Search Constraints
Filtering by:
Campus
Sacramento
Remove constraint Campus: Sacramento
Department
Computer Science
Remove constraint Department: Computer Science
Number of results to display per page
Search Results
- Creator:
- Bavishi, Ujaliben Kalpesh
- Description:
- This project is focusing on creating a chatbot to be used by students to get their queries responded easily from the college website. The College Enquiry Chatbot has the capacity to make friendly conversations; respond the course and faculty details; give the link for the academic calendar; answer the frequently asked questions; calculate the fees based on the student's input; and give the timings, address, contacts, and events information of the departments like Union, Library, IPGE, and AIRC. To build the chatbot, Microsoft Azure bot service as well as Microsoft cognitive services, namely, Text Analytics, LUIS, and QnA Maker are used. Most of the existing chatbots lack empathy and fail to accommodate anything outside of the script. In order to address these problems, the College Enquiry Chatbot extends the implementation of the current chatbots by adding sentiment analysis and active learning. Although, sentimental analysis correctly recognizes the user's query as positive, negative and neutral, the system was partially successful in adding empathy to the chatbot. It is because the system requires more rigorous training data to handle all queries which are off-script. However, for such queries, active learning helps to improve the chatbot performance since it correctly understands the user's questions, asks clarifying question, and then retrains the system to give the response what the user intends to get. The future work include training the chatbot with more varied data; increasing the scope of the chatbot by adding a speech recognition feature so that users can speak to get responses; and including integration with multiple channels such as phone call, SMS, and various social media platforms.
- Resource Type:
- Project
- Campus Tesim:
- Sacramento
- Department:
- Computer Science
- Creator:
- Shojaei, Radoyeh
- Description:
- The Sequential Ordering Problem (SOP) is a combinatorial optimization problem. Given a directed weighted graph and an unweighted directed graph representing precedence constraints among vertices, find a minimum-cost Hamiltonian path that satisfies the precedence constraints. Previous work on this problem included heuristic solutions and sequential optimal algorithms. To the best of our knowledge, there is no parallel optimal algorithm for the SOP. In this work, we propose a parallel optimal algorithm for the SOP using a branch-and-bound approach. Our current experimental results using 116 standard benchmark instances show that with a 2-hour time limit, the proposed parallel algorithm can solve 75 instances compared to 66 instances solved by the existing sequential algorithm. The average speedup across all solved instances is 2.05 for 4 threads. The best speedup with 4 threads is over 21.
- Resource Type:
- Project
- Campus Tesim:
- Sacramento
- Department:
- Computer Science
- Creator:
- Singh, Shweta Amarjeet
- Description:
- One of the biggest innovations recently in the field of computer science is cryptocurrencies and Blockchain is at the heart of it. Cryptocurrency is one use case of blockchain and there can be many more. Blockchain is an incorruptible digital ledger of economic transactions that can be programmed to record not just financial transactions but virtually everything of value. Block chain is a shared (decentralized) database and this database is continuously reconciled. This Blockchain database is decentralized i.e. data is not stored in a single location, means it can be public and verifiable. Hacker cannot corrupt the information, as he may have to hack all the copies to manipulate an information. The intention is not only implement another use case (Digital storage vault) of Blockchain but also build from ground up a new blockchain engine based on its principles of distributed ledger and cryptographic hashing. The Digital Storage Vault system will be used to manage and store the Digital Will uploaded or typed by a user. The system will provide the authenticity of the will stored in form of cryptographic hash and the security of the Digital Will. This system will thus ensure that the user who has created this will is the only one who modifies it. No one else can update or make changes to the will. If an unauthorized modification is made then the modified digital will shall be replaced by the original will during the sync. The entire system will be developed in Java language.
