Performance Analysis Of Whale Optimization Based Data Clustering, Ahamed Shafeeq B M, Zahid Ahmed Ansari, Shyam Karanth

Future Computing and Informatics Journal

Data clustering is the method of gathering of data points so that the more similar points will be in the same group. It is a key role in exploratory data mining and a popular technique used in many fields to analyze statistical data. Quality clusters are the key requirement of the cluster analysis result. There will be tradeoffs between the speed of the clustering algorithm and the quality of clusters it produces. Both the quality and speed criteria must be considered for the state-of-the-art clustering algorithm for applications. The Bio-inspired technique has ensured that the process is not trapped in …

Multilayer Perceptron With Auto Encoder Enabled Deep Learning Model For Recommender Systems, Subhashini Narayan

Future Computing and Informatics Journal

In this modern world of ever-increasing one-click purchases, movie bookings, music, health- care, fashion, the need for recommendations have increased the more. Google, Netflix, Spotify, Amazon and other tech giants use recommendations to customize and tailor their search engines to suit the user’s interests. Many of the existing systems are based on older algorithms which although have decent accuracies, require large training and testing datasets and with the emergence of deep learning, the accuracy of algorithms has further improved, and error rates have reduced due to the use of multiple layers. The need for large datasets has declined as well. …

Deep Feature Learning For Fog Episodes Prediction In Patients With Pd, Hadeer Elziaat, Nashwa El-Bendary, Ramdan Mowad

Future Computing and Informatics Journal

A common symptom of Parkinson's Disease is Freezing of Gait (FoG) that causes an interrupt of the forward progression of the patient’s feet while walking. Therefore, Freezing of Gait episodes is always engaged to the patient's falls. This paper proposes a model for Freezing of Gait episodes detection and prediction in patients with Parkinson's Disease. Predicting Freezing of Gait in this paper considers as a multi-class classification problem with 3 classes namely, FoG, pre-FoG, and walking episodes. In this paper, the extracted feature scheme applied for the detection and the prediction of FoG is Convolutional Neural Network (CNN) spectrogram time-frequency …

A Literature Review For Contributing Mining Approaches For Business Process Reengineering, Noha Ahmed Bayomy Nab, Ayman E. Khedr Aek, Laila A. Abd-Elmegid Laa, Amira M. Idrees Ami

Future Computing and Informatics Journal

Due to the changing dynamics of the business environment, organizations need to redesign or reengineer their business processes in order to provide services with the lowest cost and shortest response time while increasing quality. Thence, Business Process Re-engineering (BPR) provides a roadmap to achieve operational goals that leads to enhance flexibility and productivity, cost reduction, and quality of service/product. In this paper, we propose a literature review for the different proposed models for Business Process Reengineering. The models specify where the breakdowns occur in BPR implementation, justifies why such breakdowns occur, and propose techniques to prevent their occurrence again. The …

Bibliometric Survey On Flood Prediction Using Machine Learning, Seema Patil Prof., Daksh Khurana Mr., Kartik Rao Mr, Priyanshu Meena Mr, Shivendra Singh Mr

Library Philosophy and Practice (e-journal)

Floods are one of the most devastating natural hazards, and modelling them is extremely difficult. Flood prediction model advancement study led to factors such as loss of human and animal life, property damage, and risk mitigation. The focus of this bibliometric survey is to recognise the few studies which have upheld on the factors affecting the floods. The analysis is done based on 254 documents such as articles, conference papers, article reviews and some reviews and notes. India contributes to the maximum number of documents followed by China and the United States of America. This bibliometric survey is conducted using …

A Collaborative Knowledge-Based Security Risk Assessments Solution Using Blockchains, Tara Thaer Salman

