Agnieszka Laskowska
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Agnieszka Laskowska has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Jan Laskowski
Faculty of Management, Lublin University of Technology, 38D Nadbystrzycka Str., 20-618 Lublin, Poland
6 shared publications - Paweł Tomiło
Faculty of Management, Lublin University of Technology, 20-618 Lublin, Poland
3 shared publications - Edward Kozłowski
Faculty of Management, Lublin University of Technology, 38D Nadbystrzycka Str., 20-618 Lublin, Poland
2 shared publications - Artur Dmowski
WSEI University, Projektowa 4, 20-618 Lublin, Poland
1 shared publication - Artūras Kilikevičius
Institute of Mechanical Science, Faculty of Mechanics, Vilnius Gediminas Technical University, LT-10105 Vilnius, Lithuania
1 shared publication - Ernest Gnapowski
Faculty of Mathematics and Information Technology, Lublin University of Technology, 20-618 Lublin, Poland
1 shared publication
Latest Publications
- Open Access
Does Lower Precision Always Save Energy? Benchmarking Energy–Performance Trade-Offs in Weight-Quantized Large Language Model Inference on a GPU
Large language model (LLM) inference is an increasing component of AI energy demand, while the energy effects of weight quantization depend on workload phase and implementation. We benchmarked four LLM families—Gemma 4 E4B IT, Qwen3.5 4B, Nemotron 3 Nano 4B, and Ministral 3 3B Instruct—across Q4_K_M, Q6_K, Q8_0, and BF16 weight representations on a single NVIDIA GeForce RTX 4090 using llama.cpp/CUDA. Five workloads separated prefill from autoregressive generation, and GPU energy was estimated from NVML telemetry. In PP-512, no statistically significant differences were detected under the employed measurement protocol; in PP-1024, precision affected total energy and mean GPU power. In all generation scenarios, model family, precision, and their interaction significantly affected the primary endpoints. Relative to BF16, Q4_K_M reduced dynamic energy per token by 63.6–85.7% and increased generation throughput by 85.2–160.2% across all four model families. Ministral 3 3B Instruct–Q4_K_M ranked first in TOPSIS, whereas Nemotron 3 Nano 4B–Q4_K_M required less GPU memory. Findings are limited to single-request execution on one RTX 4090/llama.cpp-CUDA stack; output quality was not assessed, and 50 ms NVML sampling limits interpretation of short prefill measurements.
Open AccessDoes Lower Precision Always Save Energy? Benchmarking Energy–Performance Trade-Offs in Weight-Quantized Large Language Model Inference on a GPU
Large language model (LLM) inference is an increasing component of AI energy demand, while the energy effects of weight quantization depend on workload phase and implementation. We benchmarked four LLM families—Gemma 4 E4B IT, Qwen3.5 4B, Nemotron 3 Nano 4B, and Ministral 3 3B Instruct—across Q4_K_M, Q6_K, Q8_0, and BF16 weight representations on a single NVIDIA GeForce RTX 4090 using llama.cpp/CUDA. Five workloads separated prefill from autoregressive generation, and GPU energy was estimated from NVML telemetry. In PP-512, no statistically significant differences were detected under the employed measurement protocol; in PP-1024, precision affected total energy and mean GPU power. In all generation scenarios, model family, precision, and their interaction significantly affected the primary endpoints. Relative to BF16, Q4_K_M reduced dynamic energy per token by 63.6–85.7% and increased generation throughput by 85.2–160.2% across all four model families. Ministral 3 3B Instruct–Q4_K_M ranked first in TOPSIS, whereas Nemotron 3 Nano 4B–Q4_K_M required less GPU memory. Findings are limited to single-request execution on one RTX 4090/llama.cpp-CUDA stack; output quality was not assessed, and 50 ms NVML sampling limits interpretation of short prefill measurements.
- Open Access
- 3 November 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (21) , 10027
Accelerometer-Based Pavement Classification for Vehicle Dynamics Analysis Using Neural Networks
This research examines the influence of various pavement types on vehicle dynamics, specifically concentrating on vertical acceleration and its implications for unsprung mass, including the wheels and suspension system. The objective of this project was to categorize pavement types with accelerometer data, enabling a deeper comprehension of the impact of road surface conditions on vehicle stability, comfort, and mechanical stress. Two categorization methods were utilized: a neural network and a multinomial logistic regression model. Accelerometer data were gathered while a car navigated diverse terrain types, such as grates, potholes, and cobblestones. The neural network model exhibited exceptional performance, with 100% accuracy in categorizing all surface types, while the multinomial logistic regression model reached 97.14% accuracy. The neural network demonstrated exceptional efficacy in differentiating intricate surface types such as potholes and grates, surpassing the logistic regression model which had difficulties with these surfaces. These results underscore the neural network’s effectiveness in the real-time categorization of road surfaces, enhancing the comprehension of vehicle dynamics influenced by pavement conditions. Future studies must tackle the difficulty of identifying analogous surfaces by enhancing methodologies or integrating more data attributes for greater precision.
