SECTION OF COMPUTERS, INFORMATICS AND MICROELECTRONICS https://repository.utm.md/handle/5014/27837 2026-04-12T03:44:54Z 2026-04-12T03:44:54Z KONJEVIC, Alexandra AFTENI, Maria BAJENOV, Sevastian TELUG, Anatolie https://repository.utm.md/handle/5014/28266 2024-10-23T09:52:35Z 2024-01-01T00:00:00Z

Development of a Delta robot for sorting items in industrial conditions KONJEVIC, Alexandra; AFTENI, Maria; BAJENOV, Sevastian; TELUG, Anatolie This article was created as part of a Problem Based Learning (PBL) project in which we investigated delta robots, CNC machines and embedded systems. In response to the imperatives of Industry 4.0, this research introduces "DeltaSort", a delta robot system poised to revolutionize agricultural sorting processes. Through the integration of advanced gripping mechanisms and artificial intelligence-driven object recognition, DeltaSort meticulously assesses and categorizes harvested fruits and vegetables, ensuring judicious force application for gentle handling and precise sorting. Beyond the confines of agriculture, the system presents a plethora of advantages, encompassing heightened productivity, superior precision, elevated safety standards, increased production speeds, and non-stop operational capability, rendering it an instrumental solution in contemporary automated processes.

2024-01-01T00:00:00Z BARBAROV, Nadejda GARBUZ, Nelli LATCOVSCHI, Cătălin ISTRATI, Daniel https://repository.utm.md/handle/5014/28265 2024-10-23T09:08:35Z 2024-01-01T00:00:00Z

Domain specific language for email automation BARBAROV, Nadejda; GARBUZ, Nelli; LATCOVSCHI, Cătălin; ISTRATI, Daniel The purpose of this article is to explain how a domain-specific language may be useful in marketing. The benefits of using a domain-specific language in email automation are examined in the article, including increased precision, quicker processing times, reduced error rates, etc. DSL-based automation improves the client experience and makes the workflow more seamless. The DSL's functionality, grammatical characteristics, and other details are covered in the article along with the processes that were used to design it. By focusing on key components such as campaign management, personalization, automation, integration, and analytics, this new language equips users with the tools and capabilities they need to elevate their email marketing efforts in an increasingly digital world. The abstract syntax tree was created using a formal grammar as its foundation. The ANTLR 4 parser generator is used as the front-end for the DSL built as explained in this article. Python is used to implement the back end.

2024-01-01T00:00:00Z LUPAN, Lucian MIHALACHI, Mihail NEJINȚEV, Nicolai CUCOȘ, Maria FRUNZA, Valeria https://repository.utm.md/handle/5014/28264 2024-10-23T08:59:24Z 2024-01-01T00:00:00Z

DSL for ai projects architecture LUPAN, Lucian; MIHALACHI, Mihail; NEJINȚEV, Nicolai; CUCOȘ, Maria; FRUNZA, Valeria This paper addresses the complexity of Artificial Intelligent (AI) system design and deployment by advocating for a Domain-Specific Language (DSL) specifically designed for AI projects architecture. This research clarifies the possible advantages and difficulties of implementing a DSL for AI projects through creating an opportunity for organizations to stimulate innovation, shorten development cycles, and take advantage of the growing opportunities in the AI landscape by adopting a DSL designed specifically for AI.

2024-01-01T00:00:00Z PETRANIS, Ana VINOGRADSCHII, Mihail https://repository.utm.md/handle/5014/28262 2024-10-23T08:50:42Z 2024-01-01T00:00:00Z

Enhancing sports performance analysis: an ai approach for basketball and volleyball PETRANIS, Ana; VINOGRADSCHII, Mihail Artificial intelligence is increasingly being used in all areas of human activity, from the familiar text editor to the cutting-edge satellite that has just entered Earth's orbit. Modern team sports also need to implement AI to analyze the results of matches, in order to identify the strengths and weaknesses of each player, as well as to develop a right strategy for subsequent games against a specific opponent. Our study investigates the process of data collection and processing for sports analytics using basketball and volleyball games as examples. Data for analysis was sourced from the official FIBA YouTube channel "FIBA - The Basketball Channel" and the Baller TV replay library, which archives matches from various youth sports. The obtained videos were segmented into individual frames. A portion of these frames were manually labeled to create training and validation datasets. The remaining frames formed the unlabeled test dataset, crucial for evaluating the accuracy of the YOLOv8 model chosen as the foundation for this study. Our focus was on identifying players through jersey number recognition, detecting the ball and its location on the court, classifying game situations, and processing the score and timer using OCR technology. The fine-tuned YOLOv8 achieved an accuracy of 93% based on the mAP50-95 metric, which evaluates the overlap between predicted and actual bounding boxes.

2024-01-01T00:00:00Z