• Publications
  • Influence
Rainfall forecasting models using focused time-delay neural networks
Results indicate that yearly rainfall dataset gives the most accurate forecasts (94.25%). Expand
Efficient Non-iterative Domain Adaptation of Pedestrian Detectors to Video Scenes
This paper proposes a novel algorithm to automatically adapt and tune a generic pedestrian detector to specific scenes which may possess different data distributions than the original dataset from which the detector was trained. Expand
Human activity recognition for video surveillance using sequences of postures
Results show that supervised learning classifiers tend to perform better than unsupervised classifiers for the case of human posture recognition, and for each individual classifier, the recognition rate has been found to be proportional to the number of training postures. Expand
Automated daily human activity recognition for video surveillance using neural network
An intelligent human activity system recognition is developed based on the human activities features database, which was extracted from the frame sequences and shows a promising performance in the activity recognition rate. Expand
Efficient determination of the number of weak learners in AdaBoost
  • K. K. Htike
  • Computer Science
  • J. Exp. Theor. Artif. Intell.
  • 3 September 2017
This paper proposes an efficient method that does not require cross-validation or a separate validation set to determine the number of weak learners for use in AdaBoost and is evaluated on eight different publicly available data-sets to demonstrate its efficacy. Expand
Comparison of supervised and unsupervised learning classifiers for human posture recognition
This paper shows that supervised learning classifiers are superior to unsupervised ones for the task of human posture recognition and that the unsuper supervised classifiers do not learn very well for cases where a lot of postures have to be learnt as compared to the supervised learningclassifier which gives high accuracy in either case. Expand
A non-contact capacitance type level transducer for liquid characterization
  • S. Khan, Khalifa, +4 authors S. Khan
  • Materials Science
  • International Conference on Computer and…
  • 13 May 2008
The liquid properties such as buoyancy, pressure at a depth, relative electrical permittivity, electrical conductivity, thermal conductivity, absorption of radiation, liquid surface reflection ofExpand
Adapting pedestrian detectors to new domains: A comprehensive review
This paper surveys the most relevant and important state-of-the-art results for domain adaptation for image and video data, with a particular focus on pedestrian detection, and makes observations and draw conclusions from the representative papers. Expand
Forests of unstable hierarchical clusters for pattern classification
A novel ensemble classifier that consists of a diverse group of hierarchical clusterings on data that is fast to train, fully automatic and outperforms existing decision tree ensemble techniques and other state-of-the-art classifiers. Expand
Unsupervised Detector Adaptation by Joint Dataset Feature Learning
This paper proposes a novel algorithm to automatically adapt a pedestrian detector trained on a generic image dataset to a video in an unsupervised way using joint dataset deep feature learning. Expand