DSpace Home
→
Epoka University
→
Thesis
→
Master
→
Computer Engineering
→
Recent submissions

Computer Engineering: Recent submissions

Now showing items 81-100 of 113

DEEP LEARNING DRIVEN SENTIMENT ANALYSIS OF E-COMMERCE CONSUMER IMPRESSIONS USING ADVANCED FETURE EXTRACTION TECHNIQUES

Proda, Marjela (2024-06-06)

E-commerce has emerged as one of the biggest players in the current digitized business environment, and this has led to the creation of large amounts of consumer data through consumer reviews and feedback. The objective ...
EVALUATING THE EFFECT OF BIOMATERIALS ONTO A549 CELL USING DEEP LEARNING

Alushllari, Griselda (2024-06-26)

This study investigates the performance of 28 different UNet models for segmenting and determining cell confluence in brightfield microscopy images, combining various hyperparameters such as loss functions, batch sizes, ...
INVESTIGATING THE IMPACT OF DEGREE OF FREEDOM ON IRIS RECOGNITION ACCURACY: A COMPARATIVE ANALYSIS OF TRADITIONAL ALGORITHMS AND DEEP LEARNING TECHNIQUE

Mano, Petrika (2024-06-26)

Biometric identification relies heavily on iris recognition systems because of their high accuracy and dependability. In order to better understand how the degree of freedom affects iris recognition accuracy, this study ...
DEVELOPING AND IMPLEMENTING INTO PRACTICE AN ENVIRONMENTAL MONITORING STATION WITH AN ARDUINO PRO MINI

Themeli, Nasho (2024-06-28)

This study focuses on the development and practical implementation of an environmental monitoring station utilizing the Arduino Pro Mini microcontroller. The station is designed to measure and record various air quality ...
ADVANCED SIGNAL PROCESSING FOR ENHANCED MULTIMEDIA COMPRESSION AND TRANSMISSION

Oruci, Ersi (2024-06-25)

The relentless growth of multimedia content in electronic and telecommunication networks has fueled the demand for efficient image and video compression techniques. This research delves into the realm of signal processing, ...
QUANTITATIVE ANALYSIS OF THP1 CELL CONFLUENCY AND PROLIFERATION UNDER TEMPORAL AND PHARMACOLOGICAL CONDITIONS USING DEEP LEARNING TECHNIQUES

Xhepi, Alban (2024-06-26)

The proliferation and behavior of THP1 cells, a human monocytic cell line, are critical in understanding various biomedical and pharmaceutical applications. This thesis presents a comprehensive analysis of THP1 cell ...
PREDICITING CUSTOMER CHURN IN TELECOMUNICATIONS COMPANY

Veisllari, Lutfie (2024-06-28)

Customer churn is one of the most critical issues in telecom companies. As it directly affects the company’s revenue, arises the need of finding ways to predict and then prevent this kind of phenomen. Machine learning can ...
ATTACKING SYSTEMS AND DEFENSE POLICIES IN DEPTH IN LINUX VIRTUAL MACHINE ON SCADA SYSTEMS

Dakoli, Bashkim (2024-06-25)

This thesis explores the vulnerabilities and defense mechanisms of Supervisory Control and Data Acquisition (SCADA) systems. It is consolidated with a focus on Linux virtual machine environments. SCADA systems are critical ...
AUGMENTED REALITY – ENHANCED CILTURAL HETIRTAGE PRESERVATION USING POINT – CLOUD DATA

Qose, Endi (2024-06-25)

In today’s world there is a growing urgency to protect artifacts and important landmarks due, to environmental factors and human activities. As a result, experts and conservationists are reevaluating their methods realizing ...
ADVANCEMENTS IN DISEASE DETECTION THROUGH NEURAL NETWORKS IN MEDICAL IMAGE ANALYSIS

Tafa, Bora (2024-06-28)

The use of neural networks, specifically convolutional neural networks (CNNs), in medical image processing has resulted in substantial breakthroughs in illness identification. This study digs into the use of neural ...
MORPHOLOGIC ANALYSIS OF BRAIN TUMOR TO PERFORM SURVIVAL PREDICTION WITH A FOCUS ON ECCENTRICITY WITH SINGULAR VALUE DECOMPOSITION

Nako, Megi (2024-06-26)

Advancments in imaging field have evolved enough to make the detection of tumor task more accurate through 3D MRI but at the same time more time consuming and complex for medical experts. Therefore, the need for a ...
IMPLEMENTING A CRYPTOGRAPHY ALGORITHM USING RUBIK'S CUBE FOR SECURITY ON IOT DEVICES

Papa, Tea (2024-07-25)

Because more companies and individuals were transferring data to the cloud as a result of the COVID epidemic, the significance of online communication has grown dramatically. We all depend on the net to transfer data ...
COMPARISON OF DEEP LEARNING ALGORITHMS FOR LEUKEMIA CANCER CELL CLASSIFICATION

Bushi, Gerta (2024-06-28)

Leukemia is a cancer-related disease which causes the death of individuals worldwide, regardless of age and gender. It affects the blood and bone marrow, thus leading to the abnormal production of immature white blood ...
BREAST CANCER DETECTION USING DEEP LEARNING

Mucaraku, Laura (2024-06-27)

In nearly 95% of the countries worldwide, breast cancer is the main reason of female deaths. The impact that this disease has on human body, depends on the stage in whichit is diagnosed, being a life-taking disease if not ...
PANDEMIC WITHIN A PANDEMIC: THE DOMINANCE OF CYBER THREATS OVER COVID-19

Vrapi, Orges (2024-06-25)

The COVID-19 pandemic not only caused disruptions in global health and economics but also intensified weaknesses in cyberspace, resulting in a significant increase in cyber threats. This article examines the convergence ...
COMPARISON OF DIFFERENT YOLO ARCHITECTURES IN MICROSCOPIC CELL COUNTING USING CONVOLUTIONAL NEURAL NETWORKS

Tujani, Alba (2023-03-10)

As automation continues to advance rapidly, cell detection and counting plays a significant, crucial role in medical image processing’s automatic analysis. Accurately detecting and locating cells seems to be an extremely ...
DESIGN AND IMPLEMENTATION OF A CHATBOT FOR CUSTOMER SUPPORT

Bilali, Marvin (2023-03-11)

The number of companies encouraging use of chatbots as a substitute source for customer service is increasing more and more. Users must have confidence in chatbots giving them the assistance they need. But the confidence ...
PREDICTION OF STOCK MARKET USING LSTM NEURAL NETWORKS

Hoxha, Ernit (2023-03-09)

This thesis explores the use of neural networks and Long Short-Term Memory (LSTM) techniques for stock prediction. The focus is on understanding the potential of these techniques in forecasting stock prices by analyzing ...
PERFORMANCE TESTING OF COVID-19 IMAGE CLASSIFICATION USING DIFFERENT MACHINE LEARNING ARCHITECTURES

Smoqi, Enriko (2023-03-09)

The outbreak of the Covid-19 pandemic brought the need for research in this field to assist in diagnosing patients more accurately and with more speed than is possible using just human resources. Deep Learning and especially ...
SENTIMENT ANALYSIS IN TWITTER USING ORANGE

Nuriu, Rei (2023-02-10)

In this thesis the fundamentals of Natural Language Processing (NLP) will be presented. All the methods that I have tested are performed in a platform called Orange which is going to be explained throughout the thesis. The ...

Recently added

DSpace Repository

Computer Engineering: Recent submissions

Search DSpace

Browse

All of DSpace

This Collection

My Account