Mahbub E Sobhani Himel

Imbalanced intrusion classification is a complex and challenging task as there are few number of instances/intrusions generally considered as minority instances/intrusions in the imbalanced intrusion datasets. Data sampling methods such as over-sampling and under-sampling methods are commonly applied for dealing with imbalanced intrusion data. In over-sampling, synthetic minority instances are generated e.g. SMOTE (Synthetic Minority Over-sampling Technique) and on the contrary, under-sampling methods remove the majority-class instances to create balanced data e.g. random under-sampling. Both over-sampling and under-sampling methods have the disadvantages as over-sampling technique creates overfitting and under-sampling technique ignores a large portion of the data. Ensemble learning in supervised machine learning is also a common technique for handling imbalanced data. Random Forest and Bagging techniques address the overfitting problem, and Boosting (AdaBoost) gives more attention to the minority-class instances in its iterations. In this paper, we have proposed a method for selecting the most informative instances that represent the overall dataset. We have applied both over-sampling and under-sampling techniques to balance the data by employing the majority and minority informative instances. We have used Random Forest, Bagging, and Boosting (AdaBoost) algorithms and have compared their performances. We have used decision tree (C4.5) as the base classifier of Random Forest and AdaBoost classifiers and naïve Bayes classifier as the base classifier of the Bagging model. The proposed method Adaptive TreeHive addresses both the issues of imbalanced ratio and high dimensionality, resulting in reduced computational power and execution time requirements. We have evaluated the proposed Adaptive TreeHive method using five large-scale public benchmark datasets. The experimental results, compared to data balancing methods such as under-sampling and over-sampling, exhibit superior performance of the Adaptive TreeHive with accuracy rates of 99.96%, 85.65%, 99.83%, 99.77%, and 95.54% on the NSL-KDD, UNSW-NB15, CIC-IDS2017, CSE-CIC-IDS2018, and CICDDoS2019 datasets, respectively, establishing the Adaptive TreeHive as a superior performer compared to the traditional ensemble classifiers.

@article{sobhani2025adaptive,
  title={Adaptive TreeHive: Ensemble of trees for enhancing imbalanced intrusion classification},
  author={Sobhani, Mahbub E and Rodela, Anika Tasnim and Farid, Dewan Md},
  journal={PLoS One},
  volume={20},
  number={9},
  pages={e0331307},
  year={2025},
  publisher={Public Library of Science San Francisco, CA USA}
}

Agriculture has been a cornerstone of human civilization and continues evolving to meet the growing global population’s demands. In an era of rapid technological advancement, the integration of smart agriculture, also known as smart farming or precision farming, has become essential for sustainable agricultural practices. This approach uses the Internet of Things (IoT) and Artificial Intelligence (AI) to improve data collection and analysis, facilitating real-time monitoring of crop health, soil conditions, irrigation, and comprehensive farm management. By incorporating IoT, farmers can make informed decisions, optimize resource use, and improve crop yields. This study explores the scope of integrating IoT into crop management to optimize traditional crop-related issues and to improve the quality, production, and marketing process. Our in-depth analysis illustrates the IoT architecture, the IoT in smart farming, and how IoT sensors and devices collect real-time data on soil moisture, temperature, humidity, and other environmental factors, which are then processed using cloud computing platforms and stored accordingly. After conducting an exhaustive search with sorted keywords aligned with our research interests, we have identified more than a thousand research articles. A further filtering approach is applied based on inclusion and exclusion criteria to select a significant number of well-suited articles, which are thoroughly analyzed in the development of this systematic review paper. The growing number of literature in this field has created a vast area for exploration. In response, we have thoroughly studied all the aspects of IoT and have proposed a novel taxonomy for IoT to systematically classify and analyze key aspects like Sensors, Actuators, Development Board, and Communication. We examine the application of IoT in crop management, emphasizing its benefits, challenges, and future potential. In addition, we analyze key IoT components, such as sensors, data analytics, and decision-making tools, and explore their role in enhancing agricultural sustainability, economic viability, and food security. Finally, we concluded our study by addressing the challenges and outlining future directions for further advancement.

@article{EYASIN2025100127,
  title = {CropSynergy: Harnessing IoT Solutions for Smart and Efficient Crop Management},
  journal = {Crop Design},
  pages = {100127},
  year = {2025},
  issn = {2772-8994},
  doi = {https://doi.org/10.1016/j.cropd.2025.100127},
  url = {https://www.sciencedirect.com/science/article/pii/S2772899425000333},
  author = {Md Sanzid Hossain Eyasin and Mahbub E. Sobhani and Shamima Nasrin and Abu Sadat {Al Rafi} and A.K.M. {Muzahidul Islam}}
}

Abstract here.

Abstract here.

Abstract here.