that have an effect on them, to provide a high-quality working mode in the time of overflowing demand. The core of the AI-assisted BI system centered around prediction includes (i) a HW/SW architectural setup, and (ii) and AI algorithms with differing depths for data cleansing and feature engineering that enables the existence of such a smart manufacturing system architecture. Alternative AI algorithms are employed with fusing/conjunction of numerous learning algorithms for more efficient training of models with superior forecast accuracy to predict production, delivery, and external demand. The AI-assisted BI system is scalable and adaptable to more than 2 massive datasets for expectant production planning and control through training of models that can provide estimates of machine UT, jobs carried out in time, and the number of finished products. Contemplating on the trade-off between profitability and sustainability with model operationalization that considers data governance, data utilization, and data development costs alongside carbon- and energy-aware manufacturing are possible.
Keywords: Sustainable Manufacturing, Artificial Intelligence, Supply Chain Optimization, Green Manufacturing, Predictive Analytics, Smart Logistics, Resource Efficiency, Carbon Footprint Reduction, AI-Driven Decision Making, Circular Economy, Environmental Impact, Machine Learning, Real-Time Monitoring, Energy Efficiency, Data-Driven Manufacturing.
A supply chain (SC) must be designed to allow for efficient management of all aspects of supply chain planning, analysis, modeling, monitoring, and control with the support of data-driven business intelligence (BI) systems. The smart manufacturing system architecture that is detailed in this context. Singularity of the suggested system architecture shields processes, operations, systems, subsystems, and their interactions from external environment factors that have an effect on them, to provide a high-quality working mode in the time of overflowing demand. The core of the AI-assisted BI system centered around prediction includes (i) a HW/SW architectural setup, and (ii) and AI algorithms with differing depths for data cleansing and feature engineering that enables the existence of such a smart manufacturing system architecture. Alternative AI algorithms are employed with fusing/conjunction of numerous learning algorithms for more efficient training of models with superior forecast accuracy to predict production, delivery, and external demand. The AI-assisted BI system is scalable and adaptable to more than 2 massive datasets for expectant production planning and control through training of models that can provide estimates of machine UT, jobs carried out in time, and the number of finished products. Contemplating on the trade-off between profitability and sustainability with model operationalization that considers data governance, data utilization, and data development costs alongside carbon- and energy-aware manufacturing are possible.
Keywords: Sustainable Manufacturing, Artificial Intelligence, Supply Chain Optimization, Green Manufacturing, Predictive Analytics, Smart Logistics, Resource Efficiency, Carbon Footprint Reduction, AI-Driven Decision Making, Circular Economy, Environmental Impact, Machine Learning, Real-Time Monitoring, Energy Efficiency, Data-Driven Manufacturing.
Abstract
Cloud-Enabled AI Architectures for Personalized Financial Services and Payment Solutions
Jai Kiran Reddy Burugulla
DOI: 10.17148/IJIREEICE.2022.101219
Abstract: The financial industry includes a number of different sub-sectors, including revenue sources for financial instruments, organizations that broker transactions, payment systems, and fintech companies that offer consumer services. Firms using or developing these technologies compete with financial services companies, and established firms are developing in-house capabilities and making acquisitions. The recent proliferation of financial technologies is in part a consequence of mobile technologies allowing small retailers to accept payments via smartphone, and asset management firms either established their own trading and exchange businesses, or became early investors in other companies' developing liquidity technology.
By making central bank redemption clear, straightforward, and secure, a CBDC would foster trust in its own value as currency, which a commercial bank does not typically have. It would blunt the transfer of deposits from a central bank to a commercial bank, preventing bank “runs” as in the Great Depression. Beneficiaries of bank runs are often suspected of taking their banking elsewhere, curbed by a national currency impossible to avoid. If CBDC accounts contain nontransferable monetary balances, then an injection of CBDC would be of higher quality than redistributing existing confederal public debt to fight a liquidity crisis because it would not remove deposits from banks. Restrictions would also contain the more poisonous possibility of nontransferable CBDC accounts.
The proposed architecture allows banks and payment service providers to offer different types of financial services integrated with various cloud-enabled AI architectures based on their size, originality, use case, and customer needs. As efforts are made to commercialize a much wider range of financial services integrated with different payment mechanisms, this framework of schemes will contribute significantly to models and cloud-enabled big data architectures with AI capabilities for the growing middle and lower income segments of countries worldwide in Africa, South America, East Asia and the subcontinents.
Keywords: Cloud-Based AI Platforms, Personalized Financial Services, AI-Driven Payment Solutions, Financial Technology (FinTech), Cloud-Native Infrastructure, Real-Time Customer Insights, AI Personalization Engines, Hybrid Cloud Architecture, Machine Learning in Finance, Cloud Scalability in Banking, Secure AI Transactions, Intelligent Payment Routing, API-Driven Financial Services, Cloud Computing in FinTech, AI-as-a-Service (AIaaS).
