Fadi Al Machot

Followers

Following

Co-author

Public Views

Interests

Uploads

Papers by Fadi Al Machot

A Current Encyclopedia of Bioinformatics Tools, Data Formats and Resources for Mass Spectrometry Lipidomics

Metabolites

Mass spectrometry is a widely used technology to identify and quantify biomolecules such as lipid... more Mass spectrometry is a widely used technology to identify and quantify biomolecules such as lipids, metabolites and proteins necessary for biomedical research. In this study, we catalogued freely available software tools, libraries, databases, repositories and resources that support lipidomics data analysis and determined the scope of currently used analytical technologies. Because of the tremendous importance of data interoperability, we assessed the support of standardized data formats in mass spectrometric (MS)-based lipidomics workflows. We included tools in our comparison that support targeted as well as untargeted analysis using direct infusion/shotgun (DI-MS), liquid chromatography−mass spectrometry, ion mobility or MS imaging approaches on MS1 and potentially higher MS levels. As a result, we determined that the Human Proteome Organization-Proteomics Standards Initiative standard data formats, mzML and mzTab-M, are already supported by a substantial number of recent software...

Download

HFM: A Hybrid Feature Model Based on Conditional Auto Encoders for Zero-Shot Learning

Journal of Imaging

Zero-Shot Learning (ZSL) is related to training machine learning models capable of classifying or... more Zero-Shot Learning (ZSL) is related to training machine learning models capable of classifying or predicting classes (labels) that are not involved in the training set (unseen classes). A well-known problem in Deep Learning (DL) is the requirement for large amount of training data. Zero-Shot learning is a straightforward approach that can be applied to overcome this problem. We propose a Hybrid Feature Model (HFM) based on conditional autoencoders for training a classical machine learning model on pseudo training data generated by two conditional autoencoders (given the semantic space as a condition): (a) the first autoencoder is trained with the visual space concatenated with the semantic space and (b) the second autoencoder is trained with the visual space as an input. Then, the decoders of both autoencoders are fed by the test data of the unseen classes to generate pseudo training data. To classify the unseen classes, the pseudo training data are combined to train a support vecto...

Download

Human Emotion: A Survey focusing on Languages, Ontologies, Datasets, and Systems

SN Computer Science

Emotions are an essential part of a person’s mental state and influence her/his behavior accordin... more Emotions are an essential part of a person’s mental state and influence her/his behavior accordingly. Consequently, emotion recognition and assessment can play an important role in supporting people with ambient assistance systems or clinical treatments. Automation of human emotion recognition and emotion-aware recommender systems are therefore increasingly being researched. In this paper, we first consider the essential aspects of human emotional functioning from the perspective of cognitive psychology and, based on this, we analyze the state of the art in the whole field of work and research to which automated emotion recognition belongs. In this way, we want to complement the already published surveys, which usually refer to only one aspect, with an overall overview of the languages ontologies, datasets, and systems/interfaces to be found in this area. We briefly introduce each of these subsections and discuss related approaches regarding methodology, technology, and publicly acc...

Download

LipidXplorer 1.2.8

LipidXplorer is a software that supports a variety of untargeted shotgun lipidomics experiments a... more LipidXplorer is a software that supports a variety of untargeted shotgun lipidomics experiments and experiments from LC/MS lipidomics. It is designed to support bottom-up and top-down shotgun lipidomics experiments performed on all types of tandem mass spectrometers. Lipid identification does not rely on a database resource of reference or simulated mass spectra. <strong>Aims:</strong> This release is focused on improving the import module and implementing the recently introduced filtering approach based on counting reoccurrences of peaks in MS-scans and MS/MS-scans conceptually following Schuhmann et al. [1]. All other general functionalities of the former releases should not be affected [2-5]. Further changes were made for better documentation and simpler user guidance. Some experimental and/or unused options were deactivated (grouping samples, heuristic hierarchical alignment, dta/csv import). Details are listed below. <strong>Usage:</strong> The frequency...

