Heart disease, known as cardiovascular disease has been one of the main causes of death worldwide in recent years. It is affected by various risk factors such as high blood pressure, high cholesterol, diabetes, smokin...
详细信息
Autonomous Systems (AS) enable systems to adapt to drastic and unprecedented environmental changes, a capability that can be enhanced through the utilization of Digital Twins (DTs). However, the additional capabilitie...
详细信息
Developing vehicles with the Internet of Thing technology including driver health monitoring systems, driver safety systems, and accident prevention has drawn the attention of researchers in the last few years. The mo...
详细信息
Predicting student success is an important task in educational institutions, as it allows for targeted interventions and support systems to enhance educational outcomes. This paper explores the use of SHAP (SHapley Ad...
Predicting student success is an important task in educational institutions, as it allows for targeted interventions and support systems to enhance educational outcomes. This paper explores the use of SHAP (SHapley Additive exPlanations) model-agnostic method in understanding and interpreting student success prediction. The predictive model was built using Multi-Layer Perceptron neural network algorithm on a large public dataset. By shedding light on the underlying factors driving student success, this research contributes to the advancement of data-driven decision-making in education.
A particular problem in using artificial intelligence techniques in the sensor grid is the high power consumption. Remote sensors are usually limited by the amount of power available, thus our general goal is to minim...
A particular problem in using artificial intelligence techniques in the sensor grid is the high power consumption. Remote sensors are usually limited by the amount of power available, thus our general goal is to minimize it while preserving accurate experimentation results. Using emerging technologies like spiking neural networks and neuromorphic hardware, we can create sensor grids that perform data processing with preserving low power consumption. In this paper, we demonstrate a remote node with integrated visual sensor that works on less than 10mW of energy, while performing continuous scene monitoring, object detection and classification. The system has intelligent power management and the ability to send data wirelessly.
We deigned a spiking neural network that computes network weights in the temporal dimension. Such a network can be used for artificial intelligence and deep learning. We demonstrate circuits implementing blocks for bu...
We deigned a spiking neural network that computes network weights in the temporal dimension. Such a network can be used for artificial intelligence and deep learning. We demonstrate circuits implementing blocks for building such a network and then a training model. This enables creation of efficient Hessenstein-Reichardt detectors observed in motion detection networks in the nature. The proposed network allows reconfiguration across network layers algorithmically.
In this work, a production model with screening of imperfect product and green house gas emission has been developed. Here, it has been considered that the manufacturing process transfer from in-control situation to o...
详细信息
The current research is focused on designing a multithreaded parallel solution for processing a pair of raster image files that are used to create an animation. In the computational process, a multithreaded model was ...
详细信息
ISBN:
(数字)9798350362602
ISBN:
(纸本)9798350362619
The current research is focused on designing a multithreaded parallel solution for processing a pair of raster image files that are used to create an animation. In the computational process, a multithreaded model was used when processing arrays of data. The proposed approach is verified by a multithreaded parallel program implementation. The effectiveness of the proposed solution has been verified experimentally by processing an image with dimensions 4320x5400 and a white color mask. The obtained results in terms of execution time show an acceleration of the computational process when increasing the number of threads.
The principle of multiplicity is introduced for the components of the investment planning process. Some algorithms are given that ensure the process of investment planning at the regional level: the formation of integ...
The principle of multiplicity is introduced for the components of the investment planning process. Some algorithms are given that ensure the process of investment planning at the regional level: the formation of integrated assessments of investment projects, automated generation of projects, multicriteria evaluation and selection of projects, taking into account the mutual influence of projects, optimizing the composition of projects, and taking into account financing restrictions. The features of the program system intended for the formation of plans for the territorial and sectoral development of the region are considered.
The report considers the peculiarities of the distribution of computing resources in cloud systems. The most used classification of existing technologies of cloud services is considered. The advantages and disadvantag...
详细信息
暂无评论