By making central bank redemption clear, straightforward, and secure, a CBDC would foster trust in its own value as currency, which a commercial bank does not typically have. It would blunt the transfer of deposits from a central bank to a commercial bank, preventing bank “runs” as in the Great Depression. Beneficiaries of bank runs are often suspected of taking their banking elsewhere, curbed by a national currency impossible to avoid. If CBDC accounts contain nontransferable monetary balances, then an injection of CBDC would be of higher quality than redistributing existing confederal public debt to fight a liquidity crisis because it would not remove deposits from banks. Restrictions would also contain the more poisonous possibility of nontransferable CBDC accounts.
The proposed architecture allows banks and payment service providers to offer different types of financial services integrated with various cloud-enabled AI architectures based on their size, originality, use case, and customer needs. As efforts are made to commercialize a much wider range of financial services integrated with different payment mechanisms, this framework of schemes will contribute significantly to models and cloud-enabled big data architectures with AI capabilities for the growing middle and lower income segments of countries worldwide in Africa, South America, East Asia and the subcontinents.
Keywords: Cloud-Based AI Platforms, Personalized Financial Services, AI-Driven Payment Solutions, Financial Technology (FinTech), Cloud-Native Infrastructure, Real-Time Customer Insights, AI Personalization Engines, Hybrid Cloud Architecture, Machine Learning in Finance, Cloud Scalability in Banking, Secure AI Transactions, Intelligent Payment Routing, API-Driven Financial Services, Cloud Computing in FinTech, AI-as-a-Service (AIaaS).
Abstract
Power-Efficient Semiconductors for AI at the Edge: Enabling Scalable Intelligence in Wireless Systems
Goutham Kumar Sheelam
DOI: 10.17148/IJIREEICE.2022.101220
Abstract: Artificial Intelligence (AI) based applications are increasingly being deployed on the edge of the network due to the faster response times required by many of these applications [1]. At the same time, low latency operation becomes important as real-time edge datasets may not be amenable to storage on the cloud. However, this leads to a larger number of processors that are more broadly distributed over the edge of the network. Power constraints on these edge processors or AI accelerators present a challenge since these devices will usually need to operate on battery power. This may also lead to an increase in the carbon footprint of AI systems as more AI accelerator networks are deployed.
AI applications typically consume more than 50% of the power in infrastructure devices or the edge of the network. Within these devices, the AI accelerator which performs AI inferences consumes a large amount of power (typically over 50%). Subsequently, reductions of both active and idle power of AI accelerators will significantly improve the energy efficiency of infrastructure devices and overall AI systems. Various innovative methods can be used to lower the active power including quantization, pruning, RMSE loss minimization, hybrid architectures which combine different types of AI accelerators, and sparsity.
A significant portion of the power consumption of AI accelerators is due to idle power caused by the scheduling and repeated wake-up of the AI accelerators to perform AI inference tasks [2]. Redundant carry-free designs and asynchronous designs can be used to lower the active power. After compiling, sparse-structured weights can be used to reduce memory access delay, a primary source of power and delay in AI inferences. In order to better analyze the power savings due to sleek operation, a power in the fabricated unit of workloads should be explored.
Keywords: Power Efficiency, Semiconductors, Edge AI, Low Power Design, Scalable Intelligence, Wireless Systems, Embedded AI, Edge Computing, AI Accelerators, Energy Efficiency, Real-Time Processing, IoT Devices, Neural Network Hardware, Smart Sensors, Signal Processing, AI Chips, 5G Integration, Tiny ML–, Hardware Optimization, System-on-Chip (SoC)
AI applications typically consume more than 50% of the power in infrastructure devices or the edge of the network. Within these devices, the AI accelerator which performs AI inferences consumes a large amount of power (typically over 50%). Subsequently, reductions of both active and idle power of AI accelerators will significantly improve the energy efficiency of infrastructure devices and overall AI systems. Various innovative methods can be used to lower the active power including quantization, pruning, RMSE loss minimization, hybrid architectures which combine different types of AI accelerators, and sparsity.
A significant portion of the power consumption of AI accelerators is due to idle power caused by the scheduling and repeated wake-up of the AI accelerators to perform AI inference tasks [2]. Redundant carry-free designs and asynchronous designs can be used to lower the active power. After compiling, sparse-structured weights can be used to reduce memory access delay, a primary source of power and delay in AI inferences. In order to better analyze the power savings due to sleek operation, a power in the fabricated unit of workloads should be explored.
