Digital Commons Network^™

Classifying Classic Ciphers Using Machine Learning, Nivedhitha Ramarathnam Krishna

Master's Projects

We consider the problem of identifying the classic cipher that was used to generate a given ciphertext message. We assume that the plaintext is English and we restrict our attention to ciphertext consisting only of alphabetic characters. Among the classic ciphers considered are the simple substitution, Vigenère cipher, playfair cipher, and column transposition cipher. The problem of classification is approached in two ways. The first method uses support vector machines (SVM) trained directly on ciphertext to classify the ciphers. In the second approach, we train hidden Markov models (HMM) on each ciphertext message, then use these trained HMMs as features …

Machine Learning Versus Deep Learning For Malware Detection, Parth Jain

Master's Projects

It is often claimed that the primary advantage of deep learning is that such models can continue to learn as more data is available, provided that sufficient computing power is available for training. In contrast, for other forms of machine learning it is claimed that models ‘‘saturate,’’ in the sense that no additional learning can occur beyond some point, regardless of the amount of data or computing power available. In this research, we compare the accuracy of deep learning to other forms of machine learning for malware detection, as a function of the training dataset size. We experiment with a …

Earmarked Utxo For Escrow Services And Two-Factor Authentication On The Blockchain, Jisha Pillai

Master's Projects

The security of accounts on the blockchain relies on securing private keys, but they are often lost or compromised due to loopholes in key management strategies or due to human error. With an increasing number of thefts in the last few years due to compromised wallets, the security of digital currency has become a significant concern, and no matter how sophisticated and secure mechanisms are put in place to avoid the security risks, it is impossible to achieve a 100% human compliance.

This project introduces a novel concept of Earmarked Unspent Transaction Outputs (EUTXOs). EUTXOs enable every user on the …

Classification Of Malware Models, Akriti Sethi

Master's Projects

Automatically classifying similar malware families is a challenging problem. In this research, we attempt to classify malware families by applying machine learning to machine learning models. Specifically, we train hidden Markov models (HMM) for each malware family in our dataset. The resulting models are then compared in two ways. First, we treat the HMM matrices as images and experiment with convolutional neural networks (CNN) for image classification. Second, we apply support vector machines (SVM) to classify the HMMs. We analyze the results and discuss the relative advantages and disadvantages of each approach.

Ai Dining Suggestion App, Bao Pham

Master's Projects

Trying to decide what to eat can sometimes be challenging and time-consuming for people. Google and Yelp have large scale data sets of restaurant information as well as Application Program Interfaces (APIs) for using them. This restaurant data includes time, price range, traffic, temperature, etc. The goal of this project is to build an app that eases the process of finding a restaurant to eat. This app has a Tinder-like user friendly User Interface (UI) design to change the common way that lists of restaurants are presented to users on mobile apps. It also uses the help of Artificial Intelligence …

Real-Time Data Processing With Lambda Architecture, Omkar Ashok Malusare

Master's Projects

Data has evolved immensely in recent years, in type, volume and velocity. There are several frameworks to handle the big data applications. The project focuses on the Lambda Architecture proposed by Marz and its application to obtain real-time data processing. The architecture is a solution that unites the benefits of the batch and stream processing techniques. Data can be historically processed with high precision and involved algorithms without loss of short-term information, alerts and insights. Lambda Architecture has an ability to serve a wide range of use cases and workloads that withstands hardware and human mistakes. The layered architecture enhances …

Human Activity Recognition Based On Multimodal Body Sensing, Anish Hemant Narkhede

Master's Projects

In the recent years, human activity recognition has been widely popularized by a lot of smartphone manufacturers and fitness tracking companies. It has allowed us to gain a deeper insight into our physical health on a daily basis. However, with the evolution of fitness tracking devices and smartphones, the amount of data that is being captured by these devices is growing exponentially. This paper aims at understanding the process of dimensionality reduction such as PCA so that the data can be used to make meaningful predictions along with novel techniques using autoencoders with different activation functions. The paper also looks …

Javascript Metamorphic Malware Detection Using Machine Learning Techniques, Aakash Wadhwani

Master's Projects

Various factors like defects in the operating system, email attachments from unknown sources, downloading and installing a software from non-trusted sites make computers vulnerable to malware attacks. Current antivirus techniques lack the ability to detect metamorphic viruses, which vary the internal structure of the original malware code across various versions, but still have the exact same behavior throughout. Antivirus software typically relies on signature detection for identifying a virus, but code morphing evades signature detection quite effectively.

