Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Artificial Intelligence and Robotics (7)
- Engineering (3)
- Computer Engineering (2)
- Data Science (2)
- Other Computer Sciences (2)
-
- Social and Behavioral Sciences (2)
- Software Engineering (2)
- Systems Architecture (2)
- Art and Design (1)
- Arts and Humanities (1)
- Cognitive Science (1)
- Communication (1)
- Cybersecurity (1)
- Databases and Information Systems (1)
- Digital Communications and Networking (1)
- Electrical and Computer Engineering (1)
- Graphics and Human Computer Interfaces (1)
- Hardware Systems (1)
- Information Security (1)
- Painting (1)
- Signal Processing (1)
- Social Media (1)
- Social Work (1)
- Statistical Models (1)
- Statistics and Probability (1)
- Keyword
-
- Machine learning (19)
- Deep learning (12)
- Classification (5)
- Convolutional neural networks (5)
- Neural networks (5)
-
- Security (5)
- Big data (4)
- Computer vision (4)
- Data mining (4)
- Malware (4)
- MapReduce (4)
- Twitter (4)
- Analysis (3)
- Android (3)
- Cloud computing (3)
- Crowdsourcing (3)
- Fact-checking (3)
- Graph mining (3)
- MRQL (3)
- Multilayer networks (3)
- Privacy (3)
- Recurrent neural networks (3)
- Social media (3)
- AWS (2)
- Activity recognition (2)
- Apriori (2)
- Baum-Welch algorithm (2)
- Deep Learning (2)
- Deep neural networks (2)
- Degree centrality (2)
- Publication Year
- File Type
Articles 31 - 60 of 365
Full-Text Articles in Computer Sciences
Low-Dose Ct Image Denoising Using Deep Learning Methods, Zeheng Li
Low-Dose Ct Image Denoising Using Deep Learning Methods, Zeheng Li
Computer Science and Engineering Theses - Archive
Low-dose computed tomography (LDCT) has raised highly attention since the counterpart, full-dose computed tomography (FDCT), brings potential ionizing radiation influence to patients. However, LDCT still suffers from several issues such as relatively higher noise level, which limits its uses in practical applications. To improve LDCT image quality, conventional denoising methods, such as KSVD and BM3D, are first introduced to suppress noise in low-dose images. These methods, however, works under assumptions that are not robust to various data. In this paper, we conduct an extensive research on deep learning based denoising method in LDCT images. We mainly base on Generative-Adversarial Network …
End-User Framework For Robot Control, Kaustubh Kedar Rajpathak
End-User Framework For Robot Control, Kaustubh Kedar Rajpathak
Computer Science and Engineering Theses - Archive
This thesis describes in detail a developed end-user framework for a humanrobot collaborative system for common tasks, such as pick and place. The system is designed for semi-automated pick and place tasks as well as manual operation making it flexible for multiple use-case scenarios. The goal of the system is to make the robotic system multi-functional, easy to use with a graphical user interface and should perform common tasks with the help of a human teammate. Integration with object recognition neural networks (YOLOv3) and an RGB-Depth camera help automate pick and place tasks with a wide variety of objects.