Keywords: Power Efficiency, Semiconductors, Edge AI, Low Power Design, Scalable Intelligence, Wireless Systems, Embedded AI, Edge Computing, AI Accelerators, Energy Efficiency, Real-Time Processing, IoT Devices, Neural Network Hardware, Smart Sensors, Signal Processing, AI Chips, 5G Integration, Tiny ML–, Hardware Optimization, System-on-Chip (SoC)
Abstract
Transition from Digital Health Technologies to Artificial Intelligence–Driven Care
Ghatoth Mishra
DOI: 10.17148/IJIREEICE.2022.101221
Abstract: The rapid evolution of digital health technologies has laid the foundation for a transformative shift toward artificial intelligence (AI)–driven healthcare systems. While early digital health solutions primarily focused on data digitization, connectivity, and remote care delivery, recent advancements in AI have enabled more intelligent, adaptive, and predictive models of care. This transition represents a paradigm shift from reactive and standardized healthcare toward proactive, personalized, and precision-driven interventions. AI-driven care leverages machine learning algorithms, big data analytics, and real-time clinical decision support systems to enhance diagnostic accuracy, optimize treatment pathways, and improve patient outcomes. However, the integration of AI into healthcare ecosystems also introduces significant challenges related to data quality, interoperability, algorithmic bias, explainability, ethics, and governance. This paper examines the progression from traditional digital health technologies to AI-enabled care models, highlighting key technological enablers, clinical applications, and system-level impacts. Furthermore, it explores the implications for healthcare professionals, patients, and policymakers, emphasizing the need for robust regulatory frameworks and human-centered AI design. Understanding this transition is critical for ensuring that AI-driven care augments clinical expertise, enhances patient trust, and delivers equitable and sustainable healthcare solutions.
Keywords: Digital health, Artificial intelligence in healthcare, AI-driven care, Clinical decision support systems, Machine learning, Predictive analytics, Personalized medicine, Precision healthcare, Health informatics, Electronic health records (EHRs), Big data in healthcare, Remote patient monitoring, Telemedicine, Automation in healthcare, Ethical AI, Explainable AI, Healthcare transformation, Patient-centered care, Interoperability, Data governance.
Keywords: Digital health, Artificial intelligence in healthcare, AI-driven care, Clinical decision support systems, Machine learning, Predictive analytics, Personalized medicine, Precision healthcare, Health informatics, Electronic health records (EHRs), Big data in healthcare, Remote patient monitoring, Telemedicine, Automation in healthcare, Ethical AI, Explainable AI, Healthcare transformation, Patient-centered care, Interoperability, Data governance.
Abstract
Computer Vision Systems for Defect Detection in Semiconductor Fabrication
Ganesh Pambala
DOI: 10.17148/IJIREEICE.2022.101222
Abstract: The rapid growth of the semiconductor industry continues to push for advances in manufacturing quality assurance capability. Classical human-based visual inspection is becoming increasingly impractical because of high inspection cost and rapid manufacturing throughput, and thus machine vision systems for surface defect detection are becoming common solutions. To facilitate the design and evaluation of such systems, wide-ranging research into computer vision solutions for surface defect detection in semiconductor manufacture is presented. This comprises an overview of semiconductor fabrication processes and defect types, consideration of essential concepts in computer vision, examination of common detection approaches, and the creation of two openly available image datasets. These datasets, designed specifically for semiconductor contexts, are carefully annotated and then employed to assess classical image processing techniques and machine learning detectors.
The general nature of the discussion makes it relevant across numerous manufacturing domains, with emphasis on fundamental computer vision concepts of relevance to any defect detection task. Special focus is given to the preparation of image datasets, and particular attention is placed on design considerations essential for real-world deployment in high- throughput manufacturing environments.
Keywords: Semiconductor fabrication; defect detection; computer vision; image processing; machine learning; dataset; Automated Optical Inspection (AOI); Wafer Defect Detection; Deep Learning-Based Visual Inspection; Semiconductor Manufacturing Yield Analysis; Convolutional Neural Networks (CNNs) for Inspection; Inline Process Monitoring; Submicron Defect Classification; Image-Based Fault Diagnosis; Smart Manufacturing (Industry 4.0); Real-Time Quality Control Systems.
The general nature of the discussion makes it relevant across numerous manufacturing domains, with emphasis on fundamental computer vision concepts of relevance to any defect detection task. Special focus is given to the preparation of image datasets, and particular attention is placed on design considerations essential for real-world deployment in high- throughput manufacturing environments.
Keywords: Semiconductor fabrication; defect detection; computer vision; image processing; machine learning; dataset; Automated Optical Inspection (AOI); Wafer Defect Detection; Deep Learning-Based Visual Inspection; Semiconductor Manufacturing Yield Analysis; Convolutional Neural Networks (CNNs) for Inspection; Inline Process Monitoring; Submicron Defect Classification; Image-Based Fault Diagnosis; Smart Manufacturing (Industry 4.0); Real-Time Quality Control Systems.