Sobhan Sheykhivand

Dr. Sobhan Sheykhivand


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
14 December 2024 in Biomimetics
Verified
Journal Article
Open access
PDF file
BYBehzad Yousefipour
Behzad Yousefipour
VRVahid Rajabpour
Vahid Rajabpour
Hamidreza AbdoljabbariHamidreza Abdoljabbari
Hamidreza Abdoljabbari
SSSobhan Sheykhivand
Sobhan Sheykhivand
Sebelan DanishvarSebelan Danishvar
Sebelan Danishvar
In recent years, significant advancements have been made in the field of brain–computer interfaces (BCIs), particularly in the area of emotion recognition using EEG signals. The majority of earlier research in this field has missed the spatial–temporal characteristics of EEG signals, which are critical for accurate emotion recognition. In this study, a novel approach is presented for classifying emotions into three categories, positive, negative, and neutral, using a custom-collected dataset. The dataset used in this study was specifically collected for this purpose from 16 participants, comprising EEG recordings corresponding to the three emotional states induced by musical stimuli. A multi-class Common Spatial Pattern (MCCSP) technique was employed for the processing stage of the EEG signals. These processed signals were then fed into an ensemble model comprising three autoencoders with Convolutional Neural Network (CNN) layers. A classification accuracy of 99.44 ± 0.39% for the three emotional classes was achieved by the proposed method. This performance surpasses previous studies, demonstrating the effectiveness of the approach. The high accuracy indicates that the method could be a promising candidate for future BCI applications, providing a reliable means of emotion detection.

15 January 2025 in Biomimetics
Verified
Journal Article
Open access
RVReza Hadjiaghaie Vafaie
Reza Hadjiaghaie Vafaie
AFAli Fardi-Ilkhchy
Ali Fardi-Ilkhchy
SSSobhan Sheykhivand
Sobhan Sheykhivand
Sebelan DanishvarSebelan Danishvar
Sebelan Danishvar
The ability to control and manipulate biological fluids within microchannels is a fundamental challenge in biological diagnosis and pharmaceutical analyses, particularly when buffers with very high ionic strength are used. In this study, we investigate the numerical and experimental study of fluidic biochips driven by ac electrothermal flow for controlling and manipulating biological samples inside a microchannel, e.g., for fluid-driven and manipulation purposes such as concentrating and mixing. By appropriately switching the voltage on the electrode structures and inducing AC electrothermal forces within the channel, a fluidic network with pumping and manipulation capabilities can be achieved, enabling the control of fluid velocity/direction and also fluid rotation. By using finite element analysis, coupled physics of electrical, thermal, fluidic fields, and molecular diffusion transport were solved. AC electrothermal flow was studied for pumping and mixing applications, and the optimal model was extracted. The microfluidic chip was fabricated using two processes: electrode structure development on the chip and silicon mold fabrication in a cleanroom. PDMS was prepared as the microchannel material and bonded to the electrode structure. After implementing the chip holder and excitation circuit, a biological buffer with varying ionic strengths (0.2, 0.4, and 0.6 [S/m]) was prepared, mixed with fluorescent particles, and loaded into the microfluidic chip. Experimental results demonstrated the efficiency of the proposed chip for biological applications, showing that stronger flows were generated with increasing fluid conductivity and excitation voltage. The system behavior was characterized using an impedance analyzer. Frequency response analysis revealed that for a solution with an electrical conductivity of 0.6 [S/m], the fluid velocity remained almost constant within a frequency range of 100 kHz to 10 MHz. Overall, the experimental results showed good agreement with the simulation outcomes.

6 February 2026 in Biomimetics
Verified
Journal Article
Open access
PDF file
MKMehdi Khaleghi
Mehdi Khaleghi
SSSobhan Sheykhivand
Sobhan Sheykhivand
NKNastaran Khaleghi
Nastaran Khaleghi
Sebelan DanishvarSebelan Danishvar
Sebelan Danishvar
Acknowledging recent breakthroughs in the context of deep bio-inspired neural networks, several architectural deep network options have been deployed to create intelligent systems. The foundations of convolutional neural networks are influenced by hierarchical processing in the visual cortex. The graph neural networks mimic the communication of biological neurons. Considering these two computation methods, a novel deep ensemble network is used to propose a bio-inspired deep graph network for creating an intelligent supply chain model. An automated smart supply chain helps to create a more agile, resilient and sustainable system. Improving the sustainability of the network plays a key role in the efficiency of the supply chain’s performance. The proposed bio-inspired Chebyshev ensemble graph network (Ch-EGN) is hybrid learning for creating an intelligent supply chain. The functionality of the proposed deep network is assessed on two different databases including SupplyGraph and DataCo for risk administration, enhancing supply chain sustainability, identifying hidden risks and increasing the supply chain’s transparency. An average accuracy of 98.95% is obtained using the proposed network for automatic delivery status prediction. The performance metrics regarding multi-class categorization scenarios of the intelligent supply chain confirm the efficiency of the proposed bio-inspired approach for sustainability and risk management.