- Resource Type:
- Project
- Campus Tesim:
- Sacramento
- Department:
- Computer Science
- Creator:
- Narendra, Pragathi
- Description:
- The diagnosis of a disease is the most critical and vital job in medicine and it mostly depends on a doctor’s intuition based on past experiences. The unfortunate case of recognizing the incorrect symptoms results in a misdiagnosis. To avoid such medical misdiagnoses, my project shows it is beneficial to utilize large datasets collected by healthcare industries to automate the diagnosis of diseases. Such a tool can assist doctors to avoid the unwanted biases in diagnosis. In addition, an automated medical diagnosing system would be useful if the symptoms are ambiguous because including large datasets to the currently known symptoms may illuminate the case. This project aims to develop machine-learning models to automate the diagnosis of disease. Apart from existing base algorithms and hybrid algorithm (Naïve Bayes with decision tree) in literature, my project implements a new hybrid algorithm with Naïve Bayes and random forest for classification of diseases. Hybrid algorithms are used to overcome the limitations of basic algorithms thereby producing a better machine learning model, which improves accuracy of classification. The tool allows the user to select the category of disease and enter the symptoms of the selected category. Among all the machine-learning models developed using the preprocessed datasets, the model that achieves highest accuracy with the test dataset is used to analyze the symptoms entered by the user. The result of the diagnosis along with the probability of its occurrence and accuracy of the developed model are displayed to the user.
- Resource Type:
- Project
- Campus Tesim:
- Sacramento
- Department:
- Computer Science
- Creator:
- Bibodi, Jay Nikhil
- Description:
- This system will eliminate the need for common platforms to publish pod-cast. The methods create a new ERC-20 token named as 'Pods.' Users will have an ability to create an account and get some specific number of tokens (that is, Pods) as joining bonus to perform a transaction in Ethereum network. Users will have the ability to upload a podcast which could be either paid or free. A user who uploads the podcast could decide the cost associated with the podcast. If the value associated with the podcast is higher than 0 Pods, then the user will gain full profit without paying a specific amount of share to different platforms like ios/google/Spotify, etc. Users will not only be able to search a particular podcast by its name but also by tags associated with it. A user who uploaded a podcast will be able to see the list of users who purchased it and keep track of tokens received after each transaction in the Ethereum network. A user who bought a podcast would have an option to like and post comments for the podcast. Comments are disabled from the system for the free podcast but any user being part of the system will be able to like a free podcast. This system will also allow users to purchase the tokens which could be used to buy a podcast. Implementation of this system was done in NodeJS and Solidity will be used to write Smart Contract. Smart Contract will help us to exchange the 'Pods' token among the users while avoiding the services of the middlemen. This system also uses Stripe for payment gateway which will allow users to buy more tokens, Azure cosmos DB to store the metadata of the users and podcast information and AngularJS to develop a highly responsive client-side application with data-bindings.
- Resource Type:
- Project
- Campus Tesim:
- Sacramento
- Department:
- Computer Science
- Creator:
- Suryavanshi, Rajani Mohan
- Description:
- Defending today’s enterprise network has become more and more challenging considering the increasing amount of cyber-attacks. It is critical to understand how an attack happens and how the intrusion propagates inside the enterprise network. System Object Instance Graph (SOIG) is a technique that captures the dependency relationship that exists in between system objects thereby showing the intrusion propagation process. However, the SOIG for an enterprise network can be very large and difficult to comprehend. Therefore, identifying the most important objects (files, processes, and sockets) that are depended on by other objects can help understand the intrusion propagation process. Security measures can be taken towards these objects to prevent future intrusions from happening. In addition, even a small-sized network’s SOIG can result in information overload. This overwhelming information needs to be weighted and segregated to aid human analysts’ comprehension. Human analysts require a tool which can extract critical data from the huge amount of information and provide it as a list of priorities. This way, the limited financial resources can be used for critical tasks. The scarce human power can be delegated to work on the priorities and hence save time from studying the overwhelming information. To combat the overwhelming information from SOIG, this project aims to rank the SOIG using the AssetRank algorithm. AssetRank approach can automatically digest the dependency relations in a SOIG, compute the relative importance of a graph vertex and rank it. The result will be a ranked graph visualizing the most critical vertices based on rank. These ranks of objects can be used to help a security analyst to input relevant data into security tools and understand security problems in a better manner.
