Wrapper feature selection methods aim to reduce the number of features from the original feature set to and improve the classification accuracy simultaneously. In this paper, a wrapper-feature selection algorithm based on the binary dragonfly algorithm is proposed. Dragonfly algorithm is a recent swarm intelligence algorithm that mimics the behavior of the dragonflies. Eighteen UCI datasets are used to evaluate the performance of the proposed approach. The results of the proposed method are compared with those of Particle Swarm Optimization (PSO), Genetic Algorithms (GAs) in terms of classification accuracy and number of selected attributes. The results show the ability of Binary Dragonfly Algorithm (BDA) in searching the feature space and selecting the most informative features for classification tasks.

Waste management policy makers always face the problem of how to predict the future amount and composition of medical solid waste, which, in turn, helps to determine the most appropriate treatment, recycling and disposal strategy. An accurate prediction can assist in both the planning and design of medical solid waste management systems. Insufficient budget and unavailable management capacity are the main reasons for the scarcity of medical solid waste quantities and components historical records, which are so important in long-term system planning and short-term expansion programs. This article presents a new technique, using System Dynamics modeling, to predict generated medical solid waste in a developing urban area, based on a set of limited samples from Jenin District hospitals, Palestine. The findings of the model present the trend of medical solid waste generation together with its different components and indicate that a new forecasting approach may cover a variety of possible causative models and track inevitable uncertainties when traditional statistical least-squared regression methods are unable to handle such issues.

Hospitals and health centers provide a variety of healthcare services and normally generate hazardous waste as well as general waste. General waste has a similar nature to that of municipal solid waste and therefore could be disposed of in municipal landfills. However, hazardous waste poses risks to public health, unless it is properly managed. The hospital waste management system encompasses many factors, i.e., number of beds, number of employees, level of service, population, birth rate, fertility rate, and not in my back yard (NIMBY) syndrome. Therefore, this management system requires a comprehensive analysis to determine the role of each factor and its influence on the whole system. In this research, a hospital waste management simulation model is presented based on the system dynamics technique to determine the interaction among these factors in the system using a software package, ithink. This model is used to estimate waste segregation as this is important in the hospital waste management system to minimize risk to public health. Real data has been obtained from a case study of the city of Nablus, Palestine to validate the model. The model exhibits wastes generated from three types of hospitals (private, charitable, and government) by considering the number of both inpatients and outpatients depending on the population of the city under study. The model also offers the facility to compare the total waste generated among these different types of hospitals and anticipate and predict the future generated waste both infectious and non-infectious and the treatment cost incurred.

Feature selection is an important preprocessing step for classification problems. It deals with selecting near optimal features in the original dataset. Feature selection is an NP-hard problem, so meta-heuristics can be more efficient than exact methods. In this work, Ant Lion Optimizer (ALO), which is a recent metaheuristic algorithm, is employed as a wrapper feature selection method. Six variants of ALO are proposed where each employ a transfer function to map a continuous search space to a discrete search space. The performance of the proposed approaches is tested on eighteen UCI datasets and compared to a number of existing approaches in the literature: Particle Swarm Optimization, Gravitational Search Algorithm and two existing ALO-based approaches. Computational experiments show that the proposed approaches efficiently explore the feature space and select the most informative features, which help to improve the classification accuracy.

The term internet of thing (IoT) has gained much popularity in the last decade. Which can be defined as various connected devices over the internet. IoT has rapidly  spread to include all aspects of our lives. For instance, smart houses, smart cities, and variant wearable devices. IoT devices work to do their desired goals, which is to develop a person life with his/her minimal involvement. At the same time, IoT devices have many weaknesses, which attackers exploit to affect these devices security. Denial of Service (DoS) and Distributed Denial of Service (DDoS) are considered the most common attacks that strike IoT security. The main aim of these attacks is to make victim systems down and inaccessible for legitimate users by malicious malware. This paper objective is to discuss and review security issues related to DoS/DDoS Attacks and their counter measures i.e. prevention based on IoT devices layers structure.