Browsing by Author "Faisal, Fahad"

Now showing 1 - 19 of 19

A Bengali Text Generation Approach in Context of Abstractive Text Summarization Using RNN
(Lecture Notes in Networks and Systems, Springer, 2020-03-04) Abujar, Sheikh; Masum, Abu Kaisar Mohammad; Islam, Md. Sanzidul; Faisal, Fahad; Hossain, Syed Akhter
Automatic text summarization is one of the mentionable research areas of natural language processing. The amount of data is increasing rapidly, and the necessity of understanding the gist of any text is just a mandatory tool, nowadays. The area of text summarization has been developing since many years. Mentionable research has been already done through extractive summarization approach; in other side, abstractive summarization approach is the way to summarize any text as like human. Machine will be able to provide a new type of summarization, where the understanding of given summary may found as like as human-generated summary. Several research developments have already been done for abstractive summarization in English language. This paper shows a necessary method—“text generation” in context of Bengali abstractive text summarization development. Text generation helps the machine to understand the pattern of human-written text and then produce the output as is human-written text. A basis recurrent neural network (RNN) has been applied for this text generation approach. The most applicable and successful RNN—long short-term memory (LSTM)—has been applied. Contextual tokens have been used for the better sequence prediction. The proposed method has been developed in the context of making it useable for further development of abstractive text summarization.
A Comparative Analysis of SMS Spam Detection employing Machine Learning Methods
(Daffodil International University, 2022-04-13) Aliza, Humaira Yasmin; Nagary, Kazi Aahala; Ahmed, Eshtiak; Puspita, Kazi Mumtahina; Rimi, Khadiza Akter; Khater, Ankit; Faisal, Fahad
In recent times, the increment of mobile phone usage has resulted in a huge number of spam messages. Spammers continuously apply more and more new tricks that cause managing or preventing spam messages a challenging task. The aim of this study is to detect spam message to prevent different cybercrimes as spam messages have become a security threat nowadays. In this paper, studies on SMS spam problems to perform a better accuracy using several different techniques such as Support Vector Machine, K-Nearest Neighbor, Naïve Bayes, Random Forest, Logistic Regression and some more are performed. The result indicated that Support Vector Machine achieved the highest accuracy of 99%, indicating it might be useful as an effective machine learning system for future research.
A Framework to Address Security Concerns in Three Layers of IoT
(IEEE, 2020-11) Jose, Alwyn; Azam, Sami; Karim, Asif; Shanmugam, Bharanidharan; Faisal, Fahad; Islam, Ashraful; De Boer, Friso; Jonkma, Mirjam
The Internet of Things (IoT) is becoming part of many aspects of our life, including healthcare, home utilities, retail, energy, logistics, etc. This prolific and ubiquitous nature of IoT based systems brings with it the threats of cyber-attacks in a variety of forms. An IoT framework is a set of controlling rules, standards and protocols which makes implementation of IoT applications somewhat streamlined. However, due to the existence of a plethora of IoT devices, applications and technologies, standardization of IoT protocols is a complex undertaking. Several well-known IT organizations have their own customized standards for the IoT platform. However, the lack of stable standardization has been a prime concern for quite some time. This research outlines the overall technologies used in IoT security implementation and an overview of different threats faced by IoT devices. The work also recommends a security framework that can effectively be implemented with various IoT based systems.
A Framework to Address Security Concerns in Three Layers of IoT
(IEEE, 2020-11-20) Jose, Alwyn; Azam, Sami; Karim, Asif; Shanmugam, Bharanidharan; Faisal, Fahad; Islam, Ashraful; De Boer, Friso; Jonkman, Mirjam
The Internet of Things (IoT) is becoming part of many aspects of our life, including healthcare, home utilities, retail, energy, logistics, etc. This prolific and ubiquitous nature of IoT based systems brings with it the threats of cyber-attacks in a variety of forms. An IoT framework is a set of controlling rules, standards and protocols which makes implementation of IoT applications somewhat streamlined. However, due to the existence of a plethora of IoT devices, applications and technologies, standardization of IoT protocols is a complex undertaking. Several well-known IT organizations have their own customized standards for the IoT platform. However, the lack of stable standardization has been a prime concern for quite some time. This research outlines the overall technologies used in IoT security implementation and an overview of different threats faced by IoT devices. The work also recommends a security framework that can effectively be implemented with various IoT based systems.
