Saber MalekzadeH

Master of Computer Science, Artificial Intelligence

Born in May 1993


Education:

M.Sc. Computer Science (Intelligent Systems)

Vali-e-asr University, Iran, 2015-now

Proposal Title: “Persian Phoneme Based Speech Recognition”

Supervisor: Dr. Mohammad Hossein Gholizadeh

Advisor: Dr.Seyed Naser Razavi (University of Tabriz)

 

B.Sc. Computer Science

University of Tabriz, Iran, 2010-2015

Final dissertation: “Design and Implementation of Self-defense process tool”

Supervisor: Dr. Jaber Karimpour



Research Interest:

Deep learning

Sound Processing

Image Processing

Brain Computer Interaction

NLP

Reinforcement Learning



Publications:

[1] Article “Using convolutional deep neural networks recognize phonemes with 2d STFT samples in Persian speech” (Submitted)

Abstract:

In this paper a new method of phoneme recognition on Persian phonemes is proposed. The method is applied on denoised PCVC (Persian Consonant-Vowel Combination) speech dataset. There are 29 phonemes of Persian phonemes combined in this dataset. Every sound sample has two phonemes which first one is consonant and the second one is vowel pronounced together. There are all possible combination of 23 consonant and 6 vowels of Persian. For the recognition purpose, first phonemes are separated and extracted as sound samples from samples in PCVC with different time lengthes due to their length of pronunciation. Then STFT (Short time Fourier transform) is taken from every sound sample with fixed parameters. After that, all STFT data are zero padded to being given to deep neural network for the recognition process. Since all samples were 2d samples of Time-Frequency domain and also were related to each other, 2d Convolutional LSTM is used. After testing several parameters, in best experiment, a 83 percent phoneme recognition accuracy.

_____________________________________

[2] Article “Detection of subject patterns in web-based texts dynamically (Online) using GRU deep neural networks” (Preparing to submit)

Abstract:

Today, one of the most important issues in computer science is the analysis of individual behaviors on the Internet and virtual communities. In these systems, computers are tried to understand the behaviors of others as well as humans. The thesis attempts to use a text processing and classification algorithm with deep learning a number of posts in web pages to analyze and to determine if there is a subjective patterns within the texts, and then examine to what extent these topics are closely aligned or separated. For this purpose, the Reuters data collection has been used in which different text structures and separate words are examined. On the training data, classifications were also made on experimental data so artificial neural networks could distinguish texts with different titles.In many cases, web searches are used.

If there were a good algorithm for web page classification, then web pages can be grouped together in the shortest time possible for users to provide optimal search results. Therefore, in academic environments, hospitals, etc., classification of information in a particular area can be used.

_____________________________________

[3] Article “Detection of negative or positive patterns in text wrote by men and women using GRU deep neural networks” (Preparing to submit)

Abstract:

Today, one of the most important issues in computer science is the analysis of individual behaviors on the Internet and virtual communities. In these systems, computers are tried to understand the behaviors of others as well as humans. The thesis attempts to use the text processing and classification algorithms as a deep learning method for a number of posts of Different blogs to identify the gender of their writers and have been analyzed to determine whether the gender of the people is effective on their negative and positive emotions, and then examine what types of material each of the two sexes in the different mental states publish? For this purpose, a dataset of positive and negative words was first collected and then a number of texts were selected from the blog post data as the most negative and positive samples. From these data, classification was made on rest of data so artificial neural network can distinguish between positive and negative texts. Then another classroom operation was conducted to identify the gender of the author. Ultimately, classifying operations on gender data for men and women to determine the negative or positive nature of the texts written by each of these sexes determines how positive or negative the difference is between men and women.

