Search Constraints
« Previous |
1 - 10 of 998
|
Next »
Number of results to display per page
Search Results
- Creator:
- Soundararajan, Thilak Raj
- Description:
- Shoulder surfing is the process of stealing one’s personal information such as personal identification number or password by looking over the victim’s shoulder. Nowadays, a hacker can use a video camera to actively record a user entering the password to access personal banking or social networking application order to prevent this, a graphical authentication system has been created where users can use multiple images as password. In this project, we will deal with two types of image authentication, one is an image splitting method where we will deploy a matrix grid over the image and choose a specific grid as the password. The second one is the image overlapping method where a series of randomized numbers are generated over the image. There is an additional two-tier security of generating a temporary access password every time the user tries to login. The temporary password is generated only when the user covers the ambient sensor and it is available only for a temporary time. The two types of authentication system provide a secure way to access the app and make it impossible for the hackers to gain access.
- Resource Type:
- Project
- Campus Tesim:
- San Marcos
- Department:
- Computer Science
- Creator:
- Annapragada, Laxmi Subhamkar
- Description:
- Promoter sequences are the main regulatory elements of gene expression. The accurate prediction of promoters remains a challenge because the key DNA regulatory regions have variable structures, but their recognition by computer algorithms is fundamental for understanding gene expression patterns, cell specificity, and development. In this study, we utilize deep learning modules such as Convolutional Neural Networks (CNN) and Long Short Time Memory (LSTM) to analyze sequence characteristics of prokaryotic and eukaryotic promoters and build their predictive models. In this study, we apply advanced approaches to identify promoters on four different organisms: human, two types of bacteria (Escherichia coli and Bacillus subtilis) and plant (Arabidopsis) sequences. The proposed model contains diverse types of hyper-parameters, which are selected using validation accuracies. Based on the values of the hyper-parameters, we generate multiple models with distinct sets of parameters. The promoter test datasets are evaluated on all the best models generated, and the evaluation statistics such as sensitivity, specificity and correlation coefficients are calculated . The developed models demonstrated the ability of deep learning approach to grasp complex promoter sequence characteristics and achieved higher accuracy compared to the previously developed promoter prediction programs.
- Resource Type:
- Project
- Campus Tesim:
- San Marcos
- Department:
- Computer Science
- Creator:
- Chhabria, Pooja
- Description:
- LEACH is a TDMA (Time-Division Multiple Access) based clustering MAC (Medium Access Control) protocol in wireless sensor networks. This protocol frequently forms clusters of nodes and selects one of the cluster members as the cluster head. The two-tier structure of LEACH divides the network into two layers: 1) cluster members, which collect raw data from the environment and 2) cluster heads, which receive the collected data from cluster-members, and process, aggregate and transmit them to the sink. LEACH reduces the energy consumption of nodes since the most energy-consuming task, which is the long-distance transmission to the sink takes place only in cluster heads. However, LEACH selects the cluster heads randomly using a probabilistic calculation. As a result, the selected cluster heads may not be that strong to handle the high workload of a cluster head; their energy will be depleted very soon, and this reduces the network lifetime if the network desires to keep the throughput reasonably high. To overcome this tradeoff, in this thesis, we propose EALEACH (Energy Aware LEACH), a new clustering combined MAC and routing protocol, which selects cluster heads using their residual energies. This method provides an appropriate selection of cluster heads that are strong enough to handle the expected workload of cluster heads to reach high throughput. Also, our proposed protocol transmits data packets to the sink through intermediate cluster heads, which incredibly reduces the energy consumption on those cluster heads that are far from the sink and keeps them alive for a longer time. We validated the effectiveness and efficiency of our protocol through simulations. The analysis of our results shows that the cluster heads selected by the proposed protocol prolong the network lifetime by 60% in comparison to those selected by LEACH while the approached throughput remains high.
