Search

We announce the sequence of the Escherichia coli MTR_GS_S1457 strain isolated from a soil sample of a vegetable gardening system for the first time in Bangladesh. With a length of 4,918,647 bp, this strain contained one plasmid, two CRISPR arrays, 54 predicted antibiotic resistance genes, and 81 predicted virulence factor genes.

This study announces the genome sequence of the Shigella flexneri MTR_GR_V146 strain isolated from a tomato (Solanum lycopersicum) sample in Bangladesh. This strain has a 4,624,521 bp genome length (coverage: 73.07×), 2 CRISPR arrays, 1 plasmid, 52 predicted antibiotic resistance genes, and 53 virulence factor genes.

Authorship Attribution is the task of creating an appropriate characterization of text that captures the authors' writing style to identify the original author of a given piece of text. With increased anonymity on the internet, this task has become increasingly crucial in various security and plagiarism detection fields. Despite significant advancements in other languages such as English, Spanish, and Chinese, Bangla lacks comprehensive research in this field due to its complex linguistic feature and sentence structure. Moreover, existing systems are not scalable when the number of author increases, and the performance drops for small number of samples per author. In this paper, we propose the use of Average-Stochastic Gradient Descent Weight-Dropped Long Short-Term Memory (AWD-LSTM) architecture and an effective transfer learning approach that addresses the problem of complex linguistic features extraction and scalability for authorship attribution in Bangla Literature (AABL). We analyze the effect of different tokenization, such as word, sub-word, and character level tokenization, and demonstrate the effectiveness of these tokenizations in the proposed model. Moreover, we introduce the publicly available Bangla Authorship Attribution Dataset of 16 authors (BAAD16) containing 17,966 sample texts and 13.4+ million words to solve the standard dataset scarcity problem and release six variations of pre-trained language models for use in any Bangla NLP downstream task. For evaluation, we used our developed BAAD16 dataset as well as other publicly available datasets. Empirically, our proposed model outperformed state-of-the-art models and achieved 99.8% accuracy in the BAAD16 dataset. Furthermore, we showed that the proposed system scales much better even with an increasing number of authors, and performance remains steady despite few training samples., Comment: Accepted in ACM TALLIP August 2022

This article presents a probabilistic modeling method utilizing smart meter data and an innovative agent-based simulator for electric vehicles (EVs). The aim is to assess the effects of different cost-driven EV charging strategies on the power distribution network (PDN). We investigate the effects of a 40% EV adoption on three parts of Frederiksberg's low voltage distribution network (LVDN), a densely urbanized municipality in Denmark. Our findings indicate that cable and transformer overloading especially pose a challenge. However, the impact of EVs varies significantly between each LVDN area and charging scenario. Across scenarios and LVDNs, the share of cables facing congestion ranges between 5% and 60%. It is also revealed that time-of-use (ToU)-based and single-day cost-minimized charging could be beneficial for LVDNs with moderate EV adoption rates. In contrast, multiple-day optimization will likely lead to severe congestion, as such strategies concentrate demand on a single day that would otherwise be distributed over several days, thus raising concerns about how to prevent it. The broader implications of our research suggest that, despite initial worries primarily centered on congestion due to unregulated charging during peak hours, a transition to cost-based smart charging, propelled by an increasing awareness of time-dependent electricity prices, may lead to a significant rise in charging synchronization, bringing about undesirable consequences for the power distribution network (PDN).

Integrating Internet of Things (IoT) technology inside the cold supply chain can enhance transparency, efficiency, and quality, optimizing operating procedures and increasing productivity. The integration of IoT in this complicated setting is hindered by specific barriers that need a thorough examination. Prominent barriers to IoT implementation in the cold supply chain are identified using a two-stage model. After reviewing the available literature on the topic of IoT implementation, a total of 13 barriers were found. The survey data was cross-validated for quality, and Cronbach's alpha test was employed to ensure validity. This research applies the interpretative structural modeling technique in the first phase to identify the main barriers. Among those barriers, "regularity compliance" and "cold chain networks" are key drivers for IoT adoption strategies. MICMAC's driving and dependence power element categorization helps evaluate the barrier interactions. In the second phase of this research, a decision-making trial and evaluation laboratory methodology was employed to identify causal relationships between barriers and evaluate them according to their relative importance. Each cause is a potential drive, and if its efficiency can be enhanced, the system as a whole benefits. The research findings provide industry stakeholders, governments, and organizations with significant drivers of IoT adoption to overcome these barriers and optimize the utilization of IoT technology to improve the effectiveness and reliability of the cold supply chain.

We present a framework to recognize Parkinson's disease (PD) through an English pangram utterance speech collected using a web application from diverse recording settings and environments, including participants' homes. Our dataset includes a global cohort of 1306 participants, including 392 diagnosed with PD. Leveraging the diversity of the dataset, spanning various demographic properties (such as age, sex, and ethnicity), we used deep learning embeddings derived from semi-supervised models such as Wav2Vec 2.0, WavLM, and ImageBind representing the speech dynamics associated with PD. Our novel fusion model for PD classification, which aligns different speech embeddings into a cohesive feature space, demonstrated superior performance over standard concatenation-based fusion models and other baselines (including models built on traditional acoustic features). In a randomized data split configuration, the model achieved an Area Under the Receiver Operating Characteristic Curve (AUROC) of 88.94% and an accuracy of 85.65%. Rigorous statistical analysis confirmed that our model performs equitably across various demographic subgroups in terms of sex, ethnicity, and age, and remains robust regardless of disease duration. Furthermore, our model, when tested on two entirely unseen test datasets collected from clinical settings and from a PD care center, maintained AUROC scores of 82.12% and 78.44%, respectively. This affirms the model's robustness and it's potential to enhance accessibility and health equity in real-world applications., Comment: 25 pages, 5 figures, and 4 tables