A Promising Prediction of Diabetes Using a Deep Learning Approach
(Daffodil International University, 2022-01-06) Shakil, Rashiduzzaman; Akter, Bonna; Faisal, Fahad; Chowdhury, Tahmid Rashik; Roy, Tonmoy; Khater, Ankit
Diabetes is a collection of metabolic illnesses caused by a persistently high blood sugar level. If a reliable estimation is achievable, diabetes risk factors and severity can be reduced. In diabetes datasets, consistent and effective diabetes prediction is challenging because of the limited amount of labeled data and the abundance of outliers (or missing values).Alongside, the incidence rates of diabetes are rising alarmingly every year. Consequently, an early diagnosis of diabetes would be the most crucial step for receiving proper treatment. Hence, a deep learning-based reorganization system has gained popularity regarding disease identification. In this work, we used an updated Convolution Neural Network (CNN) model, modifying different hyperparameters and layer topologies on the UCI 130 USA Hospitals diabetes dataset. Additionally, five different types of optimizer, namely adaptive moment estimation (ADAM), ADAMAX, A more sustainable deal has been made using the Root Mean Square Propagation algorithm (RMSprop), stochastic gradient descent (SGD), and Nesterov accelerated adaptive moment (NADAM). Furthermore, improved accuracy of 99.98% was received by the ADAMAX optimizer.
A Proposition for a Low-Cost Effective Attendance Management System
(IEEE, 2020-06) Alam, Mohammad Jahangir; Faisal, Fahad; Karim, Asif
In this paper, a holistic methodology has been followed to gauge the quality of service for real-time attendance system. The experiment was done to compare the performance of an attendance server which will be cost-effective but reliable. To reduce the cost, users are connected to the biometric attendance device with a local server where the data is updated instantly. As a result, the chance of data loss is almost none. The available devices in the market are very expensive whereas our complete system may cost around USD50. On the other hand, most of the devices produce multiple data for a single user on a specific day as the data fetched from the internal memory of the respective device. But our proposed system provides a very well-ordered data for easy tracking of attendance. Moreover, our proposed framework requires a marginal power to drive the whole system. The complete system can be implemented using regular hardware and software at a very low cost.
An IoT based Environment Monitoring System
(IEEE, 2021-01-18) Hassan, Mosfiqun Nahid; Islam, Mohammed Rezwanul; Faisal, Fahad; Semantha, Farida Habib; Siddique, Abdul Hasib; Hasan, Mehedi
In recent years, people are getting more conscious of the environment they are living in. This consciousness is driving the need to develop a reliable environmental monitoring system. An environmental air quality monitoring system also has industrial application. In mining or in heavy industry, there is a possibility of air contamination by different harmful gases. In such hazardous situations, an environmental monitoring system can potentially save the life of the workers. In such large-scale sensor deployment, there are data collection, data management, connection, and power consumption issues. IoT technology is specifically suited for this sort of need. This paper presents an IoT based framework that effectively monitors the change in an environment using sensors, microcontroller, and IoT based technology. Users can monitor temperature, humidity, detect the presence of harmful gases both in the indoor and outdoor environment using the proposed module. The data is stored in the web server and the user can access the data anywhere in the world through an internet connection. In the proposed work a web application is developed to provide vital information to the user. The user can also set up a notification for critical changes in the sensor data. In comparison to other closely related systems, the proposed system is a low-cost one, accurate and user friendly. It is also cloud-based and has easy monitoring and data visualization modules. The system has been evaluated in different stages. After testing all the functions in different conditions, it shows a high degree of accuracy and reliability.
