627 Hits in 0.95 sec

Association between Thyroid Function and Gall Stone Disease

Md Nahid Reza, M Fardil Hossain Faisal, Tahmina Noor, Riaz Mahmud, Monsur Miah, Ibrahim Siddique, Md Manir Hossain Khan
2021 KYAMC Journal  
cross-sectional, comparative, case control study was done in department of Endocrinology, King George Hospital, and Visakhapatnam during the period of February 2011 to February 2013 by Srinivas et al. 4 Study by Hossain  ... 
doi:10.3329/kyamcj.v12i1.53366 fatcat:dphptm64tjfpzcuglsouedfdbm

Exploring Video Captioning Techniques: A Comprehensive Survey on Deep Learning Methods

Saiful Islam, Aurpan Dash, Ashek Seum, Amir Hossain Raj, Tonmoy Hossain, Faisal Muhammad Shah
2021 SN Computer Science  
Video captioning is an automated collection of natural language phrases that explains the contents in video frames. Because of the incomparable performance of deep learning in the field of computer vision and natural language processing in recent years, research in this field has been exponentially increased throughout past decades. Numerous approaches, datasets, and measurement metrics have been introduced in the literature, calling for a systematic survey to guide research efforts in this
more » ... ting new direction. Through the statistical analysis, this survey paper focuses mostly on state-of-the-art approaches, emphasizing deep learning models, assessing benchmark datasets in several parameters, and classifying the pros and cons of the various evaluation metrics based on the previous works in the deep learning field. This survey shows the most used variants of neural networks for visual and spatio-temporal feature extraction as well as language generation model. The results show that ResNet and VGG as visual feature extractor and 3D convolutional neural network as spatio-temporal feature extractor are mostly used. Besides that, Long Short Term Memory (LSTM) has been mainly used as the language model. However, nowadays, the Gated Recurrent Unit (GRU) and Transformer are slowly replacing LSTM. Regarding dataset usage, so far, MSVD and MSR-VTT are very much dominant due to be part of outstanding results among various captioning models. From 2015 to 2020, with all major datasets, some models such as, Inception-Resnet-v2 + C3D + LSTM, ResNet-101 + I3D + Transformer, ResNet-152 + ResNext-101 (R3D) + (LSTM, GAN) have achieved by far best results in video captioning. Despite rapid advancement, our survey reveals that video captioning research-work still has a lot to develop in accessing the full potential of deep learning for classifying and captioning a large number of activities, as well as creating large datasets covering diversified training video samples.
doi:10.1007/s42979-021-00487-x fatcat:uk75jtc4yngcpfmb5hzk4eqx7u

Classification of crops and weeds from digital images: A support vector machine approach

Faisal Ahmed, Hawlader Abdullah Al-Mamun, A.S.M. Hossain Bari, Emam Hossain, Paul Kwan
2012 Crop Protection  
In most agricultural systems, one of the major concerns is to reduce the growth of weeds. In most cases, removal of the weed population in agricultural fields involves the application of chemical herbicides, which has had successes in increasing both crop productivity and quality. However, concerns regarding the environmental and economic impacts of excessive herbicide applications have prompted increasing interests in seeking alternative weed control approaches. An automated machine vision
more » ... em that can distinguish crops and weeds in digital images can be a potentially cost-effective alternative to reduce the excessive use of herbicides. In other words, instead of applying herbicides uniformly on the field, a realtime system can be used by identifying and spraying only the weeds. This paper investigates the use of a machine-learning algorithm called support vector machine (SVM) for the effective classification of crops and weeds in digital images. Our objective is to evaluate if a satisfactory classification rate can be obtained when SVM is used as the classification model in an automated weed control system. In our experiments, a total of fourteen features that characterize crops and weeds in images were tested to find the optimal combination of features that provides the highest classification rate. Analysis of the results reveals that SVM achieves above 97% accuracy over a set of 224 test images. Importantly, there is no misclassification of crops as weeds and vice versa.
doi:10.1016/j.cropro.2012.04.024 fatcat:q2y56ajeo5bfvgqdvw5bewz4we

Tidal river management in Bangladesh

Faisal Hossain, Zahirul Haque Khan, C. K. Shum
2015 Nature Climate Change  
. ❐ Reply to 'Tidal river management in Bangladesh' Auerbach et al. reply -We appreciate the opportunity to address tidal river management (TRM), as raised by Hossain and colleagues 1 .  ...  Beyond the TRM implementations noted by Hossain and colleagues 1 , there have been well-documented failures resulting from both engineering challenges 3 and lack of proper social discourse 4 .  ... 
doi:10.1038/nclimate2618 fatcat:4dpywrte7bhmxkhxq337ensdri

