• Publications
  • Influence
Evaluating Signature Matching in a Multi-Sensor Vehicle Classification System ( extended ) ∗
Many academic sensornet systems consider the problem of tracking targets as they move through a fixed field of sensors. Such applications must relate sensor detections to specific targets, yet priorExpand
Computer-Aided Diagnosis of Breast DCE-MRI Images Using Bilateral Asymmetry of Contrast Enhancement Between Two Breasts
Bilateral asymmetry of kinetic features between the left and right breasts is a potentially useful image biomarker to enhance the detection of angiogenesis associated with malignancy and the feasibility of applying a simple CAD approach to classify between malignant and benign DCE-MRI examinations is demonstrated. Expand
Steam-powered sensing
This paper describes the first field-tested deployment of an industrial sensornet that employs non-solar energy harvesting, and eliminates the high cost of bringing power to the field by generating electricity from heat, exploiting the high temperature of the very pipelines the authors monitor. Expand
3D segmentation of masses in DCE-MRI images using FCM and adaptive MRF
A novel 3D segmentation method based on FCM and MRF that achieves a better segmentation performance in accuracy and has a reasonable classification performance is proposed. Expand
Accurate Pipeline Blockage Detection with Low-Cost Multi-modal Sensing
This paper shows how a combination of different types of sensors can provide reliable detection of industrial events while avoid false positives, and applies to the classes of problems where false positives from one sensing modality can be resolved by multi-modal sensing. Expand
Quantum discord of a three-qubit W-class state in noisy environments
under the influence of various Markovian noises by analytically solving the master equation in the Lindblad form. Through numerical analysis, we find that EOF decreases asymptotically to zero withExpand
Reducing False Alarms with Multi-modal Sensing for Pipeline Blockage (Extended) ∗
Industrial sensing applications place a premium on costeffectiveness and accuracy. Traditional approaches often use expensive, invasive sensors, because inexpensive sensors suffer from false positiveExpand
Association between bilateral asymmetry of kinetic features computed from the DCE-MRI images and breast cancer
The study suggested that the bilateral asymmetry of kinetic features or contrast enhancement of breast background tissue could provide valuable supplementary information to distinguish between the malignant and benign cases, which can be fused into existing computer-aided detection schemes to improve classification performance. Expand
SRVC: Sensornets for Remote Vehicle Classification
Automated vehicle classification systems based on networks of small, battery-powered and wireless, intelligent sensors should be easily deployed with brief setup time (tens of minutes), with accurateExpand