An Overview of Blockchain Applications and Attacks
(IEEE, 2019-11-14) Faisal, Fahad
In recent decades, Information Technology has contributed fundamentally to the development of financial markets, reforming the way in which financial institutions interact with each other. However, the established practices and norms of this sector may face an all-out overhaul as remarkable innovations such as Blockchain are maturing. The essence of Blockchain is that it is a public, shared and carefully designed record that allows mutually unknown individuals and institutions to share data in a reliable ledger and carry out all kinds of transactions. This ground-breaking technology is developed from cryptography and peer-to-peer network technologies. It is nearly immune to the majority of today’s digital threats. Besides financial institutions, Blockchain based solutions have made it into other industries such as real estate, health care, the media as well as Government bodies. This paper will explain how Blockchain works, what it really is, types, its applications and threats and will offer a few ideas for prospective expansion of this technology
Analysis of Complex Networks for Security Issues Using Attack Graph
(2019 International Conference on Computer Communication and Informatics, IEEE, 2019-09-02) Musa, Tanvirali; Yeo, Kheng Cher; Azam, Sami; Shanmugam, Bharanidharan; Karim, Asif; Boer, Friso De; Nur, Fernaz Narin; Faisal, Fahad
Organizations perform security analysis for assessing network health and safe-guarding their growing networks through Vulnerability Assessments (AKA VA Scans). The output of VA scans is reports on individual hosts and its vulnerabilities, which, are of little use as the origin of the attack can't be located from these. Attack Graphs, generated without an in-depth analysis of the VA reports, are used to fill in these gaps, but only provide cursory information. This study presents an effective model of depicting the devices and the data flow that efficiently identifies the weakest nodes along with the concerned vulnerability's origin.The complexity of the attach graph using MulVal has been greatly reduced using the proposed approach of using the risk and CVSS base score as evaluation criteria. This makes it easier for the user to interpret the attack graphs and thus reduce the time taken needed to identify the attack paths and where the attack originates from.
Automated Traffic Detection System Based on Image Processing
(Al-Kindi Center for Research and Development, 2020-06-30) Faisal, Fahad; Das, Sumon Kumar; Siddique, Abdul Hasib; Hasan, Mehedi; Sabrin, Samia; Hossain, Chowdhury Akram; Tong, Zhou
This paper proposes a low-cost automated traffic detection system based on image processing. Dhaka is one of the crowded cities in the world with highly challenging traffic system. There is substantial lack of awareness among the drivers of transport system. As a result, citizens do not follow the rules and regulation while driving in Dhaka city. The tendency of violating the traffic regulation is noticeable throughout the country. As a result, the whole traffic system collapses very often and sometimes it ends-up with severe accidents. In recent days, the government has taken different initiatives including enlargement of pedestrian walkways, building new flyovers and foot-over bridges, expansion of existing roads. But, violation still the outcome of all these initiatives could not improve the situation significantly. The proposed system will automatically detect the traffic through live streaming video so that the detected images can be used to detect traffic violation. Later on, the law enforcement agency will be able to take necessary legal steps based on the stored information on the database.
Bengali Abstractive Text Summarization Using Sequence to Sequence RNNs
(10th International Conference on Computing, Communication and Networking Technologies, IEEE, 2019-07-08) Talukder, Md Ashraful Islam; Abujar, Sheikh; Masum, Abu Kaisar Mohammad; Faisal, Fahad; Hossain, Syed Akhter
Text summarization is one of the leading problem of natural language processing and deep learning in recent years. Text summarization contains a condensed short note on a large text document. Our purpose is to create an efficient and effective abstractive Bengali text summarizer what can generate an understandable and meaningful summary from a given Bengali text document. To do this we have collected various texts such as newspaper articles, Facebook posts etc. and to generate summary from those text we will be using our model. Our model works with bi-directional RNNs with LSTM in encoding layer and attention model at decoding layer. Our model works as sequence to sequence model to generate summary. There are some challenges we have faced while building this model such as text pre-processing, vocabulary counting, missing words counting, word embedding, unknown words find out and so on. In this model, our main goal was to make an abstractive summarizer and reduce the train loss of that. During our research experiment, we have successfully reduced the train loss to 0.008 and able to generate a fluent short summary note from a given text.