Real-Time Raindrop Detection System Using Cellular Neural Networks (by Fadi Al

A Review of Object Classification for Video Surveillance Systems

Adaptive contrast enhancement involving CNN-based processing for foggy weather conditions & non-uniform lighting conditions

Proceedings of the Joint INDS'11 & ISTET'11, 2011

Adaptive image processing in the context of Advanced Driver Assistance Systems (ADAS) is a crucia... more Adaptive image processing in the context of Advanced Driver Assistance Systems (ADAS) is a crucial issue because bad weather conditions lead to poor vision. In a foggy weather, image contrast and visibility are low due to the presence of airlight that is generated by scattering light, which in turn is caused by fog particles. Since vision based ADAS are affected by inadequate contrast, a real-time capable solution is required. To improve such degraded images, a method is required which processes each image region separately. Hence, real-time processing is required, the method is realized with the CNN paradigm which claims the characteristic of real-time image processing. To compare the proposed method with existing state-of-the-art methods the Tenengrad measure is applied. Index Terms-Cellular Neural Network, CLAHE, weather degraded image restoration, real-time image processing, adaptive contrast enhancement.

Download

Enabling a Driver-Specific “Real-Time Road Safety” Assessment through an “Extended Floating Car Data” and Visualization System

Studies in Computational Intelligence, 2011

This paper does in a first step discuss the necessity of a “real-time road safety assessment” cap... more This paper does in a first step discuss the necessity of a “real-time road safety assessment” capability. Since traditional road safety has mainly been an offline and post-event business, the fundamental question here is that of exploring ways/concepts and technologies for enabling a form of real-time and driver-context-specific road safety assessment before fatal events such as accidents happen. The motivation is evident, as it is well known that “prevention is better than cure”. Concerning “fatal events” this paper also proposes a nuance and an extension of the concept. It does suggest a full range of event categories ranging from “hard fatal events” like a real accident to “soft fatal events” such as stress situation, some abrupt braking or just a lack of ergonomy of certain parts of the road traffic network in time and space. The availability of precious real-time data does in fact open a new research avenue for road safety. Real-time safety assessment that may be coupled to eco-driving considerations will enable a real-time recommender system for driver assistance and/or car navigation.

Smart resource-aware multimedia sensor network for automatic detection of complex events

2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2011

This paper presents a smart resource-aware multimedia sensor network. We illustrate a surveillanc... more This paper presents a smart resource-aware multimedia sensor network. We illustrate a surveillance system which supports human operators, by automatically detecting the complex events and giving the possibility to recall the detected events and searching them in an intelligent search engine. Four subsystems have been implemented, the tracking and detection system, the network configuration system, the reasoning system and an advanced archiving system in an annotated multimedia database.

Download

AVSS 2011 demo session: Smart Resource-Aware Multi-Sensor Network

2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2011

Download

CNN based high performance computing for real time image processing on GPU

Proceedings of the Joint INDS'11 & ISTET'11, 2011

Many of the basic image processing tasks suffer from processing overhead to operate over the whol... more Many of the basic image processing tasks suffer from processing overhead to operate over the whole image. In real time applications the processing time is considered as a big obstacle for its implementations. A High Performance Computing (HPC) platform is necessary in order to solve this problem. The usage of hardware accelerator make the processing time low. In recent developments, the Graphics Processing Unit (GPU) is being used in many applications. Along with the hardware accelerator a proper choice of the computing algorithm makes it an added advantage for fast processing of images. The Cellular Neural Network (CNN) is a large-scale nonlinear analog circuit able to process signals in real time [1]. In this paper, we develop a new design in evaluation of image processing algorithms on the massively parallel GPUs with CNN implementation using Open Computing Language (OpenCL) programming model. This implementation uses the Discrete Time CNN (DT-CNN) model which is derived from originally proposed CNN model. The inherent massive parallelism of CNN along with GPUs makes it an advantage for high performance computing platform [2]. The advantage of OpenCL makes the design to be portable on all the available graphics processing devices and multi core processors. Performance evaluation is done in terms of execution time with both device (i.e. GPU) and host (i.e. CPU).

Download

Real time complex event detection for resourcelim ited multimedia sensor networks

This paper presents a real-time complex event detection concept for resource-limited multimedia s... more This paper presents a real-time complex event detection concept for resource-limited multimedia sensor networks. A comprehensive solution based on Answer Set Programming (ASP) is developed. We show that ASP is an appropriate solution to detect a large number of simple and complex events (video-audio understanding) on platforms with lim-ited resources e.g. power consumption, memory and pro-cessing power. We underline the major problems of the ex-isting paradigms for complex event detection (based on e.g. logic programming and Semantic Web), with a special focus on the major challenges which reduce the performance of real-time event detection. Finally, we demonstrate the high performance of ASP compared to that of Semantic Web. 1.

