- Data Mining Algorithms and Applications
- Privacy-Preserving Technologies in Data
- Complex Network Analysis Techniques
- Cryptography and Data Security
- Rough Sets and Fuzzy Logic
- Opinion Dynamics and Social Influence
- Information and Cyber Security
- Network Security and Intrusion Detection
- Data Quality and Management
- Spam and Phishing Detection
- Internet Traffic Analysis and Secure E-voting
- Advanced Malware Detection Techniques
- Cloud Data Security Solutions
- Imbalanced Data Classification Techniques
- Data Management and Algorithms
- Advanced Graph Neural Networks
- Cloud Computing and Resource Management
- Expert finding and Q&A systems
- Bayesian Modeling and Causal Inference
- Mental Health Research Topics
- Data Visualization and Analytics
- User Authentication and Security Systems
- Big Data and Business Intelligence
- Topic Modeling
- Complexity and Algorithms in Graphs
University of Arkansas at Fayetteville
2019-2022
University of Nevada, Las Vegas
2015-2019
North Carolina Agricultural and Technical State University
2011-2015
Dakota State University
2010
Carnegie Mellon University
2007-2009
Institute of Statistical Science, Academia Sinica
2008
Sentiment analysis or opinion mining is one of the major tasks NLP (Natural Language Processing). has gain much attention in recent years. In this paper, we aim to tackle problem sentiment polarity categorization, which fundamental problems analysis. A general process for categorization proposed with detailed descriptions. Data used study are online product reviews collected from Amazon.com. Experiments both sentence-level and review-level performed promising outcomes. At last, also give...
Due to the rapid growth of resource sharing, distributed systems are developed, which can be used utilize computations. Data mining ( DM ) provides powerful techniques for finding meaningful and useful information from a very large amount data, has wide range real‐world applications. However, traditional algorithms assume that data is centrally collected, memory‐resident, static. It challenging manage large‐scale process them with limited resources. For example, amounts quickly produced...
Paraphrase Identification or Natural Language Sentence Matching (NLSM) is one of the important and challenging tasks in Processing where task to identify if a sentence paraphrase another given pair sentences. conveys same meaning but its structure sequence words varies. It as it difficult infer proper context about short length. Also, coming up with similarity metrics for inferred sentences not straightforward well. Whereas, applications are numerous. This work explores various machine...
Community detection is a fundamental component of large network analysis. In both academia and industry, progressive research has been made on problems related to community gaining significant attention importance in the area science. Regular synthetic complex networks have motivated intense interest studying unifying principles various networks. This paper presents new game-theoretic approach towards large-scale based modified modularity; this method was developed adjacency, Laplacian...
Classifying short texts to one category or clustering semantically related is challenging, and the importance of both growing due rise microblogging platforms, digital news feeds, like. We can accomplish this classifying with help a deep neural network which produces compact binary representations text, assign same that have similar representations. But problems arise when there little contextual information on texts, makes it difficult for produce codes texts. propose address issue using...
One of the most substantial ways to protect users' sensitive information is encryption. This paper about keyword index search system on encrypted documents. It has been thought that with errors over data impossible because 1 bit difference plaintexts may reduce enormous bits cyphertexts. We propose a novel idea deal data. develop two similarity schemes, implement prototypes and provide analysis. define security requirements for The first scheme can achieve perfect privacy in but second more...
There is a fair amount of research about privacy, but few empirical studies its cost have been conducted. In the area secure multiparty computation, scalar product has long reckoned as one most promising alternatives to classic logic gates. The reason for this that not only complete, which good gates, also much more efficient than As result, we set out study computation and communication resources needed some well-known frequently referenced protocols, including composite residuosity,...
Online banking authentication plays an important role in the field of online security. In past years, a number methods, including password token, short message password, and USB have been developed for authentication. this paper, we introduce new protocol banking. Our approach enhances performance robustness against various attacks by using mobile phones to store digital certificate clients. We provide attack analysis illustrate strength protocol.
Community structure is thought to be one of the main organizing principles in most complex networks. Big data and networks represent an area which researchers are analyzing worldwide. Of special interest groups vertices within connections dense. In this paper we begin with discussing community dynamics exploring network structural parameters. We put forward functional models for under situations perturbations. introduce modified adjacency Laplacian matrices. further or degree centrality...
High utility itemset mining has become an important and critical operation in the Data Mining field. generates more profitable itemsets association among these itemsets, to make business decisions strategies. Although, high is important, it not sole measure decide efficient strategies such as discount offers. It very consider pattern of based on frequency well predict itemsets. For example, a supermarket or restaurant, beverages like champagne wine might generate (profit), but also sell less...
Question Answering (QA) is a task in natural language processing that has seen considerable growth after the advent of transformers. There been surge QA datasets have proposed to challenge models improve human and existing model performance. Many pre-trained proven be incredibly effective at extractive question answering. However, generalizability remains as for majority these models. That is, some require reason more than others. In this paper, we train various fine-tune them on multiple...
Privacy preserving data mining (PPDM) is an emerging research problem that has become critical in the last decades. PPDM consists of hiding sensitive information to ensure it cannot be discovered by algorithms. Several algorithms have been developed. Most them are designed for frequent itemsets or association rules. Hiding a database can several side effects such as other non-sensitive and introducing redundant information. Finding set transactions sanitised minimises NP-hard problem. In...
Many studies have been conducted on Handwritten Signature Verification. Researchers taken many different approaches to accurately identify valid signatures from skilled forgeries, which closely resemble the real signature. The purpose of this paper is suggest a method for validating written bank checks. This model uses convolutional neural network (CNN) analyze pixels signature image recognize abnormalities. We believe feature extraction capabilities CNN can optimize processing time and...
Identifying network communities is one of the most important tasks when analyzing complex networks. Most these networks possess a certain community structure that has substantial importance in building an understanding regarding dynamics large-scale network. Intriguingly, such appear to be connected with unique spectral property graph Laplacian adjacency matrix and we exploit this connection by using modified relationship between matrix. We propose modularity optimization based on greedy...