About
Articles by Farhad
-
Research & Innovation in Computer Science & Bioinformatics
Research & Innovation in Computer Science & Bioinformatics
By Farhad Maleki
Activity
-
One of the great talks at #GECCO2024 was presented by Prof. Una-May O'Reilly and Dr Erik Hemberg from Massachusetts Institute of Technology. In the…
One of the great talks at #GECCO2024 was presented by Prof. Una-May O'Reilly and Dr Erik Hemberg from Massachusetts Institute of Technology. In the…
Liked by Farhad Maleki
-
What a fantastic start! I'm thrilled that the inaugural Ag-Tech Days event was a resounding success. Precision agriculture is an increasingly vital…
What a fantastic start! I'm thrilled that the inaugural Ag-Tech Days event was a resounding success. Precision agriculture is an increasingly vital…
Liked by Farhad Maleki
-
We're hiring for a Technology Transfer Associate (TTA). Join our Technology Transfer Office (TTO) and support research with commercial and societal…
We're hiring for a Technology Transfer Associate (TTA). Join our Technology Transfer Office (TTO) and support research with commercial and societal…
Liked by Farhad Maleki
Experience & Education
Licenses & Certifications
-
-
-
-
M.Sc. in Computer Science, Amirkabir University of Technology
Amirkabir University of Technology
Volunteer Experience
Publications
-
Generalizability of Machine Learning Models: Quantitative Evaluation of Three Methodological Pitfalls
Radiology: Artificial Intelligence
-
Radiomics as an emerging tool in the management of brain metastases
Oxford University Press
-
Importance of sex and gender factors for COVID-19 infection and hospitalisation: a sex-stratified analysis using machine learning in UK Biobank data
British Medical Journal Publishing Group
-
A Semi-Self-Supervised Learning Approach for Wheat Head Detection Using Extremely Small Number of Labeled Samples
Proceedings of the IEEE/CVF International Conference on Computer Vision
Most of the success of deep learning is owed to supervised learning, where a large-scale annotated dataset is used for model training. However, developing such datasets is challenging. In this paper, we develop a semi-self-supervised learning approach for wheat head detection. The proposed method utilized a few short video clips and only one annotated image from each video clip of wheat fields to simulate a large computationally annotated dataset used for model building. Considering the domain…
Most of the success of deep learning is owed to supervised learning, where a large-scale annotated dataset is used for model training. However, developing such datasets is challenging. In this paper, we develop a semi-self-supervised learning approach for wheat head detection. The proposed method utilized a few short video clips and only one annotated image from each video clip of wheat fields to simulate a large computationally annotated dataset used for model building. Considering the domain gap between the simulated and real images, we applied two domain adaptation steps to alleviate the challenge of distributional shift. The resulting model achieved high performance when applied to real unannotated datasets. When fine-tuned on the dataset from the Global Wheat Head Detection Challenge, the performance was further improved. The model achieved a mean average precision of 0.827, where an overlap of 50% or more between a predicted bounding box and ground truth was considered as a correct prediction. Although the utility of the proposed methodology was shown by applying it to wheat head detection, the proposed method is not limited to this application and could be used for other domains, such as detecting different crop types, alleviating the barrier of lack of large-scale annotated datasets in those domains.
-
Juxtapose: a gene-embedding approach for comparing co-expression networks
BMC Bioinformatics
-
Machine Learning Algorithm Validation: From Essentials to Advanced Applications and Implications for Regulatory Certification and Deployment
Neuroimaging Clinics of North America
-
Overview of machine learning part 1: fundamentals and classic approaches
Neuroimaging Clinics of North America
-
Overview of machine learning: deep learning for medical image analysis
Neuroimaging Clinics of North America
-
Gene Set Analysis: Challenges, Opportunities, and Future Research
Frontiers in Genetics
Gene set analysis methods are widely used to provide insight into high-throughput gene expression data. There are many gene set analysis methods available. These methods rely on various assumptions and have different requirements, strengths and weaknesses. In this paper, we classify gene set analysis methods based on their components, describe the underlying requirements and assumptions for each class, and provide directions for future research in developing and evaluating gene set analysis…
Gene set analysis methods are widely used to provide insight into high-throughput gene expression data. There are many gene set analysis methods available. These methods rely on various assumptions and have different requirements, strengths and weaknesses. In this paper, we classify gene set analysis methods based on their components, describe the underlying requirements and assumptions for each class, and provide directions for future research in developing and evaluating gene set analysis methods.
Other authorsSee publication -
pineplot: an R package for visualizing symmetric relationships
Association for Computing Machinery
An effective publication-quality visualization tells a concise story from data. Methods and tools that facilitate making such visualizations are valuable to the scientific community. In this paper, we introduce pineplot, an R package for generating insightful visualizations called pine plots. Pine plots are applicable to a wide variety of datasets and create a holistic picture of the relationship between variables across different experimental conditions. A pine plot provides a means to…
An effective publication-quality visualization tells a concise story from data. Methods and tools that facilitate making such visualizations are valuable to the scientific community. In this paper, we introduce pineplot, an R package for generating insightful visualizations called pine plots. Pine plots are applicable to a wide variety of datasets and create a holistic picture of the relationship between variables across different experimental conditions. A pine plot provides a means to visualize a group of symmetric matrices, each represented by triangular heat maps. Pine plots can be used to visualize large datasets for exploratory data analysis while controlling for different potentially confounding factors. The utility of the package is demonstrated by visualizing gene expression values of tissue-specific genes from RNA-seq data and the clinical factors in a liver disease and a heart disease dataset. The implementation of pineplot offers a straightforward procedure for generating pine plots; full control of the aesthetic elements of generated plots; and the possibility of augmenting generated plots with extra layers of graphical elements to further extend their usability.