McKelvey School of Engineering Graduate Student Theses & Dissertations

Artificial intelligence and machine learning have recently gained wide adaptation in building intelligent yet simple and proactive security risk assessment solutions. Intrusion identification, malware detection, and threat intelligence are examples of security risk assessment applications that have been revolutionized with these breakthrough technologies. With the increased risk and severity of cyber-attacks and the distributed nature of modern threats and vulnerabilities, it becomes critical to pose a distributed intelligent assessment solution that evaluates security risks collaboratively. Blockchain, as a decade-old successful distributed ledger technology, has the potential to build such collaborative solutions. However, in order to be used for such solutions, …

A Bibliometric Perspective Survey Of Iot Controlled Ai Based Swarm Robots, Rhea Sawant, Ariz Shaikh, Chetna Singh, Aman Aggarwal, Shivali Amit Wagle, Harikrishnan R, Priti Shahane

Library Philosophy and Practice (e-journal)

Robotics is the ­new-age domain of technology that deals with bringing a collaboration of all disciplines of sciences and engineering to create a mechanical machine that may or may not work entirely independently but definitely focuses on making human lives much easier. It has repeatedly shown its ability to change lives at home and in the industry. As the field of robotics research grows and reaches new worlds, the military is one area where advances can have a significant impact, and the government is aware of this. Military technology has come a long way from the days where soldiers had …

Designing Ai For Explainability And Verifiability: A Value Sensitive Design Approach To Avoid Artificial Stupidity In Autonomous Vehicles, Steven Umbrello, Roman V. Yampolskiy

Faculty and Staff Scholarship

One of the primary, if not most critical, difficulties in the design and implementation of autonomous systems is the black-boxed nature of the decision-making structures and logical pathways. How human values are embodied and actualised in situ may ultimately prove to be harmful if not outright recalcitrant. For this reason, the values of stakeholders become of particular significance given the risks posed by opaque structures of intelligent agents. This paper explores how decision matrix algorithms, via the belief-desire-intention model for autonomous vehicles, can be designed to minimize the risks of opaque architectures. Primarily through an explicit orientation towards designing for …

Breast Cancer Detection From Histopathology Images Using Machine Learning Techniques: A Bibliometric Analysis, Shubhangi A. Joshi, Anupkumar M. Bongale Dr., Arunkumar M. Bongale Dr.

Library Philosophy and Practice (e-journal)

Computer aided diagnosis has become upcoming area of research over past few years. With the advent of machine learning and especially deep learning techniques, the scenario of work flow management in healthcare sector is changing drastically. Artificial intelligence has shown potential in the field of breast cancer care. With datasets for machine learning frameworks getting eventually richer with time, we can definitely get newer insights in the field of breast cancer care. This will help in narrowing down the treatment range for patients and increasing patient survivability. The purpose of this study was to perform bibliometric analysis of the literature …

Physical Layer Security Of The Internet Of Things: Modeling And Analysis, Ali Alsadi

Theses and Dissertations

Motivated by the fifth generation of mobile networks, the Internet of Things (IoT) has emerged as one of the most promising and interesting technologies that are currently evolving IoT, which is expected to be deployed on a large-scale beyond 2020. However, this technology's main drawback is the security issue due to the variety of network access technologies and the wireless medium's nature. Thus, in the last decade, considerable efforts were expended to address this issue. However, much of the work has focused on the data link and upper layers, and much less attention has been given to the physical layer …

Smart E-Bike Conversion Kit And Helmet, Megan West, Marena Trujillo, Hossein Asghari

Honors Thesis

With many state governments across the United States implementing shutdowns to prevent the spread of COVID-19, many bike retailers have seen dramatic increases in bike sales. Electric bicycles (e-bikes) have become increasingly popular as the public searches for alternatives to public transportation. Unfortunately, e-bike users assume some risk by riding bikes that are faster than conventional bicycles. While kits to convert conventional bicycles to e-bikes exist, no “smart” e-bike/helmet kit specifically designed to keep the user safe is currently available on the market. To mitigate risks, a smart e-bike conversion kit with multiple novel safety features, including auditory and visual …

