Papers by TONMOY ROY
Progressing proficiency and performance are a necessary topic in today's world and security in th... more Progressing proficiency and performance are a necessary topic in today's world and security in the transaction system is not out of it. Various Blockchain and smart contract methods have been created and put to use in health care applications, banking industry, real property transactions, smart home appliances, cloud-based internet of things (IoT), medical transcript, data access and permission, E-Voting recording, online education, virtual power plant etc. Securing E-commerce trading is one of the basic needs in the present world but there are few proposed Blockchain and Smart Contract findings in this sector and lack of a properly implemented model. Therefore, in this work, there is an implementation of Blockchain and Smart contract model to secure E-commerce trading. There is a proposed algorithm to secure the trading. Besides that, Blockchain model is shown by the proof of work concept. Blockchain transaction implementation is shown in Angular web framework with JavaScript. Having the features of proof of work consensus algorithm, verify Blockchain to prevent tampering, generate wallet and sign transaction. Smart contract implementation is shown by Ethereum smart contract with solidity. The methods is tested by using JavaScript VM virtual Blockchain. This proposed model shows a better performance on fast and secure transaction in E-commerce.
Progressing proficiency and performance is a necessary topic in today's world and security in the... more Progressing proficiency and performance is a necessary topic in today's world and security in the transaction system is not out of it. There are several Blockchain and Smart contract methods have been created and put to use in health care applications, banking industry, real property transactions, smart home appliances, cloud-based internet of things (IoT), medical transcript, data access and permission, E-Voting Recording, Online Education, virtual power plant etc. E-commerce trading is one of the basic needs in the present world, but there are few Blockchain and Smart Contract findings in this area and a lack of properly implemented models. Therefore, in this work, there is an implementation of Blockchain and Smart contract model to secure E-commerce trading. There is a proposed algorithm to secure the trading. Furthermore, the proof of work concept is used to demonstrate Blockchain transaction implementation. The features of the protocol include a proof of work consensus algorithm, a verification of the Blockchain to prevent tampering, the generation of wallets and the signing of transactions. Smart contract implementation is shown by Ethereum smart contract with solidity. The methods are tested by using JavaScript VM virtual Blockchain. In E-commerce, this proposed model shows a better performance in terms of fast and secure transactions.
North South University, 2019
These last years with the growing population in the smart city demands efficient transportation s... more These last years with the growing population in the smart city demands efficient transportation sharing which is a bicycle sharing system for developing the smart city. Bicycle sharing as we know is an affordable, easily accessible and reliable mode of transportation. But an efficient bicycle-sharing capable of not only sharing bikes also provides information regarding the availability of bicycle per station, route business, time/day-wise bicycle schedule. The embedded sensors are able to opportunistically communicate through wireless communication with stations when available, providing real-time data about tours/minutes, speed, effort, rhythm, etc. We have been based on our study analysis data to predict regarding the bicycle’s available at stations, bicycle schedule, a location of the nearest hub where a bike is available etc., reducing the user time and effort.
IEEE Transactions on Visualization and Computer Graphics, 2000
We empirically examined the impact of virtual human animation on the emotional responses of parti... more We empirically examined the impact of virtual human animation on the emotional responses of participants in a medical virtual reality system for education in the signs and symptoms of patient deterioration. Participants were presented with one of two virtual human conditions in a between-subjects experiment, static (non-animated) and dynamic (animated). Our objective measures included the use of psycho-physical Electro Dermal Activity (EDA) sensors, and subjective measures inspired by social psychology research included the Differential Emotions Survey (DES IV) and Positive and Negative Affect Survey (PANAS). We analyzed the quantitative and qualitative measures associated with participants’ emotional state at four distinct time-steps in the simulated interpersonal experience as the virtual patient’s medical condition deteriorated. Results suggest that participants in the dynamic condition with animations exhibited a higher sense of co-presence and greater emotional response as compared to participants in the static condition, corresponding to the deterioration in the medical condition of the virtual patient. Negative affect of participants in the dynamic condition increased at a higher rate than for participants in the static condition. The virtual human animations elicited a stronger response in negative emotions such as anguish, fear, and anger as the virtual patient’s medical condition worsened.
The Proceedings of the 1st International Conference on Industrial Application Engineering 2013, 2013
A novel approach for gesture recognition based on motion history images is proposed in this paper... more A novel approach for gesture recognition based on motion history images is proposed in this paper for one-shot learning gesture recognition task. The challenge here is to perform satisfactory recognition operations with only one training example of each action, while no prior knowledge about actions, foreground/background segmentation, or any motion estimation and tracking are available. In the proposed scheme motion history imaging technique is applied to track the motion flow in consecutive frames. The information of motion flow is later utilized to calculate the percent change of motion flow for an action in different spatial regions of the frame. The space-time descriptor computed this way from the query video is a measure of the likeness of a gesture in a lexicon. Finally, gesture classification is performed based on correlation based and Euclidean distance based classifiers and the results are compared. Through extensive experimentations on a much diversified dataset the effectiveness of employing the proposed scheme is established.
