Instagram Image Filtration with Computer Vision

Instagram is one of the famous and fast-growing media sharing platforms. Instagram allows users to share photos and videos with followers. There are plenty of ways to search for images on Instagram, but one of the most familiar ways is ’hashtag.’ Hashtag search enables the users to find the precise search result on Instagram. However, there are no rules for using the hashtag; that is why it often does not match the uploaded image, and for this reason, Users are unable to find the relevant search results. This research aims to filter any human face images on search results based on hashtags on Instagram. Our study extends the author’s [2] work by implementing image processing techniques that detect human faces and separate the identified images on search results based on hashtags using the face detection technique.

Stock Price Prediction: LSTM Based Model

Stock price prediction is a critical field used by most business people and common or retail people who tried to increase their money by value with respect to time. People will either gain money or loss their entire life savings in stock market activity. It is a chaos system. Building an accurate model is complex as variation in price depends on multiple factors such as news, social media data, and fundamentals, production of the company, government bonds, historical price and country's economics factor. Prediction model which considers only one factor might not be accurate. Hence incorporating multiple factors news, social media data and historical price might increase the model's accuracy. This paper tried to incorporate the issue when someone implements it as per the model outcome. It cannot give the proper result when someone implements it in real life since capital market data is very sensitive and news-driven. To avoid such a situation, we use the hedging concept when implemented.

Using Machine Learning to Predict Distributed Denial-of-Service (DDoS) Attack

The IT space is growing in all aspects ranging from bandwidth, storage, processing speed, machine learning and data analysis. This growth has consequently led to more cyber threat and attacks which now requires innovative and predictive security approach that uses cutting-edge technologies in order to fight the menace. The patterns of the cyber threats will be observed so that proper analysis from different sets of data will be used to develop a model that will depend on the available data. Distributed Denial of Service is one of the most common threats and attacks that is ravaging computing devices on the internet. This research talks about the approaches and the development of machine learning classifiers to detect DDoS attacks before it eventually happen. The model is built with seven different selection techniques each using ten machine learning classifiers. The model learns to understand the normal network traffic so that it can detect an ICMP, TCP and UDP DDoS traffic when they arrive. The goal is to build a data-driven, intelligent and decision-making machine learning algorithm model that will use classifiers to categorize normal and DDoS traffic using KDD-99 dataset. Results have shown that some classifiers have very good predictions obtained within a very short time.

A COVID-19 Corpus Creation for Bengali: In the Context of Language Study

A corpus is a large collection of machine-readable texts, ideally, that should be representative of a Language. Corpus plays an important role in several natural language processing (NLP) and linguistic research. The corpus development itself is a substantial contribution to the resource building of language processing. The corpora play an important role in linguistic study as well as in several NLP tasks like Part-Of-Speech (POS) tagging, Parsing, Semantic tagging, in the parallel corpora, etc. There are numerous corpora in the literature of different languages and most of them are created for a specific purpose. Hence it is obvious that a researcher cannot use any corpus for their particular task. This paper also focuses on an automated technique to create a COVID-19 corpus dedicated to the research in linguistic aspects because of the pandemic situation.

Distribution System Fault Analysis Using MATLAB/SIMULINK

In this paper, the impacts of various faults in the distribution network system (DNS) have been analyzed. Modelling and simulation is done using MATLAB/Simulink software package. The proposed model is simple and it can be used by power engineers as a platform. The designed model is used to study various common faults in distribution network at different points. The waveform display due to the various faults gives us an idea of hazardousness of the respective fault. The response of the system after introducing protective device is also observed.

Road Extraction from Remotely Sensed Data: A Review

Up-to-date road networks are crucial and challenging in computer vision tasks. Road extraction is yet important for vehicle navigation, urban-rural planning, disaster relief, traffic management, road monitoring and others. Road network maps facilitate a great number of applications in our everyday life. Therefore, a systematic review of deep learning approaches applied to remotely sensed imagery for road extraction is conducted in this paper. Four main types of deep learning approaches, namely, the GANs model, deconvolutional networks, FCNs, and patch-based CNNs models are presented in this paper. We also compare these various deep learning models applied to remotely sensed imagery to show their performances in extracting road parts from high-resolution remote sensed imagery. Later future research directions and research gaps are described.

