Computer Engineering Commons^™

Detection Of Tooth Position By Yolov4 And Various Dental Problems Based On Cnn With Bitewing Radiograph, Kuo Chen Li, Yi-Cheng Mao, Mu-Feng Lin, Yi-Qian Li, Chiung-An Chen, Tsung-Yi Chen, Patricia Angela R. Abu

Department of Information Systems & Computer Science Faculty Publications

Periodontitis is a high prevalence dental disease caused by bacterial infection of the bone that surrounds the tooth. Early detection and precision treatment can prevent more severe symptoms such as tooth loss. Traditionally, periodontal disease is identified and labeled manually by dental professionals. The task requires expertise and extensive experience, and it is highly repetitive and time-consuming. The aim of this study is to explore the application of AI in the field of dental medicine. With the inherent learning capabilities, AI exhibits remarkable proficiency in processing extensive datasets and effectively managing repetitive tasks. This is particularly advantageous in professions demanding …

An Investigation Of Match For Lossless Video Compression, Brittany Sullivan-Reicks

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

A new lossless video compression technique, Match, is investigated. Match uses the similarity between the frames of a video or the slices of medical images to find a prediction for the current pixel. A portion of the previous frame is searched to find a matching context, which is the pixels surrounding the current pixel, within some distance centered on the current location. The best distance to use for each dataset is found experimentally. The matching context refers to the neighborhood of w, nw, n, and ne, where the pixel in the previous frame with the closest matching context becomes the …

Using Machine Learning To Assist Auditory Processing Evaluation, Hasitha Wimalarathna, Sangamanatha Veeranna, Minh Vu Duong, Chris Allan Prof, Sumit K. Agrawal, Prudence Allen, Jagath Samarabandu, Hanif M. Ladak

Electrical and Computer Engineering Publications

Introduction: Approximately 0.2–5% of school-age children complain of listening difficulties in the absence of hearing loss. These children are often referred to an audiologist for an auditory processing disorder (APD) assessment. Adequate experience and training is necessary to arrive at an accurate diagnosis due to the heterogeneity of the disorder.

Objectives: The main goal of the study was to determine if machine learning (ML) can be used to analyze data from the APD clinical test battery to accurately categorize children with suspected APD into clinical sub-groups, similar to expert labels.

Methods: The study retrospectively collected data from 134 children referred …

Detection Of Various Dental Conditions On Dental Panoramic Radiography Using Faster R-Cnn, Shih Lun Chen, Tsung Yi Chen, Yi Cheng Mao, Szu Yin Lin, Ya Yun Huang, Chiung An Chen, Yuan Jin Lin, Mian Heng Chuang, Patricia Angela R. Abu

Department of Information Systems & Computer Science Faculty Publications

The dental panoramic radiograph (DPR) is a pivotal diagnostic tool in dentistry. However, despite the growing prevalence of artificial intelligence (AI) across various medical domains, manual methods remain the prevailing means of interpreting DPR images. This study aims to introduce an advanced identification system for detecting seven dental conditions in DPR images by utilizing Faster R-CNN. The primary objectives are to enhance dentists' efficiency and evaluate the performance of various CNN models as foundational training networks. This study contributes significantly to the field in several notable ways. Firstly, including a Butterworth filter in the training process yielded an approximately 7% …

A Machine Learning Framework For Identifying Molecular Biomarkers From Transcriptomic Cancer Data, Md Abdullah Al Mamun

FIU Electronic Theses and Dissertations

Cancer is a complex molecular process due to abnormal changes in the genome, such as mutation and copy number variation, and epigenetic aberrations such as dysregulations of long non-coding RNA (lncRNA). These abnormal changes are reflected in transcriptome by turning oncogenes on and tumor suppressor genes off, which are considered cancer biomarkers.

However, transcriptomic data is high dimensional, and finding the best subset of genes (features) related to causing cancer is computationally challenging and expensive. Thus, developing a feature selection framework to discover molecular biomarkers for cancer is critical.

Traditional approaches for biomarker discovery calculate the fold change for each …

Supporting Coordination Of Children With Asd Using Neurological Music Therapy: A Pilot Randomized Control Trial Comparing An Elastic Touch-Display With Tambourines, Franceli L. Cibrian, Melisa Madrigal, Marina Avelais, Monica Tentori

Engineering Faculty Articles and Research

Aim

To evaluate the efficacy of Neurologic Music Therapy (NMT) using a traditional and a technological intervention (elastic touch-display) in improving the coordination of children with Autism Spectrum Disorder (ASD), as a primary outcome, and the timing and strength control of their movements as secondary outcomes.

