Algorithmic Analysis of Automatic Attendance System using Facial Recognition

Attendance management can become a tedious task for teachers if it is performed manually.. This problem can be solved with the help of an automatic attendance management system. But validation is one of the main issues in the system. Generally, biometrics are used in the smart automatic attendance system. Managing attendance with the help of face recognition is one of the biometric methods with better efficiency as compared to others. Smart Attendance with the help of instant face recognition is a real-life solution that helps in handling daily life activities and maintaining a student attendance system. Face recognition-based attendance system uses face biometrics which is based on high resolution monitor video and other technologies to recognize the face of the student. In project, the system will be able to find and recognize human faces fast and accurately with the help of images or videos that will be captured through a surveillance camera. It will convert the frames of the video into images so that our system can easily search that image in the attendance database.

Prediction of chronic obstructive pulmonary disease stages using machine learning algorithms

Identifying chronic obstructive pulmonary disease (COPD) severity stages is of great importance to control the related mortality rates and reduce the associated costs. This study aims to build prediction models for COPD stages and, to compare the relative performance of five machine learning algorithms to determine the optimal prediction algorithm. This research is based on data collected from a private hospital in Egypt for the two calendar years 2018 and 2019. Five machine learning algorithms were used for the comparison. The F1 score, specificity, sensitivity, accuracy, positive predictive value and negative predictive value were the performance measures used for algorithms comparison. Analysis included 211 patients’ records. Our results show that the best performing algorithm in most of the disease stages is the PNN with the optimal prediction accuracy and hence it can be considered as a powerful prediction tool used by decision makers in predicting severity stages of COPD.

SARCP - Exploiting Cyber-Attack Prediction Through Socially-Aware Recommendation

In the domain of cyber security, the defence mechanisms of networks has traditionally been placed in a reactionary role. Cyber security professionals are therefore disadvantaged in a cyber-attack situation due to the fact that it is vital that they maneuver such attacks before the network is totally compromised. In this paper, we utilize the Betweenness Centrality network measure (social property) to discover possible cyber-attack paths and then employ computation of similar personality of nodes/users to generate predictions about possible attacks within the network. Our method proposes a social recommender algorithm called socially-aware recommendation of cyber-attack paths (SARCP), as an attack predictor in the cyber security defence domain. In a social network, SARCP exploits and delivers all possible paths which can result in cyber-attacks. Using a real-world dataset and relevant evaluation metrics, experimental results in the paper show that our proposed method is favorable and effective.

Multi-attribute Group Decision-making (MAGDM) using Fuzzy Linguistic Modeling Integrated with the VIKOR Method for Car Purchasing Model

The change in the trend of transportation, increasing per capita income, expectation of better lifestyle, easy finance, and reduced cost of the automobile are some of the main factors that enable a commoner to have his/her own car. Therefore, it is essential to comprise such features in cars that offer qualities enabling the ease of consumer’s decision-making and comfort to purchase a car individually. Purchasing a car is a complicated multi-criteria decision-making problem as an individual may have different preferences for different criteria attributes. The attributes may be conflicting in nature depending on the need of the individual customer. Generally, it becomes quite difficult to assign ratings to these attributes based on numeric values. Therefore, the decision-making process relies on an idiosyncratic finding of the decision-makers which is in practice fuzzy with uncertainities. Hence, this article is a case study that deals with a hierarchy MCDM approach in accordance with the fuzzy logic and VIKOR method to solve a car purchasing problem.

Decision Support for Plan Adaptation in Unforeseen Situations

Handling irregular phenomena might bring great complexity for involved teams. Variables considered for undertaking recommended procedures may yield many decision alternatives, challenging to deal with at planning time. Additionally, expectations regarding the phenomena handling may not match those observed. This means that the existing plan’s application may become inappropriate, and teams must be creative in performing actions and decision-making. An approach for on-the-fly adaptation of plans aims to assist teams in identifying and diagnosing unforeseen situations, besides adjusting previously developed plans at runtime. This approach was evaluated through experiments in the emergency management domain, and the initial results indicate its feasibility in dealing with unforeseen situations while handling irregular phenomena in complex environments.

Ordering policy estimation for high utility item-sets considering negative item values in large databases

Utility mining with negative item values has recently received interest in the data mining field due to its practical considerations. Previously, the values of utility item-sets have been taken into consideration as positive. However, in real-world applications an item-set may be related to negative item values. This paper presents a method for redesigning the ordering policy by including high utility item-sets with negative items. Initially, utility mining algorithm is used to find high utility item-sets. Then, ordering policy is estimated for high utility items considering defective and non-defective items. A numerical example is illustrated to validate the results

Hate Speech Detection Using Text Mining and Machine Learning

Automatic hate speech detection on social media is becoming an outstanding concern in modern countries. Indeed, hate speech towards people brings about violent acts and social chaos, hence law prohibits it, and it engenders moral and legal implications. It is crucial that we can precisely categorize the hate speech, and not a hate speech automatically, while this allows us to identify easily real people who represent a threat for our society, and who wrongly regard as hateful speakers. In this paper, we applied a complete text mining process and Naïve Bayes machine learning classification algorithm to two different data sets (tweets_Num1 and tweets_Num2) taken from Twitter, to better classify tweets. The results obtained demonstrate that our model performed well regarding different metrics based on the confusion matrix including the accuracy metric, which achieved 87. 23% on the first dataset, and 93. 06% on the second.

Fuzzy Multi-objective Linear Programming Problem using DM's Perspective

In this paper, a two-stage method has been proposed for solving Fuzzy Multi-objective Linear Programming Problem (FMOLPP) with Interval Type-2 Triangular Fuzzy Numbers (IT2TFNs) as its coefficients. In the first stage of problem solving, the imprecise nature of the problem has been handled. All technological coefficients given by IT2TFNs are first converted to a closed interval and then the objectives are made crisp by reducing a closed interval into a crisp number and constraints are made crisp by using the concept of acceptability index. The amount by which a specific constraint can be relaxed is decided by the decision maker and thus the problem reduces to a crisp multi-objective linear programming problem (MOLPP). In the second stage of problem solving, the multi-objective nature of the problem is handled by using fuzzy mathematical programming approach. In order to explain the methodology, two numerical examples of the proposed methodology in Production planning and Diet planning problems have also been worked out in this paper.

Specifications of a queuing model-driven decision support system for predicting the healthcare performance indicators pertaining to the patients flow

This article has developed specifications for a new model-driven decision support system (DSS) that aids the key stakeholders of public hospitals in estimating and tracking a set of crucial performance indicators pertaining to the patients flow. The developed specifications have considered several requirements for ensuring an effective system, including tracking the performance indicator on the level of the entire patients flow system, paying attention to the dynamic change of the values of the indicator’s parameters, and considering the heterogeneity of the patients. According to these requirements, the major components of the proposed system, which include a comprehensive object-based queuing model and an object-oriented database, have been specified. In addition to these components, the system comprises the equations that produce the required predictions. From the system output perspective, these predictions act as a foundation for evaluating the performance indicators as well as developing policies for managing the patients flow in the public hospitals.

An approach to optimize container locations in a containership with Electre III

In this article, we treat the problem of container storage in the export direction, exactly in the containership loading process. We propose an approach to the problem of container placement in a containership by describing a decision model to help decision-makers (handling operators) to minimize the total containers shifting. This is obtained by using a multicriteria decision method named Electre III (Elimination and Choice Expressing Reality) to identify the best location of any container. Here, we consider four criteria: the container destination, the container weight, the departure date of the container and the container type. This method has as input a matrix of performance and the subjective parameters and gives a ranking of alternatives as an output.