Using Sentiment And Emotion Analysis Of News Articles To Analyze The Effects Of Leader’S Statements On Covid-19 Spread, Poojitha Thota
Using Sentiment And Emotion Analysis Of News Articles To Analyze The Effects Of Leader’S Statements On Covid-19 Spread, Poojitha Thota
Computer Science and Engineering Theses - Archive
Leaders generally include government officials, politicians, etc. Their statements can highly affect people’s decisions in many ways. Currently, in the pandemic situation, many statements were being passed every hour and day, which showed an impact on the spread of corona virus cases at certain location. So, this paper proposes a supervised model to analyze the variations of COVID-19 data based upon the leader’s statements passed at certain time and location. The proposed methodology consists of sentiment and emotion analysis for the leader’s statements to determine the true intentions of the leader. The leader’s statements are a collection of data obtained …
Learning Hierarchical Traversability Representation For Efficient Multi-Resolution Path Planning, Reza Etemadi Idgahi
Learning Hierarchical Traversability Representation For Efficient Multi-Resolution Path Planning, Reza Etemadi Idgahi
Computer Science and Engineering Theses - Archive
Path finding on grid-based obstacle maps is an important and much studied problem with applications in robotics and autonomy. Traditionally, in the AI community, heuristic search methods (e.g. based on Dijkstra and A*, or based on random trees) are used to solve this problem. This search, however incurs significant computational cost that grows with the size and resolution of the obstacle grid and has to be mitigated with effective heuristics in order to allow path finding in real time. In this work we introduce a learning framework using deep neural networks with a stackable convolution kernel to establish a hierarchy …
Structure Aware Human Pose Estimation Using Adversarial Learning, Suryam Sharma
Structure Aware Human Pose Estimation Using Adversarial Learning, Suryam Sharma
Computer Science and Engineering Theses - Archive
Pose estimation using Deep Neural Networks (DNNs) has shown outstanding performance in recent years, due to the availability of powerful GPUs and larger training datasets. However, there are still many challenges due to the large variability of human body appearances, lighting conditions, complex background, occlusions and postures. Among all these peculiarities, partial occlusions, and overlapping body poses often result in deviated pose predictions. These circumstances can result in wrong and sometimes unrealistic results. The human mind can predict such poses because of the underlying structural awareness of the geometry, of a human body. In this thesis, we discuss an efficient …
Glaze Epochs: Externalizing Material Knowledge Through Tangible Data Records In A Ceramics Studio, Hedieh Moradi
Glaze Epochs: Externalizing Material Knowledge Through Tangible Data Records In A Ceramics Studio, Hedieh Moradi
Computer Science and Engineering Theses - Archive
The "material turn" in HCI has placed a renewed focus on informing design from the relationships found in material-based interactions. While several ethnographic works provide insight into how practitioners converse with materials, it is less understood how these conversations transform into a skilled practitioner's mental model. I examine the material practice of glazing that gives ceramics its decorative and functional characteristics and involves fusing mixtures of silica, alumina, and flux onto a clay body through kiln firing. This practice evolves over decades, developing from multiple trajectories, including theoretical foundations, systematic experimentation, and happy accidents. This work describes virtual site visits …
Predict Behavioural Scores In Sleep Apnea Patients From Resting State Near-Infrared Spectroscopy (Fnirs), Amnah Abdelrahman
Predict Behavioural Scores In Sleep Apnea Patients From Resting State Near-Infrared Spectroscopy (Fnirs), Amnah Abdelrahman
Computer Science and Engineering Theses - Archive
Sleep disorders are common among adults and children; it has serious consequences on their heath, cognitive development and quality of life. However, some sleep disorders are challenging to diagnose and more challenging to treat. Practitioners often rely on AIH for OSA patients’ classification task, where considering one measurement could raise a risk of oversimplification. Studies show the correlation between sleep disorders, specifically OSA, and mental health. On the other side there are an increasing number of studies suggested evidence of a relationship between the dynamic properties of functional brain structure with the behaviors and cognition attributes. This novel work objective …
Continuous American Sign Language Translation With English Speech Synthesis Using Encoder-Decoder Approach, Preetham Ganesh
Continuous American Sign Language Translation With English Speech Synthesis Using Encoder-Decoder Approach, Preetham Ganesh
