A Review of Predictive Systems for Patients at Risk of Developing Stroke

Stroke remains one of the leading causes of death worldwide. It is usually associated with a build-up of fatty deposits inside the arteries which increases the risk of blood clotting. The unannounced nature of the disease when it strikes has posed a major challenge in the health sector. Poor medical facilities, insufficient information on how to accurately diagnose stroke, late identification of the disease by the patients due to being ignorant of the disease are some of the reasons for the increasing mortality rate due it. The application of data mining technique in the field of medicine has brought about positive development in the area of diagnosing, prediction and deeply understanding of healthcare data. This study considers some of the Predictive Models developed using some data mining approaches to predict patients at risk of developing stroke in order for other researchers to build on.

An Exploration of Community Detection and Recommendation Systems (CDR) in Social Networks

Community detection and Recommender systems are assumed as significant parts in helping the web users discover important information by proposing information of likely interest to them and a central task for network analysis means to segment a network into numerous substructures to assist with uncovering their inactive capacities. Community detection has been widely concentrated in and extensively applied to numerous real world network problems. Because of the possible worth of social relations in recommender systems, social recommendation has drawn in expanding consideration in recent years. As the issues that network strategies attempt to solve and the network information to be determined become progressively more complex, new methodologies have been proposed and created, traditional ways to deal with community detection and recommendation commonly use probabilistic graphical models and implement an assortment of earlier information to deduce community structures. Regardless of all the new progression, there is as yet an absence of astute comprehension of the hypothetical and methodological supporting of local area location, which will be fundamentally significant for future advancement of the space of social network analysis. In this paper, we start by giving conventional meanings of social networks terms and talk about the novel property of social networks and its implications. Unified architecture of network community finding methods to characterize the state-of-the-art of the field of community detection. In particular, we give a complete survey of the current community detection techniques and audit of existing recommender systems examine some exploration bearings to further develop social network capabilities.

A Conceptual Framework for Detecting and Analysing Website Performance Anomalies

Anomalies in website performance are very common. Most of the time they are short and only affect a small portion of the users. However, in e-commerce an anomaly is very expensive. Just one minute with an underperforming site means a big loss for a big e- commerce retailer. E-commerce web site operations are heavily transactional and prone to small, short time failures. Anomalies are sometimes small, and as such, they are not caught by the retailer web operations. However, the customers do perceive these anomalies. This paper highlights the major websites anomalies and formulates a conceptual framework that analyses them.

Fake News Detection System Using machine Learning

Expansion of deluding data in ordinary access news sources, for example, web-based media channels, news web journals, and online papers have made it testing to distinguish reliable news sources, hence expanding the requirement for computational apparatusesready to give bits of knowledge into the unwavering quality of online substance. In this paper, every person center around the programmed ID of phony substance in the news stories. In the first place, all of us present a dataset for the undertaking of phony news identification. All and sundry depict the pre-preparing, highlight extraction, characterization and forecast measure in detail. We've utilized Logistic Regression language handling strategies to order counterfeit news. The prepreparing capacities play out certain tasks like tokenizing, stemming and exploratory information examination like reaction variable conveyance and information quality check (for example invalid or missing qualities). Straightforward pack of-words, n-grams, TF-IDF is utilized as highlight extraction strategies. Strategic relapse model is utilized as classifier for counterfeit news identification with likelihood of truth.

Digital Wellness: A Smart Health Care System Using Machine Learning

Nowadays,people face various diseases due to environmental condition and their living habits. So the prediction of disease at an earlier stage becomes an important task. But the accurate prediction based on symptoms becomes too difficult for the doctor. The correctprediction of disease is the most challenging task. To overcome this problem data mining plays an important role to predict the disease. Medical science has a large amount of data growth per year. Due to the increasing amount of data growth in the medicaland healthcare field the accurate analysis of medical data has been benefits from early patient care. With the help of disease data, data mining finds hidden pattern information in a huge amount of medical data. We proposed general disease prediction based on the symptoms of the patient. For the disease prediction, we use Convolutional neural network (CNN) machine learning algorithm for the accurate prediction of disease. For disease prediction required disease symptoms dataset. After general disease prediction, this system able to gives the risk associated with a general disease which is a lower risk of general disease or highe

Video Object Detection for Police Surveillance using Deep Learning

Human vision is incredibly excellent and complex. In the previous years, people made significantly more leaps to expanding this visual capacity to machines. Cameras have been used as the eyes of computers.In response to increasing anxieties about crime and its threat to security and safety, the utilization of substantial numbers of closed-circuit television system (CCTV) in both public and private spaces have been considered a necessity. The use of these significant video footages is essential to incident investigations.But as the number of these systems rises, so as the need for human operator monitoring tasks.Unfortunately, many actionable incidents are utterly undetected in this manual systemdue to inherent limitations from deploying solely human operators eye-balling CCTV screens.As a result, surveillance footages are often used merely as passive records or as evidence for post-event investigations. This study aimed to develop a real-time firearm detection using deep learning embedded in CCTV cameras that pushes alert notifications to both iOS and Android mobile devices.This research used a descriptive design and asked IT experts to evaluate the develop system based on its compliance to ISO 25010 standard. Moreover, confusion matrix and intersection over union (IoU) were used to evaluate the performanceof the system.The detection system was found to be highly recommended in urban areas particularly for CCTVs found in barangay streets and establishments.