Article 1 · Research Article
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
Vol. 01, Issue 01Citations: 0Views: 1995Downloads: 1887
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.
Article 2 · Research Article
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
Vol. 01, Issue 01Citations: 0Views: 1992Downloads: 1863
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 3 · Research Article
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
Vol. 01, Issue 01Citations: 0Views: 1971Downloads: 1983
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 4 · Research Article
Analysis of Duplicate Bug Report Detection Techniques
Afrina Khatun, Sarker Foysal Mohammud Al Gabid, Nazneen Akhter, Kazi Abu Taher, Tajbia Karim
Vol. 01, Issue 01Citations: 0Views: 1965Downloads: 2033
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 5 · Research Article
Study of Spatio-temporal Variation of Humidity over the Southwestern Zone of Bangladesh
Md. Rakib Hasan, Sirajul Hoque
Vol. 01, Issue 01Citations: 0Views: 1962Downloads: 1598
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 6 · Research Article
Equal Contribution, Corresponding Author Towards Digital Twin in Aerospace Industry
Sobhana Jahan, Md. Rawnak Saif Adib, Kazi Abu Taher, Md. Sazzadur Rahman
Vol. 01, Issue 01Citations: 0Views: 1948Downloads: 1807
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 7 · Research Article
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
Vol. 01, Issue 01Citations: 0Views: 1947Downloads: 1809
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 8 · Research Article
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
Vol. 01, Issue 01Citations: 0Views: 1943Downloads: 1836
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 9 · Research Article
Investigation of Depression Using Context Analysis
Salma Akter Asma, Sadik Hasan, Nazneen Akhter, Mehenaz Afrin, Afrina Khatun, Kazi Abu Taher
Vol. 01, Issue 01Citations: 0Views: 1941Downloads: 1858
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 10 · Research Article
Present Situation Analysis of Environmental Management System on a Proposed LEED GOLD Sweater Manufacturing Company
Umma Salma Hashe
Vol. 01, Issue 01Citations: 0Views: 1931Downloads: 1812
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 11 · Research Article
Phthalate Esters (PAEs): Emerging Organic Pollutant in Aquatic Ecosystems
Raihan Sorker, Shamsunnahar Khanam
Vol. 01, Issue 01Citations: 0Views: 1912Downloads: 1830
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 12 · Research Article
Smart Farming using AI towards Bangladeshi Agriculture
Mohammed Sowket Ali, Abu Muid Md. Raafee, Abu Saleh Musa Mia
Vol. 01, Issue 01Citations: 0Views: 1842Downloads: 1931
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 13 · Research Article
A Study of Machine Learning Models with Population and Swarm Based Optimization for Cardiovascular Disease Prediction
Ruponti Muin Nova, Jawad Anzum Fahim, Sharmeen Jahan Seema
Vol. 03, Issue 01Citations: 0Views: 314Downloads: 292
Cardiovascular Diseases (CVD) remain a leading cause of global mortality, necessitating accurate and scalable diagnostic tools. This study proposes a machine learning (ML)-based framework for early CVD prediction by integrating advanced feature selection, model tuning, and hybrid optimization techniques. Five ML models were evaluated, and their performance was enhanced through the application of Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) for hyperparameter optimization. Feature selection techniques were employed to identify clinically relevant predictors, including binning strategies for age, BMI, and MAP. PSO was applied within a cross validation (CV) loop, yielding a notable improvement in Logistic Regression (LR) performance raising CV accuracy from 81.5% to 82.51%. Similarly, GA optimization improved cross validation accuracy for Random Forest (RF) and XGBoost from baseline test accuracies of 82.03% and 81.1% to 82.51% and 82.04%, respectively. Evaluation metrics such as precision, recall, F1-score, and AUC were also utilized to ensure robust model assessment, especially considering imbalance within the dataset. A comparative analysis against traditional hyperparameter tuning methods (e.g., GridSearchCV) demonstrated the superiority of PSO and GA in enhancing predictive performance. However, the study is limited using of a single public dataset without external clinical validation. These findings highlight the necessity for more extensive data validation in subsequent studies, but they also highlight the promise of hybrid optimization and feature engineering in improving ML-based CVD diagnosis.