- 3 November 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (21) , 10027
Open AccessAccelerometer-Based Pavement Classification for Vehicle Dynamics Analysis Using Neural Networks
This research examines the influence of various pavement types on vehicle dynamics, specifically concentrating on vertical acceleration and its implications for unsprung mass, including the wheels and suspension system. The objective of this project was to categorize pavement types with accelerometer data, enabling a deeper comprehension of the impact of road surface conditions on vehicle stability, comfort, and mechanical stress. Two categorization methods were utilized: a neural network and a multinomial logistic regression model. Accelerometer data were gathered while a car navigated diverse terrain types, such as grates, potholes, and cobblestones. The neural network model exhibited exceptional performance, with 100% accuracy in categorizing all surface types, while the multinomial logistic regression model reached 97.14% accuracy. The neural network demonstrated exceptional efficacy in differentiating intricate surface types such as potholes and grates, surpassing the logistic regression model which had difficulties with these surfaces. These results underscore the neural network’s effectiveness in the real-time categorization of road surfaces, enhancing the comprehension of vehicle dynamics influenced by pavement conditions. Future studies must tackle the difficulty of identifying analogous surfaces by enhancing methodologies or integrating more data attributes for greater precision.
- Open Access
Effect of Architecture and Inference Parameters of Artificial Neural Network Models in the Detection Task on Energy Demand
Artificial neural network models for the task of detection are used in many fields and find various applications. Models of this kind require adequate computational resources and thus require adequate energy expenditure. The increase in the number of parameters, the complexity of architectures, and the need to process large data sets significantly increase energy consumption, which is becoming a key sustainability challenge. Optimization of computing and the development of energy-efficient hardware technologies are essential to reduce the energy footprint of these models. This article examines the effect of the type of model, as well as its parameters, on energy consumption during inference. For this purpose, sensors built into the graphics card were used, and software was developed to measure the energy demand of the graphics card for different architectures of YOLO models (v8, v9, v10), as well as for different batch and model sizes. This study showed that the increase in energy demand is not linearly dependent on batch size. After a certain level of batch size, the energy demand begins to decrease. This dependence does not occur only for n/t size models. Optimum utilization of computing power due to the number of processed images for the studied models occurs at the maximum studied batch size. In addition, tests were conducted on an embedded device.
Open AccessEffect of Architecture and Inference Parameters of Artificial Neural Network Models in the Detection Task on Energy Demand
Artificial neural network models for the task of detection are used in many fields and find various applications. Models of this kind require adequate computational resources and thus require adequate energy expenditure. The increase in the number of parameters, the complexity of architectures, and the need to process large data sets significantly increase energy consumption, which is becoming a key sustainability challenge. Optimization of computing and the development of energy-efficient hardware technologies are essential to reduce the energy footprint of these models. This article examines the effect of the type of model, as well as its parameters, on energy consumption during inference. For this purpose, sensors built into the graphics card were used, and software was developed to measure the energy demand of the graphics card for different architectures of YOLO models (v8, v9, v10), as well as for different batch and model sizes. This study showed that the increase in energy demand is not linearly dependent on batch size. After a certain level of batch size, the energy demand begins to decrease. This dependence does not occur only for n/t size models. Optimum utilization of computing power due to the number of processed images for the studied models occurs at the maximum studied batch size. In addition, tests were conducted on an embedded device.
- Open Access
- 18 December 2023
- Published by Akademia Nauk Stosowanych WSGE im. A. De Gasperi w Józefowie in Journal of Modern Science
- Vol. 54 (5) , 395-409
Economic issue of material reserves management taking into account probabilistic model
Objectives: Running a business effectively requires ensuring continuity and regularity of the activity. For this purpose, it is important to effectively and rationally manage inventories and maintain them at various levels of optimality. Material and methods: In the paper a design of the...
- 18 December 2023
- Published by Akademia Nauk Stosowanych WSGE im. A. De Gasperi w Józefowie in Journal of Modern Science
- Vol. 54 (5) , 395-409
Open AccessEconomic issue of material reserves management taking into account probabilistic model
Objectives: Running a business effectively requires ensuring continuity and regularity of the activity. For this purpose, it is important to effectively and rationally manage inventories and maintain them at various levels of optimality. Material and methods: In the paper a design of the...
- Open Access
- 7 February 2023
- Published by MDPI AG in Sustainability
- Vol. 15 (4) , 3019
Creating Agile Institutions with Organizational Trust in the Finance Sector of Turkey: The Mediating Role of Psychological Empowerment in Times of COVID-19
The study aims to evaluate the way for creating agile institutions with organizational trust. Besides that, the understanding of the mediating role played by psychological empowerment during COVID-19 pandemic is one of the major objectives of this study. The way psychological empowerment affects the creation of agile organizations is another major aspect that the study investigated. The philosophical stance that the research has adopted is the positivism philosophy. The study was done by collecting and analyzing quantitative data. The approach for the study is deductive whereas the design of the research is descriptive. The study used a survey method for collecting information. Structural equation model was used for analyzing quantitative information. The study was done on 325 samples who are working at the finance sector of Turkey. All the samples have a residence in Turkey. It was identified that the leadership approach of a company has a huge impact on the psychological construction of the samples. Descriptive statistics and t-test for inferential statistics were done by the researchers. There is a strong positive relationship between the centricity of the organization towards the workforce or customer and employee performance. It was identified that the leadership approach helps employees to address and adopt the change in the marketplace. It was also found that an agile organizational structure has more possibilities to modify the processing based on the change in the marketplace. The structural equation model was used to represent the relationship between the variables.