Decentralized Aggregation Design And Study Of Federated Learning, Venkata Naga Surya Sameeraja Malladi

Master of Science in Software Engineering Theses

The advent of machine learning techniques has given rise to modern devices with built-in models for decision making and providing rich content to users. This typically involves processing huge volumes of data in central servers and sending updated models to end-user devices. There are two main concerns on this server architecture, one is the privacy of data that is being transferred to a central server and the other is volumes of data sent over the network for the model update. Federated Learning helps solve these problems by training models on local data within the device and aggregating the model with …

Blockchain-Based Healthcare Portal – A Bibliometric Analysis, Aditi Goyal, Aditya Banerjee, Aniket Mulik, Yashika Chhabaria, Sonali Kothari Tidke Dr, Vijayshri Khedkar

Library Philosophy and Practice (e-journal)

User privacy has been a topmost priority and one such domain where this is neglected is the area of healthcare. Our solution focuses on the idea of using blockchain to provide a platform for healthcare experts and patients, giving patients full control over the data that will be shared. This paper focuses on identifying current research that has been conducted in this area in the form of a bibliometric analysis. A bibliometric study on a research area involves a detailed analysis of citations and papers across a domain of study. The purpose of this study is a statistical analysis of …

Redai: A Machine Learning Approach To Cyber Threat Intelligence, Luke Noel

Masters Theses, 2020-current

The world is continually demanding more effective and intelligent solutions and strategies to combat adversary groups across the cyber defense landscape. Cyber Threat Intelligence (CTI) is a field within the domain of cyber security that allows for organizations to utilize threat intelligence and serves as a tool for organizations to proactively harden their defense posture. However, there is a large volume of CTI and it is often a daunting task for organizations to effectively consume, utilize, and apply it to their defense strategies. In this thesis we develop a machine learning solution, named RedAI, to investigate whether open-source intelligence (OSINT) …

Artificial Intelligence And The Ethics Behind It, Isaac Johnston

Senior Honors Theses

Artificial intelligence (AI) has been a widely used buzzword for the past couple of years. If there is a technology that works without human interaction, it is labeled as AI. But what is AI, and should individuals be concerned? The following research aims to define what artificial intelligence is, specifically machine learning (ML) and neural networks. It is important to understand how AI is used today in cars, image recognition, ad marketing, and other areas. Although AI has many benefits, there are areas of ethical concerns such as autonomous cars, military applications, social media marketing, and others. This paper helps …

Rethink Everything 2: Markets, Globalization, Development, Nikhilesh Dholakia, Deniz Atik

Markets, Globalization & Development Review

No abstract provided.

Multi-Scale, Class-Generic, Privacy-Preserving Video, Zhixiang Zhang, Thomas Cilloni, Charles Walter, Charles Fleming

Faculty and Student Publications

In recent years, high-performance video recording devices have become ubiquitous, posing an unprecedented challenge to preserving personal privacy. As a result, privacy-preserving video systems have been receiving increased attention. In this paper, we present a novel privacy-preserving video algorithm that uses semantic segmentation to identify regions of interest, which are then anonymized with an adaptive blurring algorithm. This algorithm addresses two of the most important shortcomings of existing solutions: it is multi-scale, meaning it can identify and uniformly anonymize objects of different scales in the same image, and it is class-generic, so it can be used to anonymize any class …

Malicious Hardware & Its Effects On Industry, Gustavo Perez

Computer Science and Computer Engineering Undergraduate Honors Theses

In recent years advancements have been made in computer hardware security to circumnavigate the threat of malicious hardware. Threats come in several forms during the development and overall life cycle of computer hardware and I aim to highlight those key points. I will illustrate the various ways in which attackers exploit flaws in a chip design, or how malicious parties take advantage of the many steps required to design and fabricate hardware. Due to these exploits, the industry and consumers have suffered damages in the form of financial loss, physical harm, breaches of personal data, and a multitude of other …

