Article 1
Analysis of Duplicate Bug Report Detection Techniques
Afrina Khatun, Sarker Foysal Mohammud Al Gabid, Nazneen Akhter, Kazi Abu Taher, Tajbia Karim
The reporting of large number of duplicate bug reports has generated the need for appropriate duplicate bug report detection techniques. Researchers have developed duplicate bug report detection techniques using different approaches such as Information Retrieval, Machine Learning etc. However, due to rapid development of duplicate detection techniques, it has become difficult to compare and select an appropriate duplicate bug report detection technique. Besides, the usage of different Information Retrieval and Machine Learning techniques have made it more difficult to understand the successes, failures and future opportunities of the proposed techniques. In order to draw a clear picture of the existing techniques developed from the inception to the present, this paper presents a systematic analysis of the duplicate bug report detection techniques. The analysis has been prepared from existing techniques published in ranked conference and journals. The paper has presented insights on the type of input data set used for developing and testing the techniques, the feature selection and pre-processing strategies of bug reports and the type of algorithms and evaluation metrics used for developing the techniques. The paper lastly elaborates the findings established during the discussion of the insights, and presents a road map for future research on the uncovered areas.
Article 2
Study of Spatio-temporal Variation of Humidity over the Southwestern Zone of Bangladesh
Md. Rakib Hasan, Sirajul Hoque
In the last fifty years, the pattern of humidity has changed due to natural and anthropogenic reasons in the southwestern part of Bangladesh. The humidity data was recorded at eight regional meteorological stations of the Bangladesh Meteorological Department over the period of 1974 to 2020 and is used for assessments of trends of humidity aspects in the context of seasonal variability and spatial distribution in the southwestern zone of Bangladesh. For this study, the humidity trend was analyzed through Microsoft Excel Software, and the Arc GIS tool was used for spatial distribution analysis. In Khulna, during the dry season maximum mean humidity was78.6% in 2008 and the minimum mean humidity was 63% in 1974. In the wet season, maximum mean humidity reached 87.5% in 1984 and minimum mean humidity was 78.8% in 1976. In Jessore, the maximum mean humidity in the dry season was 78.8% in 1998 and the minimum mean humidity was 65% in 1975. In the wet season, the maximum mean humidity was 84% in 1990 and the minimum mean humidity was 75.1% in 1979. In Mongla during the dry season maximum mean humidity was 78.6% in 2005 and the minimum mean humidity was 69.6% in 1989. In 2005, during the wet season maximum mean humidity was 86.2% and the minimum mean humidity was 82.7% in 2014. In Satkhira during the dry season maximum mean humidity was 79.2% in 1998 and the minimum mean humidity was 58.4% in 1984. In the wet season, the maximum mean humidity was 82.8% in 1997 and the minimum mean humidity was 72.7 % in 1979. In Barishal during the dry season maximum mean humidity was 83.4% in 1986 and the minimum mean humidity was 71.6% in 1978. In the wet season, the maximum mean humidity was 88.4% in 1975 and the minimum mean humidity was 82.4% in 1982. In Bhola during the dry season maximum mean humidity was 83.6% in 1990 and the minimum mean humidity was 74.4% in 1978. In the wet season, the maximum mean humidity was 89.5% in 1991 and the minimum mean humidity was 82.5% in 2017. In Patuakhali during the dry season maximum mean humidity was 85.8% in 2010 and the minimum mean humidity was 65% in 1982. In 1979, during the rainy season maximum mean humidity was 90.2% and the minimum mean humidity was 78.8%. In Khepupara during the dry season maximum mean humidity was 89% in 1987 and the minimum mean humidity was 57% in 1979. In 1987, the rainy season's maximum mean humidity was 88% and the minimum mean humidity was 78.6%. in 1979. In the southwestern zone of Bangladesh, dry season humidity was consistently increasing trend while wet season humidity was decreasing.
