Browsing by Author "Rabbani, Masud"

Now showing 1 - 11 of 11

A Proposed Continuous Auditing Process for Secure Cloud Storage
(Springer, 2020-09-08) Khan, Thaharim; Rabbani, Masud
In recent time, cloud is one of the most useful resources for storing data without any hassle. Integrity, originality and security of data are the main concerns in cloud computing. Through the data auditing, this problem can be solved in some amount. This proposed work follows the data auditing scheme but with different methodology for making the scheme better and secure. This procedure is divided into three phases: (i) user, (ii) data auditor and (iii) cloud server. Cloud server is used for keeping data file, and data auditor is used to check the integrity of the data which is kept by the user. The user has the permission to perform various types of action like create a block for data and generate encryption for data. The third party auditor mainly generates the encryption method and checks the integrity for data security. For encryption, data encryption standard (DES) algorithm is used as the algorithm which generates the longer ciphertext, conveying better security for data. And for data integrity, secure hash algorithm (SHA-512) is used as it checks for 64-bit words. Also, Rivest–Shamir–Adleman (RSA) is used for measuring digital signature. In this method, user can get the deleted item from cloud bin by accessing into the bin with the digital signature, and all the deleted items are stored into the bin as encrypted mode. In this method, attackers are not feasible to take access into the cloud as RSA is used for digital signature.
A Survey on RealSense
(IEEE, 2020-07) Rabbani, Masud; Mia, Md. Jueal; Khan, Thaharim; Zarif, Md Ishrak Islam
RealSense technology is such a technology which is implemented for machines and device for measuring the capabilities of those apparatus. The capabilities are related to the perceptions of those machines and devices. This technology mainly learns a machine to understand the world with cogitation. RealSense technology introduces cameras to explore the environment with ins and out as it is parallel working with high definition cameras. This technology is used in many categories. Object detection, facial expression detection, shape measurement, image processing, and so on. Among all of the types, RealSense technology is used in huge amount for object detection. In this category real sense mainly focus on the object which is vitally important for understanding the full scene, and understanding the other aspect of the scene with which the object can be classify for better understanding. This paper mainly provides an overview of RealSense technique to the modern technology with its 3D visual functionalities adding the developed application which is published based on Microsoft Kinet and also with SR300 technology. Also this work can give a clear overview to the researchers about the fact that which domain of research is easier with this RealSense technology and in which domain they get more accuracy.
An Approach to Study on MA, ES, AR for Sunspot Number (SN) Prediction and to Forecast SN with Seasonal Variations Along with Trend Component of Time Series Analysis Using Moving Average (MA) and Exponential Smoothing (ES)
(Springer, 2020-09-08) Tabassum, Anika; Rabbani, Masud; Omar, Saad Bin
Sunspots are the interesting things on the surface of sun which is why it would be more engaging if sunspots become predictable. In this study, sunspot numbers (SN) have been predicted within recent solar cycle 24. To find the best model, moving average (MA), exponential smoothing (ES) and auto regression (AR) have been used. Besides these, in another two experiments which are seasonal component was extracted from data using moving average (MA) and exponential smoothing (ES) as well as with the help of simple regression analysis (RA), trend component was calculated. This exploration is entirely about understanding the differences among these models and the influences of those two components to predict sunspot using moving average (MA) and exponential smoothing (ES). Prediction results have been conducted to expose that difference and influence. It can manifest the way of forecasting for other model of time series analysis (TSA) to predict sunspot number (SN).
An Approach to Study on Time Series Components and by Using them to Enumerate the Height of Sea Level Alteration for Both Global Mean Sea Level(GMSL) and Bay of Bengal(BOB)
(IEEE, 2019-10-17) Tabassum, Anika; Rabbani, Masud; Omar, Saad Bin
As the global climate is changing, our focus was on Sea Level Rising (SLR) which is the most threatening phenomenon in this era. Hence to hit the nail on the head, the alteration of surface level for both Global Mean Sea Level (GMSL) and Bay of Bengal (BOB) has been predicted using time series analysis (TSA). Since the time series analysis has some components, those components were brought out from data set and by using these components some terms have been calculated to match with real data. By doing that, training part was constructed and set up a method to predict the results for next years. An endeavor has been done to test the prediction results with a known data set as well as the computation was carried out in order to forecast for unknown data. In this work, the prediction has been done with respect to seasonal effects so that result can be accurate with seasonal variation. With extensive data set, other inconsistency has been considered easily. Mathematical enumeration has added a dynamism with this forecasting thoughtlessly. This study can be used to raise up a wariness among people. Besides this, this research can be used as a grounding for further study.