Coronavirus Anxiety Scale (CAS) is a widely used measure that captures somatic symptoms of coronavirus-related anxiety. In a large-scale collaboration spanning 60 countries (Ntotal = 21,513), we examined the CAS’s measurement invariance and assessed the convergent validity of CAS scores in relation to the fear of COVID-19 (FCV-19S) and the satisfaction with life (SWLS-3) scales. We utilized both conventional exact invariance tests and alignment procedures, with results revealing that the single-factor model fit the data well in almost all countries. Partial scalar invariance was supported in a subset of 56 countries. To ensure the robustness of results, given the unbalanced samples, we employed resampling techniques both with and without replacement and found the results were more stable in larger samples. The alignment procedure demonstrated a high degree of measurement invariance with 9% of the parameters exhibiting non-invariance. We also conducted simulations of alignment using the parameters estimated in the current model. Findings demonstrated reliability of the means but indicated challenges in estimating the latent variances. Strong positive correlations between CAS and FCV-19S estimated with all three different approaches were found in most countries. Correlations of CAS and SWLS-3 were weak and negative but significantly differed from zero in several countries. Overall, the study provided support for the measurement invariance of the CAS and offered evidence of its convergent validity while also highlighting issues with variance estimation.

This study announces the sequence of a multidrug-resistant Escherichia coli MAHK_SCM_BAU_30A strain isolated from bovine subclinical mastitis milk in 2022 in Bangladesh. Our assembled genome had a length of 4,884,948 bp, three plasmids, two CRISPR arrays, five prophages, 51 predicted antibiotic resistance, and 72 predicted virulence factor genes.

A balanced mixture of cement, sand, stone or brick chips, and water is carefully allowed to form concrete, a man-made building material. These elements can be adjusted appropriately to produce concrete with a variety of qualities. Although concrete may endure compressive forces, like natural stone, tensile forces can cause it to crack. As a result, crack formation is a frequent occurrence in concrete, allowing various foreign chemicals and water to enter the structures and shortening their life span. The likelihood of cracking grows with time due to variations in humidity and temperature. It can be exceedingly expensive to maintain or repair concrete construction items. The use of bio-concrete for the construction of durable structures has shown to be quite advantageous in this perspective. It is beneficial for improving the properties of concrete as well as lowering maintenance costs. In this investigation, concrete samples measuring 100×100×100 mm were made and periodically tested for compressive and split tensile strength testing. Following a 28-day curing period, the concrete treated with Escherichia coli bacteria had compressive and split tensile strengths that were 10% and 23% higher than identical bacteria-free. The non-destructive test on cylindrical samples was then conducted to evaluate the material qualities. The mortar samples of crystalline structures were also validated by SEM examination. In order to properly and reliably anticipate the strength of concrete, the RSM model was also formulated.

Job satisfaction is when an employee has a positive attitudes or feelings towards his work and shows strong interest in working to achieve an organization goal. Employee job gratification is very indispensable for every organization because its triumphcompletely depend on worker’s veneration towards the organization. As the backbone of a country’s economy is the banking institution, this paper tries to inquire the factors which affecting employees job satisfaction of bank in Mymensingh city, Bangladesh. A structured form of questionnaire is conducted to gather information for this paper. A regression analysis is conducted using SPSS version 26 to discoverthe factors contributing towards the employee’s job satisfaction by the researchers. Reliability test has been applied for ensuring the relevance of data and descriptive statistics has been employed identify the condition of the variables. This study revealed that salary, training facilities, recognition, benefits, working environment, incentives, career growth opportunities, and relationship with co-workers have a straightconnection with the satisfaction of employees in the job. The findings of this investigation will help the decision makers to formulate policy in the development of banking sector. Besides, the future research direction will help the academics to find out the new endeavor regarding job satisfaction. Keywords: Job Satisfaction, Bank Employee, Banking Industry, Bangladesh, Regression Analysis. DOI: 10.7176/EJBM/15-12-04 Publication date:June 30th 2023

There have thousands of crimes are happening daily all around. But people keep statistics only few of them, therefore crime rates are increasing day by day. The reason behind can be less concern or less statistics of previous crimes. It is much more important to observe the previous crime statistics for general people to make their outing decision and police for catching the criminals are taking steps to restrain the crimes and tourists to make their travelling decision. National institute of justice releases crime survey data for the country, but does not offer crime statistics up to Union or Thana level. Considering all of these cases we have come up with an approach which can give an approximation to people about the safety of a specific location with crime ranking of different areas locating the crimes on a map including a future crime occurrence prediction mechanism. Our approach relies on different online Bangla newspapers for crawling the crime data, stemming and keyword extraction, location finding algorithm, cosine similarity, naive Bayes classifier, and a custom crime prediction model, Comment: 9 pages

We present an artificial intelligence system to remotely assess the motor performance of individuals with Parkinson's disease (PD). Participants performed a motor task (i.e., tapping fingers) in front of a webcam, and data from 250 global participants were rated by three expert neurologists following the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS). The neurologists' ratings were highly reliable, with an intra-class correlation coefficient (ICC) of 0.88. We developed computer algorithms to obtain objective measurements that align with the MDS-UPDRS guideline and are strongly correlated with the neurologists' ratings. Our machine learning model trained on these measures outperformed an MDS-UPDRS certified rater, with a mean absolute error (MAE) of 0.59 compared to the rater's MAE of 0.79. However, the model performed slightly worse than the expert neurologists (0.53 MAE). The methodology can be replicated for similar motor tasks, providing the possibility of evaluating individuals with PD and other movement disorders remotely, objectively, and in areas with limited access to neurological care.

