Browsing by Author "Dr. Riasat Khan"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Open Access
    Arduino Based Apartment Security System with Automation
    (North South University, 2020) Faysal Ahmed; Md. Mozammel Hossain Fahim; Manjida Islam Mohona; Sadia Awal Alo; Kanij Fatema; Dr. Riasat Khan; 1620491042; 1611685042; 1611328042; 1612155042; 1610161042
    One of the most prominent things in the home security solutions is IOT(Internet of things)that can handle layered security based on any advanced algorithm. But most of them lack proper management issues besides backups and volatile issues. Beside those it has cost efficiency issues. In fact most of them can have much needed features like home automation, portability and command operations. This papers aims to provide a high quality and reliable home security that supports home automation, portability, data records, backups, data encryption and IOT. It has introduces friendly home operating system is a single master device that handles other slave devices. Portability and flexibility is the beauty besides the security layers is strength of the device. The device's price range was kept to a minimum level to make it easier for home implementation alongside providing a quality security.
  • Thumbnail Image
    Item
    Open Access
    Artificial Intelligence Smart Mirror withRaspberryPiBased on Object Detection, HumanActivityRecognition, and Emotion Detection
    (North South University, 2021) Mst. Ayesha Siddika; Aminul Islam Joy; Md Salekur Rahaman; Ania Chowdhury; Dr. Riasat Khan; 1712935042; 1711867642; 1713018042; 1721495042
    In recent years, the smart home and advanced gadgets have been a common topic. Because of theories of powerful smart gadgets, the development of these fields is increasing. Smart mirrors area recent addition to the smart home family that has recently received much interest from people. In this work, we developed an artificial intelligence- based smart mirror to minimize people’s workload and make life easier. We build a smart mirror that includes artificial intelligence. This paper describes how we can use low-cost hardware like Raspberry Pi to make a smart home. Using some default modules, this mirror can display various features that we use daily, such a clock, live news, weather, and many more. It can not only detect its user but also can detect intruder and alert the house owner. Hence, it contributes to the house’s safety. Users canals control the magic mirror and update information on the Android application. It can also identify user’s emotion through his facial movement and it also provides 75%accuracy on emotion detection. This mirror also has the ability to detect some objects as well.
  • Thumbnail Image
    Item
    Open Access
    Computer Vision-based Robotic Arm Using Pixy Cam
    (North-south University, 2021-04-30) Anika Nawer Eva; Tabassum Binth Yeahyea; Md. Abdullah-Al-Noman; Dr. Riasat Khan; 1611688042; 1530438042; 1610593042
    Many facets of human existence have been influenced by robotics. Industry activities have become more automated, increasing efficiency while lowering the time and human labor. With time, electronic technology has advanced. The objective is to make the robots as human-like as possible. In challenging situations, humans are unlikely to act successfully. In this work, robots will be used to perform a comparable job in a far more efficient manner. This research has built a robotic gripper that can select and arrange objects to complete tasks. This study utilizes the picture acquisition methodology to distinguish picked and placed objects according to the object’s color and also calculated the distance from the center of the arm. It can also detect the geometrical shape of an object. The robotic arm detects the object by its color, then preprogrammed command is generated in the robotic arm to pick the object, after picking up the object the arm releases the object according to its color behind the fixed positions of the robotic arm, then the arm comes back to its initial coordinate of the position. The pixy cam helps to load an image to detect the geometrical shape. It also detects the size of an area of the different geometrical shapes in the compare method.
  • Thumbnail Image
    Item
    Open Access
    Detection of Fake News using different Machine Learning and Natural Language Processing Algorithms
    (North South University, 2021-08-30) Md. Emanul Haque Rafi; Noshin Nirvana Prachi; Evan Alam; Md. Habibullah; Dr. Riasat Khan; 1611149042; 1610394042; 1632230642; 1712220642
    The amount of information shared on the internet, primarily via web-based networking media, grows day by day. Because of the simple availability and exponential expansion of data through social media networks, distinguishing between fake and real information. Most smartphone users tend to read news on social media rather than on the internet. The information published on news websites often needs to authenticate. The simple spread of reports by way of sharing has included the exponential development of its misrepresentation. So, fake news has been a major issue ever since the web developed and expanded it to the general mass. This paper demonstrates several models and techniques for detecting false news by using different machine learning and natural language processing (NLP) models such as Logistic Regression, Decision Tree, Naïve Bayes, Support Vector Machine (SVM), Long Short-Term Memory (LSTM), Bidirectional Encoder Representation from Transformers (BERT). We tried to combine the news, then find out if the information was authentic or fake. Various feature engineering methods such as Regex, Tokenization, stop words, Lemmatization, Term Frequency- Inverse Document Frequency (TF-IDF) generate feature vectors in this paper. Every Machine Learning and NLP model was evaluated with test data. For the machine learning model Logistic Regression, Decision Tree, Naïve Bayes, and SVM, we got 73.75%, 89.66%, 74.19%, and 76.65%, respectively. But the highest accuracy we git is for the NLP method, which is 95% for LSTM and 98% for the BERT language model.