JavaScript is used to generate metamorphic malware by changing the code’s Abstract Syntax Tree without changing the actual functionality, making it very difficult …

Topic Classification Using Hybrid Of Unsupervised And Supervised Learning, Jayant Shelke

Master's Projects

There has been research around the idea of representing words in text as vectors and many models proposed that vary in performance as well as applications. Text processing is used for content recommendation, sentiment analysis, plagiarism detection, content creation, language translation, etc. to name a few. Specifically, we want to look at the problem of topic detection in text content of articles/blogs/summaries. With the humungous amount of text content published each and every minute on the internet, it is imperative that we have very good algorithms and approaches to analyze all the content and be able to classify most of …

Multifamily Malware Models, Samanvitha Basole

Master's Projects

When training a machine learning model, there is likely to be a tradeoff between the accuracy of the model and the generality of the dataset. Previous research has shown that if we train a model to detect one specific malware family, we obtain stronger results as compared to a case where we train a single model on multiple diverse families. During the detection phase, it would be more efficient to have a single model that could detect multiple families, rather than having to score each sample against multiple models. In this research, we conduct experiments to quantify the relationship between …

Archeota, Spring 2019, Sarah Thornton, Megan Price, Francis A. Alix, Anna Belle Rosen, Kelsey Clark, David Ballantine, Kelli Roisman, Rachel Galindo, Danielle Dantema

Archeota

This is the Spring 2019 issue of Archeota, the official publication of SJSU SAASC.

Archeota is a platform for students to contribute to the archival conversation. It is written BY students, FOR students. It provides substantive content on archival concerns and issues, and promotes career development in the field of archival studies. Archeota upholds the core values of the archival profession. It is a semiannual publication of the Student Chapter of the Society of American Archivists at the San Jose State University School of Information.

Promising Truths, In Fiction & Teaching: Sincerity, Scott Jarvie

Faculty Research, Scholarly, and Creative Activity

No abstract provided.

Detection Of Hate Speech In Videos Using Machine Learning, Unnathi Bhandary

Master's Projects

With the progression of the internet and social media, people are given multiple platforms to share their thoughts and opinions about various subject matters freely. However, this freedom of speech is misused to direct hate towards individuals or group of people due to their race, religion, gender etc. The rise of hate speech has led to conflicts and cases of cyber bullying, causing many organizations to look for optimal solutions to solve this problem.

Developments in the field of machine learning and deep learning have piqued the interest of researchers, leading them to research and implement solutions to solve the …

Sensor - Based Human Activity Recognition Using Smartphones, Mustafa Badshah

Master's Projects

It is a significant technical and computational task to provide precise information regarding the activity performed by a human and find patterns of their behavior. Countless applications can be molded and various problems in domains of virtual reality, health and medical, entertainment and security can be solved with advancements in human activity recognition (HAR) systems. HAR is an active field for research for more than a decade, but certain aspects need to be addressed to improve the system and revolutionize the way humans interact with smartphones. This research provides a holistic view of human activity recognition system architecture and discusses …

Image Retrieval Using Image Captioning, Nivetha Vijayaraju

Master's Projects

The rapid growth in the availability of the Internet and smartphones have resulted in the increase in usage of social media in recent years. This increased usage has thereby resulted in the exponential growth of digital images which are available. Therefore, image retrieval systems play a major role in fetching images relevant to the query provided by the users. These systems should also be able to handle the massive growth of data and take advantage of the emerging technologies, like deep learning and image captioning. This report aims at understanding the purpose of image retrieval and various research held in …

Awareness Of E-Journals Among Library Users In University Of Delhi And Babasaheb Bhimrao Ambedkar University, Lucknow: A Study, Divyanshu Gupta, Manir Uddin Ansari

Library Philosophy and Practice (e-journal)

In this digital environment, the use of electronic resources is very common and as of today almost all the libraries compatible with electronic resources. Both the Universities has the collection open as well as the subscribed database. The present study is on the use of e-journals by the research scholars in the libraries of the University of Delhi (DU) and Babasaheb Bhimrao Ambedkar University (BBAU), Lucknow. It is intended to evaluate the purpose, types, problems in assessing the e-journals. The finding of the study revealed that a greater number of users from both the university use e-journals for their study …

Awareness, Accessibility And Factors Hindering Utilization E-Journals At The Institute Of Finance Management, Tanzania, Christian Michael Mubofu

Library Philosophy and Practice (e-journal)

