The study of human mobility is crucial due to its impact on several aspects of our society, such as disease spreading, urban planning, well-being, pollution, and more. The proliferation of digital ...

A Survey on Deep Learning for Human Mobility

Text Categorization (TC) has become recently an important technology in the field of organizing a huge number of documents. Feature Selection (FS) is commonly used to reduce dimensionality of text datasets with huge number of features which would be difficult to process further. In this paper we have implemented an efficient feature selection algorithm based on Particle Swarm Optimization (PSO) to improve the performance of Arabic text categorization. PSO is a search algorithm that employs a population of particles existing within a multi-dimensional space. We have used Radial Basis Function (RBF) networks as a text classifier. The performance of the proposed algorithm is compared to the performance of document frequency, tf×idf and Chi-square statistic algorithms. Simulation results on the Arabic dataset show the superiority of the proposed algorithm.

/pdf/text-feature-selection-using-particle-swarm-optimization-343kpzk8je.pdf

Text Feature Selection using Particle Swarm Optimization Algorithm

Combinatorial Particle Swarm Optimization (CPSO) is a relatively recent technique for solving combinatorial optimization problems. CPSO has been used in different applications, e.g., partitional clustering and project scheduling problems, and it has shown a very good performance. In partitional clustering problem, CPSO needs to determine the number of clusters in advance. However, in many clustering problems, the correct number of clusters is unknown, and it is usually impossible to estimate. In this paper, an improved version, called CPSOII, is proposed as a dynamic clustering algorithm, which automatically finds the best number of clusters and simultaneously categorizes data objects. CPSOII uses a renumbering procedure as a preprocessing step and several extended PSO operators to increase population diversity and remove redundant particles. Using the renumbering procedure increases the diversity of population, speed of convergence and quality of solutions. For performance evaluation, we have examined CPSOII using both artificial and real data. Experimental results show that CPSOII is very effective, robust and can solve clustering problems successfully with both known and unknown number of clusters. Comparing the obtained results from CPSOII with CPSO and other clustering techniques such as KCPSO, CGA and K-means reveals that CPSOII yields promising results. For example, it improves 9.26 % of the value of DBI criterion for Hepato data set.

Dynamic clustering using combinatorial particle swarm optimization

Building a Intrusion Detection System for IoT Environment using Machine Learning Techniques

The Internet of Things (IoT) has emerged as a technology capable of connecting heterogeneous nodes/objects, such as people, devices, infrastructure, and makes our daily lives simpler, safer, and fruitful. Being part of a large network of heterogeneous devices, these nodes are typically resource-constrained and became the weakest link to the cyber attacker. Classical encryption techniques have been employed to ensure the data security of the IoT network. However, high-level encryption techniques cannot be employed in IoT devices due to the limitation of resources. In addition, node security is still a challenge for network engineers. Thus, we need to explore a complete solution for IoT networks that can ensure nodes and data security. The rule-based approaches and shallow and deep machine learning algorithms– branches of Artificial Intelligence (AI)– can be employed as countermeasures along with the existing network security protocols. This paper presented a comprehensive layer-wise survey on IoT security threats, and the AI-based security models to impede security threats. Finally, open challenges and future research directions are addressed for the safeguard of the IoT network.

/pdf/security-threats-and-artificial-intelligence-based-2qjruosllv.pdf

Security Threats and Artificial Intelligence Based Countermeasures for Internet of Things Networks: A Comprehensive Survey

Graph Similarity-based Hierarchical Clustering of Trajectory Data

This paper is a research and analysis on the prediction of location of moving objects that gained popularity over the years. Trajectory specifies the path of the movement of any object. There is an increase in the number of applications using the location-based services (LBS), which needs to know the location of moving objects where trajectory mining plays a vital role. Trajectory mining techniques use the geographical location, semantics, and properties of the moving object to predict the location and behavior of the object. This paper analyses the various strategies in the process of making prediction of future location and constructing the trajectory pattern. The analyses of various mechanisms are done based on various factors including accuracy and ability to predict the distant future. Location prediction problem can be with known reference points and unknown reference points, and semantic-based prediction gives an accurate result whereas the probability-based prediction for unknown reference points.

A Survey of Location Prediction Using Trajectory Mining

In this paper, a novel Discrete Particle Swarm Optimization Algorithm (DPSOA) for data clustering has been proposed. The particle positions and velocities are defined in a discrete form. The DPSOA algorithm uses of a simple probability approach to construct the velocity of particle followed by a search scheme to constructs the clustering solution. DPSOA algorithm has been applied to solve the data clustering problems by considering two performance metrics, such as TRace Within criteria (TRW) and Variance Ratio Criteria (VRC). The results obtained by the proposed algorithm have been compared with the published results of Basic PSO (B-PSO) algorithm, Genetic Algorithm (GA), Differential Evolution (DE) algorithm and Combinatorial Particle Swarm Optimization (CPSO) algorithm. The performance analysis demonstrates the effectiveness of the proposed algorithm in solving the partitional data clustering problems.

Discrete Particle Swarm Optimization Algorithm for Data Clustering.

Chennai is a metropolitan city in India. It has many lakes and reservoirs which are changing due to urbanization. Remote sensing and GIS techniques are widely used for water body extraction and water body change detection. This study evaluates water body extraction from satellite images of Chennai city using machine learning methods. Many classifiers are trained to extract water bodies from satellite images. Landsat 5 images of Chennai were taken from USGS Earth Explorer for the year 2009. The study aims to compare the classification results of different machine learning algorithms such as J48 decision tree, naive Bayes, multilayer perceptron, k-nearest neighbor, iso-cluster and random forest in extracting the water bodies. The tools used are ArcGIS for geospatial analysis, Weka tool for classification and R for the visual interpretation of the results. The results illustrate that naive Bayes classifier is able to identify lake regions better when compared to all other classifiers.

R. Karthi

Papers

Building a Intrusion Detection System for IoT Environment using Machine Learning Techniques

Graph Similarity-based Hierarchical Clustering of Trajectory Data

A Survey of Location Prediction Using Trajectory Mining

Discrete Particle Swarm Optimization Algorithm for Data Clustering.

Evaluation of Water Body Extraction from Satellite Images Using Open-Source Tools