Search

Floods and rain significantly impact the economy of many agricultural countries in the world. Early prediction of rain and floods can dramatically help prevent natural disaster damage. This paper presents a machine learning and data-driven method that can accurately predict short-term rainfall. Various machine learning classification algorithms have been implemented on an Australian weather dataset to train and develop an accurate and reliable model. To choose the best suitable prediction model, diverse machine learning algorithms have been applied for classification as well. Eventually, the performance of the models has been compared based on standard performance measurement metrics. The finding shows that the hist gradient boosting classifier has given the highest accuracy of 91%, with a good F1 value and receiver operating characteristic, the area under the curve score.

The parsing technique based on associate grammar rules as well as probability is called stochastic parsing. This paper suggested a probabilistic method to eliminate the uncertainty from the sentences of Bangla. The technique of Binarization is applied to increase the precision of the parsing. CYK algorithm is used in this paper. The work mainly focused on intonation-based sentences, for these reasons PCFGs (Probabilistic Context-Free Grammars) is based on proposed. About 30324 words are used to test the proposed system; average 93% accuracy is achieved. GUB JOURNAL OF SCIENCE AND ENGINEERING, Vol 7, Dec 2020 P 51-56

Object: To isolate and identify the microorganisms from the burn patients admitted to the National Institute of Burn and Plastic Surgery Unit in Tertiary Medical College Hospital, Bangladesh. A total number of fifty wound surface swab samples of first and second-degree burn patients were collected and the microbial analysis as well as the study of antibacterial susceptibility was conducted. The study showed the bacterial isolates were found. 45 (90%) of wound swab were positive among 50 and only 5 samples (10%) were negative in bacterial growth, which presented invasive burn wound infection from both sex age groups marked 12 - 60 years. The total viable count TVC-11651 CFU/plate was found and the highest amount in the second-degree burn patients. The results showed that Pseudomonas aeruginosa was common in all positive samples 6636 CFU/plate (57%) followed by Staphylococcus aureus 4070 CFU/plate (35%), Klebsiella spp. 450 CFU/plate (5%), Proteus spp. 243 CFU/plate (2%), and E. coli 162 CFU/plate (1%). Most of the pathogens were found to be drug-resistant while several isolates were noted to be multi-drug resistant. The growth of multidrug-resistant organisms should be considered as a serious risk factor in a burn unit. Aggressive infection control measures should be applied to limit the emergence and spread of multidrug-resistant pathogens.

The southwestern coastal region of Bangladesh has a severe problem of extracting groundwater due to salinity intrusion. This study aims at the vulnerability assessment of the shallow aquifer of such a salinity-affected region of coastal Bangladesh. GIS-based DRASTIC Index method has been applied in Bagerhat Sadar, Fakirhat and Rampal Upazila which accounts parameters like Depth to the water table, net Recharge, Aquifer media, Soil media, Topography, Impact of the vadose zone, and hydraulic Conductivity. Finally, the mapping of the DRASTIC Index has been resulted in low-, moderate- and high-vulnerable zones. This study reveals that about 85.43% area which is 656.85 km2 is exposed to moderate vulnerability. Only 7.88% area is under low risk, whereas 6.69% area is highly vulnerable. Fortunately, the southwestern part which is adjacent to the coast has a comparatively low vulnerability. The northeastern region which carries the urban area is characterized by highly vulnerable zones. Moderate- and high-vulnerable zones imply more accessibility of saline surface water to the ground.

Solid waste generation is rising consequently with the increasing population growth in Sylhet city. Mogla Bazar, an only dumping zone is affecting the surrounding environment enormously. This study aims to determine the surface water quality of the adjacent water bodies that lie within the 500 m buffer zone of the landfill utilizing multivariate statistical methods. Physicochemical and microbial parameters along with anions were considered for evaluating water quality. Multivariate statistical techniques viz. Principal Component Analysis (PCA), Factor Analysis (FA) and Cluster Analysis (CA) were applied to assess the water quality. Besides, the Pearson correlation matrix was performed to detect the interrelation among the variables and water quality index (WQI) was also used to classify the pollution sources. All the parameters were compared with the established acceptable limit given by the World Health Organization (WHO)/ Bureau of Indian Standards (BIS). PCA/FA resulted in three principal components with a total variance of 59.89 % and 57.14 % for haor and fishing zone, wetland respectively. Factor analysis derived from principal components shows that organic substances, anthropogenic activity, fertilization, chemical waste, and wastewater runoff are responsible for deteriorating the water quality. CA and WQI detect that sampling sites of haor and fishing zone that lies on the 200 m buffer zone were highly susceptible to water pollution. Besides, topographical variation, changes in slope, and seasonal variation were also treated as an influencing factor. Finally, all the analysis implied that the declining water quality would be dangerous to the neighbourhood of the landfill and there is a high chance of exposure to the dwellers residing nearby.