Article 14 · Research Article
HDP: Simulated IoT Architecture Design Applying GridSearchCV
Nusrat N. Suzana, K. Habibul Kabir
Vol. 03, Issue 01Citations: 0Views: 310Downloads: 274
Globally, cardiovascular disease remains a major burden of morbidity and death with more than half a billion affected population. Heart Disease Prediction (HDP) is strenuous for medical staff because of the risk factors. Classifying people into various risk groups according to their traits and medical history can be done effectively and powerfully leveraging machine learning techniques. This research study leverages the Framingham Heart Study dataset to propose a machine learning enabled system regarding heart disease prediction (HDP). Utilizing GridSearchCV, six supervised machine learning algorithms were trained and optimized: gaussian naive bayes, k nearest neighbour, decision tree, support vector machine, random forests, and logistic regression. With 97.9% accuracy, 96.4% precision, 99.5% recall, and 97.9% f1-score, random forest outperformed the six algorithms with a 10-fold validation technique. To illustrate the prediction model’s possible real-time integration into patient monitoring systems, a notional Internet of Things (IoT) architecture was created. Even though the architecture is now just in simulation, it offers a framework for future use with real IoT infrastructure. The results demonstrate that combining ML with IoT for early cardiovascular risk prediction and decision assistance is both feasible and beneficial.
Article 15 · Research Article
Towards Early Intervention for Panic Disorder Detection and Dominant Feature Selection through Machine Learning Techniques
Sayma Alam Suha, Mosa. Sumiya Akter
Vol. 03, Issue 01Citations: 0Views: 279Downloads: 294
Panic disorder, marked by recurrent and unexpected panic attacks, significantly impairs daily functioning and overall well-being. Early detection is crucial to improving patient outcomes, yet traditional diagnostic methods often delay timely identification. This study investigates the application of machine learning (ML) techniques for the early detection of panic disorder and the identification of key features that contribute to its development. Utilising a comprehensive dataset of clinical and physiological data including demographics, symptoms, and vital signs from individuals with and without panic disorder, multiple ML classification algorithms were trained, tested, and evaluated. The ensemble voting feature selection method was employed to pinpoint the most relevant predictors of panic disorder. Among the models tested, the Extra Tree Bagging Ensemble ML model demonstrated exceptional performance, achieving 99.8% accuracy, along with high sensitivity and precision. Feature significance analysis revealed critical physiological and psychological factors associated with panic vulnerability, offering valuable insights into the disorder’s underlying mechanisms. This research underscores the potential of ML-based approaches in enabling early detection of panic disorder, paving the way for personalised prevention and intervention strategies. The findings highlight the importance of integrating advanced computational techniques in mental health diagnostics to enhance accuracy and timeliness in identifying panic disorder.
Article 16 · Research Article
Data Center Standards: A Review of Metrics and Standardization Gaps
S M Saiful Islam, Sayma Alam Suha, Tasnim Binte Shiraj
Vol. 03, Issue 01Citations: 0Views: 271Downloads: 304
Certifying data centers (DCs) necessitates a rigorous evaluation of diverse metrics to assess performance, efficiency, sustainability, and operational effectiveness. Key technological and infrastructural parameters are analyzed to ensure compliance with industry standards. However, inconsistencies in measurement methodologies often lead to discrepancies in evaluation, highlighting the need for standardized metrics. Current industry standards, including Uptime Institute Tier Classification, ANSI/TIA-942, ASHRAE, The Green Grid (TGG), NIST, and EPA ENERGY STAR—exhibit significant variations in scope, methodology, and applicability. A comparative analysis reveals that while these frameworks emphasize infrastructure redundancy and energy efficiency (e.g., PUE, MTBF). While energy efficiency remains a critical challenge, a more comprehensive certification approach must integrate additional dimensions such as sustainability, operational reliability, availability, and security. This paper presents a systematic review of existing data center metrics, focusing on their role in standardization and certification. These metrics are categorized into six key sub-dimensions: efficiency, sustainability, operations, reliability, availability, and security. The findings underscore the need for a unified certification framework that balances physical infrastructure metrics with emerging requirements such as software resilience, real-time adaptability, and cross-platform interoperability. Such an approach would enable more comprehensive benchmarking, particularly for hybrid and hyperscale data centers. This approach will not only improve the certification evaluation process but also enable a more holistic assessment of data center performance.
