Filters








292 Hits in 1.4 sec

Environmental Impacts of Personal Protective Clothing Used to Combat COVID-19 [article]

Mohammad Abbas Uddin, Shaila Afroj, Tahmid Hasan, Chris Carr, Kostya S Novoselov, Nazmul Karim
2021 arXiv   pre-print
Personal protective clothing is critical to shield users from highly infectious diseases including COVID-19. Such clothing is predominantly single-use, made of plastic-based synthetic fibres such as polypropylene and polyester, low cost and able to provide protection against pathogens. However, the environmental impacts of synthetic fibre-based clothing are significant and well-documented. Despite growing environmental concerns with single-use plastic-based protective clothing, the recent
more » ... 19 pandemic has seen a significant increase in their use, that could result in a further surge of oceanic plastic pollution, adding to mass of plastic waste that already threatens marine life. In this review, we briefly discuss the nature of the raw materials involved in the production of such clothing, as well as manufacturing techniques and the PPE supply chain. We identify the environmental impacts at critical points in the protective clothing value chain from production to consumption, focusing on water use, chemical pollution, CO2 emissions and waste. On the basis of these environmental impacts, we outline the need for fundamental changes in the business model, including increased usage of reusable protective clothing, addressing supply chain bottlenecks, establishing better waste management, and the use of sustainable materials and processes without associated environmental problems.
arXiv:2109.01037v1 fatcat:a2dqjbax3fa2jczilmz3goewhe

XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages [article]

Tahmid Hasan, Abhik Bhattacharjee, Md Saiful Islam, Kazi Samin, Yuan-Fang Li, Yong-Bin Kang, M. Sohel Rahman, Rifat Shahriyar
2021 arXiv   pre-print
Contemporary works on abstractive text summarization have focused primarily on high-resource languages like English, mostly due to the limited availability of datasets for low/mid-resource ones. In this work, we present XL-Sum, a comprehensive and diverse dataset comprising 1 million professionally annotated article-summary pairs from BBC, extracted using a set of carefully designed heuristics. The dataset covers 44 languages ranging from low to high-resource, for many of which no public
more » ... is currently available. XL-Sum is highly abstractive, concise, and of high quality, as indicated by human and intrinsic evaluation. We fine-tune mT5, a state-of-the-art pretrained multilingual model, with XL-Sum and experiment on multilingual and low-resource summarization tasks. XL-Sum induces competitive results compared to the ones obtained using similar monolingual datasets: we show higher than 11 ROUGE-2 scores on 10 languages we benchmark on, with some of them exceeding 15, as obtained by multilingual training. Additionally, training on low-resource languages individually also provides competitive performance. To the best of our knowledge, XL-Sum is the largest abstractive summarization dataset in terms of the number of samples collected from a single source and the number of languages covered. We are releasing our dataset and models to encourage future research on multilingual abstractive summarization. The resources can be found at .
arXiv:2106.13822v1 fatcat:achdb2tdjjc35mxgb5d7m3eu24

Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translation [article]

Tahmid Hasan, Abhik Bhattacharjee, Kazi Samin, Masum Hasan, Madhusudan Basak, M. Sohel Rahman, Rifat Shahriyar
2020 arXiv   pre-print
Hasan et al. (2019); Mumin et al. (2019a) also showed with limited parallel data available on the web that NMT provided improved translation for Bengali-English pair.  ...  Comparison with Previous Results We compared our results with Mumin et al. (2019b ), Hasan et al. (2019 ), and Mumin et al. (2019a . The first work used SMT, while the latter two used NMT models.  ... 
arXiv:2009.09359v2 fatcat:chxob2dxo5adrjfqcexualahmm

Bangla Natural Language Processing: A Comprehensive Analysis of Classical, Machine Learning, and Deep Learning Based Methods

Ovishake Sen, Mohtasim Fuad, Md. Nazrul Islam, Jakaria Rabbi, Mehedi Masud, Md. Kamrul Hasan, Md. Abdul Awal, Awal Ahmed Fime, Md. Tahmid Hasan Fuad, Delowar Sikder, Md. Akil Raihan Iftee
2022 IEEE Access  
Parts of Speech Tagging is a part of Natural Language Processing that classifies and tags different words in a sentence according to that particular human language. 1) CLASSICAL APPROACHES Hasan et al  ...  TAHMID HASAN FUAD was born in Rajshahi, Bangladesh.  ... 
doi:10.1109/access.2022.3165563 fatcat:rmersduz6vbyjjczvobrebskmi