Fast Flow Reconstruction Via Robust Invertible N X N Convolution, Thanh-Dat Truong, Chi Nhan Duong, Minh-Triet Tran, Ngan Le, Khoa Luu

Computer Science and Computer Engineering Faculty Publications and Presentations

Flow-based generative models have recently become one of the most efficient approaches to model data generation. Indeed, they are constructed with a sequence of invertible and tractable transformations. Glow first introduced a simple type of generative flow using an invertible 1x1 convolution. However, the 1x1 convolution suffers from limited flexibility compared to the standard convolutions. In this paper, we propose a novel invertible n x n convolution approach that overcomes the limitations of the invertible 1x1 convolution. In addition, our proposed network is not only tractable and invertible but also uses fewer parameters than standard convolutions. The experiments on CIFAR-10, …

Data Forgery Detection In Automatic Generation Control: Exploration Of Automated Parameter Generation And Low-Rate Attacks, Yatish R. Dubasi

Computer Science and Computer Engineering Undergraduate Honors Theses

Automatic Generation Control (AGC) is a key control system utilized in electric power systems. AGC uses frequency and tie-line power flow measurements to determine the Area Control Error (ACE). ACE is then used by the AGC to adjust power generation and maintain an acceptable power system frequency. Attackers might inject false frequency and/or tie-line power flow measurements to mislead AGC into falsely adjusting power generation, which can harm power system operations. Various data forgery detection models are studied in this thesis. First, to make the use of predictive detection models easier for users, we propose a method for automated generation …

Neural Network With Nlp, Harshita Sharma, Tinkle Jain

School of Professional Studies

This thesis is about neural networks and how their algorithmic systems work. Neural networks are well-suited to aiding people with complex challenges in real-world situations. Thesis topics include nonlinear and complicated interactions between inputs and outputs, as well as making inferences, discovering hidden links, patterns, and predictions, and modeling highly volatile data and variations to forecast uncommon events. Neural networks have the potential to help people make better decisions. NLP is a technique for analyzing, interpreting, and comprehending large amounts of text. We can no longer evaluate the text using traditional approaches due to the massive volumes of text data …

Automated Bottling Station - Packaging System, Lauren Nicole Zinzilieta

Honors College Theses

This report focuses on the packaging system used at the end of the FESTO bottling station that is located in EP 2355. The system will be made up of an x-y 300 mm x 300 mm gantry system, an Arduino, two micro-stepping stepper drivers, and two 152.4 mm (6 in) single acting cylinders with a 3D printed bracket attached to both. The gantry system will be located at the end of the conveyor belt and will be programmed to pick up three bottles at a time and then will move a specified number of steps in both the x and …

Stand-Alone Direct Current Power Network Based On Photovoltaics And Lithium-Ion Batteries For Reverse Osmosis Desalination Plant, Vishwas Powar, Rajendra Singh

Publications

Plummeting reserves and increasing demand of freshwater resources have culminated into a global water crisis. Desalination is a potential solution to mitigate the freshwater shortage. However, the process of desalination is expensive and energy-intensive. Due to the water-energy-climate nexus, there is an urgent need to provide sustainable low-cost electrical power for desalination that has the lowest impact on climate and related ecosystem challenges. For a large-scale reverse osmosis desalination plant, we have proposed the design and analysis of a photovoltaics and battery-based stand-alone direct current power network. The design methodology focusses on appropriate sizing, optimum tilt and temperature compensation techniques …

Nonlinearity In Piezotransistive Iii-Nitride Resonant Microcantilevers, Ferhat Bayram

All Dissertations

Microcantilevers are an important form of microelectromechanical systems (MEMS) and have been widely used in notable applications including bio sensing, chemical detection, and imaging. Traditionally, laser based optical read-out systems have been used to measure amplitudes of the microcantilever tip oscillations (i.e. in an atomic force microscope (AFM)). However, this technique has several drawbacks including high power requirements and bulkiness that prevent commercializing of microcantilevers based miniaturized sensors. Monitoring oscillations of a cantilever array then also becomes immensely challenging. To overcome these problems, microcantilevers with integrated piezoresistive and piezotransistive deflection transducers have been developed. Because of issues related to piezoresistive …