IEEE , 2021
Facial recognition is a fundamental method in facial-related science such as face detection, auth... more Facial recognition is a fundamental method in facial-related science such as face detection, authentication, monitoring, and a crucial phase in computer vision and pattern recognition. Face recognition technology aids in crime prevention by storing the captured image in a database, which can then be used in various ways, including identifying a person. With just a few faces in the frame, most facial recognition systems function sufficiently when the techniques have been tested under artificial illumination, with accurate facial poses and nonblurry images. in our proposed system, a face recognition system is proposed using Average pooling and MobileNetV2. The classifiers are implemented after a set of preprocessing steps on the retrieved image data. To compare the model is more effective, a performance test on the result is performed. It is observed from the study that MobileNetV2 triumphs over Average pooling with an accuracy rate of 98.89% and 99.01% on training and test data, respectively.
IEEE, 2021
In Bangladesh, agriculture is the primary source of income. It has a significant impact on the co... more In Bangladesh, agriculture is the primary source of income. It has a significant impact on the country's economy. However, agriculture is being hampered these days due to citizens shifting from rural to urban areas. Monitoring environmental factors is not a natural remedy for increasing crop production. Several causes have a significant impact on efficiency. Consequently, to address these issues, agriculture must incorporate automation. A farmer can save time, cost, resources, and energy by using an automated irrigation device. Traditional agricultural irrigation methods necessitate human interference. Human interference can be reduced with automated irrigation technology. We have designed and developed a reliable smart farming system (IoT) to reduce farmers' time costs and resources. Our proposed system can detect temperature, detect the moisture level and water level of the agricultural land, and remotely monitor the land crops. The proposed model sort out into four modules: Water Level Detection Module (WLDM) always detect the water level to avoid drops destruction; Soil Moisture Detection Module (SMDM) calculate the soil moisture level from the land, if the level goes down its start the water pump; Notification Module (NM) is responsible for generating the message service to notify the user if any parameter (Temperature, Soil Moisture, Water) not in well condition; Temperature Detection Module (TDM) is always counting the temperature and humidity of the air if its high then it will start the fan; Cloud and Notification Module (CNM) is handled the user notification through message and remotely monitoring the data of first three modules to take the necessary steps. The result shows the system successfully performed and it can be noted that our proposed can be implemented with any type of environment and agricultural land.
IEEE, 2021
The Convolutional Neural Network (CNN) is a form of artificial neural network that has become ver... more The Convolutional Neural Network (CNN) is a form of artificial neural network that has become very popular in computer vision. We proposed a convolutional neural network for classifying common types of vehicles in our country in this paper. Vehicle classification is essential in many applications, including surveillance protection systems and traffic control systems. We raised these concerns and set a goal to find a way to eliminate traffic-related road accidents. The most challenging aspect of computer vision is achieving effective outcomes in order to execute a device due to variations of data shapes and colors. We used three learning methods to identify the vehicle: MobileNetV2, DenseNet, and VGG 19, and demonstrated the methods detection accuracy. Convolutional neural networks are capable of performing all three approaches with grace. The system performs impressively on a real-time standard dataset-the Nepal dataset, which contains 4800 photographs of vehicles. DenseNet has a training accuracy of 94.32 % and a validation accuracy of 95.37%. Furthermore, the VGG 19 has a training accuracy of 91.94 % and a validation accuracy of 92.68 %. The MobileNetV2 architecture has the best accuracy, with a training accuracy of 97.01% and validation accuracy of 98.10%.
Conference Presentations by TONMOY ROY
IEEE, 2022
Progressing proficiency and performance are a necessary topic in today's world and security in th... more Progressing proficiency and performance are a necessary topic in today's world and security in the transaction system is not out of it. There are several Blockchain and Smart contract methods have been created and put to use in health care applications, banking industry, real property transactions, smart home appliances, cloud-based internet of things (IoT), medical transcript, data access and permission, E-Voting Recording, Online Education, virtual power plant etc. E-commerce trading is one of the basic needs in the present world, but there are few Blockchain and Smart Contract findings in this area and a lack of properly implemented models. Therefore, in this work, there is an implementation of Blockchain and Smart contract model to secure E-commerce trading. There is a proposed algorithm to secure the trading. Furthermore, the proof of work concept is used to demonstrate Blockchain transaction implementation. The features of the protocol include a proof of work consensus algorithm, a verification of the Blockchain to prevent tampering, the generation of wallets and the signing of transactions. Smart contract implementation is shown by Ethereum smart contract with solidity. The methods are tested by using JavaScript VM virtual Blockchain. In E-commerce, this proposed model shows a better performance in terms of fast and secure transactions.
Uploads
Papers by TONMOY ROY
Conference Presentations by TONMOY ROY