An Innovative Data Mining Approach for Determine Earthquake Probability Based on Linear Regression Algorithm
(IEEE, 2019-02-22) Khan, Thaharim; Majumder, Anup; Rabbani, Masud; Siddiquee, Shah Md. Tanvir
Earthquake (EQ) causes many damages to our environment, this paper proposes a new approach to find the Earthquake probability (EQP) using linear regression (LR-EQP) is to minimize this extensive problem with the help of geological data by predicting the intended probability of the level of EQ. This approach is to take the all the geological information which are responsible for EQ such as to create pressure on the land like density of population (DP), soil type (ST), combustible elements (CE), specify the place use latitude and longitude (Lat-Long), distance from nearest tectonic plate (TP). Since TP is the divided part of earth which move independently and responsible earth's seismic activity and LR-EQP deploy these geological data, so LR-EQP approach can determine the EQP easily and accurately. Earthquake prediction using data mining is a process, which uses only three factors: (a) ground water level, (b) chemical changes and (c) radon gas in ground water. But this is a slow approach to determine EQP because in general these factors cannot be determined so easily. LR-EQP can be used for any region by targeting the TP area. This data model can be used also for mobile application for easily detecting the probability of earthquake
An Overall Workflow of Deep Learning in Modern Technology
(International Journal of Innovative Technology and Exploring Engineering, 2019-06) Khan, Thaharim; Rabbani, Masud; Siddiquee, Shah Md. Tanvir; Marouf, Ahmed Al
Modern technology blessed us with many amenities. Those invention of modern science has lessened our workload with many others flexibility. Modern technology has been growing up significantly after the implementation of artificial intelligence (AI) in various sector. Machine Learning (ML), Natural language processing (NLP), Expert system (ES), Computer Vision (CV), Planning & Optimization (P&O), Robotics (RT), Deep Learning (DL), Image Recognition (IR) all are intertwined with AI. Deep learning, one of the most interesting affiliate of AI which terminate the provision of usual invention. One can think of various type of innovation about which only come to their imagination. Some devising work which appears in front of us seems like as a human being is doing that output. The algorithm that deep learning use is more efficient and acceptable for those modern amenities which are called the blessings of modern science. All that devising works in modern age is used by us but could not understand the way how that devising element perform or what the mechanism is. This project gives one a clear view about the deep learning. This paper focus on those algorithms and working procedure which is needed for developing innovative things and which make deep learning more acceptable to us.
Potato-Net: Classifying Potato Leaf Diseases Using Transfer Learning Approach
(Springer Nature, 2023-06-11) Bitto, Abu Kowshir; Bijoy, Md.Hasan Imam; Das, Aka; Rahman, Md.Ashikur; Rabbani, Masud
Research on pertinent topics is more important than ever for the long-term development of agriculture, given the advancements in contemporary farming and use of artificial intelligence (AI) for identifying crop illnesses. There are numerous diseases, and they all significantly affect the amount and quality of potatoes. Early and automated detection of these illnesses during the budding phase can assist increase the output of potato crops, but it requires a high level of ability. Several models have already been created to identify various plant diseases. In this study, we use a variety of convolutional neural network designs to recognize potato leaf disease and assess their early detection accuracy against that of other researchers’ work. The learning sample for our algorithm included both the original and enhanced photos, as a learning option. The model was then evaluated to ensure that it was accurate. After being trained on the dataset for the potato leaf disease using the Inception-v3, Xception, and ResNet50 models, the model’s performance was evaluated using test images. ResNet50 has the highest accuracy and lowest error rate for detecting potato leaf disease, followed by Inception-v3 with an accuracy of nighty four point two five percent (94.25%) and Xception with an accuracy of eighty-nine point seven one percent (89.71%).
