Showing papers by "Chittagong University of Engineering & Technology published in 2022"

Sustainable high-performance, self-compacting concrete using ladle slag

Abstract: High-Performance Concrete (HPC) meets special requirements (e.g., low shrinkage and permeability, high strength, and improved durability) and uniformity requirements beyond the range of conventional concrete. Self-compacting Concrete (SCC) is placed by its weight as it is enough flowable to pass through congested reinforced areas and avoid aggregate segregation. To reduce cement use and the associated CO2 production from its production, Ladle Slag, a steel industry waste material, is used to replace cement in the production of HPSCC. The material's chemical composition indicates self-cementing and pozzolanic properties. Ladle Slag (5%, 10%, 15% and 25%) is used in place of CEM I (cement) and their fresh, mechanical and durability properties are compared with the control concrete (no waste) sample. The fresh properties were tested and confirmed using Slump flow, T 500, V-funnel, and L-box. Obtained results generally indicate improvement in fresh, mechanical and durability properties of produced concretes for up to 15% use of Slag compared to the control concrete. Cost analysis suggests that industrial waste could be a promising green material for HPSCC by economically saving the carbon footprint.

Classification of Textual Sentiment Using Ensemble Technique

Abstract: In recent years, the widespread use of the Internet has resulted in a revolutionary way for people to share their feelings or sentiment on blogs, social media, e-commerce sites, and online platforms. Most of the feelings expressed on the online platforms are in textual forms (such as status, tweets, comments, and reviews). These textual expressions are unstructured, laborious, and time-consuming to organize, manipulate, or efficient storage due to their messy forms. Textual sentiment analysis refers to the automatic process of assigning an expression or text to an appropriate polarity (positive, negative, and neutral). Although Bengali is ranked seventh most popular language globally and the second famous Indic language, the development of language processing tools is minimal to date. This paper proposes an ensemble-based technique to classify Bengali textual sentiment into two categories: positive and negative. Due to the unavailability of the Bengali sentiment corpus, this work also developed a dataset (called ‘Bengali Sentiment Analysis Dataset or BSaD’) containing 8122 text expressions. This work investigates eight popular baseline classifiers [such as Logistic Regression (LR), Randon Forest (RF), Decision Tree (DT), K-nearest Neighbor (KNN), Support Vector Machine (SVM), Multinomial Naive Bayes (MNB), Stochastic Gradient Descent, and AdaBoost] with Term frequency-Inverse document frequency (TF-IDF) and Bag-of-words (BoW) feature for textual sentiment analysis on three datasets. This work also investigates the four ensemble methods (LR + RF, RF + SVM, LR + SVM, and LR + RF + SVM) developed by combining three best-performing base classifiers (LR, RF, and SVM). Experimental results show that the ensemble approach (i.e., LR + RF + SVM) with TF-IDF (uni-gram + bi-gram + tri-gram) features outperformed the other classifier models achieving the highest accuracy 82% on the developed dataset.

Effective Rate of Minority Class Over-Sampling for Maximizing the Imbalanced Dataset Model Performance

Abstract: Over-sampling is a resampling technique that has been designed to balance the imbalanced class distribution by duplicating samples of the minority class for a classification dataset. It is challenging to determine what rate of sample duplicating will be effective to maximize the model accuracy. In this research, we have proposed a method to determine an effective rate of the minority class over-sampling by which to maximize the performance of the machine learning model. We have used five over-sampling methods named Random over-sampling, SMOTE, SVMSMOTE, SMOTE Nominal, and Borderline SMOTE to evaluate the proposed method with five publicly available datasets. During the training period, we have over-sampled the minority class based on the majority class samples between the percentage ranges from 0 to 50%. Random Forest (RF) has been used as a machine learning classifier because its default hyperparameters already return great results. F1-score has been used as evaluation matrices because it is effective for imbalanced datasets. It has been seen that the proposed model has achieved a top f1-score when the minority class was over-sampled by 30–45% of the majority class samples.

Personal and socioeconomic factors affecting perceived knowledge of farmed fish

Abstract: The global decline in wild fish has given impetus to the rapid growth of seafood produced by aquaculture, as well as of farmed fish (FF). Although product knowledge is directly linked to fish consumption, continuous asymmetric information leads to consumer ambiguity and confusion regarding their knowledge of farmed fish. However, ambiguity tolerance (AT) and confusion avoidance (CA) as personal and relevant socio-economic factors positively affect fish consumption. Despite such potential of these factors, little research has investigated if the personal and socio-economic factors are associated with consumers' value perception of FF knowledge. Therefore, this study analyses the effects of AT, CA and socio-economic factors on consumers’ acquisition of knowledge of farmed fish. A total sample of 1041 households from the two major Bangladeshi urban areas of Dhaka and Chittagong were interviewed using a structured questionnaire. The data were analysed employing exploratory factor analysis and the ordered probit regression model. The findings reveal that AT affects FF knowledge positively and significantly but that CA does not. Individuals with a high level of fish consumption and who do their fish shopping personally are more likely to gather FF knowledge. However, those who buy fish from the supermarket and are members of an environmental organisation are not interested in doing so. The findings also lead to significant managerial implications for improving ways to develop substantial factors to increase FF knowledge and the consumption of such fish, which will benefit consumers and the aquaculture industry.

