5153 research outputs found
Sort by
A Novel Computer Vision-Based Framework For Supervised Classification Of Energy Outbreak Phenomena
No full textToday, there is a need to implement a proper design of an adequate surveillance system that detects and categorizes explosion phenomena in order to identify the explosion risk to reduce its impact through mitigation and preparedness. This dissertation introduces state-of-the-art classification of explosion phenomena through pattern recognition techniques on color images. Consequently, we present a novel taxonomy for explosion phenomena. In particular, we demonstrate different aspects of volcanic eruptions and nuclear explosions of the proposed taxonomy that include scientific formation, real examples, existing monitoring methodologies, and their limitations. In addition, we propose a novel framework designed to categorize explosion phenomena against non-explosion phenomena. Moreover, a new dataset, Volcanic and Nuclear Explosions (VNEX), was collected. The totality of VNEX is 10, 654 samples, and it includes the following patterns: pyroclastic density currents, lava fountains, lava and tephra fallout, nuclear explosions, wildfires, fireworks, and sky clouds. In order to achieve high reliability in the proposed explosion classification framework, we propose to employ various feature extraction approaches. Thus, we calculated the intensity levels to extract the texture features. Moreover, we utilize the YCbCr color model to calculate the amplitude features. We also employ the Radix-2 Fast Fourier Transform to compute the frequency features. Furthermore, we use the uniform local binary patterns technique to compute the histogram features. Additionally, these discriminative features were combined into a single input vector that provides valuable insight of the images, and then fed into the following classification techniques: Euclidian distance, correlation, k-nearest neighbors, one-against-one multiclass support vector machines with different kernels, and the multilayer perceptron model. Evaluation results show the design of the proposed framework is effective and robust. Furthermore, a trade-off between the computation time and the classification rate was achieved
Deterministic and Efficient Three-Party Quantum Key Distribution
No full textQuantum information processing is based on the laws of quantum physics and guarantees the unconditional security. In this thesis we propose an efficient and deterministic three-party quantum key distribution algorithm to establish a secret key between two users. Using the formal methodological approach, we study and model a quantum algorithm to distribute a secret key to a sender and a receiver when they only share entanglement with a trusted party but not with each other. It distributes a secret key by special pure quantum states using the remote state preparation and controlled gates. In addition, we employ the parity bit of the entangled pairs and ancillary states to help in preparing and measuring the secret states. Distributing a state to two users requires two maximally entangled pairs as the quantum channel and a two-particle von Neumann projective measurement. This protocol is exact and deterministic. It distributes a secret key of d qubits by 2d entangled pairs and on average d bits of classical communication. We show the security of this protocol against the entanglement attack and offer a method for privacy amplification. Moreover, we also study the problem of distributing Einstein-Podolsky-Rosen (EPR) in a metropolitan network. The EPR is the building block of entanglement-based and entanglement-assisted quantum communication protocols. Therefore, prior shared EPR pair and an authenticated classical channel allow two distant users to share a secret key. To build a network architecture where a centralized EPR source creates entangled states by the process of spontaneous parametric down-conversion (SPDC) then routes the states to users in different access networks. We propose and simulate a metropolitan optical network (MON) architecture for entanglement distribution in a typical telecommunication infrastructure. The architecture allows simultaneous transmission of classical and quantum signals in the network and offers a dynamic routing mechanism to serve the entire metropolitan optical network
A Highly Accurate Machine Learning Approach for Developing Wireless Sensor Network Middleware
No full textDespite the popularity of wireless sensor networks (WSNs) in a wide range of applications, security problems associated with them have not been completely resolved. Middleware is generally introduced as an intermediate layer between WSNs and the end user to resolve some limitations, but most of the existing middleware is unable to protect data from malicious and unknown attacks during transmission. We introduced an intelligent middleware based on an unsupervised learning technique called Generative Adversarial Networks (GANs) algorithm. GANs contain two networks: a generator (G) network and a discriminator (D) network. The G creates fake data similar to the real samples and combines it with real data from the sensors to confuse the attacker. Results illustrate that the proposed algorithm not only improves the accuracy of the data but also enhances its security by protecting data from adversaries. Data transmission from the WSN to the end user then becomes much more secure and accurate compared to conventional techniques
Saving Connecticut One Mattress at a Time: a Real-Life Case Study at to Improve Mattress Recycling Process at Park City Green
No full textUB School of Engineering has partnered with the PCG to increase their operational efficiency in addition to finding alternative markets for their raw materials. Possible expansion plans are also discussed and included in addition to other improvement opportunities. This study introduces the motivation behind the study while reporting on the findings of this collaborative research