This study focused on the awareness, accessibility and factors hindering the utilization of e-journals at the Institute of Finance Management. Specifically the study sought to identify the level of awareness, accessibility and factors affecting students and academic staff in utilizing the e-journals. To achieve these objectives the study employed mixed method research designs in which in-depth interviews and questionnaire were used to collect data from a sample of 141respondents i.e. 100 students and 41 academic staff. The surveyed data has been analysed by using SPSS (20.0) and content analysis for quantitative and qualitative data has been undertaken respectively. Table presentations …

Research Contributions And Utilization Of Researchgate By Central Universities In India: An Analytical Study, Jeyapragash Balasubramani, Rajkumar Thangavel

Library Philosophy and Practice (e-journal)

This paper examines the research contributions and utilization of ResearchGate by Central Universities in India. The study considered only Central Universities in India which are listed in UGC website. A total of 49 Central Universities available in India only 45 universities are contributed their research activities in ResearchGate. Further the data was analyzed by ResearchGate (RG) scores, memberships, publications, research contribution wise top ten universities and top ten members in ResearchGate by central universities in India. It is found that the University of Delhi has highest (21338.47) RG score, 3868 members with 8906 publications and Banaras Hindu University” has …

Awareness And Use Of Social Networking Sites Among The Physically Challenged Students Of Alagappa University Its Affliated Colleges In Sivagangai District, A Study, Raja M, Ganesan P

Library Philosophy and Practice (e-journal)

The study analysed awareness and use of social networking sites among the physically challenged students of alagappa university its affliated colleges in sivaganga districts, a study (69.5%) respondents were male, , 31.52 percentage of them are in the age group of 26 -30, 55.28% majority of respondents belong to the rural area, majority (37.15) of the respondents are doing 1^st year, majority the respondents has UG degree of studying in 33.33 %of them are in the respondents 35. (54.28) of the respondents are using Crutches, 73.33% of the respondents are regularly using the university library, the majority (89.52) of …

An Analysis Of Indian Research Information Network System (Irins), Jeyapragash Balasubramani, Muthuraj Anbalagan, Kannan Palavesam

Library Philosophy and Practice (e-journal)

Indian Research Information Network System (IRINS) developed by the Central University of Punjab, Bathinda in collaboration with Information and Library Network Centre (INFLIBNET) which can be used for higher education institution and research institutions to showcase the research contribution to the scholarly community. The data were taken from Indian Research Information Network System (http://irins.org/irins/) of 15 instances for the Academic and Research Organisations. The objectives of the article is to analyze the faculty members, department and their scholarly publications with citations and its impact. It is found that KL University, Guntur has highest 836 (17.22%) faculty member. The …

Citations V/S Altmetric Attention Score: A Comparison Of Top 10 Highly Cited Papers In Nature, Rajendra Babu, Rajendra Babu, Vysakh C

Library Philosophy and Practice (e-journal)

This study aims to analyze the correlation between citations and altmetric score of top 10 highly cited papers in Nature by extracting the data from Google metrics. It tries to investigate whether a highly cited paper has high altmetric score or not by using correlation method and the result show that there exists a high correlation. The study found that Mendeley is the main medium through which scientific papers are being disseminated more and contributing to the altmetric score intensely. The country wise tweeting data show that U.S and U.K holds the first and second position in tweeting with 1143 …

Vedic Education: The Only Means To Realise Sarvam Khalu Idam Brahman, Vandana Sharma

Library Philosophy and Practice (e-journal)

___________________________

[1] Hindustan Times, By Leena Dhankhar, 13^th November 2018

² Hindustan Times, 3^rd November 2018

³ The Deccan Chronicles, by Sonali Telang, 20^th November 2018

⁴ Times of India, 21^st October 2018

⁵ Hindustan Times, 30^th August 2017

Today we live in constant fear of being victims or witnessing someone being a victim. Such is the condition of our society. Leave alone the world and let’s merely concentrate upon what India is facing in today’s time. On November 13, 2018 a 3 year old girl was raped in Gurugram and was later put to …

E-Learning In Lis Education In India: Status And Efforts For Improvement, Ankit Mishra

Library Philosophy and Practice (e-journal)

The paper portrays the need for e-learning condition in LIS training and major an e-learning system for LIS training all through the world. It features the significant difficulties to look before the LIS experts to adapt up to the changing essence of the e-learning condition for LIS training. It likewise proposes a few suggestions to survive and confront difficulties. A short history of e-learning is given which is trailed by the activities which the legislature has taken to give instruction through advanced mode. The organizations which are giving e-learning courseware are examined alongside the portrayal of LIS courses which they …

Benchmarking Scalability Of Nosql Databases For Geospatial Queries, Yuvraj Singh Kanwar