_____________________________________

[4] Article “Persian vowel phoneme recognition with MFCC and ANN on PCVC speech dataset” Accepted in “The 5th International Conference of Electrical Engineering, Computer Science and Information Technology 2018”. (Download)

Abstract:

In this paper a new method for recognition of consonant-vowel phonemes combination on a new Persian speech dataset titled as PCVC (Persian Consonant-Vowel Combination) is proposed which is used to recognize Persian phonemes. In PCVC dataset, there are 20 sets of audio samples from 10 speakers which are combinations of 23 consonant and 6 vowel phonemes of Persian language. In each sample, there is a combination of one vowel and one consonant. First, the consonant phoneme is pronounced and just after it, the vowel phoneme is pronounced. Each sound sample is a frame of 2 seconds of audio. In every 2 seconds, there is an average of 0.5 second speech and the rest is silence. In this paper, the proposed method is the implementations of the MFCC (Mel Frequency Cepstrum Coefficients) on every partitioned sound sample. Then, every train sample of MFCC vector is given to a multilayer perceptron feed-forward ANN (Artificial Neural Network) for training process. At the end, the test samples are examined on ANN model for phoneme recognition. After training and testing process, the results are presented in recognition of vowels. Then, the average percent of recognition for vowel phonemes are computed.

_____________________________________

[5] Article “Laser Deviation measurement in passing through objects with pixel coordination changes measurement” (Submitted) (in collaboration with Laser lab of Vali-e-asr university)

_____________________________________

[6] Article “Fuzzy Controller of Reward of Reinforcement Learning in Digit Recognition” accepted in “The third international conference of applied researches in Computer Science and Information Technology 2016” and indexed in Civilica and ISC (In Persian) (Certificate(Civilica Webpage) (Download)

Abstract:

Recognition of human environment with computer systems always was a big deal in artificial intelligence. In this area handwriting recognition and conceptualization of it to computer is an important area in it. In the past years with growth of machine learning in artificial intelligence, efforts to using this technique increased. In this paper is tried to using fuzzy controller, to optimizing amount of reward of reinforcement learning for recognition of handwritten digits. For this aim first a sample of every digit with 10 standard computer fonts, given to actor and then actor is trained. In the next level is tried to test the actor with dataset and then results show improvement of recognition when using fuzzy controller of reinforcement learning.

 _____________________________________

[7] Article “A fast and secure transition method by combination of AES and LZ4 algorithms” accepted in “The third international conference of applied researches in Computer Science and Information Technology 2016” and indexed in Civilica and ISC (In Persian) (Certificate(Civilica Webpage). (Download)

Abstract:

From a long time ago, beside encryption of data and making it secure, compression packing it was also important that could make transmission of data faster. In the past years need for improvement of encryption and compression for a fast and easy transmission is more necessary. In this paper, a new method for combination of LZ4 combination and AES encryption algorithms for a fast and easy packing, securing and compressing of data is presented. Choose of these two algorithms was for some special features of them about aim of this paper. This paper also is introducing a method for Parallelism of compression and encryption in a special way for improvement of speed and security of data.

 _____________________________________

[8] B.S thesis entitled “Design and implementing of process self-protection tool” 2014. (In Persian) (Download)

 


Workshops Certificates:

- Attendance in "Blockchain business event" (Attendance Card)

- Holding of "Analysis of Spiking Data" Workshop (Poster)

- Attendance in "Analysis of Spiking Data (Computational Neuroscience)" Workshop of Albert Ludwigs University of Freiburg. (Certificate)



Patents:

- Patent as “Anti-earthquake and anti-impact flexible structures” Registered in Iran patent Registration organization

- Patent as “Social Interactive Encyclopedia” presented in 10th Khwarizmi Patents Festival

- Patent as “magnetic Car model without fuel for special uses” presented in 10th Khwarizmi Patents Festival

 


Scientific Competitions:

- Chosen as Top programmer of Programming Contest of Vali-e-asr University, Tabriz University, Shabestar branch of Islamic Azad University

Chosen as top patent in 9th and 10th Khwarizmi patent festival, Kuhsaran patent festival of National Elites Foundation



Skills:

Programming languages:

Programming languages

Professional working proficiency

Good working proficiency

Elementary proficiency

Matlab

 

 

Python

 

 

C++

 

 

C#

 

 

Java

 

 

Android

 

 

PHP

 

 

JavaScript

 

 

 

Natural Languages:

Natural languages

Native

Professional working proficiency

Elementary proficiency

Turkish

 

 

Persian

 

 

English

 

 

Arabic

 

 

Kurdish

 

 

 


Teaching Experiences:

Course Title

Level

Teaching Status

Date

Institute

Data Structures

B.Sc.