- Resource Type:
- Thesis
- Campus Tesim:
- San Marcos
- Department:
- Computer Science
4. ENVISION
- Creator:
- Maheshwari, Aastha
- Description:
- The world is getting advanced, and it becomes our responsibility to be on the same pace as the world. With the increase in the amount of data, it is becoming difficult to accommodate everything in our brain in a small span of time. Data Visualization allows us to look beyond the only process of reading and storing it all in our brains. The most important feature of visualization is that it allows visual access to huge amounts of data in understandable, simple, and powerful visuals. Taking that into consideration, this project is an effective application for visualizing data in 3D for better understanding and fast absorption of data into our brains. ENVISION is presenting folder revision activities in a more intuitive way through 3D visualization. Basically, ENVISION will help the users visualize properties of folders and files of GIT repository. ENVISION has the property to visualize data folder by folder. It will help the users to quickly estimate the progress of any project, the visualization takes place folder by folder, there would be multiplication of the pace of user’s understanding of the project history and quickly can start working further. ENVISION, also, lets the user view data by the latest entry, which also means, user can view files and folders from the latest commit to the oldest commit. With the increase demand of 3D Visualization, this project would be advantageous to all kind of users and would open the gate for another dimension to explore.
- Resource Type:
- Project
- Campus Tesim:
- San Marcos
- Department:
- Computer Science
- Creator:
- Panneer Selvam, Pratima
- Description:
- During medical emergencies, patients are often shunted from hospital to hospital due to lack of ICU beds leading to loss of many lives. Also crucial time is lost calling up every individual blood bank trying to find blood of the required group in an emergency. In a crisis, as those precious seconds slip away, knowing where the nearest vacant ICU bed is or how many blood bottles of the required type the nearest blood banks have, can mean the difference between life and death. However no service that provides such crucial real time information exists in most parts of the world - information that would be invaluable during personal medical emergencies as well as natural disasters, terrorist attacks and public health epidemics. On any case of emergency, the relatives or public take the patients to the nearest hospitals for treatments. There are chances that the further treatment and required services might not be available at that hospital. The hospital management may suggest taking the patient to some other hospital. Again moving the patient to other hospital for treatment is time consuming, expensive and it leads to discomfort of patient. This situation occurs because the relatives or public are unaware of the services provided by the hospital. So we need a system which gives all information related to different hospitals. This is the application which provides the information related to different hospitals via online and through texts. A healthcare application is proposed which facilitates the patients a list of nearest hospitals and along with the feature of services availability. So this application provides the hospital details such as services types, specialization details etc.
- Resource Type:
- Project
- Campus Tesim:
- San Marcos
- Department:
- Computer Science
- Creator:
- Panchal, Jalanilbhai
- Description:
- The use of Smartphones and its complementary technologies like wearable devices have gained immense momentum over the decade, which has led to their vast amount of use in various daily activities. On top of that, the new technologies plus their various add-ons take the scope of simple mobile apps to a new level. Taking that into consideration, this project creates an effective Virtual Reality (VR) enhanced Android smartphone application that collects data of Monarch butterfly species in the southern California area. This app provides two types of in-app surveys, with which users can submit detailed information about their observations of these butterfly species. The collected data will help researchers in their pursuit of finding the reasons behind the constant depletion of the Monarch butterfly species. While an existing website contains the same surveys to help collect Monarch butterfly data, the mobile app developed in this project complements the website by providing an in-app GPS-coordinates-collection feature and a VR feature to enhance user experience. With the in-app VR feature, users can get a unique and vivid experience of observing the Monarch butterflies in an exuberant environment. The project serves two purposes. First, overcoming the shortcomings of the existing website. Second, providing users a hint of Virtual Reality world. With this app, a huge leap has been taken in stepping in the world of Virtual Reality, which enhances the user interaction with the app by many folds.
- Resource Type:
- Project
- Campus Tesim:
- San Marcos
- Department:
- Computer Science
- Creator:
- Sudak, Bartosh
- Description:
- In software development, software teams receive bug reports that describe unintended performance of the software products frequently. When a new bug report is received, software developers usually need to recreate the bug, perform code reviews, and use various test cases to determine its root cause. This manual process can be tedious and is often extremely time consuming. In order to help lessen software developers non-autonomous attempts at locating a software bug, this thesis offers an autonomous approach to locating software bugs in source code files. This is done through measuring the text similarity between the bug report and every source code file for ranking. The top ranked source code files will be recommended as relevant to the bug report. Ranking all source files with respect to how likely they are to contain the cause of the bug would allow developers to focus their search and hence improve productivity. To further improve a systems accuracy, this thesis introduces the application of a pre-filtering technique to filter out bug reports that have been proven to be difficult for autonomous systems to process. When a bug report is received, we first classify it as either “predictable” or “unpredictable” and perform bug locating recommendation only on ”predictable” reports. Such pre-filtering is done by using a Convolutional Neural Network (CNN). CNN have never been used before in the field of bug finding, so this is a first attempt to determine if it is a viable approach. The neural network is used to represent every bug report as a vector of real numbers called features. Softmax regression is used in classifying the vector representations of bug reports. The training dataset contains previously fixed bug reports manually labeled into two categories: predictable and unpredictable. By being able to determine that a buggy file is predictable, software developers will be able to reduce the amount of false positives they come across using the software defect localization tool. To evaluate the proposed approach, we conduct an experiment on more than 3,000 Eclipse bug reports. According to the experimental result, when we look at the top ten ranked source code files in the ranked list, we made correct recommendations on 57% of predictable bug reports, increasing the overall tools accuracy by 10%. Although it is possible that there are predictable bug reports within the bug reports classified as ”unpredictable”, we do not test them. It does not make sense to run such experiments because the assumption is that ”unpredictable” reports do not contain sufficient information. Even with a effort loss of 38% of the classification result, we still improve the ranking performance. We also increase the accuracy 5% in the current leading ranking model [40] and show that the classification model is applicable to other ranking models. The experimental results show that the proposed supervised bug report classification approach can improve the bug localization ranking precision so that the ranking system is more trustworthy.