Pre-trained large language models have recently achieved ground-breaking performance in a wide variety of language understanding tasks. However, the same model can not be applied to multimodal behavior understanding tasks (e.g., video sentiment/humor detection) unless non-verbal features (e.g., acoustic and visual) can be integrated with language. Jointly modeling multiple modalities significantly increases the model complexity, and makes the training process data-hungry. While an enormous amount of text data is available via the web, collecting large-scale multimodal behavioral video datasets is extremely expensive, both in terms of time and money. In this paper, we investigate whether large language models alone can successfully incorporate non-verbal information when they are presented in textual form. We present a way to convert the acoustic and visual information into corresponding textual descriptions and concatenate them with the spoken text. We feed this augmented input to a pre-trained BERT model and fine-tune it on three downstream multimodal tasks: sentiment, humor, and sarcasm detection. Our approach, TextMI, significantly reduces model complexity, adds interpretability to the model's decision, and can be applied for a diverse set of tasks while achieving superior (multimodal sarcasm detection) or near SOTA (multimodal sentiment analysis and multimodal humor detection) performance. We propose TextMI as a general, competitive baseline for multimodal behavioral analysis tasks, particularly in a low-resource setting.

Recent advances in reinforcement learning (RL) and Human-in-the-Loop (HitL) learning have made human-AI collaboration easier for humans to team with AI agents. Leveraging human expertise and experience with AI in intelligent systems can be efficient and beneficial. Still, it is unclear to what extent human-AI collaboration will be successful, and how such teaming performs compared to humans or AI agents only. In this work, we show that learning from humans is effective and that human-AI collaboration outperforms human-controlled and fully autonomous AI agents in a complex simulation environment. In addition, we have developed a new simulator for critical infrastructure protection, focusing on a scenario where AI-powered drones and human teams collaborate to defend an airport against enemy drone attacks. We develop a user interface to allow humans to assist AI agents effectively. We demonstrated that agents learn faster while learning from policy correction compared to learning from humans or agents. Furthermore, human-AI collaboration requires lower mental and temporal demands, reduces human effort, and yields higher performance than if humans directly controlled all agents. In conclusion, we show that humans can provide helpful advice to the RL agents, allowing them to improve learning in a multi-agent setting., Comment: Submitted to Neural Computing and Applications

Parkinson's disease (PD) is a neuro-degenerative disorder that affects movement, speech, and coordination. Timely diagnosis and treatment can improve the quality of life for PD patients. However, access to clinical diagnosis is limited in low and middle income countries (LMICs). Therefore, development of automated screening tools for PD can have a huge social impact, particularly in the public health sector. In this paper, we present PULSAR, a novel method to screen for PD from webcam-recorded videos of the finger-tapping task from the Movement Disorder Society - Unified Parkinson's Disease Rating Scale (MDS-UPDRS). PULSAR is trained and evaluated on data collected from 382 participants (183 self-reported as PD patients). We used an adaptive graph convolutional neural network to dynamically learn the spatio temporal graph edges specific to the finger-tapping task. We enhanced this idea with a multi stream adaptive convolution model to learn features from different modalities of data critical to detect PD, such as relative location of the finger joints, velocity and acceleration of tapping. As the labels of the videos are self-reported, there could be cases of undiagnosed PD in the non-PD labeled samples. We leveraged the idea of Positive Unlabeled (PU) Learning that does not need labeled negative data. Our experiments show clear benefit of modeling the problem in this way. PULSAR achieved 80.95% accuracy in validation set and a mean accuracy of 71.29% (2.49% standard deviation) in independent test, despite being trained with limited amount of data. This is specially promising as labeled data is scarce in health care sector. We hope PULSAR will make PD screening more accessible to everyone. The proposed techniques could be extended for assessment of other movement disorders, such as ataxia, and Huntington's disease.

We present a web-based framework to screen for Parkinson's disease (PD) by allowing users to perform neurological tests in their homes. Our web framework guides the users to complete three tasks involving speech, facial expression, and finger movements. The task videos are analyzed to classify whether the users show signs of PD. We present the results in an easy-to-understand manner, along with personalized resources to further access to treatment and care. Our framework is accessible by any major web browser, improving global access to neurological care.

Innovation is crucial for sustainable success in today's fiercely competitive global manufacturing landscape. Bangladesh's manufacturing sector must embrace transformative technologies like the Internet of Things (IoT) to thrive in this environment. This article addresses the vital task of identifying and evaluating barriers to IoT adoption in Bangladesh's manufacturing industry. Through synthesizing expert insights and carefully reviewing contemporary literature, we explore the intricate landscape of IoT adoption challenges. Our methodology combines the Delphi and Fuzzy Analytical Hierarchy Process, systematically analyzing and prioritizing these challenges. This approach harnesses expert knowledge and uses fuzzy logic to handle uncertainties. Our findings highlight key obstacles, with "Lack of top management commitment to new technology" (B10), "High initial implementation costs" (B9), and "Risks in adopting a new business model" (B7) standing out as significant challenges that demand immediate attention. These insights extend beyond academia, offering practical guidance to industry leaders. With the knowledge gained from this study, managers can develop tailored strategies, set informed priorities, and embark on a transformative journey toward leveraging IoT's potential in Bangladesh's industrial sector. This article provides a comprehensive understanding of IoT adoption challenges and equips industry leaders to navigate them effectively. This strategic navigation, in turn, enhances the competitiveness and sustainability of Bangladesh's manufacturing sector in the IoT era.

Parkinson's disease (PD) diagnosis remains challenging due to lacking a reliable biomarker and limited access to clinical care. In this study, we present an analysis of the largest video dataset containing micro-expressions to screen for PD. We collected 3,871 videos from 1,059 unique participants, including 256 self-reported PD patients. The recordings are from diverse sources encompassing participants' homes across multiple countries, a clinic, and a PD care facility in the US. Leveraging facial landmarks and action units, we extracted features relevant to Hypomimia, a prominent symptom of PD characterized by reduced facial expressions. An ensemble of AI models trained on these features achieved an accuracy of 89.7% and an Area Under the Receiver Operating Characteristic (AUROC) of 89.3% while being free from detectable bias across population subgroups based on sex and ethnicity on held-out data. Further analysis reveals that features from the smiling videos alone lead to comparable performance, even on two external test sets the model has never seen during training, suggesting the potential for PD risk assessment from smiling selfie videos.

