Md Mamunur Rashid | Bangladesh University of Textiles (original) (raw)

Uploads

Papers by Md Mamunur Rashid

Research paper thumbnail of Development of COVID-19 Regional Forecast Models Using Machine Learning Approaches

Proceedings of the 7th North American International Conference on Industrial Engineering and Operations Management, Orlando, Florida, USA, June 12-14, 2022, 2022

The present work predicts different parameters key to a proper COVID-19 response, through machine... more The present work predicts different parameters key to a proper COVID-19 response, through machine learning methods. The number of patients affected, hospitalizations, and deaths in the context of the state of Florida is considered to provide a blueprint for regional pandemic response. To predict these variables, twenty inputs in four categories (type of tests performed, gender, race, and age group) were collected. Official data from the Florida State Department of Health were collected and submitted to a linear regression model, fuzzy logic model, and long short-term memory (LSTM) deep learning model with the intent of producing predictions as close as possible to the actual numbers. The mean absolute percentage error (MAPE) was calculated to measure the deviation of the predicted result from the actual values. In addition, a one-way analysis of variance (ANOVA) models was developed for each output parameter to statistically assess the results of these models. The LSTM deep learning model outperformed the fuzzy model, which in turn outperformed linear regression, in terms of the MAPE for the ‘number of Florida residents affected’. For the ‘number of patients hospitalized’, the LSTM deep learning model again outperformed the regression model, while the regression model and the fuzzy model were not significantly different. For ‘the number of patient deaths’, however, no model significantly outperformed any other. These findings suggest that in regional data, the fuzzy model outperforms linear regression, and the LSTM deep learning model outperforms both the fuzzy model and the linear regression model. Implications of this work include a better understanding of opportunities and appropriate tools for short-term prediction of future trends when variability is high, as well as replacement strategies for datasets with missing values.

Research paper thumbnail of Development of Anti-Theft Offline GPS Tracker

ITEGAM- Journal of Engineering and Technology for Industrial Applications (ITEGAM-JETIA)

Anti-Theft Offline GPS Tracker has been introduced in this paper to meet up the demand for secure... more Anti-Theft Offline GPS Tracker has been introduced in this paper to meet up the demand for secure use of important technological gadgets i.e. laptop, mobile phone, etc. It is developed in a way so that if any gadget gets stolen or gets lost, it can track even if it is offline. The tracker will be connected with the battery of the device where it is installed. So, even the device is switched off, it can gain power from the recharged battery from the device. Anti-Theft Offline GPS tracker is designed to locate the place of location offline, of the object with which the GPS Tracker will be attached. It will send a text message containing the Google Map link of the location to a given phone number when asked. By this, the gadget can be identified with its location point. We have followed almost all the procedures of the product development process from getting customer preferences to designing and finalizing the product. Material selection and cost analysis have also been done based on the mass production of the product. This product features exact location & real-time tracking, quick and continuous reply, rechargeable battery, easy to carry and cost efficient.

Research paper thumbnail of Reducing Screen Printing Lead Time by Implementing TQM: A Quality Control Circle Approach

Proceedings of the International Conference on Industrial Engineering and Operations Management Bangkok, Thailand, March 5-7, 2019

Total lead time of complete readymade garments depends on the sum of individual processing lead t... more Total lead time of complete readymade garments depends on the sum of individual processing lead time such as spinning, knitting, dyeing, finishing, all over printing, cutting, screen printing, embroidery, sewing, washing, packaging etc. In this work, process of receiving of input to delivery of output of Screen Printing Industry is studied. Quality Control Circle approach is used to find out the possible causes for which print delay of quality printing happens. Total Quality Management tools are applied to modify the working process which results significant reduction of lead time inside the factory which is applicable for all screen printing processes of RMG sector. Effect of reducing printing lead time is calculated in terms of monetary value for validation of the implementation of developed model.

Research paper thumbnail of Design and Development of Advanced Air Purifier Facial Mask

Proceedings of the International Conference on Industrial Engineering and Operations Management Bangkok, Thailand, March 5-7, 2019

Nowadays air pollution is the leading concern among people. To be safe from the polluted air, usi... more Nowadays air pollution is the leading concern among people. To be safe from the polluted air, using the available general mask is not sufficient to avoid severe health hazards. If modern technology can be embedded into a mask with every layer of protection from air pollution then it will be a safer mask to use. This paper is about to develop a more advanced mask with a different layer of protection from dust, bacteria and hazardous elements of the air at low cost with wirelessly airflow control systems. The product ensures 94% purification of air with its embedded technology. Before developing the mask a survey has been done and the product is designed on the basis of customer requirements. Materials of the product are selected through the relative performance index of the key features. This will be made at the lightweight so that users will feel comfortable to use. The Product is targeted to the customers’ e.g. Factory workers, Medical patients, General People. The product is low power consumption and can be charged fast. It can be run for about 8 hours with fully charged.