A Look at Education Through the Eyes of the World’s Children
No full textThe research being presented in this poster examines the current state of primary education globally. It will examine what the largest contributing factors are to children of primary age not attending primary education with a goal to propose some changes to education moving forward to insure 100% of children globally attend primary education
A Multiple Retinal Normal and Abnormal Anatomical Structures Segmentation Using Hybrid Morphological and Fuzzy Local Adaptive Thresholding
No full textEye exam can be as efficacious as physical one in determining health concerns. Retina screening can be the very first clue to detecting a variety of hidden health issues including pre-diabetes and diabetes. Through the process of clinical diagnosis and prognosis; ophthalmologists rely heavily on the binary segmented version of retina fundus image; where the accuracy of segmented vessels, optic disc and abnormal lesions extremely affects the diagnosis accuracy which in turn affect the subsequent clinical treatment steps. This paper proposes an automated retinal fundus image segmentation system composed of three segmentation subsystems follow same core segmentation algorithm. Despite of broad difference in features and characteristics; retinal vessels, optic disc and exudate lesions are extracted by each subsystem without the need for texture analysis or synthesis. For sake of compact diagnosis and complete clinical insight, our proposed system can detect these anatomical structures in one session with high accuracy even in pathological retina images. The proposed system uses a robust hybrid segmentation algorithm combines adaptive fuzzy thresholding and mathematical morphology. The proposed system is validated using four benchmark datasets: DRIVE and STARE (vessels), DRISHTI-GS (optic disc), and DIARETDB1 (exudates lesions). Competitive segmentation performance is achieved, outperforming up-to-date systems and demonstrating the capacity to deal with other heterogenous anatomical structures
Servo Motor Control Using Variable Frequency Drive
No full textVariable Frequency Drive (VFD) refers to an adjustable-speed drive where alternating current electric motor can be controlled by changing the values of frequency and voltage. This process allows the motor to change its torque and speed, depending on the need or demand from the user. VFD is used in many different applications, ranging from small to big, while preserving all other relevant advantages. Some of these advantages that come with using VFD are better process control and regulation, extended equipment life, and reduced maintenance. The components of VFD are converter, DC bus, and inverter. We successfully integrated VFD with Programmable Logic Controller (PLC) using sequencer Instruction to have a complete control over the AC servomotor, and operate motor with change in frequency of VFD. In this poster, we will examine what VFDs are and their applications. The outcome has market demand, especially that VFD applications contribute significantly to different industries
Enhanced Epilepsy Seizure Detection and Smart Phone APP for Monitoring Seizures Based on EEG Classification
No full textAutomated epilepsy seizure detection is the solution to the limitation and time consuming of manual epilepsy monitoring and detection using EEG signals. We developed a technique for epilepsy seizure detection using EEG signals. The signal will be pre-processed and filtered using multiple filters. Then, the filtered signal will be decomposed into sub-bands. Furthermore, feature extraction is applied; we developed a combined feature consists of combining three features into one. Finally, we used well-known classifiers such as Support Vector Machine (SVM), Artificial Neural Network (ANN), and K-Nears Neighbor (KNN) to differentiate between epileptic and no epileptic signals, and we achieved an accuracy of 98%. Furthermore, we developed an Android-based smartphone application for monitoring epilepsy detection based on the classification results of the EEG signal. A notification will be sent to the patient, doctors, and family members when an epilepsy seizure occurs. Once the EEG signal is classified as epileptic, the App will display a visual notification indicating that Epileptic Seizure has been detected. Moreover, it will trigger an alarm and send a message notification to all associated phone numbers. Although we are using an EEG signal from a dataset, we have generated both normal and epileptic EEG signals using a waveform generator, and we have displayed those signals on the spectrum analyzer for future real time detection using our Android App
Fabrication of Concussion Resistant Nanocomposites
No full textStudying concussions is of paramount importance. Concussions occurring in sports and sudden other accidental cases are causing major injuries to people often times it leads to CTE and eventual death. Chronic Traumatic Encephalopathy (CTE) is one type of degenerative brain disease that can be found in athletes, military veterans, and other people who have repetitive brain trauma. CTE is usually caused by repetitive hits to the head sustained over a period of years, most people diagnosed with CTE suffered hundreds or thousands of head impacts over the course of many years, such as playing contact sports or serving in the military. PDMS-based nanomaterials are gaining widespread attention in this regard. We report the use PDMS polymer and graphene oxide/graphene as nanoparticle reinforcement to produce the vibration-absorbing PDMS-graphene nanocomposite. The stiffness of PDMS and graphene-PDMS nanocomposites were measured using dynamic mechanical analyzer. We prepared a well-controlled pore containing PDMS-graphene nanocomposites that exhibited significant improvement in impact absorption properties as a function of porosity. Visual Molecular Dynamics (VMD) was used to compute the physical interactions between graphene and PDMS