Intelligent Identification of Hate Speeches To Address the Increased Rate of Individual Mental Degeneration
(Elsevier B.V., 2023-02-14) Ava, Lamima Tabassum; Karim, Asif; Hassan, Md. Mehedi; Faisal, Fahad; Azam, Sami; Al Haque, A S M Farhan; Zaman, Sadika
Hate speech is a public statement that demonstrates resentment or provokes disturbance towards a person or group often based upon race, age, religion, sexual orientation, minority group, psychical disability, political belief, etc. Such an act is a leading cause of mental degeneration in individuals observed throughout the world. We have witnessed an upsurge in the spreading of hateful speech through videos in recent times due to increased social media usage. Researchers are working on this issue because it has become more frequent on several social media platforms, and it leads to low self-esteem and has significant negative impacts on human life. In this work, we focus on collecting data from such videos as nowadays people are sharing numerous videos of this negative nature on platforms like Facebook and YouTube. The audio data of these videos were then converted into text to build the dataset, and we applied some classifier models to our dataset. In this paper, we utilized a transfer learning Bidirectional Encoder Representations from Transformers (BERT) model that gives state-of-the-art outcomes. More precisely, we fine-tuned our model based on transfer learning to evaluate BERT's capacity to capture hostile contexts inside YouTube videos. We examined Fine–Tuning BERT; with different learning rates and listed the outcomes. We train the BERT by freezing all the hyperparameters but with various random seeds to evaluate our suggested Fine-tuning approach. Compared to previous methodologies that used our dataset, our proposition fared better in terms of accuracy and execution time.
Low Cost Voltage and Current Measurement Technique Using Atmega328p
(Proceedings of the 4th International Conference on IoT in Social, Mobile, Analytics and Cloud, ISMAC 2020, IEEE, 2020-11-10) Faisal, Fahad; Karim, Asif; Hasan, Md. Zahid; Shanmugam, Bharanidharan; Mahdi, Muntasir; Moon, Nazmun Nessa
This paper is mainly focused on the low cost technique to measure both AC and DC voltage along with current by using very low cost components. The system can also be easily monitored via a smartphone. The work is intended for the engineering students as most of the Voltmeter/Ammeter is very expensive. Not only that, the acquired data can be stored as per the requirements. New features can be added very easily with this ammeter/voltmeter as well. Whole task was implemented with the help of popular micro-controller ATmega328p to reduce the cost.
Modern Tree Plantation System Based on IOT
(Proceedings of the 4th International Conference on IoT in Social, Mobile, Analytics and Cloud, ISMAC 2020, IEEE, 2020-11-10) Bithi, Muskan Hossain; Faisal, Fahad; Karim, Asif; Azam, Sami; Shanmugam, Bharanidharan; Lakshmiganthan, Rajasekaran
The disruption in the ecosystem and the atmosphere surrounding it by different pollutant categories, it can be cited as environmental pollution and when these pollutants are present in the air in form of chemicals or compounds in excess in the air it is adduced as air pollution. In this paper a method has been proposed to reduce the CO 2 level in the environment. The proposed method is pretty straight forward, where the level of emission will be detected with the help of MQ135 sensor. Once it is found that the emission of CO2 is more than the normal level, the soil type of those affected places will be tested by SEN-00200 sensor which will be monitored remotely. Based on the soil type, the appropriate type of plants which reduces the harmful gases will be determined in the long run. This work also proposes an ecofriendly environment by tree plantation in mass scale to make the environment more aesthetic and elegant as auxiliary.
Non-iterative MPPT Method
(International Journal of Renewable Energy Research, 2020-06) Ahmed, Md Tofael; Rashel, Masud Rana; Faisal, Fahad; Tlemçani, Mouhaydine
The presented work is a contribution to maximum power point tracking problem with improved performance. The analysed and discussed method is based on mathematical model of a PV panel. The output power of PV panel is dependent on the load as well as the almost unpredictable behaviour of the environment. It has a non-linear implicit behaviour on the load due to the weather parameters dependency. Due to different conditions of PV curve, it may have several local maxima. Existing MPPT techniques are mainly based on iterative method which are more time consuming and complex in nature considering the sense of comparative techniques. The most used approach is based on P&O algorithm with gradient comparison. The proposed technique improves the performance on the basis of time and computational complexity. During a low changing environmental condition this method achieves good result on the way to reach the overall point for maximum power. Taking into account the data sheet values of the panel along with the usage of existing knowledge from the datasheets, this technique is possible to implement and flexible for digital signal processing platform. An experimental setup is also done to verify the accuracy, robustness and simplicity of the introduced algorithm. It is found that the proposed technique is less complex and can be coupled with other method too.