- Resource Type:
- Project
- Campus Tesim:
- Sacramento
- Department:
- Computer Science
- Creator:
- Singh, Aditya
- Description:
- Nowadays it is very widespread to see attacks in the system. The attackers try automated tools and programs to attempt and gain access to the data of the users. However, for attackers, it is hard to boycott system calls. System calls are used by the user-level processes to request the different services from the kernel of the operating system. It is very difficult for the attacks to evade the system calls. The system calls are used to make every basic interaction between the operating system and program. The system performs allocating and deallocating memory, closing, reading, renaming and the opening of files, and starting and stopping a process. The size of the system log can be overwhelmingly huge, which makes it hard for the system admins to extract the useful information from it. In this project, we propose to analyze and visualize the system calls so that it can help the system administrators to extract information from the log easily and identify suspicious activities and behavior. The steps in the project include data collection/gathering, data exploration, data cleaning, data transformation, data mining, and data visualization. This approach helps to extract important information from the system calls by using data mining and machine learning algorithms. The statistics obtained through system call analysis and visualization provide valuable information about the system activities and reveal important patterns. This information and patterns can help identify suspicious behavior which might be related to attacks.
- Resource Type:
- Project
- Campus Tesim:
- Sacramento
- Department:
- Computer Science
- Creator:
- Raja Lemarji, Godson Miller
- Description:
- Students in a university tends to have various resources to trade. Trading has become an essential thing in our day-today life. In this project, I would like to recall barter system which is one of the oldest method of exchange. This has been used before lots of centuries and also when money was not invented. Goods and services were exchanged by people in return for other goods and services. Interchanging an item without involving any cash for another item is a great option for students. Direct exchange is a thing such that an exact match between two users who involved in trade. When such a direct match is missed then we can proceed with a new approach of involving more than two clients known as multilateral exchange. When the system finds multiple matches it prompts the client with variety of options to choose from. The client can decide the project they require based on the product description, usage, image, videos and value range etc.., The application is developed using Angular Framework, employing languages such as JavaScript and PHP. Hostgator is used as web server where all the data is stored in a SQL database.
- Resource Type:
- Project
- Campus Tesim:
- Sacramento
- Department:
- Computer Science
- Creator:
- Ghonsikar, Kasturi Kiran
- Description:
- Today with fast growing technology and increasing computing needs, industry is opting for deploying and using cloud to fulfill their extensive computing requirements. Deployment of cloud is a lengthy and convoluted process. Manual installation of cloud infrastructure takes a lot of efforts and time. Setting up cloud on a new infrastructure in a new environment has a lot of challenges and needs to be done manually for troubleshooting. This project involves manual deployment of OpenStack Cloud to overcome these challenges and setup an OpenStack Infrastructure as a Service platform on a virtual infrastructure. Further, automation is done for installation and uninstallation of OpenStack Cloud to overcome the overwhelming process of its manual deployment. Automation reduces the efforts in tedious process of manual cloud deployment and saves a significant amount of time required to install a cloud infrastructure. Automation of installation and uninstallation is done using a bash script in this project. Execution of this script on an environment with minimal requirements will setup a complete cloud infrastructure and allow users
- Resource Type:
- Project
- Campus Tesim:
- Sacramento
- Department:
- Computer Science
- Creator:
- Gampa, Ravali
- Description:
- This work presents a visual analytical tool, to assist instructors of introductory computer science courses to manage students’ learning. The first half of this project is an investigation on various visualization tools which inspired the motivation and brainstorms to build class performance analytic tooling. The second half of this project is an interactive visualization tool to understand individual student performance, compare the growth with other students in the class, and obtain an overall picture of an entire class’ performance. Focusing on students’ performance and growth can help the instructors who are the students who are doing well and who need some extra help. Careful monitoring of students’ performance can help in improving their growth. In this work, I develop an interactive visualization tool. The visualization was designed using D3.js, Javascript, and Python. This work was done in reference to an online class-room dataset. Visual tool would help to understand the insights of this dataset and looker deeper into the dataset. We present two views to analyze the performance of a class. One way is to understand how each student is performing in every topic of the subject from one exam to another exam. The second approach is to help in obtaining the overall perspective of the students’ growth from one exam to another. Both these views clearly distinguish the students who have improved from one examination to another. These views are designed by obtaining data from each student. Interactive features are incorporated to make these views easily readable and understandable.
- Resource Type:
- Project
- Campus Tesim:
- Sacramento
- Department:
- Computer Science