Saif Saad Alnuaimi

M.S.

Computer systems and Networks

B.S

Computer Science

Lecturer

Activating the scientific and academic platforms

Introducing the scientific and academic platforms

Hybrid Deep Learning Techniques for Large-Scale Video Classification

Effective large-scale video management and classification are becoming more and more necessary due to the Internet's video data rapidly increase. A comprehensive evaluation of the trade-off between timeliness and efficacy should be made during real-world implementation. In industrial deployments, the frame extraction function is frequently used to categorize video actions, while the video classification technique integrated with a time segment network is implemented. The scientific literature now contains several reviews and research articles on the topic of video categorization. With the ability to analyze spatial and temporal information concurrently and efficiently, the combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) provides an effective framework for video categorization issues. This research proposes a comparison to evaluate how CNNs and RNNs integrated into different architectures might use temporal information to enhance video classification accuracy using deep learning. To optimize the performance of the proposed design for a CNN and RNN hybrid that works well, an innovative action template-based feature extraction technique is presented. This approach extracts features by analyzing the similarity between each frame's informative areas. Using RNN based video classifiers extensive experiments were performed on the UCF-50 and UCF-101 datasets. The efficiency of the suggested Feature extraction technique is demonstrated by the considerable improvement in video categorization accuracy shown in the experimental data, as examined by a one-way statistical evaluation of variance.

Automatic Speech Emotion Recognition Using Hybrid Deep Learning Techniques

An emerging field of research is the advancement of deep learning techniques for speech emotion recognition. The current scenario of human-computer interaction is being significantly impacted by and altered by speech recognition technologies. In human-computer interaction, developing an interface that can sense and react accurately like a human is one of the main crucial challenges. As a result, the Automatic Speech Emotion Recognition (ASER) system has been developed. It extracts and identifies important data from voice signals to classify various emotional categories. The novel advancements in deep learning have also led to a major improvement in the ASER system's performance. Numerous methods, including some well-known speech analysis and classification approaches, have been used to derive emotions from signals in the literature on ASER. Recently, deep learning methods have been suggested as an alternative to conventional methods in ASER. The main goal of this research is to use deep learning techniques to analyze different emotions from speech. Because deep learning networks have sophisticated feature extraction processes, they are frequently utilized for emotional classification, in advance of traditional/machine learning systems that depend on manual feature extraction before classifying the emotional state. To extract features and identify different emotions depending on input data, the authors have implemented the most efficient hybrid deep learning algorithms, CNN+LSTM. By training and testing the suggested network algorithm with the standard dataset, the authors, accordingly, achieved the highest accuracy.

DATA DISTRIBUTION OPTIMIZATION OVER MULTI CLOUD STORAGE

Cloud storage is an essential matter for people's organization and growth. Unfortunately, it is too risky if the data and files are hosted only on a single cloud storage provider. Meanwhile, insider attacks can steal or corrupt data. Using multi-cloud storage providers and distributing the data over is a possible solution to improve data security in such a context. However, the performance of the uploading speed of a cloud service provider plays an influential role. In this study, we used multi-cloud storage with optimization parameters to speed up the uploading time spent to store data in several cloud storage services. Slicing the data and sending the contrasting amount of data over multi-cloud storage according to the optimization result can provide better security features and upload faster. This work considers the upload time and access latency parameters to implement the optimization model. Our finding shows a 12% enhancement in distribution performance compared to traditional data slicing without optimization if equally sized slices are sent over multi-cloud storage. In future work, the effectiveness of bandwidth should be included, especially on the optimization parameters.

Design and Implementation Marking system program using V.B. language Applied Research

In this paper the analysis of marking system program is performed to design a comprehensive system for students’ degrees, in terms of student registrations and documentations of the final result. The work used students data of the of Al-Turath university college as an example to run the program. The Microsoft access 2010 is used to create database and connect it with visual basic to get the results of the program properly. All the forms of program are presented by visual basic that can be an excellent program to manage and control database and can be easy for users. The program designed to not accept any wrong input data and sends a message to the user if any errors happens or if the user is update the database.

Design and Implementation of face recognition attendance system based on computer vision API

Face recognition presents a challenging problem in the field of image analysis and computer vision, and as such has received a great deal of attention over the last few years because of its many applications in various domains. Face recognition techniques can be broadly divided into three categories based on the face data acquisition methodology: methods that operate on intensity images; those that deal with video sequences; and those that require other sensory data such as 3D information or infra-red imagery. In this paper, an overview of some of the well-known methods in each of these categories is provided and some of the benefits and drawbacks of the schemes mentioned therein are examined. Furthermore, a discussion outlining the incentive for using face recognition, the applications of this technology, and some of the difficulties plaguing current systems with regard to this task has also been provided. This paper also mentions some of the most recent algorithms developed for this purpose and attempts to give an idea of the state of the art of face recognition technology.