- Resource Type:
- Thesis
- Campus Tesim:
- San Marcos
- Department:
- Computer Science
- Creator:
- Pandiri, Venkat Shiva
- Description:
- This project carried out a systematic investigation to predict the final price of each home using machine learning techniques. Various machine learning techniques such as multiple linear regression (base model), random forest regression and polynomial regression were applied to the dataset to compare the results. The data describes the sale of individual properties, various features and details of each home in Ames, IW from 2006 to 2010. The dataset comprises of 80 explanatory variables which include 23 nominal, 23 ordinal, 14 discrete, and 20 continuous variables. The programs were implemented using Python, by using core libraries like pandas, scikit–learn, NumPy. Backward elimination algorithm is applied in building optimal model and selection of features over 270 independent variables with approximately 7,91,320 observations. K-fold cross validation technique is used to measure the performance of all the models. A good high R- squared values with low variance are recorded for linear models. In order to select a good prediction model, all the regression models are explored and compared with each other. Results from K fold cross validation indicates high R-squared values for MLR and Random forest, stating a high level of performance when applied on an actual test set. Each model is evaluated with kaggle score checker. My Random forest model achieved the score of 0.14696, which is better compared to my base model Multiple linear regression (kaggle score 0.16854) and Polynomial regression (kaggle score 0.24399).
- Resource Type:
- Project
- Campus Tesim:
- San Marcos
- Department:
- Computer Science
- Creator:
- Ramamurthy, Kishore
- Description:
- An Annotation is a metadatum (comment, explanation) attached to a specific section of a document (text, image, video or other formats) after it has been created. Annotations have been used in several fields such as literature and education, software engineering, computational biology, imaging, law, linguistics etc. One important application of the Annotation technology is Video Annotations. E-Leaning has been gaining massive popularity considering several advantages such as flexibility, ease of use, 24/7 accessibility, cost effective and self-paced. The main intent of this project is to foster the advantages of Video Annotations in the existing E-Learning environments. This approach will aid the E-Learning environment by improved engagement among students and professors by quick information recall as videos are annotated with the answers, notifications and time-monitored feedback mechanism.
- Resource Type:
- Project
- Campus Tesim:
- San Marcos
- Department:
- Computer Science
- Creator:
- Chang, Lianghuang Eric
- Description:
- A Learning Management System (LMS) is a core component of distance education over the Internet. Although a number of venders have released their LMS products, such as WebCT and Blackboard, the lack of interoperability with other related systems and content sharing channels for course creators limits the extensibility of LMS and the efficiency of content creation. This thesis presents our design and implementation of an LMS, which provides solutions to the above two problems. The design of our LMS followed the latest distance education specifications: IMS Learning Resources Meta-data specifications and IMS Enterprise specifications released by the Instructional Management System (IMS). The implementation of our LMS is based on a multi-tier client/server Web-based application model. In addition, we apply the latest Web development technologies, such as Java Servlets, Java RM/, JDBC, XML, JavaScript, and HTML to our implementation. Our resulting LMS is able to exchange administrative data with Enterprise Resource and Planning Systems (ERP) and provides a content shopping store over the Internet. The promising design and implementation results establish a model for later LMS development, which may follow the IMS's later specifications for distance education.
- Resource Type:
- Thesis
- Campus Tesim:
- San Marcos
- Department:
- Computer Science