Article 3
Investigation of Depression Using Context Analysis
Salma Akter Asma, Sadik Hasan, Nazneen Akhter, Mehenaz Afrin, Afrina Khatun, Kazi Abu Taher
Depression is a major concern in today’s time as it is becoming a pandemic worldwide. Nowadays people (especially the young generation) are using social media sites to share their feelings, emotions, and personal life activities. Their mental health condition can be analysed by reviewing their social media posts and activities. Recent research work in this field is trying to go beyond manual depression detection. Hence, an automated system is necessary for analysing depression symptoms from social media for the sake of society. For this purpose, in this work, a Machine Learning based depression detection technique has been proposed. To develop the model six Machine Learning (ML) classifiers namely Support Vector Machine (SVM), Decision Tree (DT), K-Nearest Neighbour (KNN), Passive Aggressive (PA), Random Forest (RF), and Bagging classifier have been used. To improve the performance of the classifiers a dimension reduction technique namely Latent Semantic Analysis (LSA) is used. A comparison among four-dimension reduction techniques such as Latent Semantic Analysis (LSA), Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Fast Independent Component Analysis (Fast ICA) is given to justify why LSA is considered a dimension reduction technique in this work. With LSA, the Bagging classifier reached the top performance with an accuracy of 94.62%, while the base classifier is RF.
Article 4
Fruits and Vegetables Disease Detection System Based on Indications Using Machine Learning Approach: A Systematic Review
Tajbia Karim, Mariam Chowdhury, Saima Murtuza, Afrida Israt Jahan, Afrina Khatun
In agriculture science, automated and computerized methods increase the country's growth, economy and productivity as it is highly dependent on the export of fruits and vegetables. Nowadays, it is impossible to check the quality of fruits and vegetables with bare hands as they are exported in a batch. In this world of technology, artificial intelligence plays an essential role by introducing many algorithms to detect diseases that hamper quality. This paper presents a detailed review of which algorithm best detects diseases in fruits and vegetables. The paper also includes details about pre-processing, segmentation, different algorithms for detection, and image enhancement. An analysis of different algorithms proposed by researchers for disease detection within fruits and vegetables was conducted. From contemporary research works, we have come to know that there is not one perfect method for detecting diseases of all fruits and vegetables. By careful analysis, we have recommended which machine learning method might be suitable for specific types of fruits and vegetables.
Article 5
Non-communicable Disease Detection Based on Early Symptoms Using Machine Learning Approach Enabling Smart Healthcare Model (IoMT)
Tasnim Binte Shiraj, Ali Mortuza, Kazi Md Anisur Rahman, Tajbia Karim
Early detection of disease can prevent fatality and even save the lives of individuals. Since many diseases may have some common symptoms, it is essential to critically analyze symptoms for the correct prediction of diseases. Machine learning influences disease prediction, analyzing numerous features with high accuracy. In our country, elderly people suffer mostly alone as every other member remains busy outside the home, so they lack proper care and constant observation. A cloud infrastructure that allows digital devices to gather, infer, and exchange health data is called the Internet of Medical Things (IoMT). As the global economy grows, so will the cost of linked healthcare. The ever-lowering cost of sensor-based technologies is the reason behind the extraordinary expansion of IoMT. This paper reviews which machine learning algorithm is most suitable for detecting non- communicable diseases in terms of precision, specificity, accuracy, and confusion matrix. It is possible to keep track of old persons by detecting disease from the early stages of symptoms. We used OHAS (Occupational Health Automated System) dataset for finding the accuracy of the disease detection system. We utilized several machine learning techniques for detecting non-communicable diseases (for example, K-Nearest Neighbor, Decision Tree, Support Vector Machine (SVM), XG-Boost, and logistic regression). This article's objective is to investigate the repercussions of using the aforementioned algorithms effectively and find out which is the best algorithm for early Disease detection. We observed that from the mentioned algorithms, XG-Boost outperforms all other algorithms and gives the best accuracy of 86.24 percent.