Supply chain management relies on accurate backorder prediction for optimizing inventory control, reducing costs, and enhancing customer satisfaction. However, traditional machine-learning models struggle with large-scale datasets and complex relationships, hindering real-world data collection. This research introduces a novel methodological framework for supply chain backorder prediction, addressing the challenge of handling large datasets. Our proposed model, QAmplifyNet, employs quantum-inspired techniques within a quantum-classical neural network to predict backorders effectively on short and imbalanced datasets. Experimental evaluations on a benchmark dataset demonstrate QAmplifyNet's superiority over classical models, quantum ensembles, quantum neural networks, and deep reinforcement learning. Its proficiency in handling short, imbalanced datasets makes it an ideal solution for supply chain management. To enhance model interpretability, we use Explainable Artificial Intelligence techniques. Practical implications include improved inventory control, reduced backorders, and enhanced operational efficiency. QAmplifyNet seamlessly integrates into real-world supply chain management systems, enabling proactive decision-making and efficient resource allocation. Future work involves exploring additional quantum-inspired techniques, expanding the dataset, and investigating other supply chain applications. This research unlocks the potential of quantum computing in supply chain optimization and paves the way for further exploration of quantum-inspired machine learning models in supply chain management. Our framework and QAmplifyNet model offer a breakthrough approach to supply chain backorder prediction, providing superior performance and opening new avenues for leveraging quantum-inspired techniques in supply chain management.

Falls among the elderly are a major health concern, frequently resulting in serious injuries and a reduced quality of life. In this paper, we propose "BlockTheFall," a wearable device-based fall detection framework which detects falls in real time by using sensor data from wearable devices. To accurately identify patterns and detect falls, the collected sensor data is analyzed using machine learning algorithms. To ensure data integrity and security, the framework stores and verifies fall event data using blockchain technology. The proposed framework aims to provide an efficient and dependable solution for fall detection with improved emergency response, and elderly individuals' overall well-being. Further experiments and evaluations are being carried out to validate the effectiveness and feasibility of the proposed framework, which has shown promising results in distinguishing genuine falls from simulated falls. By providing timely and accurate fall detection and response, this framework has the potential to substantially boost the quality of elderly care., Comment: Accepted to publish in The 1st IEEE International Workshop on Digital and Public Health

Background: Severe acute respiratory coronavirus syndrome 2 (SARS-CoV-2) is the etiological agent of coronavirus disease 2019 (COVID-19). SARS-CoV-2 was first detected in Wuhan, China and spread to other countries and continents causing a variety of respiratory and non-respiratory symptoms which led to death in severe cases. Scope and approach: In this review, we discuss and analyze the impact of the COVID-19 pandemic on animal production systems and food production of meat, dairy, eggs, and processed food, in addition to assessing the impact of the pandemic on animal healthcare systems, animal healthcare quality, animal welfare, food chain sustainability, and the global economy. We also provide effective recommendations to animal producers, veterinary healthcare professionals, workers in animal products industries, and governments to alleviate the effects of the pandemic on livestock farming and production systems. Key findings and conclusions: Port restrictions, border restrictions, curfews, and social distancing limitations led to reduced quality, productivity, and competitiveness of key productive sectors. The restrictions have hit the livestock sector hard by disrupting the animal feed supply chain, reducing animal farming services, limiting animal health services including delays in diagnosis and treatment of diseases, limiting access to markets and consumers, and reducing labor-force participation. The inhumane culling of animals jeopardized animal welfare. Egg smashing, milk dumping, and other animal product disruptions negatively impacted food production, consumption, and access to food originating from animals. In summary, COVID-19 triggered lockdowns and limitations on local and international trade have taken their toll on food production, animal production, and animal health and welfare. COVID-19 reverberations could exacerbate food insecurity, hunger, and global poverty. The effects could be massive on the most vulnerable populations and the poorest nat

Climate change has increased the intensity, frequency, and duration of extreme weather events and natural disasters across the world. While the increased data on natural disasters improves the scope of machine learning (ML) in this field, progress is relatively slow. One bottleneck is the lack of benchmark datasets that would allow ML researchers to quantify their progress against a standard metric. The objective of this short paper is to explore the state of benchmark datasets for ML tasks related to natural disasters, categorizing them according to the disaster management cycle. We compile a list of existing benchmark datasets introduced in the past five years. We propose a web platform - NADBenchmarks - where researchers can search for benchmark datasets for natural disasters, and we develop a preliminary version of such a platform using our compiled list. This paper is intended to aid researchers in finding benchmark datasets to train their ML models on, and provide general directions for topics where they can contribute new benchmark datasets.

With online shopping gaining massive popularity over the past few years, e-commerce platforms can play a significant role in tackling climate change and other environmental problems. In this study, we report that the "attitude-behavior" gap identified by prior sustainable consumption literature also exists in an online setting. We propose SEER, a concept design for online shopping websites to help consumers make more sustainable choices. We introduce explainable environmental impact ratings to increase knowledge, trust, and convenience for consumers willing to purchase eco-friendly products. In our quasi-randomized case-control experiment with 98 subjects across the United States, we found that the case group using SEER demonstrates significantly more eco-friendly consumption behavior than the control group using a traditional e-commerce setting. While there are challenges in generating reliable explanations and environmental ratings for products, if implemented, in the United States alone, SEER has the potential to reduce approximately 2.88 million tonnes of carbon emission every year.