Feasibility of Genetic Algorithm for Textile Defect Classification Using Neural Network [article]

Md. Tarek Habib, Rahat Hossain Faisal, M. Rokonuzzaman
2012 arXiv   pre-print
The global market for textile industry is highly competitive nowadays. Quality control in production process in textile industry has been a key factor for retaining existence in such competitive market. Automated textile inspection systems are very useful in this respect, because manual inspection is time consuming and not accurate enough. Hence, automated textile inspection systems have been drawing plenty of attention of the researchers of different countries in order to replace manual
more » ... ion. Defect detection and defect classification are the two major problems that are posed by the research of automated textile inspection systems. In this paper, we perform an extensive investigation on the applicability of genetic algorithm (GA) in the context of textile defect classification using neural network (NN). We observe the effect of tuning different network parameters and explain the reasons. We empirically find a suitable NN model in the context of textile defect classification. We compare the performance of this model with that of the classification models implemented by others.
arXiv:1208.6025v1 fatcat:fahwms6mafbzxchp4nwt5wjqwa


Mohammad Arifur Rahman Md. Shahimur Parvez, Arifin Islam Lita, Solaiman Hossain, Moeen Uddin Ahmed, S. Faisal Ahmed, Tamal Peter Ghosh, Surayea Bul-Bul, Mohammad Monir Hossain Bhuiyan
2021 Zenodo  
Background:The non-alcoholic fatty liver disease is increasingly being recognized as a major cause of liver related morbidity and mortality among 15-40% of the general population. The rising incidence of obesity is associated with health complications. Currently, a liver biopsy is the gold standard method for diagnosing NAFLD. Ultrasonography is relatively inexpensive and widely available in clinical settings. NAFLD is considered to be an integral part of the metabolic syndrome. Objective: To
more » ... nd out the clinical profile with non-alcoholic fatty liver disease and metabolic syndrome patients.Methods: A cross-sectional study was conducted by Department of Cardiology, Enam Medical College and Hospital, Savar, Bangladesh. A total of 100 cases during the study period of February 2019 to January 2020 were included and investigated for metabolic syndrome according to the NCEP ATP 3 Criteria. Results: Total of 100 cases ultrasonographically diagnosed as NAFLD were included in the study and showed 49%, 38% and 13% of cases had grade I, II, and III fatty liver respectively. On physical examination mean BMI was 27.6±4.39 kg/m 2. Mean diastolic blood pressure was 92.87±6.25 and mean systolic blood pressure (mm Hg) 132.0±18.17. Out of the 100, patients with NAFLD with metabolic syndrome were 57% and without metabolic syndrome were 43%. The correlation was significant for fasting plasma glucose, diastolic blood pressure, triglycerides, high-density lipoprotein and waist circumference (p<0.05). Conclusions: From the study, it can be concluded that symptoms and signs of NAFLD are non-specific and occur later in the course of the disease hence the physician should have a high index of suspicion in order to detect NAFLD early in the course of the disease. Early detection would help not only in modifying the disease course and delaying its complications.
doi:10.5281/zenodo.5408704 fatcat:bsjs7a63dnhifirtix6e3fhe5e

Realizing ecosystem-safe hydropower from dams

Shahryar Khalique Ahmad, Faisal Hossain
2020 Renewables: Wind, Water, and Solar  
Readers are referred to Ahmad and Hossain (2020) for detailed formulation of the constraints.  ...  Our previous study (Ahmad and Hossain 2019b) describes the model development and predictor selection in more detail.  ... 
doi:10.1186/s40807-020-00060-9 pmid:32647609 pmcid:PMC7325499 fatcat:ffg377pe6vewbki6fc7clkfvve

Hydropower's hidden transformation of rivers in the Mekong

Matthew Bonnema, Faisal Hossain, Bart Nijssen, Gordon Holtgrieve
2020 Environmental Research Letters  
Hossain also conceptualized the study, analyzed results and reviewed the paper. B. Nijssen and G. Holtgrieve assisted in reviewing this paper.  ...  ., 2014; Bonnema and Hossain, 2017] .  ...  observations of storage or outflow are limited, we used remote sensing observations to derive average monthly storage patterns using a proven approach we developed in a previous study (Figure 4 ; Bonnema and Hossain  ... 
doi:10.1088/1748-9326/ab763d fatcat:okyrhfiv2je6plpksmbdg6uxga