Research paper thumbnail of Selecting a Material for an Electroplating Process Using AHP and VIKOR Multi Attribute Decision Making Method

Proceedings of the Fourth International Conference on Industrial Engineering and Operations Management, Bali, Indonesia, January 7 – 9, 2014

In this era of Industrialization every company is trying to develop their manufacturing process b... more In this era of Industrialization every company is trying to develop their manufacturing process better and better. Electroplating is one of the important processes in manufacturing company like automobile, ship, airspace, machinery, electronics, jewelry, defense, toy industries, etc. It is generally used to alter the characteristics of a surface to provide improved appearance, ability to withstand corrosive agents, resistance to abrasion, or other desired properties. In time of selecting metal for the electroplating process, it is necessary to compare their characteristics in a decisive way and should be taken into account other conflicting criteria that can influence the process. Multiple attribute decision making method can be used to solve this problem. In this paper, VIKOR method along with Analytical Hierarchy Process (AHP) is used as multiple attribute decision making method to select the appropriate metal for the electroplating process. AHP is used to calculate the weight of the criteria and by using these weights VIKOR is used to rank the alternatives. Finally the proposed model has been presented for the selection of appropriate electroplating material.

Research paper thumbnail of An Adaptive Neuro-Fuzzy Inference System based Algorithm for Long Term Demand Forecasting of Natural Gas Consumption

Fourth International Conference on Industrial Engineering and Operations Management, Bali, Indonesia, 2014

This paper represents a successful implementation of Adaptive Neuro-Fuzzy Inference System (ANFIS... more This paper represents a successful implementation of Adaptive Neuro-Fuzzy Inference System (ANFIS) to develop an algorithm to predict the long term demand of Natural Gas Consumption. The developed ANFIS model is also applicable to forecast in other related fields though it is generated on the perspective of the environment of energy sector in Bangladesh. After identifying all the reasonable factors that affect the demand of Natural Gas Consumption we have considered five parameters to construct and examine the plausibility of ANFIS model. This study also provides results from generated FIS model and evaluates them. The proposed ANFIS model provides a suitable and special algorithm for the demand forecasting of Natural Gas Consumption. The outcomes are considerably better than the forecasting of the demand of Natural Gas consumption in traditional methods.

Research paper thumbnail of Development of COVID-19 Regional Forecast Models Using Machine Learning Approaches

Proceedings of the 7th North American International Conference on Industrial Engineering and Operations Management, Orlando, Florida, USA, June 12-14, 2022, 2022

The present work predicts different parameters key to a proper COVID-19 response, through machine... more The present work predicts different parameters key to a proper COVID-19 response, through machine learning methods. The number of patients affected, hospitalizations, and deaths in the context of the state of Florida is considered to provide a blueprint for regional pandemic response. To predict these variables, twenty inputs in four categories (type of tests performed, gender, race, and age group) were collected. Official data from the Florida State Department of Health were collected and submitted to a linear regression model, fuzzy logic model, and long short-term memory (LSTM) deep learning model with the intent of producing predictions as close as possible to the actual numbers. The mean absolute percentage error (MAPE) was calculated to measure the deviation of the predicted result from the actual values. In addition, a one-way analysis of variance (ANOVA) models was developed for each output parameter to statistically assess the results of these models. The LSTM deep learning model outperformed the fuzzy model, which in turn outperformed linear regression, in terms of the MAPE for the ‘number of Florida residents affected’. For the ‘number of patients hospitalized’, the LSTM deep learning model again outperformed the regression model, while the regression model and the fuzzy model were not significantly different. For ‘the number of patient deaths’, however, no model significantly outperformed any other. These findings suggest that in regional data, the fuzzy model outperforms linear regression, and the LSTM deep learning model outperforms both the fuzzy model and the linear regression model. Implications of this work include a better understanding of opportunities and appropriate tools for short-term prediction of future trends when variability is high, as well as replacement strategies for datasets with missing values.

Research paper thumbnail of Development of Anti-Theft Offline GPS Tracker

ITEGAM- Journal of Engineering and Technology for Industrial Applications (ITEGAM-JETIA)

Anti-Theft Offline GPS Tracker has been introduced in this paper to meet up the demand for secure... more Anti-Theft Offline GPS Tracker has been introduced in this paper to meet up the demand for secure use of important technological gadgets i.e. laptop, mobile phone, etc. It is developed in a way so that if any gadget gets stolen or gets lost, it can track even if it is offline. The tracker will be connected with the battery of the device where it is installed. So, even the device is switched off, it can gain power from the recharged battery from the device. Anti-Theft Offline GPS tracker is designed to locate the place of location offline, of the object with which the GPS Tracker will be attached. It will send a text message containing the Google Map link of the location to a given phone number when asked. By this, the gadget can be identified with its location point. We have followed almost all the procedures of the product development process from getting customer preferences to designing and finalizing the product. Material selection and cost analysis have also been done based on the mass production of the product. This product features exact location & real-time tracking, quick and continuous reply, rechargeable battery, easy to carry and cost efficient.