TA

2015-2017

Vali-e-asr University

Digital Image Processing

M.Sc.

TA

2016

Vali-e-asr University

Algorithm Design

B.Sc.

TA

2016

Vali-e-asr University

Advanced Programming

B.Sc.

TA

2013

University of Tabriz

 


Courses:

Course: Natural Language Processing

                Projects:

- Implementing of NLP Project in Language model design (Python)

Course: Advanced Programming

                Projects:

- Design and implementing of Android Program about biography (Android)

- Design and implementing of object oriented university education management system (C++)

Course: Machine language and Assembly

                Projects:

- Design and implementing of Assembly text file Reader/Writer (Assembly)

Course: Algorithm design

                Projects:

- Implementing of Strasen Matrixes Multiplication, Hoffman Coding, Knapsack, TSP, etc. (C#)

- Implementing of Kruskal, Dijkstra, Prime, Knapsack, Bellman-ford, etc. (C#)

Course: Advanced Artificial Intelligence

                Projects:

- Implementing of N Queen with recursive function and Genetic Algorithm (Matlab)

- Design and implementing of a BMI expert fuzzy model (Matlab)

Course: Data Save and Recovery

                Projects:

                                - Design and implementing of Windows Based Search Engine (C++)

- Implementing of B+ Tree Search (C++)

Course: Artificial Intelligence

                Projects:

- Implementing of A*, Hill Climbing, 8 Blocks, etc. (C#)

Course: Data Structures

                Projects:

- Design and implementing of object oriented Family tree (C++)

Course: Operating Systems

                Projects:

- Design and implementing of Multi-thread programming with Semaphore Data Structure (C#)

Course: Compilers

                Projects:

- Design and implementing of a Compiler with letter by letter analyze (C#)

Course: Computer Networks

                Projects:

- Design and implementing of Social Encyclopedia with UML and ER model (C#)

Course: Computer Networks

                Projects:

                                - Implementing of information transition with socket programming (C#, Python)

- Implementing of a Cisco router model (Wire-shark)

Course: Operation Research

                Projects:

- Implementing of Simplex optimization method (Matlab)



Selected Projects:

In Collaboration with Islamic Azad University, Rafsanjan branch (not published):

- Implementation of Recognizer of all kinds of Persian vowels

In Collaboration with Nabiyye Akram University of Tabriz (preparing to submit):

Detection of subject patterns in web-based texts dynamically (Online) using GRU deep neural networks

In Collaboration with Islamic Azad University, Qazvin branch (preparing to submit):

- Detection of negative or positive patterns in text wrote by men and women using GRU deep neural networks

In Collaboration with Quchan University of Advanced Technologies Engineering (not published):

- Implementation of an Object Localization System based on Image processing (Matlab)

In Collaboration with Zarand Higher Education Complex (not published):

- Implementation of detection of mood in brain EEG signals with SVM and ANN (Matlab)

In Collaboration with IT Lab of Sajjad University (not published):

- Implementation of detection of DDOS attack with Artificial Neural Networks (Matlab)

In Collaboration with Composite Lab of Vali-e-asr University (not published):

- Implementation of Composite resistance with Image processing (Matlab)

In Collaboration with AI Lab of Vali-e-asr University (not published):

- Implementation of detection of weed intensity in agricultural land (Matlab)

In Collaboration with Laser Lab of Vali-e-asr University (sumbited):

- Implementation of measuring the laser change in the passage of materials (Matlab)

In Collaboration with Alomina Healthcare Department:

                                - Design and Implementing of Intelligent Real-time question answering system (Python)

- Implementation of Big-data transferring Web-API (Python)



Work Experiences:

-          CTO and AI developer in Alomina Healthcare Department

-          Technician in Computer Emergency of Tabriz

-          Software Manager in Aslani Mobile Shop

-          CTO in Rayan Fartak Azar



Contact me:

EMail: 0smalek0[at]gmail.com

Phone: +98-9142232172



Saber MalekzadeH