Search

Aim: The aim of this paper is to improve Accuracy in Disease prediction using symptoms by a novel multilayer perceptron classifier in comparison with the Random Forest algorithm. Materials and Methods: Novel multilayer perceptron classifier and random forest sample size (N=10) to predict the accuracy percentage of predicted disease. G-power is calculated for two different groups, alpha (0.05), power (80%). Results: Based on the measurement of data, statistical analysis, and independent sample T-test, there is a statistically insignificant difference between the two study groups with value p=0.488 (p> 0.05). It was observed that the novel multilayer perceptron algorithm obtains accuracy as 95%. It appears to have better accuracy than the random forest (81%). Conclusion: The results prove that the novel multilayer perceptron algorithm there is a significant improvement in techniques with varied seed values in disease prediction using symptoms. [ABSTRACT FROM AUTHOR]

In contrast to the past, advancements in computer and communication technologies have resulted in broad and rapid transformations. People, organizations, and governments all benefit from new inventions, yet some people, organizations, and governments are harmed. For example, security of important data, the security of stored information, and the accessibility of the data, among other things. Digital fear is one of the most critical challenges in today's world, based on these difficulties. Digital apprehension, which has caused a slew of concerns for individuals and organizations, has reached a point where it might jeopardize open and national security by many groups, including criminal organizations, Intrusion Detection Systems (IDS) were developed in this vein to keep a strategic distance from digital attacks. Currently, support vector machine computations were used to detect port sweep initiatives based on the new CICIDS 2017. In the this paper we use the ensembled based hybrid classification which can enhance the better detection rate since here we use weak and strong classifiers. [ABSTRACT FROM AUTHOR]

Nowadays, Thyroid is common disease that affects most of the people due to their modern lifestyle. A Thyroid ailments are the disorders that disturbs the thyroid gland which has a butterfly shape positioned at the front of the neck. The general endocrine carcinoma that may occur in the thyroid gland is Thyroid cancer. This type of cancer might not cause any indications at chief. But as it develops, it can show major signs and symptoms, such as swelling in the neck, voice changes and difficulty in swallowing. An ample effort has been given by many researchers in improving its diagnosis and prognosis. Thyroidectomy is considered as the main treatment method for thyroid problems. This research work mainly focuses on cleansing of thyroid cancer data from the UCI machine learning repository. This cleansing process involves removing the redundant values, impute the missing values, and selecting the best features from the existing fresh medical dataset by applying and comparing the various algorithms. It helps the medical practitioner to make an accurate diagnosis of the thyroid among various people. [ABSTRACT FROM AUTHOR]

Surfing the internet has become an integral part of our day-to-day life. This has become the potential source of intruder attacks. Hazard is cybercriminal posed threat, the simple example for the same is creating malicious URL to pose phishing attack and to gain access to user's personal information. The consequences include identity theft, other types of frauds like malware injection onto the computing devices. Malicious URL is a link that redirects the user to a fraudulent web page. Recognition of such malicious URLs is a prolonging problem since machine learning (ML) has evolved. There have been ML classifier like random forest (RF) and deep learning (DL) classifiers such as Convolutional Neural Network (CNN), Back Propagation Neural Networks (BPNN) and Long Short-Term Memory (LSTM) which may address this classification problem of segregating URLs into malicious and normal. Still these techniques are not sufficient to protect the internet users and requires a robust model that will distinguish between the normal and malicious web pages. This paper introduces a comparative study about ML and DL techniques in classification of URLs as malicious and normal in the given dataset. Among the implemented techniques BPNN gave an optimal accuracy of 96.86%. [ABSTRACT FROM AUTHOR]

Landslides are a significant issue in India due to the country's varied topography, heavy monsoon rains, and deforestation, which contribute to soil instability and increased landslide risk. These natural disasters can cause damage to infrastructure and loss of life. In light of the ongoing problem of landslides in India, this research paper aims to address the need for effective landslide prediction strategies. Through the findings of this research study, a novel approach has been presented for predicting landslide occurrences in India, which will aid in reducing the impact of these events on infrastructure, communities, and lives. The work that has been carried out using data and information based in India has shown to have a low accuracy level. As a result, the model created using this information is not deemed to be very reliable. This study focuses on predicting landslides in India using machine learning models such as (Xtreme Gradient Boost) XGboost, random forest, and AdaBoost. Previous research on landslide prediction in India had not been widely done or had not achieved acceptable accuracy levels. This study aims to address this gap in knowledge and improve the predictability of landslides in India. The research is based on a database of different areas in India and aims to increase awareness and save lives and resources by predicting landslides with 91% accuracy. [ABSTRACT FROM AUTHOR]