Article 6
Present Situation Analysis of Environmental Management System on a Proposed LEED GOLD Sweater Manufacturing Company
Umma Salma Hashe
The textile industry has become the backbone of the economy of the country, but recently it also has risks. Large businesses on the higher end of the value chain are increasingly placing pressure on small and medium enterprises to satisfy minimum environmental and social requirements with quantity, quality, and price- cost requirements. Environmental management is the management of the responsibility of an organisation for its environmental impacts. The proposed LEED GOLD sweater manufacturing company is a brand-new subsidiary of the Rashid Group. The aim of this study is to examine the current situation of sweater manufacturing company’s environmental management system and to find out the shortcomings of Environmental management system practices. In this analysis, two data collection strategies were adopted. One of them is field based study along with questioner survey and another one is collection assisted by official paper, literature review, etc. This study found that general environmental policies and approaches to management are strictly defined in this factory. The research demonstrates that strict monitoring and compliance of existing laws led the owners of the factory to prevent a poor system of environmental management. In addition to the problem of emissions, factory owners strictly comply with environmental laws and pollution regulations except for wastewater discharge management. Furthermore, the study results and recommendations will be of great benefit to the authority, including HR & Environmental Enforcement Management, EMS Management, which would show best practices and pathways for the industry to help achieve LEED GOLD certification in order to minimize its environmental impacts and improve its operating efficiency.
Article 7
Equal Contribution, Corresponding Author Towards Digital Twin in Aerospace Industry
Sobhana Jahan, Md. Rawnak Saif Adib, Kazi Abu Taher, Md. Sazzadur Rahman
A digital twin is a virtual counterpart of any physical system created by a computer. The aerospace industry is one of the vividly growing fields of this era. Along with all the possibilities, this field also comes with various risks, dangers, and uncertainties because of the usage of complex mechanisms. By appending the digital twin in the aerospace industry, we can overcome those dangers and uncertainties. As this is an ongoing field, researchers are eager to work in this arena. Furthermore, in the aerospace business, the digital twin can boost efficiency and company value. Even industrialists are also willing to get benefited from the digital twin. That is why this paper comes up with 31 research papers on digital twin models which are used in the aerospace industry in the design, manufacturing, regular monitoring, and management phases. This paper provides several findings along with possible recommendations.
Article 8
Phthalate Esters (PAEs): Emerging Organic Pollutant in Aquatic Ecosystems
Raihan Sorker, Shamsunnahar Khanam
One of the most produced organic chemicals is known as Phthalate esters (PAEs) which are also excessively used with huge applications in industrial procedures as well as in packaging, medical centers, cosmetics, painting, agriculture, and consumer product uses. These organic pollutants are ubiquitous in the environment, mostly due to uncontrolled urbanization and are a cause of adverse impacts on humans and other living organisms. They even possess carcinogenicity characteristics and endocrine disrupting properties in the aquatic environment through their metabolites. Several studies were found to report the disrupting impacts these compounds make with their prevalence, toxicity, and exposure paths in the aquatic system, including humans. Waters are specifically vulnerable to PAEs because of the various sources of input through land runoff, agriculture, urban households, leaching of wastes etc., thus making it an emerging pollutant in the water. However, modern methodologies and instrumentations have been successful to measure even small amounts of PAEs in lakes, rivers, oceans, and other samples of aquatic systems. This study aims to provide a thorough study of the distribution and characteristics of phthalate esters and their effects on aquatic ecosystems including aquatic organisms and humans all over the world. These data will be beneficial for understanding the overall distribution of PAEs in the aquatic environment and reducing their ecological footprint.
Article 9
Smart Farming using AI towards Bangladeshi Agriculture
Mohammed Sowket Ali, Abu Muid Md. Raafee, Abu Saleh Musa Mia
Agriculture is the largest employment sector in Bangladesh. Which has a great impact on the economy, employment generation, poverty alleviation, human resources development, and food circuity of Bangladesh. Traditional Farming uses age-old agriculture equipment whereas Smart Farming is driven by modern latest technology-intensive farming methods. This smart farming system is cost- effective and middle-class farmers can use it in the farm field. This article reviews data-driven smart farming solutions incorporating Artificial Intelligence (AI), Internet of Things (IoT), Robotics and the management involved in the implementation of these smart farming systems in low-income countries like Bangladeshi Agriculture.