Master's Projects

NoSQL databases provide an edge when it comes to dealing with big unstructured data. Flexibility, agility, and scalability offered by NoSQL databases become increasingly essential when dealing with geospatial data. The proliferation of geospatial applications has tremendously increased the variety, velocity, and volume of data that the data stores must manage. Such characteristics of big spatial data surpassed the capability and anticipated use cases of relational databases. Because we can choose from an extensive collection of NoSQL databases these days, it becomes vital for organizations to make an informed decision. NoSQL Database benchmarks provide system architects, who shoulder a considerable …

Role And Impact Of E-Journals: A Case Study Of University Institute Of Engineering And Technology (Uiet), Kurukshetra University, Sukhbir Singh, Neha Garg, Dr. Chetan Sharma

Library Philosophy and Practice (e-journal)

Present study aims to determine the use and awareness of e-journals among teachers and research scholars of University Institute of Engineering and Technology (UIET). Study also targets to define the purpose of e-journals’ use, access place, preferred format and frequency to use. Data was collected from 60 users of different departments of UIET. Study indicates that majority of the respondents use e-journals for their research assignments, they prefer to retrieve e-resources mainly through simple search techniques such as key word, author and title.

Decomposition Of Pig Carcasses At Varying Room Temperature, Jacqueline Abad Santos

Themis: Research Journal of Justice Studies and Forensic Science

The goal of this study is to assess the qualitative scoring of decomposition scales with statistical analysis while also determining which indoor environment will decompose the fastest. When comparing the three indoor environments, water decomposition appears to be the fastest, but the method of analysis for this study determines that using decomposition scales to analyze such environments may produce statistically insignificant results. For this study, piglets were put in a dry steel tub, a water filled steel tub, and a suitcase. These were recorded using photographs for 25 days and then scored using decomposition scales. The total score was divided …

Scientific Evidence Admissibility: Improving Judicial Proceedings To Decrease Erroneous Outcomes, Leica Kwong

Themis: Research Journal of Justice Studies and Forensic Science

In the United States, Federal Rules of Evidence 702, the Frye and Daubert standards govern the admissibility of scientific evidence in the courtroom. Some states adopted Frye while others adopted Daubert, causing varying judicial outcomes. The verdicts in some cases may be erroneous due to a nationally used standard. Frye has broad criteria of requiring scientific evidence to be generally accepted. While Daubert contains more requirements for the evidence to be admissible, such as peer review, publication, and scientific principles. Daubert, alongside FRE 702, provides a thorough guideline for trial judges who have the gatekeeping role to decide admissibility aiming …

Precursors Of School Shootings, Branden Harrington

Themis: Research Journal of Justice Studies and Forensic Science

This paper analyzes mass school shootings in the United States, stressing their root causes, indicators, demographics, and suggestive guidelines for preventable measures. Data draws associations between bullying, social dominance, and devalued masculinity amongst high school boys. Further, these trends emphasize homophobic harassment and the reassertion of lost dominance through violence. Moreover, research upholds media coverage and self-absorbed behavior as an additional precursor for inspired acts of malice. Journalistic representations of mass school shootings are identified as a source of motivation for vengeful and easily malleable youth. Studies also stress the importance of school inclusivity and interconnectedness, emitting a stark correlation …

Physical Match: Uniqueness Of Torn Paper, Marilyn Aguilar

Themis: Research Journal of Justice Studies and Forensic Science

In the forensic science field, it is generally accepted that all tears and fractures are unique; however, there is limited scientific evidence to support this. This study tests the claim that all tears are unique, focusing on paper. One-hundred Office Depot brand 3” x 5” blank, white index cards were torn in half by hand. Six halves were randomly removed; the remaining 94 halves were mixed and then matched by a novice using end-match analysis. The removal of the 6 random halves left 44 matching pairs. Of the remaining halves, all 44 pairs were correctly matched. The results show that …

Novice Ideas: Handwriting Comparisons Conducted By An Untrained Individual, Maia Lister

Themis: Research Journal of Justice Studies and Forensic Science

Forensic analysis of questioned documents includes chemical analyses of paper and ink as well as handwriting comparisons. Several elements affect handwriting analyses, including the presence of discriminatory factors that can individualize a handwriting sample and whether the handwriting has been disguised. Five handwriting samples were gathered from six individuals comprising of one reference, three natural unknowns, and one disguised sample per person. A novice conducted analyses on every collected sample and conducted comparisons of the reference sample to the unknown and disguised samples in an attempt to correctly source the unknown and disguised samples. The novice showed a high level …