BDFN: A Bilingual Model to Detect Online Fake News Using Machine Learning Technique

Abstract: The dissemination of online misinformation is causing increasing concern around the world. Government officials and other responsible agencies are deeply worried about the situation and are working tirelessly to change it, but it seems that some yellow journalists are only interested in making money by selling news with clickbait headlines and fake facts inside the news. Some shady online news sources, both in English and Bengali, are actively working to spread false information in order to create a stir. While there are several systems that can detect fake news from English news corpus, we are unaware of any system that detects fake news from both Bengali and English languages at the same time. So, here we propose a bilingual fake news detection model in this paper that employs TF-IDF and N-Gram Analysis for feature extraction in order to detect fake news from a bilingual perspective. In addition, we compare the results of six separate machine learning algorithms for detecting false news. The model employs a supervised method of operation. Among these, we have acquired the highest performance with Linear Support Vector Classification (Linear SVC) algorithm where the accuracy is 93.29% and the F1 score is 0.93.

Design and implementation of reconfigurable ASK and FSK modulation and demodulation algorithm on FPGA (Field Programmable Gate Array)

Abstract: Our modern world is completely driven by our ability to communicate all over the world with great precision, accuracy, and the least amount of time possible. Communication systems are used vastly in our worlds such as radar, aerospace, naval/maritime communication, underwater communication, mobile communication, or even in outer space such as satellite communication or space missions. Different communication system needs different types of modulation techniques. Design and implementation of reconfigurable modulators on cyclone-II FPGA (Field-programmable gate array) are proposed in this paper, wherein the type of modulations and demodulation can be dynamically reconfigured on the fly based on the requirement at any particular instance. The demodulator is intelligent enough to demodulate any modulated signal. FPGA or Field Programmable Gate Array is a computing device that can be programmed like CPU (Central Processing Unit) but fasted than CPU in parallel processing and DSP (Digital Signal Processing) related tasks. Consisting method of FPGA-based modulation does not support multiple modulation techniques at the same time and is not fast as they used Simulink-based simulation. This study has proposed FPGA based alternative to that, which can embody all the modulation techniques at once, making it way more versatile, cost-effective, and easy to use and test. The process begins with designing an algorithm. Then this algorithm has to be simulated. The algorithm is designed for both modulation and demodulation. In the modulation part, it is just simple logic to create different phrases and different frequencies of sinusoidal waves. But in demodulation, based on the frequency it can detect ASK (Amplitude Shift Keying) or FSK (Frequency Shift Keying) signal all by itself. Depending on the period of the signal, the algorithm can decide whether it is an ASK or FSK signal. After deciding it is an ASK of FSK signal, it starts to demodulate the signal. The outcome is, this FPGA-based modulator and demodulator are cheap, easy to configure, and can demodulate any type of demodulated signal. As it is reconfigurable, it's easy to deploy in any situation. • FPGA based proposed modulator and demodulator in can be reconfigured on the fly based on the requirement. • Demodulator by itself can find which modulation technique is used and works accordingly. • Depending on the period of the signal, the algorithm can decide whether it is an ASK or FSK signal. • This FPGA-based modulator and demodulator are cheap, easy to configure, and can demodulate any type of signal.

Multi-class Textual Emotion Categorization using Ensemble of Convolutional and Recurrent Neural Network

Abstract: Categorizing emotion refers to extracting the individuals’ behaviour from texts and assigning textual units into an emotion from predefined emotional connotations. Identification and categorization of emotion content have mostly been made for English, French, Chinese, Arabic, and other high-resource languages. However, very few studies have investigated emotion from the under-resourced language like Bengali. This work proposes an ensemble-based technique for classifying textual emotions into six classes: anger, disgust, fear, joy, sadness and surprise. An emotion corpus containing 9000 Bengali texts is developed to perform the emotion classification. This work investigates 22 standard classifier models developing based on three deep learning techniques (Convolutional Neural Network (CNN), Gated Recurrent Unit (GRU), Bidirectional Long Short Term Memory (BiLSTM) with different ensemble strategies and embedding models (i.e., Word2Vec, FastText). All the models are tuned, trained and tested on the developed dataset (EBEmoD-Extended Bengali Emotion Dataset) and a publicly available emotion dataset (BYCD-Bengali Youtube Comment dataset). The experimental result demonstrates that the ensemble of CNN and BiLSTM (i.e., CNN+BiLSTM) outdoes all other models by acquiring the highest weighted $$f_1$$ -score of 62.46% (for EBEmoD) and 67.57% (for BYCD), respectively.