Clinical Outcome of Surgical Diathermy in Elective Surgery-Prospective Randomized Controlled Tria

Riaz Mahmud, M Fardil Hossain Faisal, Firoz Mahmud, Munsur Miah, Md Nahid Reza, Khandaker Rezaul Hoque, Md Manir Hossain Khan, Arif Salam Khan
2019 KYAMC Journal  
Recent studies suggest that surgical diathermy shows better clinical outcome in the context of incision time, wound related postoperative pain, postoperative wound infections, and length of postoperative hospital stay and cosmetic outcome of scar in cases of elective surgical patients. Objectives: Compare the efficacy and safety of surgical diathermy versus conventional surgical blade for making skin incisions in elective mid-line laparotomy and to evaluate weather cutting diathermy is an
more » ... ive and better alternative to surgical blade incision. Materials and Methods: This prospective study was carried out in the department of surgery at BSMMU, Dhaka over a period of one year. Sample size was 64 with a follow up duration for 6 month. In Group I (D), skin incision was taken with diathermy, and in Group II (S), incision was taken with surgical blade. Results: Compared with a scalpel incision, cutting diathermy resulted in significantly shorter incision times and reduced post-operative wound related pain (P = <0·001), shorter duration of postoperative hospital stay (P = 0.003) with no differences in the wound complication rate and cosmetic outcome of scar. Conclusions: The study has demonstrated that surgical cutting diathermy is a safe and effective method to make skin incisions in elective surgery KYAMC Journal Vol. 10, No.-3, October 2019, Page 143-146
doi:10.3329/kyamcj.v10i3.44417 fatcat:ctg643yfrvbabmnrtr3rcgdeje

Early Clinical Outcomes Following Laparoscopic Vs. Open Mesh Repair of Inguinal Hernia 85

M Fardil Hossain Faisal, KM Saiful Islam, Md Manir Hossain Khan, Arup Kumar Biswas, Mohammad Abul Kalam Azad, Md Nahid Reza
2019 KYAMC Journal  
As a part of modern surgical procedure, laparoscopic mesh repair of inguinal hernia should be safe, effective and have a short period of convalescence. Objective: This study was designed to compare the outcome following inguinal hernia repair, performed by laparoscopic technique and open mesh Lichtenstein (tension-free) repair. Materials and Methods: This prospective quasi experimental study was carried out in the department of surgery, Bangabandhu Sheikh Mujib Medical University, for a period
more » ... f twelve (12) months. Total thirty six patients of inguinal hernia were included in this study. Result: Mean (±SD) age was 38.17 (±8.64) years. Mean (±SD) time for unilateral inguinal hernias were 55.30 (±11.01) minute in open mesh repair where as 76.07 (±13.71) minute in laparoscopically. For bilateral inguinal hernia, mean (±SD) time for open mesh repair was 92.4 (±10.26) minute and 81.2 (±10.44) minute in laparoscopically Seroma formation was in 4 patients of open mesh repair where as 5 patients of laparoscopic mesh repair. Sixteen patients of laparoscopic mesh repair needed more anaesthetic narcotics 16 patients of laparoscopic mesh repair had return to work within two weeks of surgery whereas only 10 (55.6%) patients of open mesh repair had return to work during same period of time. Pain at surgical site and discomfort was more in open mesh repair. Conclusion: Laparoscopic mesh repair is better than open mesh repair of inguinal hernia. KYAMC Journal Vol. 10, No.-2, July 2019, Page 85-89
doi:10.3329/kyamcj.v10i2.42785 fatcat:bq7mihzneja5lcwwnaao56kzke

Clustering and Classification with Non-Existence Attributes: A Sentenced Discrepancy Measure Based Technique [article]