Sentence Similarity Measurement for Bengali Abstractive Text Summarization
(10th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2019, IEEE, 2019-12-30) Masum, Abu Kaisar Mohammad; Abujar, Sheikh; Tusher, Raja Tariqul Hasan; Faisal, Fahad; Hossain, Syed Akhter
Text summarization is a massive research area in natural language processing. It reduces the larger text and provided the prime meaning of a text document. Find the meaning of the larger text needed of a proper text analysis which gives a better text summarizer. Abstractive text summarizer gives a summary which can present or not present in the text document. The machine produces a text summary after learning from the human given summary. Sentence similarity is a way to judge a better text summarizer. It is exploring the similarity between sentences or words. This paper we discuss several methods of sentence similarity and proposed a method for identifying a better Bengali abstractive text summarizer. We used human given summary and machine response summary sentences for similarity measurement where both sentences contain a Bengali short text. There are several approaches to English sentences similarity measurement, and we applied some of the approaches for similarity measure for our Bengali text which give a satisfying result. For our given methods we collect data from online and social media and create a summary of those texts. After creating a summary pre-processing this text and generate a summary from our abstractive text summarization model. All summary sentence similarity measurement cases using the method provided an effective value and optimal result.
Smart Electrification of Rural Bangladesh through Smart Grids
(Scopus, 2021) Debnath, Dhrupad; Siddique, Abdul Hasib; Hasan, Mehedi; Faisal, Fahad; Karim, Asif; Azam, Sami; Boer, Friso De
A smart grid is a new technology that integrates power systems with communication systems. It is an intelligent and efficient management system that has self-healing capabilities. The smart grid can be applied to manage networks that integrate different types of renewable resources for power generation. Bangladesh is currently experiencing severe power deficiency. Renewable energy sources such as solar power and biogas can play an important role in this scenario, especially in rural areas where electricity is even scarcer. By applying prototype concepts of smart grid, power generation from renewable resources and efficient load management can be achieved by a centralized control center. This will control the on-off sequence of the load and maintain the system stability. In this paper, different aspects of implementing a prototype of the smart grid in the rural areas of Bangladesh are discussed.
Using Blockchain Technology for File Synchronization
(IOP Conference Series: Materials Science and Engineering, 2019) Khan, MD. Ibrahim; Faisal, Fahad; Azam, Sami; Karim, Asif; Shanmugam, Bharanidharan; Boer, Friso De
Modern storage technology has shifted from traditional offline state to cloud based technology since some time now. Because of this transition, the present society is now more dependent on the online storage solutions. Synchronization of files and keeping a history of changes are critical parts of any cloud system. Therefore, an implementation of Blockchain Technology with traditional file synchronization and versioning system can be extremely fruitful. Blockchain is not a new technology, but recently its importance has sky-rocketed as the society is moving towards the decentralized World Wide Web. Blockchain is “an open, distributed ledger that can record transactions between two parties efficiently and in a verifiable and permanent way” [1]. Blockchain provides immutable data storage and access with the combination of Proof-of-Work [2, 3]. Due to such appealing features, the study undertaken here investigates and proposes a Blockchain based resilient cloud storage solution that makes a sound utilization of various properties fundamental to any Blockchain based framework.
Voice Activated Portable Braille with Audio Feedback
(2021) Faisal, Fahad; Hasan, Mehedi; Sabrin, Samia; Hasan, Md. Zahid; Siddique, Abdul Hasib
The goal of this paper is to create a Voice Activated Braille as a portable device that will help individuals who are blind or visually impaired without any partial help to recognize certain written characters. This is a system controlled by Arduino that will be able to direct blind people. The system acts mostly as a guide for the blind, a particular virtual environment for the visually disadvantaged, making them similarly optimistic to the rest of the world's regular citizens. Blind people will benefit from these innovative braille methods to tackle the challenge of information technology around the world. This system is compact and will keep blind people from partial assistance and can also help them read something without any help. Thus, the daily inconvenience of blind individuals can be significantly decreased and they can enjoy a certain level of freedom and activity.