TULTECH Journals
Not a member yet
235 research outputs found
Sort by
Calculation and Simulation of Vehicle Steering Dynamics
No full textThis paper presents fundamental mathematical estimations of vehicle sideslip in stationary conditions regarding the influences of the vehicle parameters such as the tire stiffness, position of gravity centre, vehicle speed and the turning radius. The vehicle dynamics on steady state and transient responses are also investigated to see the effects of the yaw natural frequency and yaw damping rate on the steering system. Results from this study can be used in designing an automatic control of tracking vehicle in the future
Solving the Bottleneck Issue of Energy Supply. Case Study of a Wind Power Plant
No full textThis paper addresses the current need for increased renewable energy capacity in the southern region of Albania near the tourist destination of Vlora. The northern half of the country is burdened with supplying the electrical needs of the country, while the southern region is using the electricity at high rates during summer months. Freely available wind energy resources, along with a wind siting study of the country which has already been performed, are used to locate, and analyze potential wind farm sites near Vlora. Less than 40 km southeast of Vlora a site is identified, and a techno-economic assessment and site performance simulation is performed using RETScreen wind energy software. The results show that this site is feasible, and a windfarm is proposed which is capable of exporting 243.4 GWh to southern Albania’s electrical grid yearly. With a short equity payback period of 5.6 years and simple payback of 9.7 years, this location could deliver substantial amounts of energy where it is needed, without worry of transmission losses over large distances
Cyberbullying Detection on Twitter Using Natural Language Processing and Machine Learning Techniques
No full textPeople use social media to engage and debate themes ranging from entertainment to sports to politics and many others. The use of social media has also resulted in an increase in cyberbullying, which is occurring at an alarming pace. Many cyberbullying messages may be found in the comment sections of many social media platforms, including Twitter, YouTube, and others. Cyberbullying has the ability to cause stress and mental distress, which should be detected early and avoid being published on social media platforms. In this study, we provide a system for detecting cyberbullying messages in English using natural language processing (NLP) and machine learning approaches. On Twitter, a total of 16851 tweets were gathered. The dataset was applied to an NLP approach to find the most offensive terms associated with cyberbullying. Based on our NLP results, it was clear that cyberbullying happens and must be addressed as soon as possible. The dataset was also utilized to train the random forest (RF) and support vector machine (SVM) algorithms. Random forest surpassed support vector machine, which attained an accuracy of 90.5%, with 98.5%. With careful attention to data preparation, where missing and outlier values are dealt beforehand, the high percentage of the model is obtained. This method facilitates the analysis of the available data at the expense of the study\u27s statistical power and ultimately the validity of its findings. Additionally, it aids in producing a significant bias in the outcomes and increases the effectiveness of the data. The Root mean square error and mean square error were used to analyse the results. In comparison to the support vector machine, the random forest earned the best error score. Our findings may be utilized by agencies and groups to educate individuals about the proper use of social media in order to avoid cyberbullying
Albanian’s Fish Skin, Sustainability and Circular Economy
No full textLeather from fish skins is by no means a new product for Albania. Regularly, this raw material goes unused and is dumped back into the sea, therefore it is wasted. Worldwide with changing consumer tastes, the circular economic practices, and sustainable sourcing, fish skin is a strong candidate to become an industry-shifting material. This is as well the best, most efficient technique to bring sustainability to the leather industry in the country and transform it into a cleaner and more circular sector. The aim of this research is to study the Albanian’s fish skin by using traditional tanning techniques to find alternate, sustainable techniques of making leather. The physico-mechanical properties of Albanian fish skins, were determined, where all fish leathers showed adequate physical strength to be used in the manufacture of leather goods such as clothing, footwear, wallets, and many other products
A Ride Sharing System for University Community
No full textIn Ghana, vehicular transportation is the commonest and widely used means of mobility which contributes a significant amount to economic development. Despite these benefits, there are however numerous challenges commuters experience such as queuing, communication difficulties, missing of destinations among others. Private individuals who use their own cars equally encounter high fuelling cost, traffic congestion and other related problems. In this paper, an online ride sharing and booking system is proposed to enable owners of private cars to offer empty seats to other users. This proposed system design was tested in a campus environment to ascertain its feasibility in densely populated areas. The online booking system which is mobile, and web-based software application proved very efficient for user registration, travel advertisement, booking, geo-location and routing, online payment systems as well as notification systems to handle all necessary aspects of the entire booking and ride sharing system. Thus, this system substantially eliminates the problems faced by both drivers and passenger and help reduce carbon emissions
