Computer Sciences Commons^™

Uniconv: A Unified Conversational Neural Architecture For Multi-Domain Task-Oriented Dialogues, Hung Le, Doyen Sahoo, Chenghao Liu, Nancy F. Chen, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Building an end-to-end conversational agent for multi-domain task-oriented dialogues has been an open challenge for two main reasons. First, tracking dialogue states of multiple domains is non-trivial as the dialogue agent must obtain complete states from all relevant domains, some of which might have shared slots among domains as well as unique slots specifically for one domain only. Second, the dialogue agent must also process various types of information across domains, including dialogue context, dialogue states, and database, to generate natural responses to users. Unlike the existing approaches that are often designed to train each module separately, we propose “UniConv" …

Deepfrag-K: A Fragment-Based Deep Learning Approach For Protein Fold Recognition, Wessam Elhefnawy, Min Li, Jianxin Wang, Yaohang Li

Computer Science Faculty Publications

Background: One of the most essential problems in structural bioinformatics is protein fold recognition. In this paper, we design a novel deep learning architecture, so-called DeepFrag-k, which identifies fold discriminative features at fragment level to improve the accuracy of protein fold recognition. DeepFrag-k is composed of two stages: the first stage employs a multi-modal Deep Belief Network (DBN) to predict the potential structural fragments given a sequence, represented as a fragment vector, and then the second stage uses a deep convolutional neural network (CNN) to classify the fragment vector into the corresponding fold.

Results: Our results show that DeepFrag-k yields …

Efficient Filters For Geometric Intersection Computations Using Gpu, Yiming Liu, Satish Puri

Computer Science Faculty Research and Publications

Geometric intersection algorithms are fundamental in spatial analysis in Geographic Information System (GIS). Applying high performance computing to perform geometric intersection on huge amount of spatial data to get real-time results is necessary. Given two input geometries (polygon or polyline) of a candidate pair, we introduce a new two-step geospatial filter that first creates sketches of the geometries and uses it to detect workload and then refines the sketches by the common areas of sketches to decrease the overall computations in the refine phase. We call this filter PolySketch-based CMBR (PSCMBR) filter. We show the application of this filter in …

Extending The Functional Subnetwork Approach To A Generalized Linear Integrate-And-Fire Neuron Model, Nicholas Szczecinski, Roger Quinn, Alexander J. Hunt

Mechanical and Materials Engineering Faculty Publications and Presentations

Engineering neural networks to perform specific tasks often represents a monumental challenge in determining network architecture and parameter values. In this work, we extend our previously-developed method for tuning networks of non-spiking neurons, the “Functional subnetwork approach” (FSA), to the tuning of networks composed of spiking neurons. This extension enables the direct assembly and tuning of networks of spiking neurons and synapses based on the network’s intended function, without the use of global optimization ormachine learning. To extend the FSA, we show that the dynamics of a generalized linear integrate and fire (GLIF) neuronmodel have fundamental similarities to those of …

Law Library Blog (November 2020): Legal Beagle's Blog Archive, Roger Williams University School Of Law

Law Library Newsletters/Blog

No abstract provided.

Cache-Based Optimization For Block Commit Of Hyperledger Fabric, Qinqi Xu, Yimin Lin, Qingshan Jiang, Mengqiu Zhang

Research Collection Lee Kong Chian School Of Business

Blockchain technology has been applied to various domains in recent years, and Hyperledger Fabric is one of the most popular blockchain systems. This paper conducts a fine analysis on the block commit of Hyperledger Fabric through latency evaluation as well as flame graph. To overcome the bottlenecks pointed out by the analysts, this paper proposes two cache-based schemata. In particular, we add a cache for index and state storage to accelerate commit. We also cache deserialized block globally for block delivery to avoid repeat operations. The experiments reveal performance improvement of 2×. Notably, our optimizations can also be implemented easily …

Contextual-Bandit Anomaly Detection For Iot Data In Distributed Hierarchical Edge Computing, Mao V. Ngo, Tie Luo, Hakima Chaouchi, Tony Q.S. Quek

Computer Science Faculty Research & Creative Works

Advances in deep neural networks (DNN) greatly bolster real-time detection of anomalous IoT data. However, IoT devices can hardly afford complex DNN models, and offloading anomaly detection tasks to the cloud incurs long delay. In this paper, we propose and build a demo for an adaptive anomaly detection approach for distributed hierarchical edge computing (HEC) systems to solve this problem, for both univariate and multivariate IoT data. First, we construct multiple anomaly detection DNN models with increasing complexity and associate each model with a layer in HEC from bottom to top. Then, we design an adaptive scheme to select one …

