Sayeed Iftekhar Yousuf
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sayeed Iftekhar Yousuf has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Machbah Uddin
Department of Computer Science and Mathematics, Bangladesh Agricultural University, Mymensingh, Bangladesh
4 shared publications - Rakib Hassan
Department of Computer Science and Mathematics, Bangladesh Agricultural University, Mymensingh, Bangladesh
3 shared publications - Farah Jahan
Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh
2 shared publications - Mohammad Khairul Islam
Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh
2 shared publications - A. K. M. Adham
Department of Irrigation and Water Management, Bangladesh Agricultural University, Mymensingh 2202, Bangladesh
1 shared publication - Aminul Islam
Prince Mohammad Bin Fahd University, Saudi Arabia
1 shared publication
Latest Publications
- Open Access
- 1 May 2026
- Published by IWA Publishing in Journal of Water and Climate Change
- Vol. 17 (5) , 1329-1357
River water level forecast sensitivity to hydrometeorological input variable selection: a comparison of machine and deep learning models in Bangladesh
Conceptual summary showing LSTM and GRU outperform ML models under meteorological-only inputs, while RFR and LGBMR dominate when lagged water level data are available, across five scenarios in the Old Brahmaputra River, Bangladesh. Accurate river water level forecasting is critical for flood management in Bangladesh's monsoon-dominated deltaic environment, yet optimal model selection under varying data availability remains unexplored. This study systematically compared six machine learning (ML) and deep learning (DL) algorithms, specifically linear regression, support vector regression, random forest regression (RFR), light gradient boosting machine regression (LGBMR), long short-term memory (LSTM), and gated recurrent unit (GRU), for water level prediction at Islampur station using 25 years of daily hydrometeorological data (1999–2024) across five input scenarios employing 5-day lag configurations. DL architectures dominated meteorological-only scenarios, with LSTM achieving R2 = 0.8809, explained variance score (EVS) = 0.8874, and symmetric mean absolute percentage error (SMAPE) = 4.83%, confirming unbiased symmetrical predictions. ML algorithms excelled with autoregressive inputs, where LGBMR achieved R2 = 0.9960 and RFR attained R2 = 0.9984; the latter's EVS = 0.9984 and SMAPE = 0.40% confirmed purely stochastic residuals. Principal component analysis (PCA)-based composite scoring of nine complementary metrics provided objective model rankings. Zero-shot spatial transferability at Sarishabari confirmed reproducible hierarchies without retraining, with violin plots and PCA composite scoring corroborating near-zero prediction bias across all transferred configurations. Results demonstrate that LSTM and GRU enable reliable forecasting under input-limited, meteorological-only conditions while ensemble ML provides superior accuracy when water level observations are available, offering actionable guidance for flood forecasting in data-constrained environments.
- 1 May 2026
- Published by IWA Publishing in Journal of Water and Climate Change
- Vol. 17 (5) , 1329-1357
Open AccessRiver water level forecast sensitivity to hydrometeorological input variable selection: a comparison of machine and deep learning models in Bangladesh
Conceptual summary showing LSTM and GRU outperform ML models under meteorological-only inputs, while RFR and LGBMR dominate when lagged water level data are available, across five scenarios in the Old Brahmaputra River, Bangladesh. Accurate river water level forecasting is critical for flood management in Bangladesh's monsoon-dominated deltaic environment, yet optimal model selection under varying data availability remains unexplored. This study systematically compared six machine learning (ML) and deep learning (DL) algorithms, specifically linear regression, support vector regression, random forest regression (RFR), light gradient boosting machine regression (LGBMR), long short-term memory (LSTM), and gated recurrent unit (GRU), for water level prediction at Islampur station using 25 years of daily hydrometeorological data (1999–2024) across five input scenarios employing 5-day lag configurations. DL architectures dominated meteorological-only scenarios, with LSTM achieving R2 = 0.8809, explained variance score (EVS) = 0.8874, and symmetric mean absolute percentage error (SMAPE) = 4.83%, confirming unbiased symmetrical predictions. ML algorithms excelled with autoregressive inputs, where LGBMR achieved R2 = 0.9960 and RFR attained R2 = 0.9984; the latter's EVS = 0.9984 and SMAPE = 0.40% confirmed purely stochastic residuals. Principal component analysis (PCA)-based composite scoring of nine complementary metrics provided objective model rankings. Zero-shot spatial transferability at Sarishabari confirmed reproducible hierarchies without retraining, with violin plots and PCA composite scoring corroborating near-zero prediction bias across all transferred configurations. Results demonstrate that LSTM and GRU enable reliable forecasting under input-limited, meteorological-only conditions while ensemble ML provides superior accuracy when water level observations are available, offering actionable guidance for flood forecasting in data-constrained environments.