Methods

Twenty-two children with ASD completed 8 NMT sessions, as a part of a 2-month intervention. Participants were randomly assigned to either use an elastic touch-display (experimental group) or tambourines (control group). We conducted pre- and post- assessment evaluations, including the Developmental Coordination Disorder Questionnaire (DCDQ) and motor assessments related to the control of …

Ml-Medic: A Preliminary Study Of An Interactive Visual Analysis Tool Facilitating Clinical Applications Of Machine Learning For Precision Medicine, Laura Stevens, David Kao, Jennifer Hall, Carsten Görg, Kaitlyn Abdo, Erik Linstead

Engineering Faculty Articles and Research

Accessible interactive tools that integrate machine learning methods with clinical research and reduce the programming experience required are needed to move science forward. Here, we present Machine Learning for Medical Exploration and Data-Inspired Care (ML-MEDIC), a point-and-click, interactive tool with a visual interface for facilitating machine learning and statistical analyses in clinical research. We deployed ML-MEDIC in the American Heart Association (AHA) Precision Medicine Platform to provide secure internet access and facilitate collaboration. ML-MEDIC’s efficacy for facilitating the adoption of machine learning was evaluated through two case studies in collaboration with clinical domain experts. A domain expert review was also …

Improving 3d Printed Prosthetics With Sensors And Motors, Rachel Zarin

Honors Projects

A 3D printed hand and arm prosthetic was created from the idea of adding bionic elements while keeping the cost low. It was designed based on existing models, desired functions, and materials available. A tilt sensor keeps the hand level, two motors move the wrist in two different directions, a limit switch signals the fingers to open and close, and another motor helps open and close the fingers. All sensors and motors were built on a circuit board, programmed using an Arduino, and powered by a battery. Other supporting materials include metal brackets, screws, guitar strings, elastic bands, small clamps, …

A Neuroimaging Web Interface For Data Acquisition, Processing And Visualization Of Multimodal Brain Images, Gabriel M. Lizarraga

FIU Electronic Theses and Dissertations

Structural and functional brain images are generated as essential modalities for medical experts to learn about the different functions of the brain. These images are typically visually inspected by experts. Many software packages are available to process medical images, but they are complex and difficult to use. The software packages are also hardware intensive. As a consequence, this dissertation proposes a novel Neuroimaging Web Services Interface (NWSI) as a series of processing pipelines for a common platform to store, process, visualize and share data. The NWSI system is made up of password-protected interconnected servers accessible through a web interface. The …

Compact Hardware Implementation Of A Sha-3 Core For Wireless Body Sensor Networks, Yi Yang, Debiao He, Neeraj Kumar, Sherali Zeadally

Information Science Faculty Publications

One of the most important Internet of Things applications is the wireless body sensor network (WBSN), which can provide universal health care, disease prevention, and control. Due to large deployments of small scale smart sensors in WBSNs, security, and privacy guarantees (e.g., security and safety-critical data, sensitive private information) are becoming a challenging issue because these sensor nodes communicate using an open channel, i.e., Internet. We implement data integrity (to resist against malicious tampering) using the secure hash algorithm 3 (SHA-3) when smart sensors in WBSNs communicate with each other using the Internet. Due to the limited resources (i.e., storage, …

Design And Performance Evaluation Of A Prototype Mrf-Based Haptic Interface For Medical Applications, Mehrdad Kermani Ph.D., P.Eng., Nima Najmaei, Ali Asadian, Rajni Patel

Electrical and Computer Engineering Publications

This paper describes the construction and stability and transparency evaluation of a prototype two degrees-of-freedom (DoF) haptic interface, which takes ad-vantage of magneto-rheological fluid (MRF)-based clutches for actuation. These small-scale clutches were designed in our lab, and their evaluation were reported previously [1],[2]. MRF-based actuators exhibit superior characteristics,which can significantly contribute to transparency and stability of haptic devices. Based on these actuators, a distributed antagonistic configuration is used to develop the2-DoF haptic interface. This device is incorporated in a master–slave teleoperation setup intended for medical per-cutaneous interventions and soft-tissue palpation. Preliminary studies on the stability and transparency of the haptic …

Vcare: A Personal Emergency Response System To Promote Safe And Independent Living Among Elders Staying By Themselves In Community Or Residential Settings, Priyankar Bhattacharjee

Computer and Electronics Engineering: Dissertations, Theses, and Student Research

‘Population aging’ is a growing concern for most of us living in the twenty first century, primarily because many of us in the next few years will have a senior person to care for - spending money towards their healthcare expenditures AND/OR having to balance a full-time job with the responsibility of care-giving, travelling from another city to be with this elderly citizen who might be our parent, grand-parent or even community elders. As informal care-givers, if somehow we were able to monitor the day-to-day activities of our elderly dependents, and be alerted when wrong happens to them that would …

