Ali Daher

Mr. Ali Daher

University of Genoa
+2
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 September 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Ali DaherAli Daher
Ali Daher
ARAli Rizik
Ali Rizik
MMMARCO MUSELLI
MARCO MUSELLI
Hussein ChibleHussein Chible
Hussein Chible
Daniele D. CavigliaDaniele D. Caviglia
Daniele D. Caviglia
Edge Computing enables to perform measurement and cognitive decisions outside a central server by performing data storage, manipulation, and processing on the Internet of Things (IoT) node. Also, Artificial Intelligence (AI) and Machine Learning applications have become a rudimentary procedure in virtually every industrial or preliminary system. Consequently, the Raspberry Pi is adopted, which is a low-cost computing platform that is profitably applied in the field of IoT. As for the software part, among the plethora of Machine Learning (ML) paradigms reported in the literature, we identified Rulex, as a good ML platform, suitable to be implemented on the Raspberry Pi. In this paper, we present the porting of the Rulex ML platform on the board to perform ML forecasts in an IoT setup. Specifically, we explain the porting Rulex’s libraries on Windows 32 Bits, Ubuntu 64 Bits, and Raspbian 32 Bits. Therefore, with the aim of carrying out an in-depth verification of the application possibilities, we propose to perform forecasts on five unrelated datasets from five different applications, having varying sizes in terms of the number of records, skewness, and dimensionality. These include a small Urban Classification dataset, three larger datasets concerning Human Activity detection, a Biomedical dataset related to mental state, and a Vehicle Activity Recognition dataset. The overall accuracies for the forecasts performed are: 84.13%, 99.29% (for SVM), 95.47% (for SVM), and 95.27% (For KNN) respectively. Finally, an image-based gender classification dataset is employed to perform image classification on the Edge. Moreover, a novel image pre-processing Algorithm was developed that converts images into Time-series by relying on statistical contour-based detection techniques. Even though the dataset contains inconsistent and random images, in terms of subjects and settings, Rulex achieves an overall accuracy of 96.47% while competing with the literature which is dominated by forward-facing and mugshot images. Additionally, power consumption for the Raspberry Pi in a Client/Server setup was compared with an HP laptop, where the board takes more time, but consumes less energy for the same ML task.

20 December 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Ali DaherAli Daher
Ali Daher
ARAli Rizik
Ali Rizik
Andrea RandazzoAndrea Randazzo
Andrea Randazzo
ETEMANUELE TAVANTI
EMANUELE TAVANTI
Hussein ChibleHussein Chible
Hussein Chible
Daniele D. CavigliaDaniele D. Caviglia
Daniele D. Caviglia
Nowadays, cities can be perceived as increasingly dangerous places. Usually, CCTV is one of the main technologies used in a modern security system. However, poor light situations or bad weather conditions (rain, fog, etc.) limit the detection capabilities of image-based systems. Microwave radar detection systems can be an answer to this limitation and take advantage of the results obtained by low-cost technologies for the automotive market. Transportation by car may be dangerous, and every year car accidents lead to the fatalities of many individuals. Humans require automated assistance when driving through detecting and correctly classifying approaching vehicles and, more importantly, pedestrians. In this paper, we present the application of machine learning to data collected by a 24 GHz short-range radar for urban classification. The training and testing take place on a Raspberry Pi as an edge computing node operating in a client/server arrangement. The software of choice is Rulex, a high-performance machine learning package controlled through a remote interface. Forecasts with a varying number of classes were performed with one, two, or three classes for vehicles and one for humans. Furthermore, we applied a single forecast for all four classes, as well as cascading forecasts in a tree-like structure while varying algorithms, cascading the block order, setting class weights, and varying the data splitting ratio for each forecast to improve prediction accuracy. In the experiments carried out for the validation of the presented approach, an accuracy of up to 100% for human classification and 96.67% for vehicles, in general, was obtained. Vehicle sub-classes were predicted with 90.63% accuracy for motorcycles and 77.34% accuracy for both cars and trucks.