On Social Media Addiction and Negative Effects in Southeast European University Students During the COVID-19 Pandemic
No full textStudents of Southeast European University in distance learning during the COVID-19 pandemic had few opportunities to socialize in person, resulting in a significant rise in the use of smartphones and technology. For educational purposes the use of smartphones generally represented an alternative and turned to be useful but, however excessive use may promote addictive tendencies towards social media use, and at the same time with negative consequences for students’ psychological health. Furthermore, with this study, we examined the occurrence of smartphone and social media application use in first year students in distance education at Southeast European University during COVID-19 pandemic. Respectively, we investigate the impact of different social media applications on self- described tendencies toward social media addiction Respectively, the prevalence of smartphone and social media application use and its relative impact of different social media applications was based on self-reported tendencies by students toward social media addiction. I have interviewed 95 students of both genders who spoke on the use of the smartphone and social media applications, specifically WhatsApp, Facebook, Twitter, TikTok, Instagram, Snapchat, Telegram, Messenger, and YouTube. The whole research was administered during the second wave of the COVID-19 pandemic. Differences in social media addiction with different patterns of social media use were investigated. On average students using WhatsApp and Viber reported the lowest social media addiction compared with students using Facebook and TikTok. In general, we found time spent on smartphone using Facebook
Smart Mechatronic Elbow Brace using EMG Sensors
No full textMajority of injuries are involved in damages of elbow and the recovery therapy period may take up to 12-24 months in health care centres. Therefore, it is needed to supply a smart mechatronic brace for patients who cannot come to health care centres, can exercise their rehabilitation at home. This project designs and tests a smart mechatronic brace for home rehabilitation of elbow injured patients. The device is run by electromyography (EMG) sensors. Data from EMG sensors is processed, filtered, smoothed, and converted into pulse width modulation (PWM) to run the DC motor. The system is controlled by adaptive linear quadratic Gaussian (LQG) and Kalman filter (KF). The DC motor can track well the human motion with the error less than 5%. The system is relatively simple, reliable, safe, low cost and high accuracy
A Review of Missing Data Handling Techniques for Machine Learning
No full textReal-world data are commonly known to contain missing values, and consequently affect the performance of most machine learning algorithms adversely when employed on such datasets. Precisely, missing values are among the various challenges occurring in real-world data. Since the accuracy and efficiency of machine learning models depend on the quality of the data used, there is a need for data analysts and researchers working with data, to seek out some relevant techniques that can be used to handle these inescapable missing values. This paper reviews some state-of-art practices obtained in the literature for handling missing data problems for machine learning. It lists some evaluation metrics used in measuring the performance of these techniques. This study tries to put these techniques and evaluation metrics in clear terms, followed by some mathematical equations. Furthermore, some recommendations to consider when dealing with missing data handling techniques were provided
Weighted Trimean as a Regressor in the Estimate of Theil-Sen Regression
No full textThe most used method in nonparametric regression analysis is the Theil-Sen approach. With this method, all coefficient estimations are made with the median parameter as opposed to parametric methods. The most important criticism in computations with the median parameter is that the impact of extreme values does not participate in calculations. In this study, it was proposed to use the trimean parameter by weighting, which more effectively adds the effect of outliers to the average account in Theil-Sen regression analysis. In applications with 5 data sets, Theil-Sen calculations with weighted trimean were found to be more successful than calculations with the median parameter. Thus, in cases where the outliers are too high or directly affect the data, it can be said that the use of weighted trimean will yield more effective results
Interpreting Results of Band Maths Operations in Sentinel-2 Image
No full textMany studies have been done on environmental pollution of the Reps region regarding Acid Mine Drainage, but there are no studies with the help of remote sensing which is a science of collecting data without a physical contact. In this setting, the purpose of this research work is to monitor the environmental impact of the abandoned mines in water, vegetation and non-vegetation areas by exploring Sentinel-2 data in Reps regions. The information utilized in this paper has been developed from the program of European Space Agency Copernicus. After the selection of the Reps region it has been explored the products in the Sentinel Application Platform. According to our data, the incorporation of visual optical of flora, ground covering and humidity as well as computing Spectral Angle Mapper can help us in the early identification of Acid Mine Drainage. The combination of field studies with remote sensing increase the overall efficacy in detecting pollution and protecting the environment