Computer Science and Engineering Theses - Archive
Interaction between human beings brings about improvements in science and technology. However, the interaction is limited for people who are deaf or hard-of-hearing, as they can only communicate with others who also know their sign language. With the help of recent technologies, such as Deep Learning, the gap can be bridged by converting Sentence-based Sign Language videos into English language speech. The methods discussed in this thesis are taking a step closer to solve that problem. There are four steps involved in converting ASL (American Sign Language) videos to English language speech. Step 1 is to recognize the phrases performed …
Generating Adversarial Examples For Recruitment Ranking Algorithms, Anahita Samadi
Generating Adversarial Examples For Recruitment Ranking Algorithms, Anahita Samadi
Computer Science and Engineering Theses - Archive
There is no doubt that recruitment process plays an important role for both employers and applicants. Based on huge number of job candidates and open vacancies, recruitment process is expensive, time consuming and stressful for both applicants and companies. In today’s world so many recruitment processes are based on machine learning techniques. Therefore, it is very important to ensure security of these algorithms. Adversarial examples are proposed to examine vulnerability of machine leaning algorithms. Many research studies have been done on evaluating the resistance of artificial intelligence-based systems, in computer vision and text classification, against adversarial examples. However, to the …
Semi-Automatic Hand Pose Estimation Using A Single Depth Camera, Giffy Jerald Chris
Semi-Automatic Hand Pose Estimation Using A Single Depth Camera, Giffy Jerald Chris
Computer Science and Engineering Theses - Archive
This paper addresses the problem of 3D hand pose annotations using a single depth camera. Although hand pose estimation methods rely critically on accurate 3D training data, creating such reliable training data is challenging and labor intensive. We propose a semi-automatic method for efficiently and accurately labeling the 3D hand key-points in a hand depth video. The process starts by selecting a subset of frames that are representative of all the frames in the dataset and the annotator only provides an estimate of the 2D hand key-points in these selected frames. We use this information to infer the 3D location …
A Survey On Ddos Attacks In Edge Servers, Iftakhar Ahmad
A Survey On Ddos Attacks In Edge Servers, Iftakhar Ahmad
Computer Science and Engineering Theses - Archive
In modern times, the need for latency sensitive applications is growing rapidly. Cloud computing infrastructure is unable to provide support to such delay sensitive applications. Therefore, a new paradigm called edge computing has emerged. In edge computing various paradigms like Fog, Cloudlet, Mobile Edge Computing, etc. provide real-time, location aware services to users. As a result number of requests are generated for processing in the edge servers. If these edge servers for some reason become unavailable for providing service, users will not be able to perform their delay sensitive or location aware operations. Like other servers in the network, edge …
Incomplete Time Series Forecasting Using Generative Neural Networks, Harshit Tarun Shah
Incomplete Time Series Forecasting Using Generative Neural Networks, Harshit Tarun Shah
Computer Science and Engineering Theses - Archive
Dealing with missing data is a long pervading problem and it becomes more challenging when forecasting time series data because of the complex relationships between data and time, which is why incomplete data can lead to unreliable results. While some general-purpose methods like mean, zero, or median imputation can be employed to alleviate the problem, they might disrupt the inherent structure and the underlying data distributions. Another problem associated with conventional time series forecasting methods whose goal is to predict mean values is that they might sometimes overlook the variance or fluctuations in the input data and eventually lead to …
Link Prediction Based Face Clustering Using Variational Attentional Graph Autoencoder, Harish Deepak Verlekar
Link Prediction Based Face Clustering Using Variational Attentional Graph Autoencoder, Harish Deepak Verlekar
Computer Science and Engineering Theses - Archive
In this work, we address the problem of clustering faces according to their individual identities present inherently in the dataset.The current clustering frameworks are either based on some heuristic method or require labelled data for training the models,also some of them make assumptions on data distribution or shape of the clusters.We have framed the problem of forming clusters to that of link prediction on graphs and learn how to do that in a completely unsupervised way by proposing to use Variational Graph Autoencoders and use Graph Attentional Network as the Encoder. We call this network as Variational Attentional Graph Autoencoder(VAGAE).Our …
