Technologies
Competitive Advantages:
Cloud-based system, Real-time identification and reporting, Minimal to zero human intervention is required,
Time and cost savings, Improved accuracy.
Identifying insect species integrates image processing, feature selection, unsupervised clustering, and a support vector machine (SVM) learning algorithm for classification. Results with a total of 101 mosquito specimens spread across nine different vector carrying species demonstrate high accuracy in species identification. When implemented as a smart-phone application, the latency and energy consumption were minimal. The currently manual process of species identification and recording can be sped up, while also minimizing the ensuing cognitive workload of personnel. Citizens at large can use the system in their own homes for self-awareness and share insect identification data with public health agencies.USF inventors have developed a method for automatic identification of mosquito genus, species, and anatomy from smart-phone images. The method involves anyone (including untrained personnel) to take pictures of mosquitos with smartphones, the species type is identified, and images and population results are automatically uploaded to a cloud system. Through the use of this digital image processing and a deep learning application, everyone across the globe could take a picture of dead and physically un-deformed mosquitos. Therefore, the species would be identified immediately and reported to the Mosquito Control Board remotely. This invention is suitable for application in vector control programs, health organizations, and pest control industries. It is a fast and cost-effective method which takes advantage of everyone’s access to a smartphone. The efficiency of the system will improve with usage and population.
Identifying insect species integrates image processing, feature selection, unsupervised clustering, and a support vector machine (SVM) learning algorithm for classification. Results with a total of 101 mosquito specimens spread across nine different vector carrying species demonstrate high accuracy in species identification. When implemented as a smart-phone application, the latency and energy consumption were minimal. The currently manual process of species identification and recording can be sped up, while also minimizing the ensuing cognitive workload of personnel. Citizens at large can use the system in their own homes for self-awareness and share insect identification data with public health agencies.USF inventors have developed a method for automatic identification of mosquito genus, species, and anatomy from smart-phone images. The method involves anyone (including untrained personnel) to take pictures of mosquitos with smartphones, the species type is identified, and images and population results are automatically uploaded to a cloud system. Through the use of this digital image processing and a deep learning application, everyone across the globe could take a picture of dead and physically un-deformed mosquitos. Therefore, the species would be identified immediately and reported to the Mosquito Control Board remotely. This invention is suitable for application in vector control programs, health organizations, and pest control industries. It is a fast and cost-effective method which takes advantage of everyone’s access to a smartphone. The efficiency of the system will improve with usage and population.
A system for authenticating an individual's location activity includes a mobile communications device connected to a network and in electronic communication with at least one other computer. The mobile communications device is configured to authenticate the individual's presence at a location using biometric data entered by the individual. The mobile communications device has applications stored thereon to access location information for the mobile communications device using a GPS application stored on the mobile communications device and to access time information for the mobile communications device from a clock application stored on the mobile communications device. The mobile communications devices creates a digital signature that authenticates an individual's location activity by storing an encrypted digital certificate comprising a hash calculation using the biometric data, a validation key generated by authenticating the biometric data, the location information, and the time information.USF inventors have developed a method that combines the location information obtained from a mobile device with a system of authentication that relies on individual biometrics, specifically voice (or even video) to verify an individual's exact location at a specific point in time. This invention has been instantiated as a mobile application combined with software that resides on the cloud servers. The system is designed to detect spoofing of GPS, voice captured from an electronic device, and other fraudulent activities and to deny authentication. Individual components of this functionality have been made available as APIs for integration into existing solutions and services. This invention can be applied in family and employee tracking systems, location-based authentication software and services, and law enforcement offices.
A method of identifying a living creature includes training a convolutional neural network model using pretrained convolutional neural networks to generate proposals about the regions where there might be an anatomical object within a digital image. Introducing a residual connection to get the input from the previous layer to the next layer helps in solving gradient vanishing problem. The next step is to design an object detector network that does three tasks: classifying the boxes with respective anatomies, tightening the boxes, and generating a mask (i.e., pixel-wise segmentation) of each anatomical component. In constructing the architecture of the object detector network, the network uses per-pixel sigmoid, and binary cross-entropy loss function (to identify the k anatomical components) and rigorously train them.Computer Science, Engineering,