arXiv subjects

Mir Mohsen Pedram

Publications and source records attributed to Mir Mohsen Pedram.

4 recordsLinked to original sources

arXiv2024

Solving the decision-making differential equations from eye fixation data in Unity software by using Hermite Long-Short-Term Memory neural network

Cognitive decision-making processes are crucial aspects of human behavior, influencing various personal and professional domains. This research delves into the application of differential equations in analyzing decision-making accuracy by leveraging eye-tracking data within a virtual industrial town setting. The study unveils a systematic approach to transforming raw data into a differential equation, essential for deciphering the relationship between eye movements during decision-making processes. Mathematical relationship extraction and variable-parameter definition pave the way for deriving a differential equation that encapsulates the growth of fixations on characters. The key factors in this equation encompass the fixation rate $(λ)$ and separation rate $(μ)$, reflecting user interaction dynamics and their impact on decision-making complexities tied to user engagement with virtual characters. For a comprehensive grasp of decision dynamics, solving this differential equation requires initial fixation counts, fixation rate, and separation rate. The formulation of differential equations incorporates various considerations such as engagement duration, character-player distance, relative speed, and character attributes, enabling the representation of fixation changes, speed dynamics, distance variations, and the effects of character attributes. This comprehensive analysis not only enhances our comprehension of decision-making processes but also provides a foundational framework for predictive modeling and data-driven insights for future research and applications in cognitive science and virtual reality environments.

cs.HC↗

arXiv2021

A Novel Deep Learning Method for Textual Sentiment Analysis

Sentiment analysis is known as one of the most crucial tasks in the field of natural language processing and Convolutional Neural Network (CNN) is one of those prominent models that is commonly used for this aim. Although convolutional neural networks have obtained remarkable results in recent years, they are still confronted with some limitations. Firstly, they consider that all words in a sentence have equal contributions in the sentence meaning representation and are not able to extract informative words. Secondly, they require a large number of training data to obtain considerable results while they have many parameters that must be accurately adjusted. To this end, a convolutional neural network integrated with a hierarchical attention layer is proposed which is able to extract informative words and assign them higher weight. Moreover, the effect of transfer learning that transfers knowledge learned in the source domain to the target domain with the aim of improving the performance is also explored. Based on the empirical results, the proposed model not only has higher classification accuracy and can extract informative words but also applying incremental transfer learning can significantly enhance the classification performance.

cs.CL↗

arXiv2018

A robust image-based cryptology scheme based on cellular non-linear network and local image descriptors

Cellular nonlinear network (CNN) provides an infrastructure for Cellular Automata to have not only an initial state but an input which has a local memory in each cell with much more complexity. This property has many applications which we have investigated it in proposing a robust cryptology scheme. This scheme consists of a cryptography and steganography sub-module in which a 3D CNN is designed to produce a chaotic map as the kernel of the system to preserve confidentiality and data integrity in cryptology. Our contributions are three-fold including (1) a feature descriptor is applied to the cover image to form the secret key while conventional methods use a predefined key, (2) a 3D CNN is used to make a chaotic map for making cipher from the visual message, and (3) the proposed CNN is also used to make a dynamic $k$-LSB steganography. Conducted experiments on 25 standard images prove the effectiveness of the proposed cryptology scheme in terms of security, visual, and complexity analysis.

cs.CR↗

arXiv2012

Presentation an Approach for Optimization of Semantic Web Language Based on the Document Structure

Pattern tree are based on integrated rules which are equal to a combination of some points connected to each other in a hierarchical structure, called Enquiry Hierarchical (EH). The main operation in pattern enquiry seeking is to locate the steps that match the given EH in the dataset. A point of algorithms has offered for EH matching; but the majority of this algorithms seeks all of the enquiry steps to access all EHs in the dataset. A few algorithms such as seek only steps that satisfy end points of EH. All of above algorithms are trying to locate a way just for investigating direct testing of steps and to locate the answer of enquiry, directly via these points. In this paper, we describe a novel algorithm to locate the answer of enquiry without access to real point of the dataset blindly. In this algorithm, first, the enquiry will be executed on enquiry schema and this leads to a schema. Using this plan, it will be clear how to seek end steps and how to achieve enquiry dataset, before seeking of the dataset steps. Therefore, none of dataset steps will be seek blindly.

cs.DB↗