Hydrological Aspects

Abstract: AbstractThe young science ‘hydrology’ reached mathematical analysis for many hydrological principles and involvements of sophisticated instruments and computer techniques. Rainwater harvesting is solely dependent on the ‘hydrological cycle.’ This chapter describes the conventional measurement and computation of precipitation, infiltration, surface runoff, and groundwater movement.

Groundwater Recharge

Abstract: AbstractGroundwater recharge is a part of the hydrologic cycle; water moves downward through drainage or percolation from the water table to the saturated zone. In this process, water enters through an aquifer and encompasses water movement in the vadose zone. Groundwater recharges both naturally (i.e., hydrologic cycle) and artificially, as described in Chap. 2. In the managed aquifer recharge or artificial groundwater recharge, rainwater, or recycled water are considered to be routed into the subsurface. This chapter introduces the managed aquifer recharge, relevant technologies, and worldwide specific regulations and guidelines. Thus, the possibilities and challenges of other technologies are incorporated in rainwater harvesting, stormwater, and greywater reuse to recharge aquifers are discussed in this chapter.

Developing Fruitful Communication

Abstract: To smoothly transition to the educational platforms and integrate into the new country, especially after the heinous impact of the COVID-19 pandemic, international students need adequate support from the leaders of educational institutions. Leaders not only refer to the administrative leaders but also include the teachers who lead these students in their regular classes. Leaders may also refer to their peers and even the students themselves, who make decisions about their own lives and lead themselves. The toolkit of emotional intelligence (EQ) is valuable for all leaders because it is a multifaceted ability that helps individuals apply the power of emotions as a source of trust, communication, and influence. This chapter focuses on an account of the learning experience of one international doctoral student's transition within a new cultural context. Self-reflection on the hurdles experienced and the importance of respectful communication during the evolution to becoming an international doctoral student in Ontario informs the analysis.

Introduction

Abstract: AbstractUrbanization poses increased water demand due to rapid population growth, and also increased impervious lands exaggerate surface runoff and lessen groundwater resources. On the other hand, climate change significantly influences the quantity and quality of rainfall. Worldwide urban water management faces three-dimensional challenges, i.e., potable water shortage, urban floods, or waterlogging and depleting groundwater. This chapter provides an overview of urban hydrology, challenges on urban water management, the glorious history of rainwater harvesting systems, briefly implementation and direction, and their potentiality towards a water smart city.

Emergency Vehicle Detection Using Deep Convolutional Neural Network

Abstract: In densely populated cities, emergency vehicles getting caught in traffic is a regular occurrence. As a result, emergency vehicles arrive late, resulting in asset and human life losses. It is critical to treat emergency vehicles differently to avoid losses. The purpose underlying this research is to preserve human lives and reduce losses. For this, an automated method for detecting emergency vehicles is implemented. Ambulance and fire trucks are considered an emergency, and other vehicles are considered non-emergency vehicles in the proposed method. Initially, it identifies several vehicles from an image. The YOLOv4 object detector accomplished this part of the method. The identified vehicles are the region of interest for the rest of the research. Finally, the method classifies the vehicles into emergencies or non-emergencies. This study contributes by developing a model based on rigorous testing and analysis and includes a viral algorithm in deep learning: convolutional neural network (CNN). Furthermore, the transfer learning technique with VGG16’s fine-tuned model is employed for emergency vehicle detection. On the Emergency Vehicle Identification v1 dataset, this model had an average accuracy of 82.03%.

Wind Energy: The Promising Future of Bangladesh Power Sector

Abstract: As fossil fuel reserves have been rapidly drained over the past few years, Bangladesh has had severe electricity problems. Bangladesh should explore alternative sources of energy. The issue can be resolved by the wind. The wind is a great source of renewable energy that is also free. Long coastal area is observed in Bangladesh, where a good amount of wind is found all around the year. It sustains several blows in different seasons' various fashions. In this study, some statistical information is gathered about wind flow rates in Bangladesh's various locations and, after figuring out the cost of extracting the wind energy, it is compared to other energy sources in Bangladesh. Furthermore, the feasibility of installing wind power plants in Bangladesh is also discussed.