PR-SEO
(Scopus, 2021) Khan, Thaharim; Hassan, Md. Imrose; Zarif, Md. Ishrak Islam; Rabbani, Masud
This chapter proposes an approach for product ranking with SEO (PR-SEO). PR-SEO is such a way with which all the products in an e-commerce site can get a rank. Search engine optimization (SEO) is now become one of the most useable techniques because of the e-commerce business. With the development of technology, nowadays online shopping has become more attractive to all the users. To represent the product in front of all the user, search engine optimization (SEO) helps a lot by ranking the product. In recent few days, the search engine optimization (SEO) becomes more popular because of only the e-commerce sites. Now in this era of digital marketing, all the e-commerce sites are in a competition because of their profit for the product. For generating a new lead of organic traffic, all the e-commerce sites need to be available in the top search when a customer is willingly searching for it without this new lead of organic traffic will not be generated. This proposed product ranking with SEO (PR-SEO)mainly focuses on the SEO tactics for digital marketing as well as e-commerce sites.
RBS
(Scopus, 2020) Bijoy, Md. Hasan Imam; Hasan, Md. Rakibul; Rabbani, Masud
In modern technology or practical application, all things are gradually arranged. Therefore, in this paper, we attempt to establish a new sorting algorithm and compare it with some other standard sorting algorithms by their execution times. We designed and developed a methodology that can be executed on random data, ordering data, and some specific data (data means integers value), which can provide the best result for Right Bounding Sort (RBS). The methodology is comparing the array's left value with the rightmost value. Under a particular condition, these two values are swapped, then left index increase, and after completing the first step, the right index decrease, and it continues up to array size. Though there are many sorting algorithms invented for sorting an array with specific time complexity, space complexity, and other factors, they have some limitations because there is no sorting that is perfect for all various types of data. Some are good for small ranges of value, some are vast ranges of data, some are stable, and some are unstable. This algorithm performs with Big-O(n 2 ) time complexity and Big-O (1) space complexity. We see that our new sorting algorithms provide better solutions than some other existing sorting algorithms like the bubble sort, insertion sort, cycle sort, etc. On the experimental dataset in respect of time complexity.
Skin Disease Recognition
(2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), IEEE, 2021-06-03) Nawar, Anika; Sabuz, Noor Kibria; Siddiquee, Shah Md. Tanvir; Rabbani, Masud; Biswas, Al Amin; Majumder, Anup
Progressively a large number of people are being invaded by various types of skin diseases all over the world. With the help of modern medical equipment, it is very much easy to find out the diseases. But sometimes people wouldn't able to reach a hospital or any diagnostic center in a short time and it is also very much costly for most people especially for developing country. In that scenario, we proposed a prototype in this paper by which we can recognize the problem urgently and at a low cost. Mainly this is an image processing technique. Using color segmentation technique with SVM classifier, our proposed system can recognize several types of skin diseases based on some feature extraction. This method efficiently recognizes eight different skin diseases with an accuracy rate of percentage is 94.79%. Our recommended model is so simple, fast, and requires any kinds of programmable devices like desktop, android phones, tabs, IOS, and so on.
SOT
(Scopus, 2021) Rabbani, Masud; Jamil, Ali Md Musfick; Khan, Thaharim; Zarif, Md Ishrak Islam
This chapter proposes a new and innovative method of smart optical character recognition (OCR) for translation (SOT) from an English image to Bangla and Hindi language. For translation, this OCR system can take any picture from any documents which contain printed English sentences. SOT can translate the image into text within two languages. The translated text from SOT can also be copied and kept for further use. SOT can convert the full image in a text format and then can translate some of the portions of an image by cropping. Google translator has been used here for the OCR. This API can translate the image into a printed text or a machine-encoded text. But the translated text cannot be kept for further use which is an immense disparity between SOT and Google translator. Moreover, many APIs also deploy, which can translate the image into a text format but cannot ferry the limit of copying text which is collected after translating text from the image. SOT can be beneficiary among all the OCR as it struck the limit of copying text.