Browsing by Author "Kim, Dongsoo Stephen"

Now showing 1 - 7 of 7
  • Thumbnail Image
    Item
    Dynamic Control of Adsorption Sensitivity for Photo-EMF-Based Ammonia Gas Sensors Using a Wireless Network
    (MDPI, 2011-11-22) Vashpanov, Yuriy; Choo, Hyunseung; Kim, Dongsoo Stephen; Electrical and Computer Engineering, School of Engineering and Technology
    This paper proposes an adsorption sensitivity control method that uses a wireless network and illumination light intensity in a photo-electromagnetic field (EMF)-based gas sensor for measurements in real time of a wide range of ammonia concentrations. The minimum measurement error for a range of ammonia concentration from 3 to 800 ppm occurs when the gas concentration magnitude corresponds with the optimal intensity of the illumination light. A simulation with LabView-engineered modules for automatic control of a new intelligent computer system was conducted to improve measurement precision over a wide range of gas concentrations. This gas sensor computer system with wireless network technology could be useful in the chemical industry for automatic detection and measurement of hazardous ammonia gas levels in real time.
  • Thumbnail Image
    Item
    Exploration of Deep Learning Applications on an Autonomous Embedded Platform (Bluebox 2.0)
    (2019-12) Katare, Dewant; El-Sharkawy, Mohamed; Rizkalla, Maher; Kim, Dongsoo Stephen
    An Autonomous vehicle depends on the combination of latest technology or the ADAS safety features such as Adaptive cruise control (ACC), Autonomous Emergency Braking (AEB), Automatic Parking, Blind Spot Monitor, Forward Collision Warning or Avoidance (FCW or FCA), Lane Departure Warning. The current trend follows incorporation of these technologies using the Artificial neural network or Deep neural network, as an imitation of the traditionally used algorithms. Recent research in the field of deep learning and development of competent processors for autonomous or self-driving car have shown amplitude of prospect, but there are many complexities for hardware deployment because of limited resources such as memory, computational power, and energy. Deployment of several mentioned ADAS safety feature using multiple sensors and individual processors, increases the integration complexity and also results in the distribution of the system, which is very pivotal for autonomous vehicles. This thesis attempts to tackle two important adas safety feature: Forward collision Warning, and Object Detection using the machine learning and Deep Neural Networks and there deployment in the autonomous embedded platform. 1. A machine learning based approach for the forward collision warning system in an autonomous vehicle. 2. 3-D object detection using Lidar and Camera which is primarily based on Lidar Point Clouds. The proposed forward collision warning model is based on the forward facing automotive radar providing the sensed input values such as acceleration, velocity and separation distance to a classifier algorithm which on the basis of supervised learning model, alerts the driver of possible collision. Decision Tress, Linear Regression, Support Vector Machine, Stochastic Gradient Descent, and a Fully Connected Neural Network is used for the prediction purpose. The second proposed methods uses object detection architecture, which combines the 2D object detectors and a contemporary 3D deep learning techniques. For this approach, the 2D object detectors is used first, which proposes a 2D bounding box on the images or video frames. Additionally a 3D object detection technique is used where the point clouds are instance segmented and based on raw point clouds density a 3D bounding box is predicted across the previously segmented objects.
  • Thumbnail Image
    Item
    An integrated sensor system for early fall detection
    (2013-05) Bandi, Ajay Kumar; Rizkalla, Maher E.; Salama, Paul; Kim, Dongsoo Stephen
    Physical activity monitoring using wearable sensors give valuable information about patient's neuro activities. Fall among ages of 60 and older in US is a leading cause for injury-related health issues and present serious concern in the public health care sector. If the emergency treatments are not on time, these injuries may result in disability, paralysis, or even death. In this work, we present an approach that early detect fall occurrences. Low power capacitive accelerometers incorporated with microcontroller processing units were utilized to early detect accurate information about fall events. Decision tree algorithms were implemented to set thresholds for data acquired from accelerometers. Data is then verified against their thresholds and the data acquisition decision unit makes the decision to save patients from fall occurrences. Daily activities are logged on an onboard memory chip with Bluetooth option to transfer the data wirelessly to mobile devices. In this work, a system prototype based on neurosignal activities was built and tested against seven different daily human activities for the sake of differentiating between fall and non-fall detection. The developed system features low power, high speed, and high reliability. Eventually, this study will lead to wearable fall detection system that serves important need within the health care sector. In this work Inter-Integrated Circuit (I2C) protocol is used to communicate between the accelerometers and the embedded control system. The data transfer from the Microcontroller unit to the mobile device or laptop is done using Bluetooth technology.