Blockchain and smart contract for IoT enabled smart agriculture

Tahmid Hasan Pranto, Abdulla All Noman, Atik Mahmud, AKM Bahalul Haque
2021 PeerJ Computer Science  
Decentralized storage (blockchain) of Interplanetary file system to store and share industrial spare parts data has been implemented by Hasan et al. (2020) .  ...  Hasan et al. (2020) integrates smart contracts in their industrial spare parts traceability research work to implement the necessary function, modifiers, and events inside their proposed system, which  ...  Author Contributions Tahmid Hasan Pranto conceived and designed the experiments, performed the experiments, analyzed the data, performed the computation work, prepared figures and/ or tables, authored  ... 
doi:10.7717/peerj-cs.407 pmid:33834098 pmcid:PMC8022535 fatcat:j2v4l2xlord6tbxmcdstiskd6q

BanglaNLG: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla [article]

Abhik Bhattacharjee, Tahmid Hasan, Wasi Uddin Ahmad, Rifat Shahriyar
2022 arXiv   pre-print
We chose the Bangla portion of XL-Sum (Hasan et al., 2021b) for this task.  ...  For this task, we use the BanglaNMT parallel corpus introduced by (Hasan et al., 2020a) .  ... 
arXiv:2205.11081v2 fatcat:5z3xeoix5zf2zcapyqthkuegbe

Prediction of Epidemics Trend of COVID-19 in Bangladesh

Raguib Hassan, Abu Sayem Dosar, Joytu Kumar Mondol, Tahmid Hassan Khan, Abdullah Al Noman, Mirajus Salehin Sayem, Moinul Hasan, Nasrin Sultana Juyena
2020 Frontiers in Public Health  
Amid a critical and emergent situation like the coronavirus disease (COVID-19) pandemic related to extreme health and economic repercussions, we used and presented the mathematical modeling like susceptible–infectious–recovered (SIR) to have a numerical demonstration that can shed light to decide the fate of the scourge in Bangladesh. To describe the idea about the factors influencing the outbreak data, we presented the current situation of the COVID-19 outbreak with graphical trends.Methods:
more » ... imary data were collected and analyzed by using a pre-created Google Survey form having a pre-set questionnaire on the social distancing status of different districts. Secondary data on the total and the daily number of laboratory tests, confirmed positive cases, and death cases were extracted from the publicly available sources to make predictions. We estimated the basic reproduction number (R◦) based on the SIR mathematical model and predicted the probable fate of this pandemic in Bangladesh.Results: Quarantine situations in different regions of Bangladesh were evaluated and presented. We also provided tentative forecasts until 31 May 2020 and found that the predicted curve followed the actual curve approximately. Estimated R◦-values (6.924) indicated that infection rate would be greater than the recovery rate. Furthermore, by calibrating the parameters of the SIR model to fit the reported data, we assume the ultimate ending of the pandemic in Bangladesh by December 2022.Conclusion: We hope that the results of our analysis could contribute to the elucidation of critical aspects of this outbreak and help the concerned authority toward decision making.
doi:10.3389/fpubh.2020.559437 pmid:33330309 pmcid:PMC7734053 fatcat:gizvxznpubgevkde7vqiqmrtyq

Recent Advances in Deep Learning Techniques for Face Recognition

Md. Tahmid Hasan Fuad, Awal Ahmed Fime, Delowar Sikder, Md. Akil Raihan Iftee, Jakaria Rabbi, Mabrook S. Al-Rakhami, Abdu Gumae, Ovishake Sen, Mohtasim Fuad, Md. Nazrul Islam
2021 IEEE Access  
In recent years, researchers have proposed many deep learning (DL) methods for various tasks, and particularly face recognition (FR) made an enormous leap using these techniques. Deep FR systems benefit from the hierarchical architecture of the DL methods to learn discriminative face representation. Therefore, DL techniques significantly improve state-of-the-art performance on FR systems and encourage diverse and efficient real-world applications. In this paper, we present a comprehensive
more » ... is of various FR systems that leverage the different types of DL techniques, and for the study, we summarize 171 recent contributions from this area. We discuss the papers related to different algorithms, architectures, loss functions, activation functions, datasets, challenges, improvement ideas, current and future trends of DL-based FR systems. We provide a detailed discussion of various DL methods to understand the current state-of-the-art, and then we discuss various activation and loss functions for the methods. Additionally, we summarize different datasets used widely for FR tasks and discuss challenges related to illumination, expression, pose variations, and occlusion. Finally, we discuss improvement ideas, current and future trends of FR tasks. INDEX TERMS Deep learning, face recognition, artificial neural network, convolutional neural network, auto encoder, generative adversarial network, deep belief network, reinforcement learning. 99112 This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ VOLUME 9, 2021
doi:10.1109/access.2021.3096136 fatcat:g5sftnugunbczppu56dbymlhra