Early Detection Of Glaucoma Using Modified Residual U-Net Convolutional Neural Network, Balasubramaniam Theetharappan
Early Detection Of Glaucoma Using Modified Residual U-Net Convolutional Neural Network, Balasubramaniam Theetharappan
Computer Science and Engineering Theses - Archive
Glaucoma is the second leading cause of blindness all over the world, with apparently 75 million cases reported worldwide in 2018. If it’s not diagnosed at an early stage, glaucoma may cause irreversible damage to the optic nerve which results in blindness. The Optic head examination is the widely used structured diagnosis approach in the current medical field for Glaucoma detection which involves measuring the Optic Cup-to-Disc ratio from the fundus image. Estimation of Optic Cup-to-Disc requires accurate segmentation of the Optic Cup and Optic Disc from the fundus which is a tedious and time-consuming task even for the experienced …
Evaluating The Accuracy Of Gaze Detection For Moving Character, Sanath Narasimhan
Evaluating The Accuracy Of Gaze Detection For Moving Character, Sanath Narasimhan
Computer Science and Engineering Theses - Archive
Joint attention, where a caregiver and an infant follow each other’s eye gaze plays an important role in the learning of language for new-born infants. To study joint attention, it is required to record and analyze the joint attention in a naturalistic environment. For this, we can use the head-mounted eye tracker. However, natural interaction involves the body movement which a?ects the accuracy of the measurement. In this work, I evaluated the accuracy of the eye-tracking system in the three di?erent scenarios: when the subject is sitting still in front of the target when the subject looks at the target …
"How Good Are They?" - A State Of The Effectiveness Of Anti-Phishing Tools On Twitter, Sayak Saha Roy
"How Good Are They?" - A State Of The Effectiveness Of Anti-Phishing Tools On Twitter, Sayak Saha Roy
Computer Science and Engineering Theses - Archive
Phishing websites are one of the most pervasive online attack vectors, with nearly 1.5 million such attacks created every month. Social media is the primary ground for phishing attacks, with 86% of these attacks originating from Twitter, Facebook, LinkedIn, etc. Prevalent approaches against these attacks includes URL scanners, anti-phishing blacklists and social media's own detection systems. In this work, we focus on Twitter, and through a combination of data-driven methods and emulations, we evaluate the verdicts provided by URL scanners, and Twitter’s detection system. We show that these sources provide a good amount of misinformation, which not only can lead …
In Situ Sensor Calibration Using Noise Consistency, Shriiesh Var Sharma
In Situ Sensor Calibration Using Noise Consistency, Shriiesh Var Sharma
Computer Science and Engineering Theses - Archive
Robots rely on sensors to map their surroundings. As a result, the accuracy of the map depends heavily on the sensor noise and in particular on accurate knowledge of it. The common way to minimize the impact of sensor noise is to use filtering algorithms. Accuracy of these filtering algorithms (like the Kalman filter) relies on the accuracy of the user supplied measurement noise model. Inaccurate noise models lead to higher residual noise in state estimates and errors in the estimate of the precision of the state estimate. It is therefore important to have precise noise models and thus accurately …
Classification Of Factual And Non-Factual Statements Using Adversarially Trained Lstm Networks, Daniel Obembe
Classification Of Factual And Non-Factual Statements Using Adversarially Trained Lstm Networks, Daniel Obembe
Computer Science and Engineering Theses - Archive
Being able to determine which statements are factual and therefore likely candidates for further verification is a key value-add in any automated fact-checking system. For this task, it has been shown that LSTMs outperform regular machine learning models, such as SVMs. However, the complexity of LSTMs can also result in over fitting (Gal and Ghahramani,1997), leading to poorer performance as models fail to generalize. To resolve this issue, we set out to utilize adversarial training as away to improve the performance of LSTMs for the task of classifying statements as factual or non-factual. In our experiment, we implement the adversarial …
Activity Recognition To Mimic Human Perception, Alankrit Gupta
Activity Recognition To Mimic Human Perception, Alankrit Gupta
Computer Science and Engineering Theses - Archive
The recognition of activities from video is a capability that is important for a wide range of applications, ranging from basic scene understanding to the successful prediction of behavior in autonomous vehicle applications. At this time, human capabilities in this task by far outperform computer applications and thus the idea to mimic human perception should be promising. In this thesis we are proposing an architecture that processes videos to extract important action instances that describe the essential behaviors contained in any video and help us map the information from the video to a machine-understandable form. This is an important research …
