Ammar Adl

Predicting Personality Traits and Social Context Based on Mining the Smartphones SMS Data

Reality Mining is one of the first efforts that have been exerted to utilize smartphone’s data; to analyze human behavior. The smartphone data are used to identify human behavior and discover more attributes about smartphone users, such as their personality traits and their relationship status. Text messages and SMS logs are two of the main data resources from the smartphones. In this paper, The proposed system define the user personality by observing behavioral characteristics derived from smartphone logs and the language used in text messages. Hence, The supervised machine learning methods (K-nearest nighbor (KNN), support vector machine, and Naive Bayes) and text mining techniques are used in studying the textual matter messages. From this study, The correlation between text messages and predicate users personality traits is broken down. The results provided an overview on how text messages and smartphone logs represent the user behavior; as they chew over the user personality traits with accuracy up to 70 %.

PQSAR: The membrane quantitative structure-activity relationships in cheminformatics

Abstract The applications of quantitative structure activity relationships (QSAR) are used to establish a correlation between structure and biological response. Similarity searching is one of QSAR major phases. Innovating new strategies for similarity searching is an urgent task in cheminformatics research for three reasons: (i) the increasing size of chemical search space of compound databases; (ii) the importance of similarity measurements to (2D) and (3D) QSAR models; and (iii) similarity searching is a time consuming process in drug discovery. In this study, we introduce theoretical similarity searching strategy based on membrane computing. It solves time consumption problem. We adopt a ranking sorting algorithm with P System to rank probabilities of similarity according to a predefined similarity threshold. That bio-inspired model, simulating biological living cell, presents a high performance parallel processing system, we called it PQSAR. It relies on a set of rules to apply ranking algorithm on probabilities of similarity. The simulated experiments show how the effectiveness of PQSAR method enhanced the performance of similarity searching significantly; and introduced a standard ranking algorithm for similarity searching.

Towards a Computational Human Behavioral Model

This paper introduces a computational model capable of receiving human behavior patterns, extracting relations and generating new inferences and insights about targeted actors as well as predictions about expected patterns of behavior. Designing an abstract behavior model is the core problem being solved here to reach behavioral analysis goals such as relations extraction, insights generation and prediction. The level of abstraction is being achieved by defining abstract data structures that can receive, qualify and quantify behavioral information for a targeted person, as well as the definition of logical and mathematical relations among data structures using a set of logical and mathematical rules. Identifying data and logic elements properly leads to a behavioral model that can be the basis of any intelligent computer system understanding human behavior and responding according to human needs. Revolution in human-machine interfaces and sensory technology made any computer system capable of capturing natural human input. However, systems are still limited in how such input is interpreted.

A Social Relationship Modifiers Modeller

Social relationships or personalize interfaces is one of the most impressive topic in human behavior studies. A social relationship modeling depends on relation modifiers. The relation modifiers represent relation attitude and change. Some Social relationships modeling is need to be identified and standardized circles of relations. In present study, we introduce a relation modifiers modeller to identify circles of social relationships based on smartphone photo gallery. There are four relation modifiers drived in study such as (degree of relation, transitivity, decay or lifetime, and trust). These modifiers represent the main part of proposed relation modifiers modeller. This is the first paper introduces relation modifiers identification from smartphone photo gallery. The model results achieved accuracy up to 70% with decay modifiers, and accuracy of trust modifier reached 98%.

An Orphan Drug Legislation System

Orphan drugs are a treatment for rare diseases. From that, comes the importance of orphan drug development and discovery. For an orphan drug to be approved by the FDA, it does not have to be similar to any approved orphan drug. So chemists opinions are important to determine the probability of similarity. It is too hard to check all orphan drugs for any rare disease. It takes a long time and big effort, so we introduce in this study a system that classifies the orphan drugs according to their probability of structural similarity. It also compares between them and the unauthorized orphan drug to determine the closest orphan drug to it. That system helps chemists to study a certain orphan database using the five features. That system provides better results. It provides chemists with the clusters of orphan drugs after adding the drug that needs to be authorized to its cluster.

Criminal Act Detection and Identification Model

In this paper, we are examining and analyzing human behavior model throughout reality data sources to extract patterns and clues of criminal and suspicious acts. Reality data composed of the digital traces people leave while interacting with computing devices. In this paper, we are focusing on data from peoples interaction with social networks and mobile usage such as location markers and call logs. This work also introduces a model for detecting suspicious behavior based on social network feeds. It is based on classification model that can categorize a set of input actions and movements into three types of behavior, criminal, suspicious, or normal. The proposed system is expected to help crime analysts create faster and precise decisions.The model is expected to provide a behavior profile to help crime analysts in the process of crime prevention, understanding crime motivations, and proactive policing.

Digital Pathological Services Capability Framework

Pathology digital lab is the modern, flexible and time effec- tive research assistant. The process of creating pathology slides contains five creation steps from the tissue samples collection till clearing and staining stage. The reservation and sharing of such slides using classical models limit the ability of pathologists to benefit from important and rare slides. The virtual lab with its digital slides conquers those limita- tions and adds more intelligence to research and diagnosis fields. Having the digital slides, it is easy to save, share, search, apply automatic di- agnosis through pattern recognition techniques, getting alerts for new slides and much more. The target of this work is to present the virtual lab design with its functionalities by explaining the glass slides creation process and then digitalize through scanners and the digital lab platform.

Orphan Drug Legislation with Data Fusion Rules Using Multiple Fingerprints Measurements

The orphan drug certification process from the European committee is depending on experts opinions that it is not similar to any other drug, this stage is very complicated and those opinions differ based on the expertise. So, this paper introduces computational model that gives one accurate probability of similarity, using multiple fingerprints measurements to similarity, and fuse these measurements by data fusion rules, that give one probability of similarity helping experts to determine that drug is similar to existing anyone or not.