- 7 February 2023
- Published by MDPI AG in Sustainability
- Vol. 15 (4) , 3019
Open AccessCreating Agile Institutions with Organizational Trust in the Finance Sector of Turkey: The Mediating Role of Psychological Empowerment in Times of COVID-19
The study aims to evaluate the way for creating agile institutions with organizational trust. Besides that, the understanding of the mediating role played by psychological empowerment during COVID-19 pandemic is one of the major objectives of this study. The way psychological empowerment affects the creation of agile organizations is another major aspect that the study investigated. The philosophical stance that the research has adopted is the positivism philosophy. The study was done by collecting and analyzing quantitative data. The approach for the study is deductive whereas the design of the research is descriptive. The study used a survey method for collecting information. Structural equation model was used for analyzing quantitative information. The study was done on 325 samples who are working at the finance sector of Turkey. All the samples have a residence in Turkey. It was identified that the leadership approach of a company has a huge impact on the psychological construction of the samples. Descriptive statistics and t-test for inferential statistics were done by the researchers. There is a strong positive relationship between the centricity of the organization towards the workforce or customer and employee performance. It was identified that the leadership approach helps employees to address and adopt the change in the marketplace. It was also found that an agile organizational structure has more possibilities to modify the processing based on the change in the marketplace. The structural equation model was used to represent the relationship between the variables.
- Open Access
- 22 December 2022
- Published by MDPI AG in Sustainability
- Vol. 15 (1) , 194
“Silver” Generation at Work—Implications for Sustainable Human Capital Management in the Industry 5.0 Era
The demographic low, and thus the inevitable aging of the populations of economically developed countries, makes it necessary to extend the working life of citizens. Therefore, an increasing percentage of workers are representatives of the so-called “silver” generation, i.e., people over 50 years of age. The main objective of the study is to characterize the system of values, attitudes to work, and related expectations of professionally active women and men over 50 years of age and to determine whether, and if so, how the hierarchy of values, attitudes to work, and job satisfaction affect the further development of their professional careers. In order to achieve such a goal, a CAVI survey was conducted on a sample of n = 600 respondents. The statistical significance of the differences between the groups was tested with the Mann–Whitney U test. To verify the main hypothesis, ordinal logistic regression models were built. The results of the study were supplemented with elements of descriptive statistics. In the course of the research work, it was confirmed that there are significant differences between the studied men and women in the assessment of traits concerning their value hierarchy, attitudes towards work, and career prospects. Traits such as value hierarchy and attitudes toward work have a significant impact on the career development of both women and men of the “silver” generation, while job satisfaction shows a significant impact on career development only for women.
- 22 December 2022
- Published by MDPI AG in Sustainability
- Vol. 15 (1) , 194
Open Access“Silver” Generation at Work—Implications for Sustainable Human Capital Management in the Industry 5.0 Era
The demographic low, and thus the inevitable aging of the populations of economically developed countries, makes it necessary to extend the working life of citizens. Therefore, an increasing percentage of workers are representatives of the so-called “silver” generation, i.e., people over 50 years of age. The main objective of the study is to characterize the system of values, attitudes to work, and related expectations of professionally active women and men over 50 years of age and to determine whether, and if so, how the hierarchy of values, attitudes to work, and job satisfaction affect the further development of their professional careers. In order to achieve such a goal, a CAVI survey was conducted on a sample of n = 600 respondents. The statistical significance of the differences between the groups was tested with the Mann–Whitney U test. To verify the main hypothesis, ordinal logistic regression models were built. The results of the study were supplemented with elements of descriptive statistics. In the course of the research work, it was confirmed that there are significant differences between the studied men and women in the assessment of traits concerning their value hierarchy, attitudes towards work, and career prospects. Traits such as value hierarchy and attitudes toward work have a significant impact on the career development of both women and men of the “silver” generation, while job satisfaction shows a significant impact on career development only for women.
- Open Access
- 1 June 2021
- Published by ISMA SYC INT in EUROPEAN RESEARCH STUDIES JOURNAL
- Vol. XXIV (Special 2) , 666-680
Towards a Secure Economic Growth: Development of a Common European Union Counter-Terrorism Policy
- 1 June 2021
- Published by ISMA SYC INT in EUROPEAN RESEARCH STUDIES JOURNAL
- Vol. XXIV (Special 2) , 666-680
Open AccessTowards a Secure Economic Growth: Development of a Common European Union Counter-Terrorism Policy