Recent Advances in Deep Learning Techniques for Face Recognition [article]

Md. Tahmid Hasan Fuad, Awal Ahmed Fime, Delowar Sikder, Md. Akil Raihan Iftee, Jakaria Rabbi, Mabrook S. Al-rakhami, Abdu Gumae, Ovishake Sen, Mohtasim Fuad, Md. Nazrul Islam
2021 arXiv   pre-print
In recent years, researchers have proposed many deep learning (DL) methods for various tasks, and particularly face recognition (FR) made an enormous leap using these techniques. Deep FR systems benefit from the hierarchical architecture of the DL methods to learn discriminative face representation. Therefore, DL techniques significantly improve state-of-the-art performance on FR systems and encourage diverse and efficient real-world applications. In this paper, we present a comprehensive
more » ... is of various FR systems that leverage the different types of DL techniques, and for the study, we summarize 168 recent contributions from this area. We discuss the papers related to different algorithms, architectures, loss functions, activation functions, datasets, challenges, improvement ideas, current and future trends of DL-based FR systems. We provide a detailed discussion of various DL methods to understand the current state-of-the-art, and then we discuss various activation and loss functions for the methods. Additionally, we summarize different datasets used widely for FR tasks and discuss challenges related to illumination, expression, pose variations, and occlusion. Finally, we discuss improvement ideas, current and future trends of FR tasks.
arXiv:2103.10492v1 fatcat:h526swzntjgmlcjmwnuidqg44u

The Mental Health Act and Public Perception on Resource Allocation in Bangladesh

Md. Sanwar Siraj, Rebecca Susan Dewey, Md Ikhtiar Uddin Bhuiyan, Kamrul Hasan, Md Yousuf Ali, Ahnaf Tahmid Arnab
2021 American Journal of Psychiatry and Neuroscience  
The Bangladesh government passed a new Mental Health Act in 2018, which formally came into effect on November 14. In order to decrease the significance and endurance of the hundred-year-old statute, the Lunacy Act of 1912, the government enacted the new Act by reformation. The Act is designed to ensure the provision of health services, the preservation of dignity, property rights and rehabilitation, and the general wellbeing of individuals suffering from diseases and disorders associated with mental health.
doi:10.11648/j.ajpn.20210902.13 fatcat:fxntewook5fgrewkkvhatlpw7a

DESIGN OF A POWER SYSTEM (SOLAR-DIESEL GENERATOR) FOR A GARMENT INDUSTRY AND LOAD OPTIMIZATION

Ahnaf Tahmid Nahian, Md.Tahmid Farhan Himel, Mahmudul Hasan, Nafeez Rahman, Chowdhury Akram Hossain
2019 International Journal of Engineering Applied Sciences and Technology  
Due to adverse effect of global warming and environmental pollution, future world is looking for decontaminated green energy resources for power generation. Economy of today's world is based on commercial activities and rapid industrialization. To ensure sustainable economic activity we need to fulfil the energy demand of equipment as well as to serve the automation technology of industrial sector. This results an excess pressure on electricity demand significantly. In spite of many
more » ... and proper technical support Bangladesh is looking forward to extract energy from its available renewable resources like other countries. Hybrid power system is a good choice to serve this purpose. This work mainly emphasis on the design and feasibility study of hybrid power system in the context of a particular garment industry, as the garments are the major source of foreign currency and employment in our country. The system is comprised of solar PV and diesel generator. Cost analysis and load optimization is done by HOMER Pro. System validity and advantages are also discussed in explicit way.
doi:10.33564/ijeast.2019.v04i08.001 fatcat:agw5pd6imbamzoespy77c4zbsu

Insight about Detection, Prediction and Weather Impact of Coronavirus (Covid-19) using Neural Network