Background: Novel psychoactive substances (NPSs) are relatively new substances in the illicit drug market, notpreviously listed in the United Nations Office on Drugs and Crime (UNDOC). Strox and Voodoo are consideredsome of the most popular blends of NPS in the Egyptian drug market.Objectives: The current study was conducted to assess NPS's use pattern: Voodoo and Strox among acutelyintoxicated patients presented to the poison control center of Ain Shams University Hospitals (PCC- ASUH).Methods: A single center based cross-sectional study was carried out in the PCC-ASUH among acutely intoxicatedpatients presenting to the emergency department (ED) over four months (from January–April 2019. using apreviously adopted and validated Fahmy and El-Sherbini socioeconomic scale (SES). Data were presented asmean, median and range as appropriate. Both smoking and crowding indexes were calculated and presented aspreviously reported.Results: Fifty-one patients were presented to the ED of PCC-ASUH during the study period. A total of 96.1% (n ¼49) were males. The mean age was 25 7.5 years. The most common NPS used was Strox: 54.9% (n ¼ 28),followed by Voodoo: 27.4% (n ¼ 14). Neurological and gastrointestinal (GI) symptoms were the most frequentpresentations. The most common motive behind NPS use was the desire to give a trial of new psychoactivesubstances. The mean SES score was 35.1 13.17. Most patients have the preparatory as the highest education36.0% (n ¼ 18).Conclusions: NPS use is common among young males in preparatory education from different social classes,starting it most commonly as a means to experiencing a new high. Neurological and GI manifestations are themost common presenting symptoms of NPS intoxication.

In this paper, we investigated whether we can 1) detect participants with ataxia-specific gait characteristics (risk-prediction), and 2) assess severity of ataxia from gait (severity-assessment) using computer vision. We created a dataset of 155 videos from 89 participants, 24 controls and 65 diagnosed with (or are pre-manifest) spinocerebellar ataxias (SCAs), performing the gait task of the Scale for the Assessment and Rating of Ataxia (SARA) from 11 medical sites located in 8 different states across the United States. We develop a computer vision pipeline to detect, track, and separate out the participants from their surroundings and construct several features from their body pose coordinates to capture gait characteristics like step width, step length, swing, stability, speed, etc. Our risk-prediction model achieves 83.06% accuracy and an 80.23% F1 score. Similarly, our severity-assessment model achieves a mean absolute error (MAE) score of 0.6225 and a Pearson's correlation coefficient score of 0.7268. Our models still performed competitively when evaluated on data from sites not used during training. Furthermore, through feature importance analysis, we found that our models associate wider steps, decreased walking speed, and increased instability with greater ataxia severity, which is consistent with previously established clinical knowledge. Our models create possibilities for remote ataxia assessment in non-clinical settings in the future, which could significantly improve accessibility of ataxia care. Furthermore, our underlying dataset was assembled from a geographically diverse cohort, highlighting its potential to further increase equity. The code used in this study is open to the public, and the anonymized body pose landmark dataset is also available upon request.

In recent advancement towards computer based diagnostics system, the classification of brain tumor images is a challenging task. This paper mainly focuses on elevating the classification accuracy of brain tumor images with transfer learning based deep neural network. The classification approach is started with the image augmentation operation including rotation, zoom, hori-zontal flip, width shift, height shift, and shear to increase the diversity in image datasets. Then the general features of the input brain tumor images are extracted based on a pre-trained transfer learning method comprised of Inception-v3. Fi-nally, the deep neural network with 4 customized layers is employed for classi-fying the brain tumors in most frequent brain tumor types as meningioma, glioma, and pituitary. The proposed model acquires an effective performance with an overall accuracy of 96.25% which is much improved than some existing multi-classification methods. Whereas, the fine-tuning of hyper-parameters and inclusion of customized DNN with the Inception-v3 model results in an im-provement of the classification accuracy., Comment: 7 pages, 4 figures, 2 tables, International Virtual Conference on ARTIFICIAL INTELLIGENCE FOR SMART COMMUNITY, Malaysia

Social media platforms and online streaming services have spawned a new breed of Hate Speech (HS). Due to the massive amount of user-generated content on these sites, modern machine learning techniques are found to be feasible and cost-effective to tackle this problem. However, linguistically diverse datasets covering different social contexts in which offensive language is typically used are required to train generalizable models. In this paper, we identify the shortcomings of existing Bangla HS datasets and introduce a large manually labeled dataset BD-SHS that includes HS in different social contexts. The labeling criteria were prepared following a hierarchical annotation process, which is the first of its kind in Bangla HS to the best of our knowledge. The dataset includes more than 50,200 offensive comments crawled from online social networking sites and is at least 60% larger than any existing Bangla HS datasets. We present the benchmark result of our dataset by training different NLP models resulting in the best one achieving an F1-score of 91.0%. In our experiments, we found that a word embedding trained exclusively using 1.47 million comments from social media and streaming sites consistently resulted in better modeling of HS detection in comparison to other pre-trained embeddings. Our dataset and all accompanying codes is publicly available at github.com/naurosromim/hate-speech-dataset-for-Bengali-social-media

As computers have become efficient at understanding visual information and transforming it into a written representation, research interest in tasks like automatic image captioning has seen a significant leap over the last few years. While most of the research attention is given to the English language in a monolingual setting, resource-constrained languages like Bangla remain out of focus, predominantly due to a lack of standard datasets. Addressing this issue, we present a new dataset BAN-Cap following the widely used Flickr8k dataset, where we collect Bangla captions of the images provided by qualified annotators. Our dataset represents a wider variety of image caption styles annotated by trained people from different backgrounds. We present a quantitative and qualitative analysis of the dataset and the baseline evaluation of the recent models in Bangla image captioning. We investigate the effect of text augmentation and demonstrate that an adaptive attention-based model combined with text augmentation using Contextualized Word Replacement (CWR) outperforms all state-of-the-art models for Bangla image captioning. We also present this dataset's multipurpose nature, especially on machine translation for Bangla-English and English-Bangla. This dataset and all the models will be useful for further research., Comment: Accepted in the 13th Edition of Language Resources and Evaluation Conference (LREC 2022)

Several recent studies have shown that citric acid/citrate (CA) can confer abiotic stress tolerance to plants. Exogenous CA application leads to improved growth and yield in crop plants under various abiotic stress conditions. Improved physiological outcomes are associated with higher photosynthetic rates, reduced reactive oxygen species, and better osmoregulation. Application of CA also induces antioxidant defense systems, promotes increased chlorophyll content, and affects secondary metabolism to limit plant growth restrictions under stress. In particular, CA has a major impact on relieving heavy metal stress by promoting precipitation, chelation, and sequestration of metal ions. This review summarizes the mechanisms that mediate CA-regulated changes in plants, primarily CA's involvement in the control of physiological and molecular processes in plants under abiotic stress conditions. We also review genetic engineering strategies for CA-mediated abiotic stress tolerance. Finally, we propose a model to explain how CA's position in complex metabolic networks involving the biosynthesis of phytohormones, amino acids, signaling molecules, and other secondary metabolites could explain some of its abiotic stress-ameliorating properties. This review summarizes our current understanding of CA-mediated abiotic stress tolerance and highlights areas where additional research is needed.