Article 10
Detection of Fake Job Postings on Online Using Convolutional Neural Network
Md Istakiak Adnan Palash, Arijit Diganto, Osama Nazmul Fatan, Kazi Abu Taher, Md Jaber Al Nahian
The present era focuses on every aspect of modern civilization that can be handled online, such as internet banking, teaching, safety, and employment, etc. This advancement in technology makes it easy for scammers to make money very quickly by looting people. Fake job advertisements are among the latest scams. When people apply for these fake jobs, they have topay fees and send their personal information to the fraudsters, which results in a scam and losing money. Therefore, in this paper, we have proposed a novel Convolutional Neural Network(CNN) to identify fake job postings efficiently. A publicly available dataset named EMSCAD was used to validate our proposed model. A comparison was also made between our proposed model and several state-of-the-art machine learning algorithms. In our experiments, we found that our proposed model had a greater accuracy than other machine learning algorithms. In addition, this study conducts a critical comparison of our method with the most recent existing studies.
Article 11
Public Perception about Climate Change and Its Impact in Different Seasons: A Micro-level Community Based Study in the South-Western Vulnerable Coastal Area, Bangladesh
Shamsunnahar Khanam, Md. Golam Muktadir, Afnan Dilshad
The southwestern coastal zone of Bangladesh is the most vulnerable area to climate change because of its dynamic geomorphology, poverty and reliance of many livelihoods on climate sensitive sectors. The study investigates the key determinants of micro-level community perception of climate change in different seasons and dimensions as well as their source of predictions. In this study, we have applied both qualitative and quantitative methods. Data were collected from both primary and secondary sources. A field investigation was performed in two Upazilas of the Bagerhat district and primary data were collected through personal interviews of 65 respondents with the structured questionnaire checklist. And secondary data were collected from journals, reports, and historical meteorological data. Findings reveal that there is a sharp economical gap among the interviewed people and 96% of them perceive the increase of heat intensity and extension of summer. 65% of respondents find the shortening of the winter season and feel the 3oC increase of minimum temperature that also revealed by the historical meteorological data analysis. The climate data also exhibits the 742.8 mm shortage of total rainfall during monsoon within a decade that is supported by 71% of people. Less than 25% of respondents find difficulties with groundwater but more than 50% complain the irrigation water dries up very soon. Almost all the respondents consider social media and TV news as well as their various senses are the source of their perception about local climate change. More than 90% of respondents perceive cyclones and salinity are their major hazards and also predict that storm surge along with sea level rise would add to this group. Policymakers should emphasize the outcomes of such study and design a zone wise adaptation plan that reflects public opinion, values, and demand.
Article 12
Impacts of Tannery Effluents on the Environmental Quality of Hazaribagh Area of Bangladesh and its Possible Remediation Measures: A Review
Faria Jahan, Md. Arifur Rahman Bhuiyan, Israt Jahan, Md. Golam Muktadir, Fatema Shahinur Jahan
Tannery effluents are containing harmful inorganic chemical substances such as chlorides, sulphides, chromium, lead, mercury, nitrogenous compounds and tannins as well as trace organic chemicals. The increased use of synthetic chemicals like dyes and finishing agents are mainly responsible for these pollutants. In the last few decades, pollution from tanneries at the leading industrial site in Dhaka discharged into the Buriganga River. These substances are commonly toxic and persistent, posing health and environmental risks. In this article, we discussed the deterioration of environmental quality with tannery effluents. The health impacts, water quality, damaging ecology, and threatening people's livelihoods are directly and indirectly related to exposure to hazardous wastes, including carcinogenic effects, reproductive system damage, respiratory system effects and central nervous system effects. The goal of this review was to evaluate the environmental quality in the Hazaribagh tannery industrial area. This study discusses many remediation approaches that help improve environmental quality. These findings recommend monitoring and cleaning up tannery effluent simultaneously. This review examined heavy metal contamination, exposure toxicity, research gaps, existing regulations, and long-term remediation methods in Hazaribagh to enhance environmental quality.