Y. A. Joarder, Emran Hossain, Al Faisal Mahmud
2020 arXiv   pre-print
For some or all of the data instances a number of independent-world clustering issues suffer from incomplete data characterization due to losing or absent attributes. Typical clustering approaches cannot be applied directly to such data unless pre-processing by techniques like imputation or marginalization. We have overcome this drawback by utilizing a Sentenced Discrepancy Measure which we refer to as the Attribute Weighted Penalty based Discrepancy (AWPD). Using the AWPD measure, we modified
more » ... he K-MEANS++ and Scalable K-MEANS++ for clustering algorithm and k Nearest Neighbor (kNN) for classification so as to make them directly applicable to datasets with non-existence attributes. We have presented a detailed theoretical analysis which shows that the new AWPD based K-MEANS++, Scalable K-MEANS++ and kNN algorithm merge into a local prime among the number of iterations is finite. We have reported in depth experiments on numerous benchmark datasets for various forms of Non-Existence showing that the projected clustering and classification techniques usually show better results in comparison to some of the renowned imputation methods that are generally used to process such insufficient data. This technique is designed to trace invaluable data to: directly apply our method on the datasets which have Non-Existence attributes and establish a method for detecting unstructured Non-Existence attributes with the best accuracy rate and minimum cost.
arXiv:2002.10411v1 fatcat:cdw2xzqterezlnzwuj6dydlx44

Modeling aerosol cloud aerodynamics during human coughing, talking, and breathing actions

Mamdud Hossain, Nadimul Haque Faisal
2021 AIP Advances  
doi:10.1063/5.0042952 fatcat:cb5qndg2yjhezg6hd3f4yhsjeq

Assessment of a Probabilistic Scheme for Flood Prediction

Faisal Hossain, Emmanouil N. Anagnostou
2005 Journal of hydrologic engineering  
Hossain et al. 2004a .  ...  demonstrated in a number of studies dealing with hydrologic prediction uncertainty ͑Romanowicz et Freer et al. 1996; Fisher and Beven 1996; Franks and Beven 1997; Franks et al. 1998; Beven and Freer 2001; Hossain  ... 
doi:10.1061/(asce)1084-0699(2005)10:2(141) fatcat:meal7tudanfmzoy2vb4lqb75lm

Gastrointestinal fistulas: An Update

ABM Moniruddin, Salma Chowdhury, Md Sayeed Bin Sharif, Md Masudar Rahman, M Fardil Hossain Faisal, Tanvirul Hasan, Md Rashed Khan
2018 KYAMC Journal  
<p>A gastrointestinal (GI) fistula is an abnormal connection between gut (GI tract) and an epithelialized surface of skin or another hollow organ or another part of gut. These GI fistulas can cause profound GI bleeding, which may need emergency surgery. Other complications include Malnutrion, Undernutrion, Anaemias, Fluid, and Electrlyte imbalances, Hypovolemic shock, Septic shock, Pyaemic abscesses, Kidney malfunction and failure, Cardiac dysrhythmias, and failure, Hepatitis, Cerebral
more » ... on and strokes, DIC etc if neglected, maltreated or untreated. Most GI fistulas occur as a complication of abdominal surgery. However, some fistulas evolve spontaneously and are usually the result of intra-abdominal inflammation or infection. Several classification systems for GI fistulas exist, none of which are used exclusively. The most commonly used classification systems are based on anatomic, physiologic (output volume), and etiologic characteristics. Used in combination, these classifications can help to provide an integrated understanding and optimal management scheme for the fistula. History taking, Physical examination, Endoscopy, Imaging studies and other laboratory tests are variably required for total assessment, evaluation, and concrete diagnosis. Intensive medical, and surgical therapies are now quite dramatically helpful to reduce the morbidity and mortality. This treatise on GI fistula is here to update the information about the latest developments of GI fistula.</p><p>KYAMC Journal Vol. 9, No.-2, July 2018, Page 87-94</p>
doi:10.3329/kyamcj.v9i2.38155 fatcat:t5meiwtcdvbd7dqjthgmimn6pq

A computationally efficient flash flood early warning system for a mountainous and transboundary river basin in Bangladesh

Nishan Kumar Biswas, Faisal Hossain, Matthew Bonnema, A. M. Aminul Haque, Robin Kumar Biswas, Arifuzzaman Bhuyan, Amirul Hossain
2020 Journal of Hydroinformatics  
WRF-based downscaling methods improve the accuracy of the forecasts, computational resources, and limited internet accessibility are a concern in developing countries like Bangladesh (Sikder & Hossain  ...  WRF downscaling can be tested to illustrate the relative improvements from the existing methods. • Explore different correction methods of QPF (i.e., clima- tology-based QPF correction by Sikder & Hossain  ... 
doi:10.2166/hydro.2020.202 fatcat:rwhfaalyfvaytkpj6ekcia3v2q
« Previous Showing results 1 — 15 out of 627 results