Lead exposure is harmful at any time in life, but pre-natal and early childhood exposures are particularly detrimental to cognitive development. In Bangladesh, multiple household-level lead exposures pose risks, including turmeric adulterated with lead chromate and food storage in lead-soldered cans. We developed and evaluated an intervention to reduce lead exposure among children and their caregivers in rural Bangladesh. We conducted formative research to inform theory-based behavioral recommendations. Lead exposure was one of several topics covered in the multi-component intervention focused on early child development. Community health workers (CHWs) delivered the lead component of the intervention during group sessions with pregnant women and mother-child dyads (<15 months old) in a cluster-randomized trial. We administered household surveys at baseline (control n = 301; intervention n = 320) and 9 months later at endline (control n = 279; intervention n = 239) and calculated adjusted risk and mean differences for primary outcomes. We conducted two qualitative assessments, one after 3 months and a second after 9 months, to examine the feasibility and benefits of the intervention. At endline, the prevalence of lead awareness was 52 percentage points higher in the intervention arm compared to the control (adjusted risk difference: 0.52 [95% CI 0.46 to 0.61]). Safe turmeric consumption and food storage practices were more common in the intervention versus control arm at endline, with adjusted risk differences of 0.22 [0.10 to 0.32] and 0.13 [0.00 to 0.19], respectively. Semi-structured interviews conducted with a subset of participants after the intervention revealed that the perceived benefit of reducing lead exposure was high because of the long-term negative impacts that lead can have on child cognitive development. The study demonstrates that a group-based CHW-led intervention can effectively raise awareness about and m

Forensic analysis of manipulated pixels requires the identification of various hidden and subtle features from images. Conventional image recognition models generally fail at this task because they are biased and more attentive toward the dominant local and spatial features. In this paper, we propose a novel Gated Context Attention Network (GCA-Net) that utilizes non-local attention in conjunction with a gating mechanism in order to capture the finer image discrepancies and better identify forged regions. The proposed framework uses high dimensional embeddings to filter and aggregate the relevant context from coarse feature maps at various stages of the decoding process. This improves the network's understanding of global differences and reduces false-positive localizations. Our evaluation on standard image forensic benchmarks shows that GCA-Net can both compete against and improve over state-of-the-art networks by an average of 4.7% AUC. Additional ablation studies also demonstrate the method's robustness against attributions and resilience to false-positive predictions., Comment: Accepted for publication at the CVPR 2022 Media Forensics Workshop

In this paper, we present HS-BAN, a binary class hate speech (HS) dataset in Bangla language consisting of more than 50,000 labeled comments, including 40.17% hate and rest are non hate speech. While preparing the dataset a strict and detailed annotation guideline was followed to reduce human annotation bias. The HS dataset was also preprocessed linguistically to extract different types of slang currently people write using symbols, acronyms, or alternative spellings. These slang words were further categorized into traditional and non-traditional slang lists and included in the results of this paper. We explored traditional linguistic features and neural network-based methods to develop a benchmark system for hate speech detection for the Bangla language. Our experimental results show that existing word embedding models trained with informal texts perform better than those trained with formal text. Our benchmark shows that a Bi-LSTM model on top of the FastText informal word embedding achieved 86.78% F1-score. We will make the dataset available for public use., Comment: Submitted to ICON 21 (Rejected)

A Randomized Control Trial (RCT) is considered as the gold standard for evaluating the effect of any intervention or treatment. However, its feasibility is often hindered by ethical, economical, and legal considerations, making observational data a valuable alternative for drawing causal conclusions. Nevertheless, healthcare observational data presents a difficult challenge due to its high dimensionality, requiring careful consideration to ensure unbiased, reliable, and robust causal inferences. To overcome this challenge, in this study, we propose a novel two-stage feature selection technique called, Outcome Adaptive Elastic Net (OAENet), explicitly designed for making robust causal inference decisions using matching techniques. OAENet offers several key advantages over existing methods: superior performance on correlated and high-dimensional data compared to the existing methods and the ability to select specific sets of variables (including confounders and variables associated only with the outcome). This ensures robustness and facilitates an unbiased estimate of the causal effect. Numerical experiments on simulated data demonstrate that OAENet significantly outperforms state-of-the-art methods by either producing a higher-quality estimate or a comparable estimate in significantly less time. To illustrate the applicability of OAENet, we employ large-scale US healthcare data to estimate the effect of Opioid Use Disorder (OUD) on suicidal behavior. When compared to competing methods, OAENet closely aligns with existing literature on the relationship between OUD and suicidal behavior. Performance on both simulated and real-world data highlights that OAENet notably enhances the accuracy of estimating treatment effects or evaluating policy decision-making with causal inference.