  • Thumbnail Image
    Item
    Link failure detection in OSPF network using OpenFlow protocol
    (2014-05-21) Pamulapati, Santhan; Kim, Dongsoo Stephen; King, Brian; Rizkalla, Maher E.
    The study of this thesis is focused on reducing the link failure detection time in OSPF network. When a link failure occurs, OSPF protocol detects it using RouterDeadInterval time. This timer is fired only after a predefined time interval, thus increasing the time of convergence after the link failure. There are previous studies to reduce the RouterDeadInterval time, but they introduce other effects which are discussed later in the thesis. So, a novel approach is proposed in this thesis to reduce the link failure detection time with the help of emerging network architecture Software Defined Networking (SDN) and OpenFlow Protocol.
  • Thumbnail Image
    Item
    OpenFlow based load balancing and proposed theory for integration in VoIP network
    (2014-05-21) Pandita, Shreya; Kim, Dongsoo Stephen; King, Brian; Rizkalla, Maher E.
    In today's internet world with such a high traffic, it becomes inevitable to have multiple servers representing a single logical server to share enormous load. A very common network configuration consists of multiple servers behind a load balancer. The load balancer determines which server would service a clients request or incoming load from the client. Such a hardware is expensive, runs a fixed policy or algorithm and is a single point of failure. In this paper, we will implement and analyze an alternative load balancing architecture using OpenFlow. This architecture acquires flexibility in policy, costs less and has the potential to be more robust. This paper also discusses potential usage of OpenFlow based load balancing for media gateway selection in SIP-PSTN networks to improve VoIP performance.
  • Thumbnail Image
    Item
    Performance evaluation of routing protocols using NS-2 and realistic traces on driving simulator
    (2014-05-21) Chen, Mingye; Li, Lingxi; Chen, Yaobin; Kim, Dongsoo Stephen; King, Brian
    With the rapid growth in wireless mobile communication technology, Vehicular Ad-hoc Network (VANET) has emerged as a promising method to effectively solve transportation-related issues. So far, most of researches on VANETs have been conducted with simulations as the real-world experiment is expensive. A core problem affecting the fidelity of simulation is the mobility model employed. In this thesis, a sophisticated traffic simulator capable of generating realistic vehicle traces is introduced. Combined with network simulator NS-2, we used this tool to evaluate the general performance of several routing protocols and studied the impact of intersections on simulation results. We show that static nodes near the intersection tend to become more active in packet delivery with higher transferred throughput.
  • Thumbnail Image
    Item
    Predicting transit times for outbound logistics
    (2020-08) Cochenour, Brooke R.; Ben Miled, Zina; King, Brian; Kim, Dongsoo Stephen
    On-time delivery of supplies to industry is essential because delays can disrupt production schedules. The aim of the proposed application is to predict transit times for outbound logistics thereby allowing suppliers to plan for timely mitigation of risks during shipment planning. The predictive model consists of a classifier that is trained for each specific source-destination pair using historical shipment, weather, and social media data. The model estimates the transit times for future shipments using Support Vector Machine (SVM). These estimates were validated using four case study routes of varying distances in the United States. A predictive model is trained for each route. The results show that the contribution of each input feature to the predictive ability of the model varies for each route. The mean average error (MAE) values of the model vary for each route due to the availability of testing and training historical shipment data as well as the availability of weather and social media data. In addition, it was found that the inclusion of the historical traffic data provided by INRIXTM improves the accuracy of the model. Sample INRIXTM data was available for one of the routes. One of the main limitations of the proposed approach is the availability of historical shipment data and the quality of social media data. However, if the data is available, the proposed methodology can be applied to any supplier with high volume shipments in order to develop a predictive model for outbound transit time delays over any land route.