Download

A Novel Real-Time Emotion Detection System for Advanced Driver Assistance Systems

This paper presents a real-time emotion recognition concept of voice streams. A comprehensive sol... more This paper presents a real-time emotion recognition concept of voice streams. A comprehensive solution based on Bayesian Quadratic Discriminate Clas-sifier(QDC) is developed. The developed system supports Advanced Driver Assis-tance Systems (ADAS) to detect the mood of the driver based on the fact that aggres-sive behavior on road leads to traffic accidents. We use only 12 features to classify between 5 different classes of emotions. We illustrate that the extracted emotion features are highly overlapped and how each emotion class is effecting the recogni-tion ratio. Finally, we show that the Bayesian Quadratic Discriminate Classifier is an appropriate solution for emotion detection systems, where a real-time detection is deeply needed with a low number of features. 1

Download

Probabilistic Ontology Reasoning in Ambient Assistance: Predicting Human Actions

2018 IEEE 32nd International Conference on Advanced Information Networking and Applications (AINA), 2018

Providing reminders to elderly people in their home environment, while they perform their daily a... more Providing reminders to elderly people in their home environment, while they perform their daily activities, is considered as a user support activity, and thus a relevant topic in Active and Assisted Living (AAL) research and development. Determining such reminders implies decision-making, since the actions' flow (behavior) usually involves probabilistic branches. An automated system needs to decide which of the next actions is the best one for the user in a given situation. Problems of this nature involve uncertainty levels that have to be dealt with. Many approaches to this problem exploit statistical data only, thus ignoring important semantic data as, for instance, are provided by Ontologies. However, ontologies do not support reasoning over uncertainty natively. In this paper, we present a probabilistic semantic model that enables reasoning over uncertainty without losing semantic information. This model will be exemplified by an extension of the Human Behavior Monitoring an...

Decision Support Systems based on Answer Set Programing

Description logics is a group of logics for knowledge modeling, which are derived from semantic n... more Description logics is a group of logics for knowledge modeling, which are derived from semantic networks. They are to be understood essentially as accessible fragments of predicate logic of first order, to allow strong expressions t o be expressed through a complexity class with restrictions. Other description logics provide such strong expressions in polynomial complexity. For description logics, there ar e a special inputs and intuitive notation that facilitates the handling of them substantially. Modeling in expert systems is very important, especially systems are having a complex domain where the spatial and temporal data are needed to be modeled. The ontology model permits the use of a reasoner that can check definitions of the statements in the ontology, if they are consistent or not . It can also recognize which concepts are the best for which definitions. The reasoner can therefore help to maintain the hierarchy correctly. This is particularly helpful when dea ling with mult...

Download

A Hybrid Reasoning Approach for Activity Recognition Based on Answer Set Programming and Dempster–Shafer Theory

Studies in Systems, Decision and Control

This chapter discusses a promising approach for multisensor-based activity recognition in smart h... more This chapter discusses a promising approach for multisensor-based activity recognition in smart homes. The research originated in the domain of active and assisted living, particularly in the field of supporting people in mastering their daily life activities. The chapter proposes (a) a reasoning method based on answer set programming that uses different types of features for selecting the optimal sensor set, and (b) a fusion approach to combine the beliefs of the selected sensors using an advanced evidence combination rule of Dempster-Shafer theory. In order to check the overall performance, this approach was tested with the HBMS dataset on an embedded platform. The results demonstrated a highly promising accuracy compared to other approaches.

Download

Intelligent Transportation Related Complex Systems and Sensors

Sensors

Building around innovative services related to different modes of transport and traffic managemen... more

Download

Real Time Complex Event Detection Based on Answer Set Programing

A Hybrid Reasoning Approach for Activity Recognition Based on Answer Set Programming and Dempster–Shafer Theory

This chapter discusses a promising approach for multisensor-based activity recognition in smart h... more This chapter discusses a promising approach for multisensor-based activity recognition in smart homes. The research originated in the domain of active and assisted living, particularly in the field of supporting people in mastering their daily life activities. The chapter proposes (a) a reasoning method based on answer set programming that uses different types of features for selecting the optimal sensor set, and (b) a fusion approach to combine the beliefs of the selected sensors using an advanced evidence combination rule of Dempster–Shafer theory. In order to check the overall performance, this approach was tested with the HBMS dataset on an embedded platform. The results demonstrated a highly promising accuracy compared to other approaches.

Download

Complex Event Detection and Analysis in Video-Audio-Based Sensor Networks

Fadi Al Machot

Uploads

Papers by Fadi Al Machot

Log In