Commit d6c34c3c authored by Chamodi Mandakini's avatar Chamodi Mandakini

Update README.md

parent 3b99c94d
The Use of Web Based Expert System Application for Children with Special Needs with Special Needs Service Management and 24/7 Monitoring System
AI (Artificial Intelligence), ML(Machine Learning), and Data Science is especially influential for children who need special education. These children mostly have one type of learning disability, so they have some impairments in social skills like language and communication or they have trouble in reading, writing and mathematics. Having all this in mind, it is obvious that the traditional one size fits all approach is not applicable for children taking special education.
Developing fully intelligent education tools and new virtual teaching assistants will take time for sure. But given the current technological advancements, here is the five changes AI, ML, and Data Science is already making on special market today:
Our plan is making a one system for children with special need in all around the world and using this web system their parent/guardian can monitor them and give them proper education at home with this. They do not need to find a place for their educations and skill development. All the parents/ guardians receive a detailed report of their children at the end. For an example how is he mental health, whether they happy or not.
We Targeting the children with mental disorders and who is hard do their work lonely, With the help of this system they can continue there studies at home and give a help to Work with decisions properly, main thing is the purposed system monitoring them all time with this parent don’t need to suffer about finding place to take care of them
Main Objective:
The system created should be able to assist the parent/guardian in understanding the state of the child such as type of feeling expressed and help their education with the system
Sub Objective 1: Face recognition Monitoring and Attention Recognition
Sub Objective 2: Game Based learning platform
Sub Objective 3: Sentiment Analysis of children
Sub Objective 4: AI based decision support platform with Depression analysis
Research Problem:
In order for children with special needs mostly (5 years old to 18 years old) to be independent and productive members of the society, their needs should be identified, and they should be provided with the necessary training environments and services[1] ,Children with disabilities form one of the most marginalized and excluded groups in society, whose rights are generally ignored [2].
In recent years, the number of children and young people with disabilities has dramatically increased all over the world. These days parents of special need children getting trouble because of they have to find proper place for their education and place for take care of them, and most of special need children can’t say their emotions correctly.
Today Information and Communication Technologies (ICT) have been broadly applied to the field of education and learning technologies transformed educational systems with impressive progress. The enhanced use of ICT in most sectors of the community, especially in supporting education and inclusion for persons with disabilities can be a powerful tool to improve their quality of life.
Many children with disabilities are facing a wide range of barriers, including omitted from educational opportunities and do not complete primary education [3] Game-based learning refers to the borrowing of certain gaming principles and applying them to real-life settings to engage users .The motivational psychology involved in game- based learning allows students to engage with educational materials in a playful and dynamic way.
Skin cancer is a form of cancer that arises in the skin's cells. Millions of cases are diagnosed each year around the world, making it the most
prevalent type of cancer. Skin exposed to ultraviolet (UV) radiation from sources like tanning beds or sunshine is more likely to develop skin
cancer.
Actinic keratoses and intraepithelial carcinoma/disease, Bowen's basal cell carcinoma, benign keratosis-like lesions (solar lentigines/
seborrheic keratoses and lichen-planus like keratoses, BKL), dermatofibroma, melanoma, melanocytic nevi, and vascular lesions are the seven main
types of skin cancer (angiomas, angiokeratomas, pyogenic granulomas and hemorrhage, VASC). The most prevalent forms of skin cancer, basal cell
carcinoma and squamous cell carcinoma, are typically less dangerous than melanoma. The most deadly kind of skin cancer, melanoma, can be fatal
if it is not found and treated in a timely manner.
Changes in the appearance of the skin, such as the emergence of a new mole or a modification in the size, shape, or color of an already-existing
mole, can be signs of skin cancer. Another sign could be the formation of a sore or lump that won't go away, or a scaly, red spot on the skin.
Skin cancer management success depends on early detection and treatment. Surgery, radiation therapy, chemotherapy, and other drugs are all
possible treatment choices. Skin cancer risk can also be decreased by taking preventive steps like applying sunscreen and limiting exposure to
the sun.Skin cancer prediction systems have evolved over the past few decades, with the development of advanced technologies and data analytics
driving significant improvements in accuracy and reliability.
The Glasgow Seven-Point Checklist, which was created in the early 1990s and employed a list of seven criteria to evaluate the risk of skin cancer
, was one of the first models for skin cancer prediction. This model, which was developed based on a visual examination of skin lesions, is now
frequently employed in dermatology procedures.Since then, scientists have worked to further develop and enhance skin cancer prediction models,
adding fresh data from genetic and imaging sources to increase precision. Large datasets have also been analyzed using machine learning
algorithms to find patterns and trends in patient data that can be used to estimate the likelihood of developing skin cancer.
Today, skin cancer prediction systems are widely used in dermatology and primary care settings, helping healthcare providers to identify
patients at high risk of skin cancer and develop personalized treatment plans to reduce that risk. These systems continue to evolve and improve,
with ongoing research and development focused on improving accuracy and usability and expanding the range of patient data sources that can be
analyzed.
A combination of cutting-edge technologies and data analytics are used by current skin cancer prediction systems to pinpoint those who are most
likely to get the disease. These systems often make use of a variety of patient data sources, such as dermoscopy images, medical history, skin
type, and history of sun exposure. This data is analyzed using machine learning algorithms to spot patterns and trends that can be used to
gauge a patient's risk of acquiring skin cancer. These algorithms can also be used to determine which risk factors are crucial for a particular
patient, enabling medical professionals to create individualized treatment schedules that target those particular risk factors.
Skin cancer prediction systems are typically used in a clinical setting, where healthcare providers can use the results of the analysis to
develop personalized treatment plans for high-risk patients. This may involve regular skin cancer screenings, advice on sun protection
measures, or other interventions to reduce the risk of skin cancer.
Overall, skin cancer prediction systems are a valuable tool for improving patient outcomes by allowing for early detection and preventive
measures to reduce the risk of skin cancer. Ongoing research and development are focused on improving the accuracy and usability of these
systems, as well as expanding the range of patient data sources that can be analyzed
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment