Reference no: EM133745306 , Length: word count:1500

INTELLIGENT SYSTEMS

Learning Outcome 1: Analyse intelligent systems using concepts from machine learning, fuzzy logic, search, expert systems, neural networks, and peripheral techniques

Learning Outcome 2: Implement intelligent systems to solve business problems

Learning Outcome 3: Present and communicate complex results, derived from intelligent systems, to non-technical audiences to encourage data-driven changes

Learning Outcome 4: Evaluate emerging trends and ethical issues in intelligent systems and their application in industry

Briefly described below are the teaching methods/strategies used in this subject

Task Details: Complete the weekly tutorial exercises that encompass a range of topics related to intelligent systems. The exercises will simulate real-world scenarios to ensure practical proficiency.

Project with presentation
Assessment purpose: The purpose of this assignment is to assess the students' knowledge about understanding of data and analysis of intelligent systems. Students need to write a report on this task followed by the knowledge-based scheme implemented with respect to the chosen topic. This assessment contributes to learning outcomes a, c, and d.

Task details:

Intelligent systems are technologically advanced machines that perceive and respond to the world around them. Intelligent systems have played a very active role in society's economic and technological transformation. For industrial value chains and international businesses, it means that a structural change is necessary since these machines can learn and apply new information in making forecasts, processing, and interacting with people. These systems use powerful enough techniques, strategies, and mathematical modelling to tackle complex actual problems. Because of its inevitable progress further into the future, there have been considerable safety and ethical concerns. In this context, the goal of this assessment is to investigate the emerging trends of intelligent systems (the benefits that it brings to the society), the moral challenges that come from ethical algorithms, learned or pre-set ideals, as well as discussing the ethical issues and malpractices of such systems.

Suggested report structure:
Abstract
Introduction
Dataset, Materials, and Methods
Design
Ethical issues
References

Artificial Intelligence (AI) and Machine Learning (ML) enabled IoT Solutions are trending topics for research as they are growing in various sectors. The growth of IOT in industry, engineering, science and technology, and medicine have provided manifold possibilities to practice AI and ML in these domains. These technologies can benefit IOT solutions when they are shared at device as well as service level. AI when combined with ML can be used for practicing the data analysis and future prediction in the medical domain, industrial IOT, healthcare and health informatics. The combination of AI and ML with IOT sensors will also

be beneficial in the field of big data analysis and smart homes for enabling home automated experience. This technology will be useful in assessing human behaviour using motion sensors, facial recognition, and making corresponding modifications in home lighting and temperature. This topic will motivate recent research in the emerging areas of AI and ML enabled IOT for providing effective prominent solutions.

Accordingly, topics are listed below (but not limited to):
Emerging application of AI and ML empowered IOT solutions for healthcare and health informatics
Emerging trends of industrial IOT (IIOT) enabling AI and ML for security-based applications
AI and ML enabled IOT solutions for home automation, motion sensing, facial recognition, etc.
AI/ML based IOT modules for condition screening, visualization and patient monitoring in healthcare
AI and ML empowered IOT solutions for big data analysis utilizing various protocols and standards
AI and ML enabled optimized IOT frameworks for power management in distributed systems
Recent advances and applications of AIOT, Edge AI and edge intelligence in cloud-based applications
Optimized IOT frameworks communication and network virtualization.

Assessment - Group Assignment

Research and Practical assignment
Assessment purpose: The purpose of this assignment is to assess the students' knowledge on data understanding, intelligent model implementation, achieving hidden knowledge/insights. Students need to write a report on this task followed by the knowledge-based scheme implemented with respect to the given case study. This assessment contributes to learning outcomes a, b, c, d.

knowledge-based schemes on a benchmark dataset Task Details:
A stroke is a medical condition in which poor blood flow to the brain causes cell death. There are two main types of stroke: ischemic, due to lack of blood flow, and haemorrhagic, due to bleeding. Both cause parts of the brain to stop functioning properly. Signs and symptoms of a stroke may include an inability to move or feel on one side of the body, problems understanding or speaking, dizziness, or loss of vision to one side. Signs and symptoms often appear soon after the stroke has occurred. If symptoms last less than one or two hours, the stroke is a transient ischemic attack (TIA), also called a mini-stroke. A haemorrhagic stroke may also be associated with a severe headache. The symptoms of a stroke can be permanent. Long-term complications may include pneumonia and loss of bladder control.

The main risk factor for stroke is high blood pressure. Other risk factors include high blood cholesterol, tobacco smoking, obesity, diabetes mellitus, a previous TIA, end-stage kidney disease, and atrial fibrillation. An ischemic stroke is typically caused by blockage of a blood vessel, though there are also fewer common causes. A haemorrhagic stroke is caused by either bleeding directly into the brain or into the space between the brain's membranes. Bleeding may occur due to a ruptured brain aneurysm. Diagnosis is typically based on a physical exam and is supported by medical imaging such as a CT scan or MRI scan. A CT scan can rule out bleeding, but may not necessarily rule out ischemia, which early on typically does not show up on a CT scan. Other tests such as an electrocardiogram (ECG) and blood tests are done to determine risk factors and rule out other possible causes. Low blood sugar may cause similar symptoms.
Prevention includes decreasing risk factors, surgery to open up the arteries to the brain in those with problematic carotid narrowing, and warfarin in people with atrial fibrillation. Aspirin or statins may be recommended by physicians for prevention. A stroke or TIA often requires emergency care. An ischemic stroke, if detected within three to four and half hours, may be treatable with a medication that can break down the clot. Some haemorrhagic strokes benefit from surgery. Treatment to attempt recovery of lost function is called stroke rehabilitation, and ideally takes place in a stroke unit; however, these are not available in much of the world.

Attribute Information:
gender: "Male", "Female" or "Other"
age: age of the patient
hypertension: 0 if the patient doesn't have hypertension, 1 if the patient has hypertension
heart disease: 0 if the patient doesn't have any heart diseases, 1 if the patient has a heart disease
ever-married: "No" or "Yes"
worktype: "children", "Govtjov", "Neverworked", "Private" or "Self-employed" 7) Residencetype: "Rural" or "Urban"
avgglucoselevel: average glucose level in blood
bmi: body mass index
smoking_status: "formerly smoked", "never smoked", "smokes" or "Unknown"*
stroke: 1 if the patient had a stroke or 0 if not

Students are recommended to use the following report structure that address the marking rubric criteria:

Introduction: introduces the case study and the objective
Data understanding: Visualize the data. Explain the data. What preparation methods are required? What feature play important role in your prediction model?
Model implementation and evaluation: show the screenshot of your implemented models followed by the explanation. How would you improve the performance of your models? Compared the models against each other.
Insights: Discuss the output that you receive for the implemented models. Explain the knowledge and insight about the examples in the dataset.
Conclusion: Conclude the model implementation and the results you receive from them. Highlight the key points in the insights.
References: follow a consistent format and use Harvard style.