A Tripartite Model Of Trust In Facebook: Acceptance Of Information Personalization, Privacy Concern, And Privacy Literacy, Sonny Rosenthal, Ole-Christian Wasenden, Gorm-Andreas Gronnevet, Rich Ling

Research Collection College of Integrative Studies

This study draws on the mental accounting perspective and a tripartite model of trust to explain why users trust Facebook. We argue that trust in Facebook is related to (1) trust in companies that collect personal data, (2) acceptance of information personalization, (3) low privacy concern, and (4) low privacy literacy. Further, we argue that privacy literacy amplifies the relationship between privacy concern and the other factors. This is because, among individuals with high privacy literacy, privacy concern is especially diagnostic of the potential harms of a loss of privacy. These arguments align broadly with theorizations about factors influencing privacy-related …

Usage Of The Symbols And Dionis Square In The Cryptosystem Of Dionis, Dionis Shabani

UBT International Conference

The rapid developments of technology which have brought with them a host of benefits to humanity have also left behind a host of spaces which have mostly aided cyber piracy who exploit the many benefits of the internet for purposes that are in their favor,but these actions which negatively affect the privacy of all internet users. In this project I will present some modifications which are enabled through the 16x16 square of Dionis with 256 elements based in the Masonic Cipher method, with the help of which based on the rules I have created and developed it is different from …

Proposal Of A Legal Framework Through The Development Of New Domain Specific Languages (Dsl) In Compliance With Gdpr, Tea Tavanxhiu, Andrea Alberici, Kozeta Sevrani

UBT International Conference

The adaptation of company processes to the EU Regulation represents a major opportunity to review, update and improve the internal processes and management tools used. The loss of data, in most cases, causes serious damage to the image and very often the total closure of the company. The legislation therefore represents an opportunity and a stimulus to verify the management methods applied, to define an organizational model and a code of conduct (policies, processes, rules / provisions and controls) capable of improving internal processes, defining and achieving desired objectives, ensure data and systems protection with proper risk management and assessment. …

Suggestions And Recommendations For Fulfillment And Implementation Of The Project For Broadband Internet In Macedonia, Zoran Aleksov, Boris Arsov, Vergim Sherifi, Nenad Popovic

UBT International Conference

Nowadays, broadband is defined on the basis of a number of parameters that can be offered through existing electronic communications networks (fixed or mobile networks) and the construction of some next generation of advanced electronic communications networks. This is extremely important for the quality of the received service, because with the existence of a quality electronic communication network, you will distribute a quality and fast data transfer to the end users, some of whom actually want it. Optical cable, among other types of cables, using the Operator and the access method known as " fiber to the home ", has …

Constructing Hadamard Matrices Using Binary Codes, Hizer Leka, Faton Kabashi

UBT International Conference

In this paper is presented a very efficient method for constructing Hadamard matrices, using binary code products. We will construct such matrices using the scalar production of two vectors and the tensor production of Hadamard matrices. This method is based on the representation of the natural number as a binary code which takes only two values 0 or 1. Such a method of generating Hadamard matrices can be used in practice to generate different codes, in telecommunication systems, to correct blocked codes, but also in science as for example in Boolean algebra.

An Alternative Probabilistic Protocol For Relaying Wireless Networks, Faton Maliqi

UBT International Conference

In this paper we propose an alternative probabilistic protocol for relaying wireless network. Usually, the communication protocols are designed to be deterministic when it comes to the order of retransmission from the communication nodes. In contrast, we propose an alternative probabilistic protocol where the retransmitting nodes are chosen probabilistically, and which allows easier performance optimization. Using Monte Carlo simulations, we will show at which location of the Relay do we get the best performance. Due to energy consuming concern and due to lower complexity advantage, as required in technologies such as Internet of Things (IoT), we will consider the case …

Fraud Detection Using Data-Driven Approach, Arianit Mehana, Krenare Pireva Nuci

UBT International Conference

The extensive use of internet is continuously drifting businesses to incorporate their services in the online environment. One of the first spectrums to embrace this evolution was the banking sector. In fact, the first known online banking service came in 1980. It was deployed from a community bank located in Knoxville, called the United American Bank. Since then, internet banking has been offering ease and efficiency to costumers in completing their daily banking tasks. The ever increasing use of internet banking and the large number of online transactions, increased fraudulent behaviour also. As if fraud increase wasn’t enough, the massive …

Big Data Analytics On Cloud: Challenges, Techniques And Technologies, Aleksander Biberaj, Olimpion Shurdi, Bledar Kazia, Renalda Kushe, Alban Rakipi