Design And Development Of Two Component Hydrogel Ejector For Three-Dimensional Cell Growth, Thomas Dunkle, Jessica Deschamps, Connie Dam

Honors Scholar Theses

Hydrogels are useful in wound healing, drug delivery, and tissue engineering applications, but the available methods of injecting them quickly and noninvasively are limited. The medical industry does not yet have access to an all-purpose device that can quickly synthesize hydrogels of different shapes and sizes. Many synthesis procedures that have been developed result in the formation of amorphous hydrogels. While generally useful, amorphous hydrogels exhibit limited capability in tissue engineering applications, especially due to their viscous properties. This endeavor aims to modulate the appropriate gelation parameters, optimize the injection process, and create a prototype that allows for the extrusion …

A Knowledge-Based Clinical Toxicology Consultant For Diagnosing Multiple Exposures, Joel D. Schipper, Douglas D. Dankel Ii, A. Antonio Arroyo, Jay L. Schauben

Publications

Objective: This paper presents continued research toward the development of a knowledge-based system for the diagnosis of human toxic exposures. In particular, this research focuses on the challenging task of diagnosing exposures to multiple toxins. Although only 10% of toxic exposures in the United States involve multiple toxins, multiple exposures account for more than half of all toxin-related fatalities. Using simple medical mathematics, we seek to produce a practical decision support system capable of supplying useful information to aid in the diagnosis of complex cases involving multiple unknown substances.

Methods: The system is automatically trained using data mining …

Activity Intent Recognition Of The Torso Based On Surface Electromyography And Inertial Measurement Units, Zhe Zhang

Masters Theses 1911 - February 2014

This thesis presents an activity mode intent recognition approach for safe, robust and reliable control of powered backbone exoskeleton. The thesis presents the background and a concept for a powered backbone exoskeleton that would work in parallel with a user. The necessary prerequisites for the thesis are presented, including the collection and processing of surface electromyography signals and inertial sensor data to recognize the user’s activity. The development of activity mode intent recognizer was described based on decision tree classification in order to leverage its computational efficiency. The intent recognizer is a high-level supervisory controller that belongs to a three-level …

A Wireless And Digital Electrode Bus Topology For Biopotential Measurement, Mark Nolan, Edward Burke, Eugene Coyle

Conference Papers

The conventional biopotential measurement configuration utilises long lead wires which connect measuring electrodes to signal conditioning circuitry. The majority of bioelectric signals that are measured from the human body have a tiny signal amplitude (5µV-5mV range) and thus any interference that is induced on the lead wires can have a detrimental effect on the original signal. In this paper, we present an alternative configuration, in which digitisation occurs on the electrode, potentially providing enhanced signal measurement as well as significant benefits in terms of the simplification of the physical interconnections between electrodes. Multiple electrodes are combined to form a digital …

The Presence Of Regional Accents In Electrolarynx Speech And The Resultant Effect On Overall Intelligibility., Brian Madden, Eugene Coyle

Conference Papers

During voiced speech, the larynx provides quasi-periodic acoustic excitation of the vocal tract. In most electrolarynxes, mechanical vibrations are produced by a linear electromechanical actuator, the armature of which percusses against a metal or plastic plate at a frequency within the range of glottal excitation. In this paper, a phonological analysis of a section of results from an online perceptual intelligibility test was performed which compared speech produced using a novel hands-free electrolarynx and a commercially available electrolarynx. A portion of the test consisted of a closed-set format containing a selection of four sets of four random CVC audio samples …

Intelligibility Of Electrolarynx Speech Using A Novel Hands-Free Actuator, Brian Madden, Mark Nolan, Ted Burke, James Condron, Eugene Coyle

Conference Papers

During voiced speech, the larynx provides quasi-periodic acoustic excitation of the vocal tract. In most electrolarynxes, mechanical vibrations are produced by a linear electromechanical actuator, the armature of which percusses against a metal or plastic plate at a frequency within the range of glottal excitation. In this paper, the intelligibility of speech produced using a novel hands-free actuator is compared to speech produced using a conventional electrolarynx. Two able-bodied speakers (one male, one female) performed a closed response test containing 28 monosyllabic words, once using a conventional electrolarynx and a second time using the novel design. The resulting audio recordings …

Augmented Control Of A Hands-Free Electrolarynx, Brian Madden, James Condron, Eugene Coyle