7 November 2025 in Biomimetics
Verified
Journal Article
Open access
PDF file
RVReza Hadjiaghaie Vafaie
Reza Hadjiaghaie Vafaie
EPElnaz Poorreza
Elnaz Poorreza
SSSobhan Sheykhivand
Sobhan Sheykhivand
Sebelan DanishvarSebelan Danishvar
Sebelan Danishvar
Cancers are diseases described by the irregular spread of cells that have developed invasive features, enabling them to invade adjacent tissues. The specific diagnosis and effective management of oncological treatments depend on the timely detection of circulating tumor cells (CTCs) in a patient’s bloodstream. One of the most promising approaches to CTC separation from blood fractions involves the dielectrophoresis (DEP) technique. This research presents a new DEP-based bionic system designed for MDA-MB-231 breast cancer cell isolation from white blood cell (WBC) subtypes with a viable approach to cell viability. This work leverages the principle that every cell type possesses a unique dielectric fingerprint. This dielectrophoresis microfluidic device is designed to act as a scanner, reading these fingerprints to achieve a continuous, label-free separation of cancer cells from blood components with a high efficiency. In the proposed system that consists of three different stages, the first stage allows for separating B-lymphocytes and Monocytes from Granulocytes and MDA-MB-231 cells. The separation of B-lymphocytes from Monocytes occurs in the second step, while the last step concerns the separation of Granulocytes and MDA-MB-231 cells. In the analysis, x-y graphs of the electric potentials, velocity fields, pressure distributions, and cellular DEP forces applied to the cells, as well as the resulting particle paths, are provided. The model predicts that the system operates with a separation efficiency of nearly 92%. This work focuses on an investigation of the impact of electrode potentials, the velocity of cells, the number of electrodes, the width of the channel, and the output angles on enhancing the separation efficiency of particles.

22 June 2026 in Biomimetics
Verified
Journal Article
Open access
PDF file
MKMehdi Khaleghi
Mehdi Khaleghi
Farshad PashootanizadehFarshad Pashootanizadeh
Farshad Pashootanizadeh
NKNastaran Khaleghi
Nastaran Khaleghi
SSSobhan Sheykhivand
Sobhan Sheykhivand
Sebelan DanishvarSebelan Danishvar
Sebelan Danishvar
VGVahidReza Ghezavati
VahidReza Ghezavati
Systematic logistics plays a key role in fostering profitable development in supply chains. An intelligent logistics model can help create a more agile, sustainable, and resilient supply chain. In recent years, several brain-inspired deep learning architectures, such as long short-term memory networks, graph neural networks, and convolutional neural networks, have been introduced for intelligent decision-making tasks. From a biomimetic perspective, these models are inspired by biological information-processing mechanisms. Convolutional neural networks reflect hierarchical procedures similar to those in the visual cortex, graph neural networks mimic communication among biological neurons, and LSTM networks are motivated by short-term and long-term memory mechanisms in the brain. Inspired by these biomimetic computational principles, this study proposes a novel hybrid deep learning strategy composed of LSTM, convolutional layers and GraphSAGE geometric layers for smart supply chain logistics management. This strategy enables leveraging information pertaining to LSTM-based long-term dependencies, convolutional local patterns and graph-related hidden connections of the supply chain dataset for intelligent decision-making. The GraphSAGE framework helps with scalable graph learning, which enhances predictive accuracy in the case of unseen data. The optimizer in the proposed methodology performs sequential optimization using the biomimetic particle swarm optimizer and the Adam approach (PSO-Adam), considering the hybrid cost function. The prediction of logistics parameters is investigated using five datasets, including DataCo, Shipping, Smart Logistics, Hospital Supply Chain, and Pharmaceutical Supply Chain. The average accuracies of 97.8%, 100%, 96.6%, 98.7% and 99.4% are obtained for practical multi-category logistics parameter forecasts. The evaluation metrics for ten logistics predictions confirm the effectiveness of the proposed intelligent logistics model and highlight the potential of biomimetic geometric networks for complex supply chain decision-making. The model is a cost-efficient approach with consideration of the prediction capabilities, helping to reduce the occurrence of logistics risks, increase the productivity of the supply chain and affect the supply chain visibility, customer satisfaction, and industry reputation.