The work is a report on the implementation of interdisciplinary group project classes conducted in accordance with the Project Based Learning approach. The aim of the project was to develop an automated station for me...
详细信息
Pest detection and identification in a timely manner is a crucial step for precision agriculture. Halyomorpha Halys is a common pest whose negative effects are known in agricultural areas and on various crops. The pre...
Pest detection and identification in a timely manner is a crucial step for precision agriculture. Halyomorpha Halys is a common pest whose negative effects are known in agricultural areas and on various crops. The present work implemented and studied four performant neural networks, VGG19_BN, EfficientNetB7, DenseNet161, and ResNet152 for the detection of these insects. Although the detection of these insects in the natural environment through automated means, excluding traps, is a challenge, the results obtained are promising.
The evolution of web technologies has brought to the fore new solutions for content management and distribution. The development of these new technologies has managed to lay the foundations of a strong web industry an...
详细信息
Most research addressing OCR through machine learning techniques is focused on the actual algorithms and on using the MNIST data set as the de facto benchmark. Little effort was made to extend the data set or to build...
Most research addressing OCR through machine learning techniques is focused on the actual algorithms and on using the MNIST data set as the de facto benchmark. Little effort was made to extend the data set or to build an entirely new one. Furthermore, support for characters other than English ones is mostly limited. This paper presents an OpenStack based approach that aims to overcome this last limitation by providing a community-oriented solution for developing and maintaining richer, language agnostic, community-shared data sets for OCR based applications. The proposed architecture is integrated with OpenStack services and relies on new Cloud perspectives, such as Function-as-a-Service (FaaS), to achieve a greater degree of flexibility. The included modules allow users to upload their own data sets, select or fine-tune their desired pre-processing methods, and derive the required features for their target character set. Both the input and the output data are stored using OpenStack specific data services and are shared for all the users of the Cloud deployment. An interesting feature is that the underlying FaaS functionality would also allow interested parties to upload their own pre-processing and feature extraction stages.
The development area of web technologies has gained great popularity due to the power with which these new technologies can manage resources and due to developers or experts of various types who can build applications...
详细信息
This paper describes the design and software implementation of a wearable prototype that allows users to monitor the vital signs of COVID-19 patients in quarantine areas. This prototype consists of two parts, the brac...
详细信息
Text simplification (TS) is the process of generating easy-to-understand sentences from a given sentence or piece of text. The aim of TS is to reduce both the lexical (which refers to vocabulary complexity and meaning...
详细信息
Misinformation is considered a threat to our democratic values and principles. The spread of such content on social media polarizes society and undermines public discourse by distorting public perceptions and generati...
详细信息
Misinformation is considered a threat to our democratic values and principles. The spread of such content on social media polarizes society and undermines public discourse by distorting public perceptions and generating social unrest while lacking the rigor of traditional journalism. Transformers and transfer learning proved to be state-of-the-art methods for multiple wellknown natural language processing tasks. In this paper, we propose MisRoBÆRTa, a novel transformer-based deep neural ensemble architecture for misinformation detection. MisRoBÆRTa takes advantage of two state-of-the art transformers, i.e., BART and RoBERTa, to improve the performance of discriminating between real news and different types of fake news. We also benchmarked and evaluated the performances of multiple transformers on the task of misinformation detection. For training and testing, we used a large real-world news articles dataset (i.e., 100,000 records) labeled with 10 classes, thus addressing two shortcomings in the current research: (1) increasing the size of the dataset from small to large, and (2) moving the focus of fake news detection from binary classification to multi-class classification. For this dataset, we manually verified the content of the news articles to ensure that they were correctly labeled. The experimental results show that the accuracy of transformers on the misinformation detection problem was significantly influenced by the method employed to learn the context, dataset size, and vocabulary dimension. We observe empirically that the best accuracy performance among the classification models that use only one transformer is obtained by BART, while DistilRoBERTa obtains the best accuracy in the least amount of time required for fine-tuning and training. However, the proposed MisRoBÆRTa outperforms the other transformer models in the task of misinformation detection. To arrive at this conclusion, we performed ample ablation and sensitivity testing with MisRoBÆRTa on t
The paper presents project and its verification of a prototype integrated circuit containing an analog, programmable finite impulse response (FIR) filter, implemented in CMOS 350 nm technology. The structure of the fi...
The paper presents project and its verification of a prototype integrated circuit containing an analog, programmable finite impulse response (FIR) filter, implemented in CMOS 350 nm technology. The structure of the filter is based on the switched capacitor technique. In circuits of this type, one of main challenges is an efficient implementation of filter coefficients, which result from several factors described in this work. When implementing such filters as programmable circuits, the values of their coefficients have to be limited to a selected range, i.e. a given resolution in bits. In the implemented prototype filter, the filter coefficients are represented by 6 bits in sign-magnitude notation, so they can take 63 different values only. In such filters, it is not possible to directly implement any frequency response of the filter. Each time, it is necessary to properly round the theoretical values of the coefficients so that they fit into the available range of discrete values resulting from the implementation. The authors of the work designed an algorithm that allows such matching. The paper also presents results of measurements of the prototype chip.
暂无评论