Mostafa Charmi

Dr. Mostafa Charmi

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2019 in Biomedical Signal Processing and Control
Verified
Journal Article
Closed access
SMSeyedeh Somayyeh Mousavi
Seyedeh Somayyeh Mousavi
MFMohammad Firouzmand
Mohammad Firouzmand
MCMostafa Charmi
Mostafa Charmi
MHMohammad Hemmati
Mohammad Hemmati
MMMaryam Moghadam
Maryam Moghadam
YGYadollah Ghorbani
Yadollah Ghorbani

9 June 2023 in IEEE Access
Verified
Journal Article
Open access
SPShima Pouyan
Shima Pouyan
MCMostafa Charmi
Mostafa Charmi
AAAli Azarpeyvand
Ali Azarpeyvand
HHHossein Hassanpoor
Hossein Hassanpoor
Crime prediction in video-surveillance systems is required to prevent incident and protect assets. In this sense, our article proposes first artificial intelligence approach for Robbery Behavior Potential (RBP) prediction and detection in an indoor camera. Our method is based on three detection modules including head cover, crowd and loitering detection modules for timely actions and preventing robbery. The two first modules are implemented by retraining YOLOV5 model with our gathered dataset which is annotated manually. In addition, we innovate a novel definition for loitering detection module which is based on DeepSORT algorithm. A fuzzy inference machine renders an expert knowledge as rules and then makes final decision about predicted robbery potential. This is laborious due to: different manner of robber, different angle of surveillance camera and low resolution of video images. We accomplished our experiment on real world video surveillance images and reaching the F1-score of 0.537. Hence, to make an experimental comparison with the other related works, we define threshold value for RBP to evaluate video images as a robbery detection problem. Under this assumption, the experimental results show that the proposed method performs significantly better in detecting the robbery as compared to the robbery detection methods by distinctly report with F1-score of 0.607. We strongly believe that the application of the proposed method could cause reduction of robbery detriment in a control center of surveillance cameras by predicting and preventing incident of robbery. On the other hand, situational awareness of human operator enhances and more cameras can be managed.

1 October 2018
Verified
Conference Paper
Closed access
SMSeyedeh Somayyeh Mousavi
Seyedeh Somayyeh Mousavi
MHMohammad Hemmati
Mohammad Hemmati
MCMostafa Charmi
Mostafa Charmi
MMMaryam Moghadam
Maryam Moghadam
MFMohammad Firouzmand
Mohammad Firouzmand
YGYadollah Ghorbani
Yadollah Ghorbani
The relationship between the heart's electrical and mechanical activities is expressed by Mechano-Electric Coupling (MEC) term, and blood pressure (BP) is the output of these activities. Electrocardiogram (ECG) is a representation of heart's electrical activity. Previous studies show that there is a nonlinear relationship between the ECG signal and BP values. This paper presents a new algorithm for estimating BP using only the ECG signal and without any cuff. A new feature vector extraction method in the frequency domain, called the frequency whole-based method, is proposed. According to the British Hypertension Society (BHS) standards, the proposed algorithm achieves grade B for the Diastolic Blood Pressure (DBP) and grade C for Mean Atrial Blood Pressure (MAP) estimations on MIMIC II dataset.

6 February 2021 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
SMShokoufeh Mousavi
Shokoufeh Mousavi
MCMostafa Charmi
Mostafa Charmi
HHHossein Hassanpoor
Hossein Hassanpoor

1 April 2021 in IET Image Processing
Verified
Journal Article
Open access
PDF file
MMMahnaz Moghaddam
Mahnaz Moghaddam
MCMostafa Charmi
Mostafa Charmi
HHHossein Hassanpoor
Hossein Hassanpoor
Pedestrian attributes recognition is an important issue in computer vision and has a special role in the field of video surveillance. The previous methods presented to solve this issue are mainly based on multi‐label end‐to‐end deep neural networks. These methods neglect to apply attributes for defining local feature areas and they suffer from the problems of the bounding box presence. A new framework for jointly human semantic parsing and pedestrian attribute recognition to achieve effective attribute recognition is proposed. By extracting human parts via semantic parsing, both semantic and spatial information can be explored with eliminating of background. The framework also uses multi‐scale features to employ rich details and contextual information through proposed attribute recognition‐bidirectional feature pyramid network. For baseline network that has a significant impact on the performance, EfficientNet‐B3 is selected as a baseline network from The EfficientNet family which provides an appropriate trade‐off between the three factors of CNNs scaling (depth/width/resolution). Finally, the proposed framework is tested on datasets PETA, RAP and PA‐100k. Experimental results show that our method has superior performance in both mean accuracy and instance‐based metrics compared to state‐of‐the‐art results.

12 January 2022 in Complexity
Verified
Journal Article
Open access
PDF file
MZMaryam Zolfaghari-Nejad
Maryam Zolfaghari-Nejad
MCMostafa Charmi
Mostafa Charmi
HHHossein Hassanpoor
Hossein Hassanpoor
In this work, we introduce a new non‐Shilnikov chaotic system with an infinite number of nonhyperbolic equilibrium points. The proposed system does not have any linear term, and it is worth noting that the new system has one equilibrium point with triple zero eigenvalues at the origin. Also, the novel system has an infinite number of equilibrium points with double zero eigenvalues that are located on the z‐axis. Numerical analysis of the system reveals many strong dynamics. The new system exhibits multistability and antimonotonicity. Multistability implies the coexistence of many periodic, limit cycle, and chaotic attractors under different initial values. Also, bifurcation analysis of the system shows interesting phenomena such as periodic window, period‐doubling route to chaos, and inverse period‐doubling bifurcations. Moreover, the complexity of the system is analyzed by computing spectral entropy. The spectral entropy distribution under different initial values is very scattered and shows that the new system has numerous multiple attractors. Finally, chaos‐based encoding/decoding algorithms for secure data transmission are developed by designing a state chain diagram, which indicates the applicability of the new chaotic system.