Conference Papers

During voiced speech, the larynx acts as the sound source, providing a quasi-periodic excitation of the vocal tract. Following a total laryngectomy, some people speak using an electrolarynx which employs an electromechanical actuator to perform the excitatory function of the absent larynx. Drawbacks of conventional electrolarynx designs include the monotonic sound emitted, the need for a free-hand to operate the device, and the difficulty experienced by many laryngectomees in adapting to its use. One improvement to the electrolarynx, which clinicians and users frequently suggest, is the provision of a convenient hands-free control facility. This would allow more natural use of …

On Improving Electrooculogram-Based Computer Mouse Systems: The Accelerometer Trigger, Johnalan Keegan, Edward Burke, James Condron, Eugene Coyle

Conference Papers

Eye tracking is a well-established method of computer control for profoundly paralysed people (Anson et al., 2002). Cameras are commonly used to track eye movements (Morimoto et al., 2005) but one alternative is the bioelectrical signal known as the electrooculogram (EOG). There are some EOG mouse control systems that facilitate the use of GUI applications, but certain actions, which are straightforward using a conventional mouse, remain impossible. Unless the eyes are tracking a target, they move in saccades (jumps), making it impossible to voluntarily trace out smooth trajectories with one's gaze, as would be required to draw a smooth curve. …

Towards Supervised Autonomous Task Completion Using An In Vivo Surgical Robot, Jason J. Dumpert

Department of Mechanical and Materials Engineering: Dissertations, Theses, and Student Research

Laparoscopy is a minimally invasive alternative to traditional abdominal surgery. Unlike traditional surgery, a laparoscopic procedure can be completed using small incisions. The use of these small incision results in reduced pain to the patient, shorter recovery times, and less trauma to skin, muscle and other tissues. However, these benefits to the patient are offset by the increased difficulty to the surgeon performing the procedure. These difficulties include reduced dexterity, reduced perception, and longer procedure times. The use of small in vivo robotic devices in minimally invasive surgery is one possible solution to these problems. The movement of these devices …

An Electrooculogram-Based Binary Saccade Sequence Classification (Bssc) Technique For Augmentative Communication And Control, Johnalan Keegan, Ted Burke, James Condron

Conference Papers

In the field of assistive technology, the electroocu-logram (EOG) can be used as a channel of communication and the basis of a man-machine interface. For many people with severe motor disabilities, simple actions such as changing the TV channel require assistance. This paper describes a method of detecting saccadic eye movements and the use of a saccade sequence classification algorithm to facilitate communication and control. Saccades are fast eye movements that occurs when a person's gaze jumps from one fixation point to another. The classification is based on pre-defined sequences of saccades, guided by a static visual template (e.g. a …

Least Squares Support Vector Machine Based Classification Of Abnormalities In Brain Mr Images, S. Thamarai Selvi, D. Selvathi, R. Ramkumar, Henry Selvaraj

Electrical & Computer Engineering Faculty Research

The manual interpretation of MRI slices based on visual examination by radiologist/physician may lead to missing diagnosis when a large number of MRIs are analyzed. To avoid the human error, an automated intelligent classification system is proposed. This research paper proposes an intelligent classification technique to the problem of classifying four types of brain abnormalities viz. Metastases, Meningiomas, Gliomas, and Astrocytomas. The abnormalities are classified based on Two/Three/ Four class classification using statistical and textural features. In this work, classification techniques based on Least Squares Support Vector Machine (LS-SVM) using textural features computed from the MR images of patient are …

An Electro-Oculogram Based System For Communication And Control Using Target Position Variation, Ronan Fitzmaurice, Ted Burke, Annraoi De Paor

Conference Papers

In this paper we describe a novel mode of human computer interaction based on gaze tracking using the electro-oculogram (EOG). Despite the relative simplicity of recording this signal, it is often discounted as a reliable method of gaze tracking because of problems arising from changing sensitivity and DC drift. We describe an original technique, Target Position Variation (TPV), which addresses this issue by presenting moving icons which, when followed with the eye, create a corresponding pattern in the EOG signal which can be used to infer the correct gaze position and to compensate for variations in sensitivity.

An Investigation Into Non-Verbal Sound-Based Modes Of Human-To-Computer Communication With Rehabilitation Applications, Ted Burke

Conference Papers

During the course of our work in the National Rehabilitation Hospital in Ireland we have encountered patients who, while unable to speak, are capable of making reproducible utterances. We present techniques used to harness such utterances, in addition to whistling, as a means of communication and control. A simple technique for identifying the phonemes /o/ and /s/ (in single-symbol ARPAbet notation) is presented with applications. The use of pitch variation as a means of controlling a continuously variable parameter is described with two applications - a microcontroller based light dimmer switch and a computer program which facilitates mouse pointer control. …