29 September 2020 in IEEE Access
The COVID-19 pandemic has triggered an urgent call to contribute to the fight against an immense threat to the human population. Computer Vision, as a subfield of artificial intelligence, has enjoyed recent success in solving various complex problems in health care and has the potential to contribute to the fight of controlling COVID-19. In response to this call, computer vision researchers are putting their knowledge base at test to devise effective ways to counter COVID-19 challenge and serve the global community. New contributions are being shared with every passing day. It motivated us to review the recent work, collect information about available research resources, and an indication of future research directions. We want to make it possible for computer vision researchers to find existing and future research directions. This survey paper presents a preliminary review of the literature on research community efforts against COVID-19 pandemic.
11 January 2018 in IEEE Transactions on Power Delivery
High-impedance faults (HIFs) are linked to enduring unaddressed knowledge gaps due to their diverse and complex behavior, despite being extensively researched disturbances. Vegetation HIFs, for instance, are a particular type of fault that can lead to great fire hazards and life risks. They have unique fault signatures and should receive special attention if fire risk mitigation is desired. This paper focuses on the detection of these distinct, very small current faults. As the main correlational features, the proposed methodology uses the vegetation fault signatures' high-frequency content. Different from many previous works that rely on HIF models, the approach validation is performed using a real dataset comprising a large number of experiments, sampled in a functioning network in the presence of noise. The classification is performed by boosted decision trees, which showed high dependability and security in the classification of small phase-to-earth and phase-to-phase HIFs.
31 October 2019 in IEEE Transactions on Instrumentation and Measurement
High-Impedance Faults (HIFs) behavior in power distribution systems depends on multiple factors, making it a challenging disturbance to model. Factors such as network characteristics and impedance surface can change the phenomena so intensely that insights about their behavior may not translate well between faults with different parameters. Signal processing techniques can help reveal patterns from specific types of fault given the availability of sampled data from real faults. The methodology described in this paper uses the Shift-Invariant Sparse Coding (SISC) technique on a data set of staged vegetation HIFs to address this hypothesis. The technique facilitates the uncoupling of shifted and convoluted patterns present in the recorded fault signals, while a methodology to correlate them with fault occurrences is proposed. The investigation of under-discussed high-frequency fault signals from a specific type of fault (small current vegetation HIFs) distinguishes this paper from related works. The methodology to attest the found patterns as fault signatures and their analysis, while using a particular high-frequency sampling method are key novel aspects presented. Nonetheless, the evidence of consistent behavior in real vegetation HIFs at higher frequencies that could assist their detection is the main contribution of this paper. These results can enhance phenomena awareness and support future methodologies dealing with such disturbances.
1 September 2019 in Electric Power Systems Research
5 April 2023 in IEEE Access
Quantitative assessment of the abdominal region from CT scans requires the accurate delineation of abdominal organs. Therefore, automatic abdominal image segmentation has been the subject of intensive research for the past two decades. Recently, deep learning-based methods have resulted in state-of-the-art performance for the 3D abdominal CT segmentation. However, the complex characterization of abdominal organs with weak boundaries prevents the deep learning methods from accurate segmentation. Specifically, the voxels on the boundary of organs are more vulnerable to misprediction due to the highly-varying intensities. This paper proposes a method for improved abdominal image segmentation by leveraging organ-boundary prediction as a complementary task. We train 3D encoder-decoder networks to simultaneously segment the abdominal organs and their boundaries via multi-task learning. We explore two network topologies based on the extent of weights shared between the two tasks within a unified multi-task framework. In the first topology, the whole-organ prediction task and the boundary detection task share all the layers in the network except for the last task-specific layers. The second topology employs a single shared encoder but two separate task-specific decoders. The effectiveness of utilizing the organs’ boundary information for abdominal multi-organ segmentation is evaluated on two publically available abdominal CT datasets: Pancreas-CT and the BTCV dataset. The improvements shown in segmentation results reveal the advantage of the multi-task training that forces the network to pay attention to ambiguous boundaries of organs. A maximum relative improvement of 3.5% and 3.6% is observed in Mean Dice Score for Pancreas-CT and BTCV datasets, respectively.