Research paper thumbnail of Reducing Screen Printing Lead Time by Implementing TQM: A Quality Control Circle Approach

Proceedings of the International Conference on Industrial Engineering and Operations Management Bangkok, Thailand, March 5-7, 2019

Total lead time of complete readymade garments depends on the sum of individual processing lead t... more Total lead time of complete readymade garments depends on the sum of individual processing lead time such as spinning, knitting, dyeing, finishing, all over printing, cutting, screen printing, embroidery, sewing, washing, packaging etc. In this work, process of receiving of input to delivery of output of Screen Printing Industry is studied. Quality Control Circle approach is used to find out the possible causes for which print delay of quality printing happens. Total Quality Management tools are applied to modify the working process which results significant reduction of lead time inside the factory which is applicable for all screen printing processes of RMG sector. Effect of reducing printing lead time is calculated in terms of monetary value for validation of the implementation of developed model.

Research paper thumbnail of Design and Development of Advanced Air Purifier Facial Mask

Proceedings of the International Conference on Industrial Engineering and Operations Management Bangkok, Thailand, March 5-7, 2019

Nowadays air pollution is the leading concern among people. To be safe from the polluted air, usi... more Nowadays air pollution is the leading concern among people. To be safe from the polluted air, using the available general mask is not sufficient to avoid severe health hazards. If modern technology can be embedded into a mask with every layer of protection from air pollution then it will be a safer mask to use. This paper is about to develop a more advanced mask with a different layer of protection from dust, bacteria and hazardous elements of the air at low cost with wirelessly airflow control systems. The product ensures 94% purification of air with its embedded technology. Before developing the mask a survey has been done and the product is designed on the basis of customer requirements. Materials of the product are selected through the relative performance index of the key features. This will be made at the lightweight so that users will feel comfortable to use. The Product is targeted to the customers’ e.g. Factory workers, Medical patients, General People. The product is low power consumption and can be charged fast. It can be run for about 8 hours with fully charged.

Research paper thumbnail of Selecting a Material for an Electroplating Process Using AHP and VIKOR Multi Attribute Decision Making Method

Proceedings of the Fourth International Conference on Industrial Engineering and Operations Management, Bali, Indonesia, January 7 – 9, 2014

In this era of Industrialization every company is trying to develop their manufacturing process b... more In this era of Industrialization every company is trying to develop their manufacturing process better and better. Electroplating is one of the important processes in manufacturing company like automobile, ship, airspace, machinery, electronics, jewelry, defense, toy industries, etc. It is generally used to alter the characteristics of a surface to provide improved appearance, ability to withstand corrosive agents, resistance to abrasion, or other desired properties. In time of selecting metal for the electroplating process, it is necessary to compare their characteristics in a decisive way and should be taken into account other conflicting criteria that can influence the process. Multiple attribute decision making method can be used to solve this problem. In this paper, VIKOR method along with Analytical Hierarchy Process (AHP) is used as multiple attribute decision making method to select the appropriate metal for the electroplating process. AHP is used to calculate the weight of the criteria and by using these weights VIKOR is used to rank the alternatives. Finally the proposed model has been presented for the selection of appropriate electroplating material.

Research paper thumbnail of An Adaptive Neuro-Fuzzy Inference System based Algorithm for Long Term Demand Forecasting of Natural Gas Consumption

Fourth International Conference on Industrial Engineering and Operations Management, Bali, Indonesia, 2014

This paper represents a successful implementation of Adaptive Neuro-Fuzzy Inference System (ANFIS... more This paper represents a successful implementation of Adaptive Neuro-Fuzzy Inference System (ANFIS) to develop an algorithm to predict the long term demand of Natural Gas Consumption. The developed ANFIS model is also applicable to forecast in other related fields though it is generated on the perspective of the environment of energy sector in Bangladesh. After identifying all the reasonable factors that affect the demand of Natural Gas Consumption we have considered five parameters to construct and examine the plausibility of ANFIS model. This study also provides results from generated FIS model and evaluates them. The proposed ANFIS model provides a suitable and special algorithm for the demand forecasting of Natural Gas Consumption. The outcomes are considerably better than the forecasting of the demand of Natural Gas consumption in traditional methods.