Despite the success of the neural sequence-to-sequence model for abstractive text summarization, it has a few shortcomings, such as repeating inaccurate factual details and tending to repeat themselves. We propose a hybrid pointer generator network to solve the shortcomings of reproducing factual details inadequately and phrase repetition. We augment the attention-based sequence-to-sequence using a hybrid pointer generator network that can generate Out-of-Vocabulary words and enhance accuracy in reproducing authentic details and a coverage mechanism that discourages repetition. It produces a reasonable-sized output text that preserves the conceptual integrity and factual information of the input article. For evaluation, we primarily employed "BANSData" - a highly adopted publicly available Bengali dataset. Additionally, we prepared a large-scale dataset called "BANS-133" which consists of 133k Bangla news articles associated with human-generated summaries. Experimenting with the proposed model, we achieved ROUGE-1 and ROUGE-2 scores of 0.66, 0.41 for the "BANSData" dataset and 0.67, 0.42 for the BANS-133k" dataset, respectively. We demonstrated that the proposed system surpasses previous state-of-the-art Bengali abstractive summarization techniques and its stability on a larger dataset. "BANS-133" datasets and code-base will be publicly available for research., Comment: {copyright} 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

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 dataset 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 \url{https://github.com/csebuetnlp/xl-sum}., Comment: Findings of the Association for Computational Linguistics, ACL 2021 (camera-ready)

The creation of altered and manipulated faces has become more common due to the improvement of DeepFake generation methods. Simultaneously, we have seen detection models' development for differentiating between a manipulated and original face from image or video content. In this paper, we focus on identifying the limitations and shortcomings of existing deepfake detection frameworks. We identified some key problems surrounding deepfake detection through quantitative and qualitative analysis of existing methods and datasets. We found that deepfake datasets are highly oversampled, causing models to become easily overfitted. The datasets are created using a small set of real faces to generate multiple fake samples. When trained on these datasets, models tend to memorize the actors' faces and labels instead of learning fake features. To mitigate this problem, we propose a simple data augmentation method termed Face-Cutout. Our method dynamically cuts out regions of an image using the face landmark information. It helps the model selectively attend to only the relevant regions of the input. Our evaluation experiments show that Face-Cutout can successfully improve the data variation and alleviate the problem of overfitting. Our method achieves a reduction in LogLoss of 15.2% to 35.3% on different datasets, compared to other occlusion-based techniques. Moreover, we also propose a general-purpose data pre-processing guideline to train and evaluate existing architectures allowing us to improve the generalizability of these models for deepfake detection.

Image Captioning is an arduous task of producing syntactically and semantically correct textual descriptions of an image in natural language with context related to the image. Existing notable pieces of research in Bengali Image Captioning (BIC) are based on encoder-decoder architecture. This paper presents an end-to-end image captioning system utilizing a multimodal architecture by combining a one-dimensional convolutional neural network (CNN) to encode sequence information with a pre-trained ResNet-50 model image encoder for extracting region-based visual features. We investigate our approach's performance on the BanglaLekhaImageCaptions dataset using the existing evaluation metrics and perform a human evaluation for qualitative analysis. Experiments show that our approach's language encoder captures the fine-grained information in the caption, and combined with the image features, it generates accurate and diversified caption. Our work outperforms all the existing BIC works and achieves a new state-of-the-art (SOTA) performance by scoring 0.651 on BLUE-1, 0.572 on CIDEr, 0.297 on METEOR, 0.434 on ROUGE, and 0.357 on SPICE., Comment: Accepted in "IJCACI 2020: International Joint Conference on Advances in Computational Intelligence"

The rapid outbreak of COVID-19 has caused humanity to come to a stand-still and brought with it a plethora of other problems. COVID-19 is the first pandemic in history when humanity is the most technologically advanced and relies heavily on social media platforms for connectivity and other benefits. Unfortunately, fake news and misinformation regarding this virus is also available to people and causing some massive problems. So, fighting this infodemic has become a significant challenge. We present our solution for the "Constraint@AAAI2021 - COVID19 Fake News Detection in English" challenge in this work. After extensive experimentation with numerous architectures and techniques, we use eight different transformer-based pre-trained models with additional layers to construct a stacking ensemble classifier and fine-tuned them for our purpose. We achieved 0.979906542 accuracy, 0.979913119 precision, 0.979906542 recall, and 0.979907901 f1-score on the test dataset of the competition.

In this work, we introduce BanglaBERT, a BERT-based Natural Language Understanding (NLU) model pretrained in Bangla, a widely spoken yet low-resource language in the NLP literature. To pretrain BanglaBERT, we collect 27.5 GB of Bangla pretraining data (dubbed `Bangla2B+') by crawling 110 popular Bangla sites. We introduce two downstream task datasets on natural language inference and question answering and benchmark on four diverse NLU tasks covering text classification, sequence labeling, and span prediction. In the process, we bring them under the first-ever Bangla Language Understanding Benchmark (BLUB). BanglaBERT achieves state-of-the-art results outperforming multilingual and monolingual models. We are making the models, datasets, and a leaderboard publicly available at https://github.com/csebuetnlp/banglabert to advance Bangla NLP., Comment: Findings of North American Chapter of the Association for Computational Linguistics, NAACL 2022 (camera-ready)

Most humans are in contact with animals in a way or another. A zoonotic disease is a disease or infection that can be transmitted naturally from vertebrate animals to humans or from humans to vertebrate animals. More than 60% of human pathogens are zoonotic in origin. This includes a wide variety of bacteria, viruses, fungi, protozoa, parasites, and other pathogens. Factors such as climate change, urbanization, animal migration and trade, travel and tourism, vector biology, anthropogenic factors, and natural factors have greatly influenced the emergence, re-emergence, distribution, and patterns of zoonoses. As time goes on, there are more emerging and re-emerging zoonotic diseases. In this review, we reviewed the etiology of major zoonotic diseases, their impact on human health, and control measures for better management. We also highlighted COVID-19, a newly emerging zoonotic disease of likely bat origin that has affected millions of humans along with devastating global consequences. The implementation of One Health measures is highly recommended for the effective prevention and control of possible zoonosis.