- Open Access
- 3 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 156188-156202
Phylogeny Reconstruction Using Multi-Agent Surface Area Pressure Features
Phylogenetic analysis of species is essential for understanding the various biological activities of an organism, including gene editing, drug design, and vaccine development. Traditional alignment-based (AB) methods, however, face significant computational challenges, becoming NP-hard when applied to large or medium-sized sequences. As a result, alignment-free (AF) approaches have gained attraction. Despite their growing popularity, AF methods struggle to optimize the critical aspects of computational time, accuracy, and memory usage. Due to the time inefficiency of AF approaches, significant man-hours are wasted in laboratories. Consequently, different studies have employed statistical approaches on entire sequences; however, these are less efficient because they lose positional information, for which relative information-based approaches, including entropy and joint probability, have achieved higher performance. However, entropy-based methods are not highly sensitive to small changes in DNA sequences. In response to these limitations, a novel multi-agent surface area pressure (MASAP) feature-based method is proposed, which is highly sensitive and efficient in representing the relative information of a DNA sequence. First, it selects the length of the k-mer and constructs a 2D list for the positional information of k-mers, where each row corresponds to a specific k-mer. Subsequently, the positional data is converted into relative data from which the MASAP feature is derived, and this is used for feature descriptor generation and phylogenetic tree reconstruction. Extensive experiments were carried out on benchmark datasets, and the proposed MASAP method consistently achieved top-ranked accuracy across all datasets. Furthermore, in terms of computational time, MASAP significantly outperforms existing methods, being 5, 151 to 8, 162 times faster than the MEGA tool. The source code and datasets are available at https://github.com/machbah/MASP.
- 3 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 156188-156202
Open AccessPhylogeny Reconstruction Using Multi-Agent Surface Area Pressure Features
Phylogenetic analysis of species is essential for understanding the various biological activities of an organism, including gene editing, drug design, and vaccine development. Traditional alignment-based (AB) methods, however, face significant computational challenges, becoming NP-hard when applied to large or medium-sized sequences. As a result, alignment-free (AF) approaches have gained attraction. Despite their growing popularity, AF methods struggle to optimize the critical aspects of computational time, accuracy, and memory usage. Due to the time inefficiency of AF approaches, significant man-hours are wasted in laboratories. Consequently, different studies have employed statistical approaches on entire sequences; however, these are less efficient because they lose positional information, for which relative information-based approaches, including entropy and joint probability, have achieved higher performance. However, entropy-based methods are not highly sensitive to small changes in DNA sequences. In response to these limitations, a novel multi-agent surface area pressure (MASAP) feature-based method is proposed, which is highly sensitive and efficient in representing the relative information of a DNA sequence. First, it selects the length of the k-mer and constructs a 2D list for the positional information of k-mers, where each row corresponds to a specific k-mer. Subsequently, the positional data is converted into relative data from which the MASAP feature is derived, and this is used for feature descriptor generation and phylogenetic tree reconstruction. Extensive experiments were carried out on benchmark datasets, and the proposed MASAP method consistently achieved top-ranked accuracy across all datasets. Furthermore, in terms of computational time, MASAP significantly outperforms existing methods, being 5, 151 to 8, 162 times faster than the MEGA tool. The source code and datasets are available at https://github.com/machbah/MASP.
