Community detection, also known as graph clustering, in multi-layer networks has been extensively studied in the literature. The goal of community detection is to partition vertices in a network into densely connected components so called communities. Networks contain a set of strong, dominant communities, which may interfere with the detection of weak, natural community structure. When most of the members of the weak communities also belong to stronger communities, they are extremely hard to be uncovered. We call the weak communities the hidden or disguised community structure. In this paper, we present a method to uncover weak communities in a network by weakening the strength of the dominant structure. With the aim to detect the weak communities, through experiments, we observe real-world networks to answer the question of whether real-world networks have hidden community structure or not. Results of the hidden community detection (HCD) method showed the great variation in the number of communities detected in multiple layers when compared with the results of other community detection methods.

Uncovering Hidden Community Structure in Multi-Layer Networks

Preventing or detecting the car accidents involves lots of studies and researches. In this case, most of the researches includes detecting objects which may or might result in accident. In the system we proposed, a system is designed in such a case that it detects when the accident happens and it will be gone through. This proposed system will gather appropriate information from vehicles that are adjacent to each other and process the data with the help of machine learning tools which are used to detect accidents that are possible to happen. Machine learning techniques has given success on differentiating abnormal behaviors than normal behaviors. The system's main goal is to examine behavior of the traffic and consider the vehicles that move to different than the present traffic as an road accident.

Road Accident Detection Using Machine Learning

Local intrinsic density based community detection using branch-and-bound and Minimum Spanning Tree

Blood Donor Management System is an associate work that brings voluntary blood donors and those in need of blood to an emergency. The purpose of this paper is to develop a mobile application that will help the seekers to identify the blood donors near their location. The donors as well as the seekers have toregister themselves by providing their basic details in the mobile application. When there is a need for blood, the person should raisea request through the mobile application that is visible to all donors. Then the seeker can also find the nearby blood banks. After the request is made by the seeker, the notification will be sent to all donors. And the donor can be able to accept or reject the request. Only if the donor wishes to donate the blood, his/herdetails will be shared with the seeker and also the seeker will be provided with the directions to reach the donor’s location. The personal information of the donor will not be sent to the seeker without his/her knowledge ensuring data security. After the donation process is over, the donor can update the status. One Time Password is generated to authenticate the users while registering into the application.

Blood Donor Management System - An Android Based Model and Implementation

The coronavirus COVID-19 causes a global health problem and therefore effective methods of wearing masks in common place according to the WHO. The COVID-19 epidemic forced governments all over the world impose many restrictions. Reports show that wearing mask while working significantly decrease the chance of getting affected. Effective and economical way to use Artificial Intelligence to develop some useful in production settings. The model using the face mask detection machine will be created. The detection database contains a mask and in addition to the facial images, we will use Open Computer Vision to achieve face mask detection in the webcam.

Realtime Face Mask Detection using Machine Learning

Detection of densely interconnected nodes also called modules or communities in static or dynamic networks has become a key approach to comprehend the topology, functions and organizations of the networks. Over the years, numerous methods have been proposed to detect the accurate community structure in the networks. State-of-the-art approaches only focus on finding non-overlapping and overlapping communities in a network. However, many networks are known to possess a hidden or embedded structure, where communities are recursively grouped into a hierarchical structure. Here, we reinvent such sub-communities within a community, which can be redefined based on nodes similarity. We term those derived communities as hidden or hierarchical communities. In this work, we present a method called Hidden Community based on Neighborhood Similarity Computation (HCNC) to uncover undetected groups of communities that embedded within a community. HCNC can detect hidden communities irrespective of density variation within the community. We define a new similarity measure based on the degree of a node and it’s adjacent nodes degree. We evaluate the efficiency of HCNC by comparing it with several well-known community detectors through various real-world and synthetic networks. Results show that HCNC has better performance in comparison to the candidate community detectors concerning various statistical measures. The most intriguing findings of HCNC is that it became the first research work to report the presence of hidden communities in Les Miserables, Karate and Polbooks networks.

Bashiru Aremu

Papers

Uncovering hidden community structures in evolving networks based on neighborhood similarity