Other authorsSee publication -
Measuring consistency among gene set analysis methods: A systematic study
Journal of Bioinformatics and Computational Biology
-
Gene Set Overlap: An Impediment to Achieving High Specificity in Over-representation Analysis
BIOSTEC 2019, 12th International Joint Conference on Biomedical Engineering Systems and Technologies.
-
Method Choice in Gene Set Analysis has Important Consequences for Analysis Outcome
BIOSTEC 2019, 12th International Joint Conference on Biomedical Engineering Systems and Technologies.
-
Sample Size and Reproducibility of Gene Set Analysis
The IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
-
DAPPLE 2: a tool for the homology-based prediction of post-translational modification sites
Journal of Proteome Research
-
Evolutionary approach for developing fast and stable offline humanoid walk
Thirteenth International Computer 2006 Conference, Iran, Kish Island
-
Dual Energy Computed Tomography in Head and Neck Imaging: Pushing the Envelope
euroimaging Clinics of North America
Multiple applications of dual-energy computed tomography (DECT) have been described for the evaluation of disorders in the head and neck, especially in oncology. We review the body of evidence suggesting the advantages of DECT for the evaluation of the neck compared with conventional single energy computed tomography scans, but the full potential of DECT is still to be realized. There is early evidence suggesting significant advantages of DECT for the extraction of quantitative biomarkers using…
Multiple applications of dual-energy computed tomography (DECT) have been described for the evaluation of disorders in the head and neck, especially in oncology. We review the body of evidence suggesting the advantages of DECT for the evaluation of the neck compared with conventional single energy computed tomography scans, but the full potential of DECT is still to be realized. There is early evidence suggesting significant advantages of DECT for the extraction of quantitative biomarkers using radiomics and machine learning, representing a new horizon that may enable this technology to reach its full potential.
Other authors -
-
Gene Set Databases: A Fountain of Knowledge or a Siren Call?
10th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM BCB)
-
Size Matters: How Sample Size Affects the Reproducibility and Specificity of Gene Set Analysis
BMC Human Genomics
Courses
-
Deep Learning for Plant Image Analysis
CMPT 898-14
-
Artificial intelligence
-
-
Bioinformatics and Computational Biology
CMPT 830
-
Biostatistics I
CHEP 805
-
Biostatistics for Public Health II
PUBH 811
-
Image Processing
-
-
Machine Learning
-
-
Optimization
-
-
Special Topics in Applied Mathematics (An Introduction to the Art and Science of Large Data)
MATH 818
-
Special Topics in Operations Research – Modeling for Decision Making
CMPT 858
-
Theory of computer Science
-
Honors & Awards
-
Best Student Paper Award
BIOSTEC 2019: the 12th International Joint Conference on Biomedical Engineering Systems and Technologies
Awarded to:
Method Choice in Gene Set Analysis Has Important Consequences for Analysis Outcome
Authors:
Farhad Maleki, Katie L. Ovens, Elham Rezaei, Alan M. Rosenberg and Anthony J. Kusalik
"The BIOSTEC joint conference received 271 paper submissions from 47 countries in all continents, of which 12.5% were accepted as full papers." -
Second Place - Local ACM Programming Contest
University of Saskatchewan
Second Place: Local ACM Programming Contest- University of Saskatchewan
-
Teacher Scholar Doctoral Fellowship
University of Saskatchewan
-
Saskatchewan Innovation and Opportunity Scholarship
Government of Saskatchewan/University of Saskatchewan
-
Teacher Scholar Doctoral Fellowship
University of Saskatchewan
Declined
-
Dean’s Scholarship
University of Saskatchewan
-
Dean’s Scholarship
University of Saskatchewan
-
Saskatchewan Innovation and Opportunity Scholarship
Government of Saskatchewan/University of Saskatchewan
-
Dean’s Scholarship
University of Saskatchewan
Languages
-
Kurdish
-
-
Persian
-
-
English
-
Organizations
-
Computer Science Graduate Course Council
President
- Present -
Research Fest 2016 / Research & Innovation in Computer Science & Bioinformatics
Lead Organizer
-http://csgcc-devel.usask.ca/researchfest/2016/
-
Computer Science Graduate Course Council (CSGCC)
PhD Representative
-
More activity by Farhad
-
The Agri-food sector in Canada is using technology like we’ve never seen before to create new solutions. 🌱🦾 And this innovation is a team sport.…
The Agri-food sector in Canada is using technology like we’ve never seen before to create new solutions. 🌱🦾 And this innovation is a team sport.…
Liked by Farhad Maleki
People also viewed
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Farhad Maleki
43 others named Farhad Maleki are on LinkedIn
See others named Farhad Maleki