- 30 March 2024
- Published by Springer Nature
- p. 33-47
Phylogeny Reconstruction Using $k-mer$ Derived Transition Features- 30 March 2024
- Published by Springer Nature
- p. 33-47
Phylogeny Reconstruction Using $k-mer$ Derived Transition Features- 6 May 2022
- Published by Springer Nature in Environmental Science and Pollution Research
- Vol. 29 (44) , 67103-67114
An assessment of meteorological parameters effects on COVID-19 pandemic in Bangladesh using machine learning models
Coronavirus (COVID-19) is a highly contagious virus (SARS-CoV-2) that has caused a global pandemic since January 2020. Scientists around the world are doing extensive research to control this disease. They are working tirelessly to find out the origin and causes of the disease. Several studies and experiments mentioned that there are some meteorological parameters which are highly correlated with COVID-19 transmission. In this work, we studied the effects of 11 meteorological parameters on the transmission of COVID-19 in Bangladesh. We first applied statistical analysis and observed that there is no significant effect of these parameters. Therefore, we proposed a novel technique to analyze the insight effects of these parameters by using a combination of Random Forest, CART, and Lasso feature selection techniques. We observed that 4 parameters are highly influential for COVID-19 where \(T_{min}\) and Cloud have positive association whereas WS and AQ have negative impact. Among them, Cloud has the highest positive impact which is 0.063 and WS has the highest negative association which is \(-0.021\). Moreover, we have validated our performance using DLNM technique. The result of this investigation can be used to develop an alert system that will assist the policymakers to know the characteristics of COVID-19 against meteorological parameters and can impose different policies based on the weather conditions.- 6 May 2022
- Published by Springer Nature in Environmental Science and Pollution Research
- Vol. 29 (44) , 67103-67114
An assessment of meteorological parameters effects on COVID-19 pandemic in Bangladesh using machine learning models
Coronavirus (COVID-19) is a highly contagious virus (SARS-CoV-2) that has caused a global pandemic since January 2020. Scientists around the world are doing extensive research to control this disease. They are working tirelessly to find out the origin and causes of the disease. Several studies and experiments mentioned that there are some meteorological parameters which are highly correlated with COVID-19 transmission. In this work, we studied the effects of 11 meteorological parameters on the transmission of COVID-19 in Bangladesh. We first applied statistical analysis and observed that there is no significant effect of these parameters. Therefore, we proposed a novel technique to analyze the insight effects of these parameters by using a combination of Random Forest, CART, and Lasso feature selection techniques. We observed that 4 parameters are highly influential for COVID-19 where \(T_{min}\) and Cloud have positive association whereas WS and AQ have negative impact. Among them, Cloud has the highest positive impact which is 0.063 and WS has the highest negative association which is \(-0.021\). Moreover, we have validated our performance using DLNM technique. The result of this investigation can be used to develop an alert system that will assist the policymakers to know the characteristics of COVID-19 against meteorological parameters and can impose different policies based on the weather conditions.- Open Access
- 11 October 2021
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 8 (1) , 657-671
Paddy seed variety identification using T20-HOG and Haralick textural features
The seed is an inevitable element for agricultural and industrial production. The non-destructive paddy seed variety identification is essential to assure paddy purity and quality. This research is aimed at developing a computer vision-based system to identify paddy varieties using multiple heterogeneous features, exploiting textural, external, and physical properties. We captured the paddy seed images without any fixed setup to make the system user friendly at both industry and farmer levels, which can lead to illumination problems in the images. To overcome this problem, we introduced a modified histogram oriented gradient (T20-HOG) feature that can describe the illumination, scale, and rotational variations of a paddy image. We also utilized the existing Haralick and traditional features and the dimensionality of the features is reduced by the Lasso feature selection technique. The selected features are used to train the feed-forward neural network (FNN) to predict the paddy variety. The experiments conducted on two different datasets: BDRICE, and VNRICE. Results of our method are shown in terms of four standard evaluation metrics, namely, accuracy, precision, recall, and F_1 score, and achieved 99.28%, 98.64%, 98.48%, and 98.56% score, respectively. We also compared our system efficiency with existing studies. The experimental results demonstrate that our proposed features are effective to identify paddy variety and achieved a new state-of-the-art performance. And we also observed that our newly proposed T20-HOG features have a major impact on overall system performance.
- 11 October 2021
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 8 (1) , 657-671
Open AccessPaddy seed variety identification using T20-HOG and Haralick textural features
The seed is an inevitable element for agricultural and industrial production. The non-destructive paddy seed variety identification is essential to assure paddy purity and quality. This research is aimed at developing a computer vision-based system to identify paddy varieties using multiple heterogeneous features, exploiting textural, external, and physical properties. We captured the paddy seed images without any fixed setup to make the system user friendly at both industry and farmer levels, which can lead to illumination problems in the images. To overcome this problem, we introduced a modified histogram oriented gradient (T20-HOG) feature that can describe the illumination, scale, and rotational variations of a paddy image. We also utilized the existing Haralick and traditional features and the dimensionality of the features is reduced by the Lasso feature selection technique. The selected features are used to train the feed-forward neural network (FNN) to predict the paddy variety. The experiments conducted on two different datasets: BDRICE, and VNRICE. Results of our method are shown in terms of four standard evaluation metrics, namely, accuracy, precision, recall, and F_1 score, and achieved 99.28%, 98.64%, 98.48%, and 98.56% score, respectively. We also compared our system efficiency with existing studies. The experimental results demonstrate that our proposed features are effective to identify paddy variety and achieved a new state-of-the-art performance. And we also observed that our newly proposed T20-HOG features have a major impact on overall system performance.