Person Identification And Tinetti Score Assessment Using Balance Parameters To Determine Fall Risk, Varsha Rani Chawan
Person Identification And Tinetti Score Assessment Using Balance Parameters To Determine Fall Risk, Varsha Rani Chawan
Computer Science and Engineering Theses - Archive
This thesis is aimed at a substantial health problem among the elderly population that is “Fall”, a major cause of accidental home deaths. Studies show approximately one-third of community-dwelling people over 65 years of age will experience one or more falls each year. The balance and walking pattern are useful to determine the risk of fall in an individual and is highly influenced by several parameters and conditions. The deterioration in the balance and walking stability of an individual can occur because of the natural processes related to aging or as a result of various underlying health conditions, fatigue, muscle …
Das Page Replacement Algorithm, Ramya Danappa
Das Page Replacement Algorithm, Ramya Danappa
Computer Science and Engineering Theses - Archive
There are different page replacement algorithms and yet there seems to be some drawbacks in them, making no page replacement algorithm ideal. To be one step closer to achieving the ideal algorithm it is vital to have a maximum cache hit ratio and strong consistent across different workload. In this paper we shall explore a new cache management policy called “Dynamic and Stable page replacement algorithm” uses frequency and recency importance dynamically”. The proposed page replacement algorithm has overcome the drawbacks of the LRU (Least Recently Used) algorithm in many scenarios and also overcome the drawbacks of LFU (Least Recently …
Semi-Supervised Learning Using Triple-Siamese Network, Debapriya Banerjee
Semi-Supervised Learning Using Triple-Siamese Network, Debapriya Banerjee
Computer Science and Engineering Theses - Archive
Missing data problem is inevitable in mostly all research areas including Artificial Intelligence, Machine Learning and Computer Vision where we have modicum knowledge about the complete dataset. One of the key reasons of missing data in AI is insufficiency of accurately labeled data. To solve a classification problem using ML or training a Deep Neural Network model, we need a huge amount of labeled data. It is difficult to get labeled data but unlabeled data is inexpensive and available easily. It is usual that we get no more than a single element per class to train our models due to …
Development Of Text Analytics For Debriefing Reflection Essays, Md Shadekur Rahman
Development Of Text Analytics For Debriefing Reflection Essays, Md Shadekur Rahman
Computer Science and Engineering Theses - Archive
Evaluating and providing feedback to hundreds of free text assignments in an online environment is a challenging task for an instructor where he has to scan through essays to identify perspectives that are expected to appear in those essays. Reading large number of essays and then finding themes and providing customized feedback are time-consuming process. We have proposed a text analytics system named EssayIQ that aids course instructor in identifying assignment themes, providing theme presence statistics and giving feedback to learners. To the best of our knowledge, this is the first system that analyzes free text assignments in line with …
Tapin: A Two-Factor User Authentication Scheme For Smartwatches Through Secret Finger Tapping, Akash Lohani
Tapin: A Two-Factor User Authentication Scheme For Smartwatches Through Secret Finger Tapping, Akash Lohani
Computer Science and Engineering Theses - Archive
Nowadays, smartwatches have become one of the most common wearable gadgets as they are small and portable. As more and more personal information is managed and processed inside smartwatches, it is important to have a secure user authentication scheme in place. There have been many successful authentication schemes for a smartphones such as Password/PIN, bio-metric approach(e.g. fingerprint, face recognition), etc directly used on smartwatches. However, these approaches are not quite suitable for smartwatches due to its constraints in size and limited computation power. To address this issue, we propose TaPIN that allows users to authenticate themselves by playing out the …
Mln-Subdue: Decoupling Approach-Based Substructure Discovery In Multilayer Networks (Mlns), Anish Rai
Mln-Subdue: Decoupling Approach-Based Substructure Discovery In Multilayer Networks (Mlns), Anish Rai
Computer Science and Engineering Theses - Archive