26 January 2021
Verified
Book Chapter
Closed access
PDF file
Ali DaherAli Daher
Ali Daher
ARAli Rizik
Ali Rizik
MMMarco Muselli
Marco Muselli
Hussein ChibleHussein Chible
Hussein Chible
DCDaniele D. Caviglia
Daniele D. Caviglia

22 June 2022 in Computing
Verified
Journal Article
Open access
PDF file
Ali DaherAli Daher
Ali Daher
EFEnrico Ferrari
Enrico Ferrari
MMMARCO MUSELLI
MARCO MUSELLI
Hussein ChibleHussein Chible
Hussein Chible
Daniele D. CavigliaDaniele D. Caviglia
Daniele D. Caviglia
Machine learning techniques aim to mimic the human ability to automatically learn how to perform tasks through training examples. They have proven capable of tasks such as prediction, learning and adaptation based on experience and can be used in virtually any scientific application, ranging from biomedical, robotic, to business decision applications, and others. However, the lack of domain knowledge for a particular application can make feature extraction ineffective or even unattainable. Furthermore, even in the presence of pre-processed datasets, the iterative process of optimizing Machine Learning parameters, which do not translate from one domain to another, maybe difficult for inexperienced practitioners. To address these issues, we present in this paper a Vectorized Automated ML Pre-processIng and post-pRocEssing framework, approximately named (VAMPIRE), which implements feature extraction algorithms capable of converting large time-series recordings into datasets. Also, it introduces a new concept, the Activation Engine, which is attached to the output of a Multi Layer Perceptron and extracts the optimal threshold to apply binary classification. Moreover, a tree-based algorithm is used to achieve multi-class classification using the Activation Engine. Furthermore, the internet of things gives rise to new applications such as remote sensing and communications, so consequently applying Machine Learning to improve operation accuracy, latency, and reliability is beneficial in such systems. Therefore, all classifications in this paper were performed on the edge in order to reach high accuracy with limited resources. Moreover, forecasts were applied on three unrelated biomedical datasets, and on two other pre-processed urban and activity detection datasets. Features were extracted when required, and training and testing were performed on the Raspberry Pi remotely, where high accuracy and inference speed were achieved in every experiment. Additionally, the board remained competitive in terms of power consumption when compared with a laptop which was optimized using a Graphical Processing Unit.

26 October 2022 in OSF Preprints
Verified
Preprint
Open access
Ali DaherAli Daher
Ali Daher
As the complexity of analog integrated circuits increases, so too does the design effort and the experience required to reach a specified performance criterion. This is an accurate assessment not due to lack of skill or ingenuity but is derived from the complexity of MOSFET transistor models where classical design equations are inaccurate. Therefore, with the aim of speeding up the design process, engineers resort to Artificial Intelligence techniques to optimize the circuit at hand. Due to the complexity of spice models, a black-box approach is usually employed to approximate the system function. Bayesian optimizers are ideal for this approach, and so in this paper we present ABADDON, an Automated Bayesian Analog Design of Devices for SoC Amplifier Systems, which relies on transient-based features with square waveforms to optimize the stability, linearity, and to set the gain of any amplifier circuit. A basic two-stage op-amp in negative feedback was optimized along with a new ultra-fast-settling AGC-based VGA which utilizes a novel 5.2 THz unity-gain Buffer/Amplifier. Additionally, a novel operational amplifier architecture has been designed and optimized using ABADDON, where the circuit competes with or outperforms high-speed and general-purpose commercial amplifiers. Experiments prove that through ABADDON classical and novel circuits can be optimized wherein the results demonstrate superior performance when compared with the literature and market.

3 October 2018 in Analog Integrated Circuits and Signal Processing
Verified
Journal Article
Closed access
PDF file
Ali DaherAli Daher
Ali Daher
ZOZiad Ahmad Osman
Ziad Ahmad Osman
AHAli Massoud Haidar
Ali Massoud Haidar