Article 17 · Research Article
An Explainable Ensemble Learning Framework for Brain Tumour Using Pretrained Models and XAI Techniques
Muhammad Mahbub Sarwar Shafi, Jannatul Ferdous Mirza
Vol. 03, Issue 01Citations: 0Views: 263Downloads: 288
Brain tumours pose serious health challenges worldwide, demanding early and accurate diagnosis for effective treatment. Traditional diagnostic methods are time-consuming and subject to human error. While deep learning models have advanced automated brain tumour classification, their black-box nature limits clinical trust. This study introduces an ensemble learning framework that integrates EfficientNetB0, InceptionV3, and DenseNet for improved classification accuracy. High-pass filtering (HPF) is employed in the preprocessing phase to enhance tumour-specific features. Three machine learning classifiers—Random Forest, Support Vector Machine, and Logistic Regression—are combined using a soft voting strategy to deliver final predictions. To ensure interpretability, Local Interpretable Model-Agnostic Explanations (LIME) is used to visualise feature contributions. The proposed method achieved a validation accuracy of 97.3% and an AUC-ROC score of 0.9986 on a publicly available brain MRI dataset. These results outperform individual models and enhance clinical reliability. This study demonstrates that combining deep learning, ensemble learning, and XAI techniques can bridge the gap between model performance and interpretability, promoting real-world adoption of AI-based medical diagnosis.
Article 18 · Research Article
Analysis of Safety Margin Aspects of the BAEC TRIGA Research Reactor using the Deterministic Code System SRAC2006
Md Masud Rana, M J H Khan, Md. Asaduzzaman
Vol. 03, Issue 01Citations: 0Views: 258Downloads: 322
The goal of this study is to test the ability of the BAEC 3 MW TRIGA Mark-II research reactor, intended to run at its steady state full power 3 MWth with suitable safety limits. The neutronics design safety margins of the core were calculated based on the deterministic method. Two methods have been applied, and they are (i) the collision probability lattice transport code SRAC-PIJ for the region averaged group coefficients of fuel and non-fuel units separately, and (ii) the neutron diffusion theory code SRAC-CITATION for global core computations. The realistic calculated safety margin features of the BAEC TRIGA core are effective multiplication factor (Keff), surplus reactivity (ρex), efficacy of control rod, shutdown margin (SDM), safety reactivity factor (SRF) and fuel temperature reactivity coefficient (FTC). The calculated results were evaluated with the experimental data, as well as the values provided by the International Atomic Energy Agency (IAEA) and the results obtained from the Monte Carlo N-Particle (MCNP) and WIMS-CITATION simulations. The IAEA safety principle says that the safety reactivity factor of a research reactor should be greater than 1.5 and the calculated values of SRF are 1.588 and 1.589, which exceeds 1.5 and also indicates that the reactor exhibits improved operational and safety characteristics, which echoes that the SRAC2006 code system yields the physical TRIGA core model truthfully. Therefore, the analysis gratifies each safety margin feature of existing core arrangement of 3 MW TRIGA Mark-II research reactor following IAEA safety viewpoints for its effective safe operation.
Article 19 · Research Article
A Systematic Analysis of Machine Learning and Deep Learning Techniques to Detect Fake News
Nazneen Akhter, Sahara Alam Tuba, Afrina Khatun
Vol. 03, Issue 01Citations: 0Views: 254Downloads: 304
Expanding social media platforms produce a large amount of news daily that is not always accurate, true, or reliable. Some dishonest news vendors intentionally generate misinformation to misguide public views, manipulate people’s opinions, and further create a political agenda or confusion for their economic benefit. Automated techniques such as Machine Learning (ML) and Deep Learning (DL), are frequently used to prevent the spread of fake news. This work conducts a systematic assessment of the existing ML and DL strategies with a focus on data pre-processing, feature extraction, feature selection, and contextual analysis that enhance the performance of the fake news detection model. A comparison-based description of the fundamental models of ML and DL is provided, where it is found that DL techniques are more explainable and perform well in detecting fake news than ML classifiers.
Article 20 · Review Article
Bangla Sign Language Recognition: A Comprehensive Review of Machine Learning Approaches and Data Sources
Jasiya Fairiz Raisa, Rumana Yasmin
Vol. 03, Issue 01Citations: 0Views: 254Downloads: 305
Sign language is the primary medium of communication for deaf and dumb individuals, but it is difficult to interpret for every demographic, which makes communication extremely difficult. Bangla is among the most widely spoken languages worldwide, and substantial research on Bangla Sign Language (BdSL) has emerged to address this issue. In recent years, researchers have been working to automate BdSL recognition using different techniques. This review paper evaluates research trends in BdSL by comparing the features and evaluation outcomes of various systems and approaches applied to both existing and novel datasets. We have gathered and integrated metadata from datasets encompassing all BdSL alphabets and numbers implemented to date. The analysis of this paper shows that most suggested models work well on images with static and single-handed signs, but performance drops in complicated backgrounds. Additionally, we concentrated on identifying insights and parallels within the existing systems, identifying research gaps, and suggesting potential future directions.
