What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
His main research concerns Artificial intelligence, Pattern recognition, Computer vision, Algorithm and Feature extraction.
His work investigates the relationship between Artificial intelligence and topics such as Machine learning that intersect with problems in Data mining.
His studies in Pattern recognition integrate themes in fields like Speech recognition, Overfitting and Sensitivity.
The concepts of his Algorithm study are interwoven with issues in Filter, Image processing, Median filter, Nonlinear system and Electronic engineering.
His study in Median filter is interdisciplinary in nature, drawing from both Image restoration and Signal processing.
His research integrates issues of Data modeling and Particle swarm optimization in his study of Artificial neural network.
His most cited work include:
- Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks (577 citations)
- Weighted median filters: a tutorial (557 citations)
- Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks (423 citations)
What are the main themes of his work throughout his whole career to date?
Artificial intelligence, Computer vision, Pattern recognition, Algorithm and Artificial neural network are his primary areas of study.
His Artificial intelligence study combines topics in areas such as Machine learning and Coding.
His study involves Multiview Video Coding, Motion compensation, Pixel, Data compression and Image processing, a branch of Computer vision.
In Multiview Video Coding, Moncef Gabbouj works on issues like Coding tree unit, which are connected to Context-adaptive binary arithmetic coding.
His Pattern recognition study combines topics from a wide range of disciplines, such as Contextual image classification, Image and Image retrieval.
His Algorithm research incorporates themes from Filter, Mathematical optimization, Discrete cosine transform and Median filter.
He most often published in these fields:
- Artificial intelligence (58.22%)
- Computer vision (25.33%)
- Pattern recognition (23.46%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (58.22%)
- Pattern recognition (23.46%)
- Deep learning (5.48%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Artificial intelligence, Pattern recognition, Deep learning, Convolutional neural network and Machine learning.
Normalization is closely connected to Time series in his research, which is encompassed under the umbrella topic of Artificial intelligence.
Moncef Gabbouj works mostly in the field of Pattern recognition, limiting it down to concerns involving Color constancy and, occasionally, ColorChecker.
In his research on the topic of Deep learning, Density estimation and Gaussian is strongly related with Data mining.
In his work, Facial recognition system is strongly intertwined with Training set, which is a subfield of Convolutional neural network.
As a member of one scientific family, Moncef Gabbouj mostly works in the field of Machine learning, focusing on Order book and, on occasion, Optimization problem.
Between 2018 and 2021, his most popular works were:
- 1D Convolutional Neural Networks and Applications: A Survey (74 citations)
- 1-D Convolutional Neural Networks for Signal Processing Applications (53 citations)
- Temporal Attention-Augmented Bilinear Network for Financial Time-Series Data Analysis (50 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
Moncef Gabbouj focuses on Artificial intelligence, Convolutional neural network, Artificial neural network, Machine learning and Pattern recognition.
His study in Deep learning, Feature extraction, Perceptron, Benchmark and Color constancy is carried out as part of his Artificial intelligence studies.
His Convolutional neural network research is multidisciplinary, incorporating elements of Fault detection and isolation, Anomaly detection, Voltage source and Identification.
He has researched Artificial neural network in several fields, including Jump and Training set.
His Machine learning research is multidisciplinary, relying on both Field and Linear subspace.
His study looks at the relationship between Pattern recognition and topics such as X ray image, which overlap with Early detection, Classifier and Segmentation.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
