Browsing by Author "Abdullah, Hasan"
Now showing 1 - 7 of 7
- Results Per Page
- Sort Options
Item Detecting propagandistic poster title: a machine learning approach(BRAC University, 2024-03) Mahmood, Riaz; Shah, Intiajul Alam; Hassan, Tasnimul; Abdullah, Hasan; Mubassir, Taskin Mohammad; Alam, Md. Golam RabiulDetecting propagandistic content is crucial in today’s digital age where misinformation spreads rapidly. In this study, we propose a machine learning approach aimed at identifying propaganda in poster titles. Our methodology encompasses various text classification techniques, including Random Forest, Logistic Regression, K-Nearest Neighbor (KNN), Naive Bayes classifier, Support Vector Machine (SVM), RoBERTa, Stacking Classifier, Stacking Classifier With Feature Engineering, and RoBERTa XGBoost Hybrid Model. We employ robust feature extraction methods such as TF-IDF and Word2Vec, along with advanced ensemble learning strategies, to enhance the accuracy and effectiveness of the classification process. Specifically, we introduce two hybrid models: the Stacking Classifier With Feature Engineering, which incorporates word2vec and TF-IDF to improve accuracy, and the RoBERTa XGBoost Hybrid Model, which utilizes a combination of TF-IDF vectorization and RoBERTa embeddings followed by XGBoost classification. Through extensive experimentation and evaluation, we analyze the performance of each model in terms of accuracy, precision, recall, and F1-score. Our findings demonstrate promising results, with certain models exhibiting significant improvements over baseline approaches. Moreover, we conduct a thorough analysis of the models’ strengths and weaknesses, providing insights into their efficacy in detecting propagandistic content. Overall, our research contributes to the development of effective tools for combating propagandistic title and promoting media literacy in the digital landscape.Item Exploring the Optical Properties of Exposed-core-based Photonic-crystal Fibers(Springer, 2021-03-25) Mitu, Sumaiya Akhtar; Ahmed, Kawsar; Abdullah, Hasan; Paul, Bikash Kumar; Al-Zahrani, Fahad Ahmed; Patel, Shobhit K.; Rajan, M. S. ManiA photonic-crystal fiber (PCF) based on the surface plasmon resonance (SPR) effect with low confinement loss and high sensitivity response is designed and its optical properties analyzed when varying different parameters. The SPR-based PCF design is analyzed to enable control over its light propagation and evanescent properties. In this investigation, gold (Au) is used as a plasmonic material to generate the SPR effect at the interface. The simulation results reveal a maximum sensitivity response of 45,303 nm/RIU with resolution of 7.0634 × 10–6 and low confinement loss of 0.575 dB/cm in the wavelength range from 1.2 to 2 µm. A high figure of merit of 378 with low full-width at half-maxima is also obtained. The proposed structure thus offers ultralow confinement loss and high sensitivity.Item Exploring the Optical Properties of Exposed-core-based Photonic-crystal Fibers(Vol.:(0123456789)1 3Journal of Computational Electronics, Springer, 2021-03-25) Mitu, Sumaiya Akhtar; Ahmed, Kawsar; Abdullah, Hasan; Paul, Bikash Kumar; Al-Zahrani, Fahad Ahmed; Patel, Shobhit K.; Rajan, M. S. ManiA photonic-crystal fiber (PCF) based on the surface plasmon resonance (SPR) effect with low confinement loss and high sensitivity response is designed and its optical properties analyzed when varying different parameters. The SPR-based PCF design is analyzed to enable control over its light propagation and evanescent properties. In this investigation, gold (Au) is used as a plasmonic material to generate the SPR effect at the interface. The simulation results reveal a maximum sensitivity response of 45,303 nm/RIU with resolution of 7.0634 × 10–6 and low confinement loss of 0.575 dB/cm in the wavelength range from 1.2 to 2 µm. A high figure of merit of 378 with low full-width at half-maxima is also obtained. The proposed structure thus offers ultralow confinement loss and high sensitivity.Item High-Sensitivity Gold-Coated Refractive Index Biosensor Based on Surface Plasmon Resonance(Springer Nature, 2023-07-11) Abdullah, Hasan; Uddin, Muhammad Shahin; Paul, Bikash Kumar"High-sensitivity gold-coated photonic crystal fiber (PCF) refractive index (RI) biosensor based on surface plasmon resonance (SPR) is proposed. To evaluate the sensing characteristics of the proposed sensor, the finite element method (FEM) is used. As a base material, silica is used and as a plasmonic material, 40-nm thickness gold layer is chosen. Resonance of electrons requires active plasmonic material. Gold is chosen