UBT International Conference

These days it is known that Big Data Analytics is taking a huge attention from researchers and also from business. We all are witness of the data growth that every institution, company or even individuals store in order to use them in the future. There is a big potential to extract useful data from this Big Data that is stored usually in Cloud because sometimes there is not enough local space to store big amounts of data. There is a huge number of sectors where Big Data can be helpful including economic and business activities, public administration, national security, scientific …

Multithreaded Approach For Using Blockchain As An Automated Versioning Tool, Arber Kadriu, Dijar Kadriu, Donjet Salihi, Edmond Jajaga

UBT International Conference

Blockchain is a new and growing technology with a bright future ahead. It can be implemented in many different ways and different industries like banking, cryptocurrencies, health information systems etc. Its powerfulness in security and systematic tracking of different items makes it one of its kind and attractive to work with. This technology is also a suitable environment for multithreaded programming to be adopted in, while using blocks and items to be tracked by single threads. This paper presents an innovative approach of using blockchain as a versioning control tool for personal or commercial usage.

Performance Evaluation Of Non-Relational Data On Big Data Environments, Edmond Jajaga, Edi Hasaj

UBT International Conference

Big data management is a real challenge for traditional systems. The experimental evaluation is performed on measurement of performance of five different databases with an open non-relational dataset. It was structured and tested separately in each store, giving some advantages and limitations to them from a practical point of view. The results are drawn based on the throughput per number of users executed respectively. It was loaded and executed more than a million of records in each and every database. Following its semi-persistent model, Redis performed better than other databases.

Peer To Peer Audio And Video Communication, Kushtrim Pacaj, Kujtim Hyseni, Donika Sfishta

UBT International Conference

In this paper we introduce a simple way on how you can build your own “end-to- end” audio and video chat. You can expect to learn how to add new features on it, as well as building your own signaling server, your mobile UI and mobile calls logic implemented in a perfect coexistence between NodeJS, Java and Kotlin. What makes this application special is the possibility to express yourself with different annotations while you’re on a video chat.

Oauth2.0 In Securing Apis, Olimpion Shurdi, Aleksander Biberaj, Igli Tafa, Genci Mesi

UBT International Conference

Today’s modern applications are mostly designed around API’s. API’s are used for a variety of things such as passing data to another webservice reading data from a database etc. The problem with this is that not all the API’s are secure. Most of the today’s API’s are old and rely only on an authentication token where the user data often had to share their credentials with the application to enable such an API call on their behalf or string them, which is often hardcoded. We will focus on OAUTH 2.0 as new protocol in securing our API’s. This is a …

Aspects Of The Use Of Nanotechnology And Nanomedicine In Medicine, Muhamet Avdyli, Era Kastrati

UBT International Conference

The purpose of this paper is to show aspects of the application of nanotechnology nowadays, especially in health. Nanotechnologies are the design, characterization, production and application of structures, equipment and systems by controlling the shape and size at the nanometer scale. The special branch that deals with the study of medicine in nanotechnology is called nanomedicine. Nanomedicine is a branch of medicine that applies the knowledge and tools of nanotechnology in the prevention and treatment of disease. Nanomedicine involves the use of nanoscale materials, such as nanoparticles and nanorobots, for diagnostic, dispersing, sensitizing, or activating purposes in a living organism. …

A Hybrid Agent-Based And Equation Based Model For The Spread Of Infectious Diseases, Elizabeth Hunter, Brian Mac Namee, John D. Kelleher

Articles

Both agent-based models and equation-based models can be used to model the spread of an infectious disease. Equation-based models have been shown to capture the overall dynamics of a disease outbreak while agent-based models are able to capture heterogeneous characteristics of agents that drive the spread of an outbreak. However, agent-based models are computationally intensive. To capture the advantages of both the equation-based and agent-based models, we create a hybrid model where the disease component of the hybrid model switches between agent-based and equation-based. The switch is determined using the number of agents infected. We first test the model at …

International Conference On Computer Science And Communication Engineering, University For Business And Technology - Ubt

UBT International Conference

UBT Annual International Conference is the 9th international interdisciplinary peer reviewed conference which publishes works of the scientists as well as practitioners in the area where UBT is active in Education, Research and Development. The UBT aims to implement an integrated strategy to establish itself as an internationally competitive, research-intensive university, committed to the transfer of knowledge and the provision of a world-class education to the most talented students from all background. The main perspective of the conference is to connect the scientists and practitioners from different disciplines in the same place and make them be aware of the recent …

International Conference Information Systems And Security, University For Business And Technology - Ubt

