| 1. |
- Kavathatzopoulos, Iordanis, 1956-
(författare)
-
Robots and systems as autonomous ethical agents
- 2010
-
Ingår i: INTECH 2010. - Bangkok : Assumption University. - 9789746151108 ; , s. 5-9
-
Konferensbidrag (refereegranskat)abstract
- IT systems and robots can help us to solve many problems caused by the quantity, variation and complexity of information; because we need to handle dangerous and risky situations; or because of our social and emotional needs like elderly care. In helping us, these systems have to make decisions and act accordingly to achieve the goals for which they were built. Ethical decision support tools can be integrated into robots and other decision making systems to secure that decisions are made according to the basic theories of philosophy and to the findings of psychological research. This can be done, in non-independent systems, as a way for the system to report to its operator, and to support the operator's ethical decision making. On the other hand, fully independent systems should be able to regulate their own decision making strategies and processes. However, this cannot be based on normative predefined criteria, or on the ability to make choices, or on having own control, or on ability of rational processing. It seems that it is necessary for an independent robot or decision system to have "emotions." That is, a kind of ultimate purposes that can lead the decision process, and depending on the circumstances, guide the adoption of a decision strategy, whatever it may be, rational, heuristic or automatic.
|
|
| 2. |
- Kavathatzopoulos, Iordanis, 1956-, et al.
(författare)
-
What are ethical agents and how can we make them work properly?
- 2011
-
Ingår i: The computational turn. - Münster : MV-Wissenschaft. - 9783869913551 ; , s. 151-153
-
Konferensbidrag (refereegranskat)abstract
- To support ethical decision making in autonomous agents, we suggest to implement decision tools based on classical philosophy and psychological research. As one possible avenue, we present EthXpert, which supports the process of structuring and assembling information about situations with possible moral implications.
|
|
| 3. |
- Chen, D., et al.
(författare)
-
Artificial intelligence enabled Digital Twins for training autonomous cars
- 2022
-
Ingår i: Internet of Things and Cyber-Physical Systems. - : KeAi Communications Co.. - 2667-3452. ; 2, s. 31-41
-
Tidskriftsartikel (refereegranskat)abstract
- This exploration is aimed at the system prediction and safety performance of the Digital Twins (DTs) of autonomous cars based on artificial intelligence technology, and the intelligent development of transportation in the smart city. On the one hand, considering the problem of safe driving of autonomous cars in intelligent transportation systems, it is essential to ensure the transmission safety of vehicle data and realize the load balancing scheduling of data transmission resources. On the other hand, convolution neural network (CNN) of the deep learning algorithm is adopted and improved, and then, the DTs technology is introduced. Finally, an autonomous cars DTs prediction model based on network load balancing and spatial-temporal graph convolution network is constructed. Moreover, through simulation, the performance of this model is analyzed from perspectives of Accuracy, Precision, Recall, and F1-score. The experimental results demonstrate that in comparative analysis, the accuracy of road network prediction of the model reported here is 92.70%, which is at least 2.92% higher than that of the models proposed by other scholars. Through the analysis of the security performance of network data transmission, it is found that this model achieves a lower average delay time than other comparative models. Besides, the message delivery rate is basically stable at 80%, and the message leakage rate is basically stable at about 10%. Therefore, the prediction model for autonomous cars constructed here not only ensures low delay but also has excellent network security performance, so that information can interact more efficiently. The research outcome can provide an experimental basis for intelligent development and safety performance improvement in the transportation field of smart cities. © 2022 The Authors
|
|
| 4. |
- Kavathatzopoulos, Iordanis, 1956-, et al.
(författare)
-
How ethical robots process information, communicate and act
- 2015
-
Ingår i: 1st TRANSOR Workshop.
-
Konferensbidrag (refereegranskat)abstract
- Robots can be of great help to obtain optimal solutions to problems in situations where humans have difficulties to perceive and process information, or make decisions and implement actions because of the quantity, variation and complexity of information. However, if they do not act in accordance to our ethical values they will not be used or will cause harm. Classical philosophical theory and psychological research on problem solving and decision making gives us a concrete definition of ethics and opens up the way for the construction of robots that can support handling of moral problems. Linguistic research focusing on language use as realization of meaning during the communication between humans and robots gives us the tools for investigating how particular linguistic features such as words and grammar may be related to ethical thinking. In such research work we can focus on three different kinds of robots: The first one is already programmed to act in certain ways, and the focus is on designers using ethical tools to identify moral problems and formulate solutions. The second is an integrated system which is also pre-programmed but also contains an ethical tool to gather information, to present it to the operators and to communicate with them. The third is trained autonomous systems in which we will implement automatic judgment. Such research will help us to clarify theoretical issues, to formulate working methods, and to develop technical solutions that will support ethical decision making of automated IT systems.
|
|
| 5. |
- Hallström, Erik, et al.
(författare)
-
Label-free deep learning-based species classification of bacteria imaged by phase-contrast microscopy
- 2023
-
Ingår i: PloS Computational Biology. - : Public Library of Science (PLoS). - 1553-734X .- 1553-7358. ; 19:11
-
Tidskriftsartikel (refereegranskat)abstract
- Reliable detection and classification of bacteria and other pathogens in the human body, animals, food, and water is crucial for improving and safeguarding public health. For instance, identifying the species and its antibiotic susceptibility is vital for effective bacterial infection treatment. Here we show that phase contrast time-lapse microscopy combined with deep learning is sufficient to classify four species of bacteria relevant to human health. The classification is performed on living bacteria and does not require fixation or staining, meaning that the bacterial species can be determined as the bacteria reproduce in a microfluidic device, enabling parallel determination of susceptibility to antibiotics. We assess the performance of convolutional neural networks and vision transformers, where the best model attained a class-average accuracy exceeding 98%. Our successful proof-of-principle results suggest that the methods should be challenged with data covering more species and clinically relevant isolates for future clinical use. Bacterial infections are a leading cause of premature death worldwide, and growing antibiotic resistance is making treatment increasingly challenging. To effectively treat a patient with a bacterial infection, it is essential to quickly detect and identify the bacterial species and determine its susceptibility to different antibiotics. Prompt and effective treatment is crucial for the patient's survival. A microfluidic device functions as a miniature "lab-on-chip" for manipulating and analyzing tiny amounts of fluids, such as blood or urine samples from patients. Microfluidic chips with chambers and channels have been designed for quickly testing bacterial susceptibility to different antibiotics by analyzing bacterial growth. Identifying bacterial species has previously relied on killing the bacteria and applying species-specific fluorescent probes. The purpose of the herein proposed species identification is to speed up decisions on treatment options by already in the first few imaging frames getting an idea of the bacterial species, without interfering with the ongoing antibiotics susceptibility testing. We introduce deep learning models as a fast and cost-effective method for identifying bacteria species. We envision this method being employed concurrently with antibiotic susceptibility tests in future applications, significantly enhancing bacterial infection treatments.
|
|