In recent years, the foreign exchange (FOREX) market has attracted quite a lot of scrutiny from researchers all over the world. Due to its vulnerable characteristics, different types of research have been conducted to accomplish the task of predicting future FOREX currency prices accurately. In this research, we present a comprehensive review of the recent advancements of FOREX currency prediction approaches. Besides, we provide some information about the FOREX market and cryptocurrency market. We wanted to analyze the most recent works in this field and therefore considered only those papers which were published from 2017 to 2019. We used a keyword-based searching technique to filter out popular and relevant research. Moreover, we have applied a selection algorithm to determine which papers to include in this review. Based on our selection criteria, we have reviewed 39 research articles that were published on “Elsevier”, “Springer”, and “IEEE Xplore” that predicted future FOREX prices within the stipulated time. Our research shows that in recent years, researchers have been interested mostly in neural networks models, pattern-based approaches, and optimization techniques. Our review also shows that many deep learning algorithms, such as gated recurrent unit (GRU) and long short term memory (LSTM), have been fully explored and show huge potential in time series prediction., Validerad;2020;Nivå 2;2020-09-24 (alebob)

Full Text, Thesis (PhD Doctorate), Doctor of Philosophy (PhD), School of Info & Comm Tech, Science, Environment, Engineering and Technology, Due to the recent development and advancement of communication technologies, healthcare industries are becoming more attracted towards information and communication technology services. One of the interesting services is the remote monitoring of patients through the use of a wireless body area network (WBAN), which enables healthcare providers to monitor, diagnose and prescribe patients without being present physically. To develop reliable and exible remote patient monitoring services, in this thesis, the current state-of-the art of WBAN and the limitations of current WBAN technologies are investigated in the healthcare domain. To this end, the relevant background, implementation challenges and limitations of WBAN are overviewed. The in-depth literature survey identifies the lack of a current WBAN architecture in terms of administrative control, static architecture, vendor dependency, traffic priority arrangements, resource utilization, secure data sharing etc. To find a solution to the limitations of WBAN, software-defined networking (SDN) is considered to be one of the promising solutions in this paradigm. However, the incorporation of SDN into WBAN has several challenges in terms of architectural framework, resource optimization and secure data sharing. In this thesis, an SDN-based WBAN (SDWBAN) architecture is proposed to incorporate the functionalities and principles of SDN on top of the traditional WBAN architecture to overcome the existing barriers of WBAN. The proposed communication model of the SDWBAN framework utilizes the sector-based distance (SBD) routing protocol for data packet dissemination. Furthermore, an application classification algorithm is developed to prioritize emergency applications over normal applications. The proposed architecture and communication model have been simulated and experiments are conducted in Castalia 3.2. The simulation outcome demonstrates enhanced performance in terms of the packet delivery rate (PDR) and the latency of

Observing the damages that can be done by the rapid propagation of fake news in various sectors like politics and finance, automatic identification of fake news using linguistic analysis has drawn the attention of the research community. However, such methods are largely being developed for English where low resource languages remain out of the focus. But the risks spawned by fake and manipulative news are not confined by languages. In this work, we propose an annotated dataset of ~50K news that can be used for building automated fake news detection systems for a low resource language like Bangla. Additionally, we provide an analysis of the dataset and develop a benchmark system with state of the art NLP techniques to identify Bangla fake news. To create this system, we explore traditional linguistic features and neural network based methods. We expect this dataset will be a valuable resource for building technologies to prevent the spreading of fake news and contribute in research with low resource languages., Comment: LREC 2020

Language models are generally employed to estimate the probability distribution of various linguistic units, making them one of the fundamental parts of natural language processing. Applications of language models include a wide spectrum of tasks such as text summarization, translation and classification. For a low resource language like Bengali, the research in this area so far can be considered to be narrow at the very least, with some traditional count based models being proposed. This paper attempts to address the issue and proposes a continuous-space neural language model, or more specifically an ASGD weight dropped LSTM language model, along with techniques to efficiently train it for Bengali Language. The performance analysis with some currently existing count based models illustrated in this paper also shows that the proposed architecture outperforms its counterparts by achieving an inference perplexity as low as 51.2 on the held out data set for Bengali., Comment: 6 pages

Characters are the smallest unit of text that can extract stylometric signals to determine the author of a text. In this paper, we investigate the effectiveness of character-level signals in Authorship Attribution of Bangla Literature and show that the results are promising but improvable. The time and memory efficiency of the proposed model is much higher than the word level counterparts but accuracy is 2-5% less than the best performing word-level models. Comparison of various word-based models is performed and shown that the proposed model performs increasingly better with larger datasets. We also analyze the effect of pre-training character embedding of diverse Bangla character set in authorship attribution. It is seen that the performance is improved by up to 10% on pre-training. We used 2 datasets from 6 to 14 authors, balancing them before training and compare the results., Comment: 5 pages

Identifying cause-effect relations among variables is a key step in the decision-making process. While causal inference requires randomized experiments, researchers and policymakers are increasingly using observational studies to test causal hypotheses due to the wide availability of observational data and the infeasibility of experiments. The matching method is the most used technique to make causal inference from observational data. However, the pair assignment process in one-to-one matching creates uncertainty in the inference because of different choices made by the experimenter. Recently, discrete optimization models are proposed to tackle such uncertainty. Although a robust inference is possible with discrete optimization models, they produce nonlinear problems and lack scalability. In this work, we propose greedy algorithms to solve the robust causal inference test instances from observational data with continuous outcomes. We propose a unique framework to reformulate the nonlinear binary optimization problems as feasibility problems. By leveraging the structure of the feasibility formulation, we develop greedy schemes that are efficient in solving robust test problems. In many cases, the proposed algorithms achieve global optimal solutions. We perform experiments on three real-world datasets to demonstrate the effectiveness of the proposed algorithms and compare our result with the state-of-the-art solver. Our experiments show that the proposed algorithms significantly outperform the exact method in terms of computation time while achieving the same conclusion for causal tests. Both numerical experiments and complexity analysis demonstrate that the proposed algorithms ensure the scalability required for harnessing the power of big data in the decision-making process.