MAMohsen Ahmadkhani

Mohsen Ahmadkhani

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mohsen Ahmadkhani has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    TopoSinGAN: Learning a Topology-Aware Generative Model from a Single Image

    by Mohsen Ahmadkhani, Eric Shook

    Generative adversarial networks (GANs) have significantly advanced synthetic image generation, yet ensuring topological coherence remains a challenge. This paper introduces TopoSinGAN, a topology-aware extension of the SinGAN framework, designed to enhance the topological accuracy of generated images. TopoSinGAN incorporates a novel, differentiable topology loss function that minimizes terminal node counts along predicted segmentation boundaries, thereby addressing topological anomalies not captured by traditional losses. We evaluate TopoSinGAN using agricultural and dendrological case studies, demonstrating its capability to maintain boundary continuity and reduce undesired loop openness. A novel evaluation metric, Node Topology Clustering (NTC), is proposed to assess topological attributes independently of geometric variations. TopoSinGAN significantly improves topological accuracy, reducing NTC index values from 15.15 to 3.94 for agriculture and 14.55 to 2.44 for dendrology, compared to the baseline SinGAN. Modified FID evaluations also show improved realism, with lower FID scores: 0.1914 for agricultural fields compared to 0.2485 for SinGAN, and 0.0013 versus 0.0014 for dendrology. The topology loss enables end-to-end training with direct topological feedback. This new framework advances the generation of topologically accurate synthetic images, with applications in fields requiring precise structural representations, such as geographic information systems (GIS) and medical imaging.


  • Aedes albopictus: a spatial risk mapping of the mosquito using geographic information system in Iran

    by Reza Shirzad, Ali Asghar Alesheikh, Mohsen Ahmadkhani, Saied Reza Naddaf


  • Open Access

    Exploring the role of parental proximity in the maternal–neonate bond and parental investment in moose (Alces alces) through postcapture movement dynamics

    by Glenn D. DelGiudice, Mohsen Ahmadkhani, Véronique St‐Louis, William J. Severud, Tyler R. Obermoller

    Disturbance can induce some dams to abandon their neonates, whereas others continue parental investment. Understanding the variability of the dam–neonate bond and parental investment of large, mobile species, reclusive during calving, such as moose (Alces alces), can be challenging. Advances in global positioning system (GPS) collar technology and analytical approaches allowed us to better understand the role that dam–neonate proximity plays in maintaining the maternal–neonate bond and maternal investment. In 2013 and 2014, we used movement behavior of 50 free‐ranging GPS‐collared dams and their 74 GPS‐collared neonates during 96 hr postcapture/release of neonates to examine home range (HR) sizes, overlap of their HRs, reunions (≤26 m), and dynamic interactions of their movements. Mean area of 95% kernel density estimator (KDE) HRs of neonates (23.5 ha) not abandoned by their dams was more than 2 times that of abandoned neonates (10.4 ha). Mean HR area of dams continuing to invest in their neonates (104 ha) was smaller than that (897 ha) of abandoning dams. Mean overlap of core (50% KDE) and 95% KDE HRs of dam–neonate pairs when investment continued was 38.7% and 42%, whereas corresponding overlap of HRs associated with abandonment was 0.1% and 2.7%. Mean proportion of pairwise hourly location‐fixes indicative of reunions of dams investing in their neonates was 0.37 and occurred at a mean interval of 2.7 hr. A stronger (p ≤ .05) interaction of mean hourly distances moved (did) between dams investing in their neonates was associated with closer proximity compared with dams abandoning neonates. Our collective data indicate that the spatial proximity of dams investing in their neonates, and their stronger bond, nurtured neonate vitality in a way that reinforced continued investment. In contrast, the abandoning behavior of more distant dams had a diminishing influence on viability of their neonates via nutritional deprivation and limited reciprocal stimulation.


  • Open Access

    SPATIO-STATISTICAL MODELING OF HUMAN BRUCELLOSIS USING ENVIRONMENTAL PARAMETERS: A CASE STUDY OF NORTHERN IRAN

    by N. Seyedalizadeh, A. A. Alesheikh, M. Ahmadkhani

    Brucellosis is one of the most important zoonotic diseases which is endemic in Iran. This disease is considered a significant hazard to citizens’ health and imposes heavy economic burdens, hence, requires a thorough control and management plan. The aims of this study are identifying the areas having the highest risk of brucellosis, as well as discovering the contributing environmental factors. The maximum entropy (MaxEnt) method was used to model the probability of brucellosis in Golestan, Mazandaran, and Guilan provinces. The possible contribution of 12 environmental parameters in this disease was also measured using the Jackknife method. The results showed that the highest risk of brucellosis is located in southern Golestan, East, and West of Mazandaran, and south of Guilan province, and moisture, slope, vegetation and elevation are the most effective environmental factors on the spatial distribution of the disease. In addition, the probability of the disease in northern Iran increases from west to east. These findings could assist the public health managers and decision-makers in organizing a more efficient public health system.