Substructure discovery is well-researched for single graphs (both simple and attribute) as it is an important component of knowledge discovery for many applications such as finding the core substructure in a protein, important concept in a large graph, etc. However, multilayer networks or MLNs (instead of attribute graphs) have been shown to be better for modeling complex data sets that have multiple entity and feature types. This model provides more clarity on semantics of data sets as well as the ability to use an arbitrary subset of layers for analysis. However, the challenge is that many algorithms such as community …
Randomized And Evolutionary Approaches To Dataset Characterization, Feature Weighting, And Sampling In K-Nearest Neighbors, Suryoday Basak
Randomized And Evolutionary Approaches To Dataset Characterization, Feature Weighting, And Sampling In K-Nearest Neighbors, Suryoday Basak
Computer Science and Engineering Theses - Archive
K-Nearest Neighbors (KNN) has remained one of the most popular methods for supervised machine learning tasks. However, its performance often depends on the characteristics of the dataset and on appropriate feature scaling. In this thesis, characteristics of a dataset that make it suitable for being used within KNN are explored. As part of this, two new measures for dataset dispersion, called mean neighborhood target variance (MNTV), and mean neighborhood target entropy (MNTE) are developed to help determine the performance we expect while using KNN regressors and classifiers, respectively. It is empirically demonstrated that these measures of dispersion can be indicative …
3d Skeleton Construction From Multiple Camera Views For Quantifying Gait Parameters, Saket Gupta
3d Skeleton Construction From Multiple Camera Views For Quantifying Gait Parameters, Saket Gupta
Computer Science and Engineering Theses - Archive
Research has shown that human gait characteristics permit inference with respect to different personal and health characteristics and can thus be used as a diagnostic tool. To do this automatically it is important to be able to extract them from senor information. This thesis work is aimed at doing this from multiple camera views and for this focuses on construction of a 3D body skeleton from multiple viewpoint video (MVV) and then quantifying a number of gait characteristics such as swing time, step time, cadence, stride length, single support, or double support. The method introduced here uses a marker-less approach …
Intrinsic Curiosity In Reinforcement Learning By Improving Next State Prediction, Paul Lewis Lobo
Intrinsic Curiosity In Reinforcement Learning By Improving Next State Prediction, Paul Lewis Lobo
Computer Science and Engineering Theses - Archive
In Reinforcement Learning, an agent receives feedback from the environment in the form of an extrinsic reward. It learns to take actions that maximize this extrinsic reward. However, to start learning, the agent needs to be able to get feedback from the environment by using random actions. This works in environments with frequent rewards, however, in environments where the rewards are sparse the probability of reaching any reward even once becomes very low. One way to explore an environment efficiently is for the agent to generate its own intrinsic reward by using the prediction error from a model that is …
Azul - Using Multimodal Sensors From Mobile And Wearable Devices For Assessment And Monitoring Of Depression Symptoms, Manu Srivastava
Azul - Using Multimodal Sensors From Mobile And Wearable Devices For Assessment And Monitoring Of Depression Symptoms, Manu Srivastava
Computer Science and Engineering Theses - Archive
With the ubiquitous presence of mobile phones, there is too much data that can be collected for different purposes which can be correlated to monitor multiple more user information. If used responsibly, this data can be used to assess and monitor various mental health conditions. For example, fitness sensors in wearable devices collect step counts, sleep-related data and heart rate; GPS sensors in smartphones continually collect device location, and Android on-device services collect smartphone usage habits of the user. All the data from the previous example relate to exhibited depression symptoms in users. This data, when used in conjugation, has …
Mr_Qp: A Scalable Approach To Query Processing On Arbitrary-Size Graphs Using The Map/Reduce Framework, Harshit Ashokkumar Modi
Mr_Qp: A Scalable Approach To Query Processing On Arbitrary-Size Graphs Using The Map/Reduce Framework, Harshit Ashokkumar Modi
Computer Science and Engineering Theses - Archive
The utility and widespread use of Relational Database Management Systems(RDBMSs) comes not only from its simple, easy-to-understand data model (a relation or a set) but mainly from the ability to write non-procedural queries and their optimization by the system. Queries produce exact answers that match the contents of the database. Query processing of RDBMSs has been researched for more than 4 decades and includes extensions to more complex analysis on data warehouses. In contrast, search has not been addressed by RDBMSs. As the use of other other data types (key-value store, column-store, and graphs to name a few) are becoming …