A K M Bahalul Haque, Tahmid Hasan Pranto, Abdulla All Noman, Atik Mahmood
2020 International Journal of Artificial Intelligence & Applications  
The world is facing a tough situation due to the catastrophic pandemic caused by novel coronavirus (COVID-19). The number people affected by this virus are increasing exponentially day by day and the number has already crossed 6.4 million. As no vaccine has been discovered yet, the early detection of patients and isolation is the only and most effective way to reduce the spread of the virus. Detecting infected persons from chest X-Ray by using Deep Neural Networks, can be applied as a time and
more » ... aborsaving solution. In this study, we tried to detect Covid-19 by classification of Covid-19, pneumonia and normal chest X-Rays. We used five different Convolutional Pre-Trained Neural Network models (VGG16, VGG19, Xception, InceptionV3 and Resnet50) and compared their performance. VGG16 and VGG19 shows precise performance in classification. Both models can classify between three kinds of X-Rays with an accuracy over 92%. Another part of our study was to find the impact of weather factors (temperature, humidity, sun hour and wind speed) on this pandemic using Decision Tree Regressor. We found that temperature, humidity and sun-hour jointly hold 85.88% impact on escalation of Covid-19 and 91.89% impact on death due to Covid-19 where humidity has 8.09% impact on death. We also tried to predict the death of an individual based on age, gender, country, and location due to COVID-19 using the LogisticRegression, which can predict death of an individual with a model accuracy of 94.40%.
doi:10.5121/ijaia.2020.11406 fatcat:lgmsjlphf5c5pky32ivjfx2bey

Bangla Natural Language Processing: A Comprehensive Review of Classical, Machine Learning, and Deep Learning Based Methods [article]

Ovishake Sen, Mohtasim Fuad, MD. Nazrul Islam, Jakaria Rabbi, MD. Kamrul Hasan, Mohammed Baz, Mehedi Masud, Md. Abdul Awal, Awal Ahmed Fime, Md. Tahmid Hasan Fuad, Delowar Sikder, MD. Akil Raihan Iftee
2021 arXiv   pre-print
TAHMID HASAN FUAD was born in Rajshahi, Bangladesh.  ...  Hasan is serving as an Assistant Professor at KUET in the EEE department.  ... 
arXiv:2105.14875v2 fatcat:kvqmgxpthvh2fj7jza64n6kaiq

Machine Learning and Artificial Intelligence in Circular Economy: A Bibliometric Analysis and Systematic Literature Review

Abdulla All Noman, Umma Habiba Akter, Tahmid Hasan Pranto, AKM Bahalul Haque
2022 Annals of Emerging Technologies in Computing  
With unorganized, unplanned and improper use of limited raw materials, an abundant amount of waste is being produced, which is harmful to our environment and ecosystem. While traditional linear production lines fail to address far-reaching issues like waste production and a shorter product life cycle, a prospective concept, namely circular economy (CE), has shown promising prospects to be adopted at industrial and governmental levels. CE aims to complete the product life cycle loop by bringing
more » ... ut the highest values from raw materials in the design phase and later on by reusing, recycling, and remanufacturing. Innovative technologies like artificial intelligence (AI) and machine learning(ML) provide vital assistance in effectively adopting and implementing CE in real-world practices. This study explores the adoption and integration of applied AI techniques in CE. First, we conducted bibliometric analysis on a collection of 104 SCOPUS indexed documents exploring the critical research criteria in AI and CE. Forty papers were picked to conduct a systematic literature review from these documents. The selected documents were further divided into six categories: sustainable development, reverse logistics, waste management, supply chain management, recycle & reuse, and manufacturing development. Comprehensive research insights and trends have been extracted and delineated. Finally, the research gap needing further attention has been identified and the future research directions have also been discussed.
doi:10.33166/aetic.2022.02.002 fatcat:sq4destgxfb53hbxcbbtq2mafi

BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla [article]

Abhik Bhattacharjee, Tahmid Hasan, Wasi Uddin Ahmad, Kazi Samin, Md Saiful Islam, Anindya Iqbal, M. Sohel Rahman, Rifat Shahriyar
2022 arXiv   pre-print
., 2018) dataset: we translated the MultiNLI training data using the English to Bangla translation model by Hasan et al. (2020) and had the evaluation sets translated by expert human translators. 4  ... 
arXiv:2101.00204v4 fatcat:l3u5thti6nar5folnd6ljyzf3i
« Previous Showing results 1 — 15 out of 292 results