Chittagong University of Engineering & Technology

About: Chittagong University of Engineering & Technology is a education organization based out in Chittagong, Bangladesh. It is known for research contribution in the topics: Computer science & Renewable energy. The organization has 1200 authors who have published 1444 publications receiving 10418 citations. The organization is also known as: Engineering College, Chittagong & Bangladesh Institute of Technology, Chittagong.

Context pre-modeling: an empirical analysis for classification based user-centric context-aware predictive modeling

Abstract: Nowadays, machine learning classification techniques have been successfully used while building data-driven intelligent predictive systems in various application areas including smartphone apps. For an effective context-aware system, context pre-modeling is considered as a key issue and task, as the representation of contextual data directly influences the predictive models. This paper mainly explores the role of major context pre-modeling tasks, such as context vectorization by defining a good numerical measure through transformation and normalization, context generation and extraction by creating new brand principal components, context selection by taking into account a subset of original contexts according to their correlations, and eventually context evaluation, to build effective context-aware predictive models utilizing multi-dimensional contextual data. For creating models, various popular machine learning classification techniques such as decision tree, random forest, k-nearest neighbor, support vector machines, naive Bayes classifier, and deep learning by constructing a neural network of multiple hidden layers, are used in our study. Based on the context pre-modeling tasks and classification methods, we experimentally analyze user-centric smartphone usage behavioral activities utilizing their contextual datasets. The effectiveness of these machine learning context-aware models is examined by considering prediction accuracy, in terms of precision, recall, f-score, and ROC values, and has been made an empirical discussion in various dimensions within the scope of our study.

Smoke Detection Method Based on LBP and SVM from Surveillance Camera

Abstract: Wildfire is a regular incident worldwide today. It destroys forests and also the living areas of wild animals. So, to reduce the harmful effects of such disasters this paper describes a method of smoke detection for surveillance cameras. This smoke detection will ease the fire detection. Proposed method is based on Local Binary Pattern (LBP) and Support Vector Machine (SVM). Initially, Approximate Median Filtering Algorithm was applied to subtract the background from input frame. Then, shape based filtering method was applied to get the region of interest. Thirdly, LBP values and histograms were calculated from the pixels of region of interest to form a feature vector. The proposed method also applied Bhattacharyya coefficients to verify the smoke region for accurate result. Finally, SVM classified the region of interest as smoke image. Results using real scene data show that the proposed method can give accurate results in different conditions of real world situations.

Seismic damage assessment using RADIUS and GIS: A case study of Sylhet City, Bangladesh

Abstract: Seismic risk of urban areas around the world is a major concern to stakeholders due to the potential losses of lives and extensive damage to infrastructure that can occur following an earthquake. As risk mitigation resources are limited, a method for assessing risk and prioritizing structures for seismic retrofit at a city or regional scale is required. Scenario-based seismic damage prediction can be used by decision-makers for identifying the riskiest structures that can be prioritized for risk mitigation to optimize the use of available resources. In this case study, for the first time, seismic damage estimation is performed for Sylhet City Corporation (SCC), Bangladesh by integrating Risk Assessment tools for Diagnosis of Urban areas against Seismic disasters (RADIUS) and Geophysical Information System (GIS). Building structures, infrastructure, and soil type information for SCC from a recent study performed by the local government under the framework of the Comprehensive Disaster Management Program (CDMP) are used. The building inventory and other information in the study area are divided into 1.0 × 1.0 square km grids and the information is mapped into RADIUS. Two scenario earthquakes are chosen to perform damage estimation of existing buildings and infrastructures. The study reveals that the two scenario earthquakes (Mw 8.0 from Dauki Fault and Mw 7.6 from Plate Boundary Fault 2) can result in extensive damage and a high number of casualties in the SCC area. The integrated GIS and RADIUS approach provides useful information for decision making in the seismic risk mitigation plan of the city.

Effect of Sea Salts on Structural Concrete in a Tidal Environment

Abstract: Structural concrete exposed to the tidal/splash zone of marine environments is always subjected to ambient external, as well as internal, action of seawater over its entire lifespan. The environmental loading causes maximum damage to structural concrete in the tidal/splash zone of marine environments where it experiences the concentrated effect of salt ions found in seawater in presence of atmospheric oxygen, carbon dioxide and other harmful gases. The gradual penetration of sea salt ions and the formation of expansive/leachable compounds leads to cracking, spalling and even structural distress. This paper presents a part of a durability study on the effect of sea salts on structural concrete exposed to simulated tidal/splash zone marine conditions over a period of one year. The concrete specimens cast from two different grades of concrete were exposed to seawater of different concentration under submerged, alternate wetting-drying and atmospheric state of exposure in a controlled humidity and temperature environment. Using accelerated test techniques, the deteriorative effects were measured by studying visual appearance, weight and volume change, compressive strength, permeability and stress-strain characteristics, and x-ray diffraction patterns of salt-attacked concrete specimens. The test data provide useful information regarding the durability of structural concrete exposed to the tidal/splash zone of marine environments.

Physical properties of predicted MAX phase borides Hf2AB (A = Pb, Bi): A DFT insight

Abstract: We have used density functional theory to study the recently predicted MAX phase borides Hf2AB (A = Pb, Bi) in which the mechanical, electronic, thermal, and optical properties have been investigated for the first time. A good agreement of the obtained lattice constants with the reported values confirmed the well accuracy of the present calculations. The stiffness constants (Cij) attest the mechanical stability of all title compounds. The mechanical behaviors have been scrutinized discreetly by considering the bulk modulus, shear modulus, Young’s modulus, as well as hardness parameters. The failure mode of Hf2AB (A = Pb, Bi) borides is predicted to be brittle. The electronic band structure and density of states (DOS) revealed the metallic behavior of the titled materials. The anisotropy in electrical conductivity has been disclosed by considering the energy dispersion along different directions. The variation of Vickers hardness is explained in terms of total DOS of Hf2AB (A = Pb, Bi). The anisotropic nature of mechanical properties of the phases has also been studied. The technologically important parameters (Debye temperature, minimum thermal conductivity, and Gruneisen parameter) have also been used to evaluate the thermal behaviors of the titled materials. The possibility of Hf2AB (A = Pb, Bi) for use as coating materials has been assessed by studying the reflectivity.