Performance Enhancement Of Time Delay And Convolutional Neural Networks Employing Sparse Representation In The Transform Domains, Masoumeh Kalantari Khandani

Electronic Theses and Dissertations, 2020-2023

Deep neural networks are quickly advancing and increasingly used in many applications; however, these networks are often extremely large and require computing and storage power beyond what is available in most embedded and sensor devices. For example, IoT (Internet of Things) devices lack powerful processors or graphical processing units (GPUs) that are commonly used in deep networks. Given the very large-scale deployment of such low power devices, it is desirable to design methods for efficient reduction of computational needs of neural networks. This can be done by reducing input data size or network sizes. Expectedly, such reduction comes at the …

Heterogeneous Graph-Based User-Specific Review Helpfulness Prediction, Dongkai Chen

Dartmouth College Master’s Theses

With the popularity of e-commerce and review websites, it is becoming increasingly important to identify the helpfulness of reviews. However, existing works on predicting reviews’ helpfulness have three major issues: (i) the correlation between helpfulness and features from review text is not clear yet, although many standard features are proposed, (ii) the relations between users, reviews and products have not been considered, (iii) the effectiveness of the existing approaches have not been systematically compared. To address these challenges, we first analyze the correlation between standard features and review helpfulness that are widely used in other work. Based on this analysis, …

The Future Of Artificial Intelligence, Alex Guerra

Emerging Writers

Whether we like it or not Artificial Intelligence (AI) is coming, and we are not ready for it. AI has unimaginable potential and will revolutionize the world over the next few decades, but with this great potential we are faced with choices that could prove detrimental to humanity. This article examines the challenges AI presents and explores possible solutions to make AI align with human interests.

Machine Learning-Based Recognition On Crowdsourced Food Images, Aditya Kulkarni

Honors Scholar Theses

With nearly a third of the world’s population suffering from food-induced chronic diseases such as obesity, the role of food in community health is required now more than ever. While current research underscores food proximity and density, there is a dearth in regard to its nutrition and quality. However, recent research in geospatial data collection and analysis as well as intelligent deep learning will help us study this further.

Employing the efficiency and interconnection of computer vision and geospatial technology, we want to study whether healthy food in the community is attainable. Specifically, with the help of deep learning in …

A Study Of Deep Reinforcement Learning In Autonomous Racing Using Deepracer Car, Mukesh Ghimire

Honors Theses

Reinforcement learning is thought to be a promising branch of machine learning that has the potential to help us develop an Artificial General Intelligence (AGI) machine. Among the machine learning algorithms, primarily, supervised, semi supervised, unsupervised and reinforcement learning, reinforcement learning is different in a sense that it explores the environment without prior knowledge, and determines the optimal action. This study attempts to understand the concept behind reinforcement learning, the mathematics behind it and see it in action by deploying the trained model in Amazon's DeepRacer car. DeepRacer, a 1/18^th scaled autonomous car, is the agent which is trained …

A Framework To Detect The Susceptibility Of Employees To Social Engineering Attacks, Hashim H. Alneami

Doctoral Dissertations and Master's Theses

Social engineering attacks (SE-attacks) in enterprises are hastily growing and are becoming increasingly sophisticated. Generally, SE-attacks involve the psychological manipulation of employees into revealing confidential and valuable company data to cybercriminals. The ramifications could bring devastating financial and irreparable reputation loss to the companies. Because SE-attacks involve a human element, preventing these attacks can be tricky and challenging and has become a topic of interest for many researchers and security experts. While methods exist for detecting SE-attacks, our literature review of existing methods identified many crucial factors such as the national cultural, organizational, and personality traits of employees that enable …