Twitter Data Sentiment Analysis to Understand the Effects of COVID-19 on Mental Health

Coronavirus pandemic has caused major change in peoples’ personal and social lives. The psychological effects have been substantial because it has affected the ways people live, work, and even socialize. It has also become major discussions on social media platforms as people showcase their opinions and the effect of the virus on their mental health particularly. This pandemic is the first of its kind as humans has never encountered anything like this virus. Handling it was very difficult at first as its characteristics are peculiar. Eventually, it was detected that it is airborne and so there is need to social distance. Before the virus surfaced, some countries of the world were dealing with mental health cases, with over 40 percent of adults in the USA reported experiencing mental health challenges, including anxiety and depression. Social media has become one of the major sources of information due to information sharing on a very large scale. People perception and emotions are also portrayed through their conversations. In this research work, the interaction and conversation of people on social media, particularly Twitter, will be analyzed using machine learning tools and algorithm to determine the effect of the virus on the mental health of people and help suggest the area of concentration to medical practitioners in order to speed up the recovery process and reduce the mental health issues which has escalated due to the virus.

Technical Domain Classification of Bangla Text using BERT

Coarse-grained tasks are primarily based on Text classification, one of the earliest problems in NLP, and these tasks are done on document and sentence levels. Here, our goal is to identify the technical domain of a given Bangla text. In Coarse-grained technical domain classification, such a piece of the Bangla text provides information about specific Coarse-grained technical domains like Biochemistry (bioche), Communication Technology (com-tech), Computer Science (cse), Management (mgmt), Physics (phy) Etc. This paper uses a recent deep learning model called the Bangla Bidirectional Encoder Representations Transformers (Bangla BERT) mechanism to identify the domain of a given text. Bangla BERT (Bangla-Bert-Base) is a pretrained language model of the Bangla language. Later, we discuss the Bangla BERT accuracy and compare it with other models that solve the same problem.

Data Mining and Principal Component Analysis on Coimbra Breast Cancer Dataset

Machine Learning (ML) techniques play an important role in the medical field. Early diagnosis is required to improve the treatment of carcinoma. During this analysis Breast Cancer Coimbra dataset (BCCD) with ten predictors are analyzed to classify carcinoma. In this paper method for feature selection and Machine learning algorithms are applied to the dataset from the UCI repository. WEKA (“Waikato Environment for Knowledge Analysis”) tool is used for machine learning techniques. In this paper Principal Component Analysis (PCA) is used for feature extraction. Different Machine Learning classification algorithms are applied through WEKA such as Glmnet, Gbm, ada Boosting, Adabag Boosting, C50, Cforest, DcSVM, fnn, Ksvm, Node Harvest compares the accuracy and also compare values such as Kappa statistic, Mean Absolute Error (MAE), Root Mean Square Error (RMSE). Here the 10-fold cross validation method is used for training, testing and validation purposes.

IoT Based Automation and Blockchain for Medical Drug Storage and Smart Drug Store

The increase in the work stress and decrease in the time for oneself has led to the rise in the dependency on the medicines and drugs. The drugs and medicines are the key sources for saving the human life when the patient is in the danger. In order to maintain regular and quality supply of the drugs and medicines has to monitor on the regular basis. There are numerous medicines and drugs brought in the store but usually drugs and medicines are stolen to satisfy one’s greed, get expired or placed at unknown locations in the store. So to prevent such situation and saving the life of the patient Drug and Medicine Monitoring Model can be used. The model uses the RFID and IoT technology in order to monitor the drugs and medicines in the store. In medical and drug using systems which are increasing work stress and decreasing the time for oneself that has risen in dependency. The danger situation drugs and medicine is the main source for saving human life when the people are in danger. A daily regular basis to maintain a quality supply of the drug and medicine has been monitored. While traveling and transportation time is numerous medicines and drugs brought from the store but usually it is stolen to one’s greed and the medicines and drugs or placed at unknown locations. To prevent and save a patent life and monitoring model can be used to check the medicine and drug. In our model RFID tag and IoT technology can be used to monitor medicine and drug storage with the help of hospitals and how having a knowledge of the system and chemist of the medical and drugs available, the medicines and drugs quality of location and their safety.