because it has the highest plasmonic activity of all active plasmonic materials and offers the best resonance. The uppermost wavelength sensitivity response of 45,409.14 nm/RIU is obtained at RI 1.35. The maximum amplitude resolution, amplitude sensitivity response, birefringence, transmittance, coupling length, and dispersion of 2.52 × 10−05, 7679.06 RIU−1, 3.1 × 10−4, − 24.5 dB, 1,87,500 µm, and − 7000 ps/(nm-km) are obtained respectively. The proposed sensor is a strong contender for detecting microfluidic analytes in the biosensor field for its exceptional sensitivity response, compact structural design, and tunable performance.Item Micro-structure Ring Fiber–based Novel Magnetic Sensor with High Birefringence and High Sensitivity Response in Broad Waveband(Plasmonics, Springer, 2021-01-11) Mitu, Sumaiya Akhtar; Ahmed, Kawsar; Zahrani, Fahad Ahmed Al; Abdullah, Hasan; Hossain, Md.Nadim; Paul, Bikash KumarThe magnetic fluid sensor is proposed and numerically investigated by using finite-element-method (FEM) based on the photonic crystal fiber (PCF) with butterfly-shaped air holes and a ring core. Ethanol is used as a magnetic fluid that is injected in the ring core which provides unique characteristics. The goal of the proposed structure is to gain a better response to birefringence and relative sensitivity. In this work, the observed birefringence is 1.27×10−21.27×10−2; the sensitivity responses are 40 nm/Oe, and 94047.13 nm/RIU can be gained for the variations of magnetic field strength from 50 to 200 Oe and 200 Oe, respectively. With best of knowledge, this sensitivity response is the highest response in the magnetic sensing. For better sensing performance the proposed butterfly structure can be used in the bio-optics field and nanofluidic technologies.Item PREVALENCE AND RISK FACTORS OF MYIASIS AT SOME SELECTED AREAS OF CHITTAGONG OF BANGLADESH AND TAMIL NADU STATE OF INDIA.(Chittagong Veterinary and Animal Sciences University Chittagong – 4225, Bangladesh, 2015-01) Abdullah, HasanABSTRACT A prospective study for nine months was undertaken to estimate the prevalence and probable predisposing and risk factors of myiasis in different species of animals at some selected areas of Chittagong Division of Bangladesh as well as Tamil Nadu state of India from February, 2014 to October 2014. A total of 178 cases were identified manifesting signs of myiasis. By extensive cross-questioning of animal owners, farmers and attendants and scientific clinical examinations different pre-disposing factors and probable other risk factors were noted. The prevalence rates were recorded 59% in goat and 26% in cattle. In addition, the seasonal prevalence was explored the highest in autumn (55.5%) than the winter (11.6%). Statistically significant difference in the prevalence was noted with breed, age, sex, depth of wound, body temperature and general attitude of animal. Above 6 months aged animals (69.8%) and cross breeds (35.5%) were mostly infected where females (62.5%) were more prone to myiasis. The study attempted to addres the probable health hazards caused by flies in different animals that will benefit the veterinarians, farmers and animal owners in avoiding and clinically contain them as well. Further extensive studies are recommended as molecular identification of species of flies and economic analysis caused by myiasis in these selected areas.Item Theoretical Analysis of Highly Temperature-Sensitive Fem Based Optical Sensor in the Infrared Range(Scopus, 2020) Abdullah, Hasan; Islam, Md. Rafiqul; Ahmed, Kawsar; Malka, Dror; Nguyen, Truong Khang; Hossain, Md. Nadim; Paul, Bikash Kumar; Dhasarathan, Vigneswaranhis paper demonstrates a highly sensitive temperature sensor based on photonic crystal fiber (PCF) to evaluate the temperature of an analyte. The proposed structure is evaluated by a finite-element method (FEM) which is composed of one silica core and an analyte core. The maximum wavelength sensitivity of 29,411.765 nm/refractive-index unit (RIU) and the maximum temperature sensitivity of 5000 pm/°C are recorded for the proposed PCF based temperature sensor. According to our knowledge, this measurement represents the maximum sensitivity response to the PCF based temperature sensor. Additionally, the temperature is tuned between 30–60 °C for getting highest sensitivity response. Besides, the peak wavelength shifts, different loss spectra are also investigated for the proposed model. In the future, this proposed structure can be used for multiple sensing purposes such as gas sensing, biomedical sensing, salinity sensing, chemical sensing with modification and analyzing upon this structure.