UBT International Conference

UBT Annual International Conference is the 9th international interdisciplinary peer reviewed conference which publishes works of the scientists as well as practitioners in the area where UBT is active in Education, Research and Development. The UBT aims to implement an integrated strategy to establish itself as an internationally competitive, research-intensive university, committed to the transfer of knowledge and the provision of a world-class education to the most talented students from all background. The main perspective of the conference is to connect the scientists and practitioners from different disciplines in the same place and make them be aware of the recent …

The Efficiency And Accuracy Of Yolo For Neonate Face Detection In The Clinical Setting, Jacqueline Hausmann

USF Tampa Graduate Theses and Dissertations

There are many face detection classification models available for download and use in the modern technological world. Based in the field of deep neural networks, these off-the-shelf solutions are generally inadequate to solve real world challenges. This work presents how current approaches biased towards detecting adult human faces must be modified in order to better accommodate face detection of the neonate in a NICU setting.

YOLO is a powerful object detection algorithm. Due to optimizations such as Cross mini-batch Normalization, Modified Spatial Attention Modules, Modified Path Aggregation Networks, Self-Adversarial Training, Mosaic Data Augmentation, DropBox Regularization, Multi-Input Weighted Residual Connections and …

Communicating Uncertain Information From Deep Learning Models In Human Machine Teams, Harishankar V. Subramanian, Casey I. Canfield, Daniel Burton Shank, Luke Andrews, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

The role of human-machine teams in society is increasing, as big data and computing power explode. One popular approach to AI is deep learning, which is useful for classification, feature identification, and predictive modeling. However, deep learning models often suffer from inadequate transparency and poor explainability. One aspect of human systems integration is the design of interfaces that support human decision-making. AI models have multiple types of uncertainty embedded, which may be difficult for users to understand. Humans that use these tools need to understand how much they should trust the AI. This study evaluates one simple approach for communicating …

Analysis Of Glutathione Supplementation Effects On Female Metabolic Syndrome Condition Using Classification Techniques, Nur Rasyidah Hasan Basri

Student Works (2020-2029)

Lesser known to the public that main antioxidants in our body, Glutathione are also said to influence the metabolic syndrome (MS) condition. Oral supplementation consisting of glutathione precursors and vitamin C introduced in the study was to improve glutathione (GSH) status of the consumer and the main objective of this study is to investigate GSH effects on selected MS condition. Several known studies had proven that oral supplementation improved GSH level of consumer. However, there is no definite proof on how it’s affecting MS parameters. Also, there is less study carried out on the relationship between glutathione levels and metabolic …

Control Of A Human Arm Robotic Unit Using Augmented Reality And Optimized Kinematics, Carlo Canezo

USF Tampa Graduate Theses and Dissertations

There are more than 350000 amputees in the US who suffer loss of functionality in their daily living activities, and roughly 100000 of them are upper arm amputees. Many of these amputees use prostheses to compensate part of their lost arm function, including power prostheses. Research on 6-7 degree of freedom powered prostheses is still relatively new, and most commercially available powered prostheses are typically limited to 1 to 3 degrees of freedom. Due to the myriad of possible options for various powered protheses from different manufacturers, each configuration is governed by a distinct control scheme typically specific to the …

"Authors On The Hill " Presents Prof. Giovanni Spani, Giovanni Spani

Authors on the Hill

Professor Giovanni Spani of the World Languages, Literatures, and Cultures Department at the College of the Holy Cross will present his work on Dante's Florence, a multimedia educational app for Android and iOS.

Controlling Aircraft Yaw Movement By Interval Type-2 Fuzzy Logic, Yamama Shafeek, Laith Majeed, Rasha Naji

Emirates Journal for Engineering Research

Aircraft yaw movement is essential in maneuvering; it has been controlled by some methods which achieved tracking but not fast enough. This paper performs the dynamic modeling of aircraft yaw movement and develops PI and PI-like interval type-2 fuzzy logic controller for the model. The mathematical model is derived by inserting the parameters values of single-engine Navion aircraft into standard equations. Using Matlab/ Simulink platform, the controllers' effectivity is tested and verified in two different cases; system without disturbance and when system is disturbed by some wind gust to investigate the system robustness. Simulation results show that PI controller response …

Towards Increasing Trust In Expert Evidence Derived From Malware Forensic Tools, Ian M. Kennedy, Blaine Price, Arosha Bandara

Journal of Digital Forensics, Security and Law

Following a series of high profile miscarriages of justice in the UK linked to questionable expert evidence, the post of the Forensic Science Regulator was created in 2008. The main objective of this role is to improve the standard of practitioner competences and forensic procedures. One of the key strategies deployed to achieve this is the push to incorporate a greater level of scientific conduct in the various fields of forensic practice. Currently there is no statutory requirement for practitioners to become accredited to continue working with the Criminal Justice System of England and Wales. However, the Forensic Science Regulator …