Search

The recognition of named entities in the field of water conservancy is of great significance for the building of water conservancy knowledge graphs and intelligent question answering systems. However, in the current field of water conservancy, there are shortcomings in named entity recognition, such as a lack of annotated corpus, low recognition accuracy of traditional methods and inability to solve polysemous entities. Aiming at the characteristics of water conservancy texts, a Named Entity Recognition Model for Machine Reading Comprehension (MRC) based on data (vocabulary and entity type labels) enhancement, namely the MRC-WLE model was put forward. Mainly, the vocabulary feature information and entity type label feature information in water conservancy texts were injected into the model as "knowledge". It introduced models such as BERT-CRF, BERT-CRF-Word, BERT-BILSTM-CRF and BERT-BILSTM-CRF-Word as controls to evaluate the performance of the MRC-WLE model. The results show that compared with the BERT-CRF and other models mentioned above, the micro average F1 value of the MRC-WLE model has been improved. Compared with the MRC model, the micro average F1 value of the MRC-WLE model has been increased by 0.85%, reflecting the effectiveness of data augmentation. [ABSTRACT FROM AUTHOR]

Utilizing deep learning for data mining in biomedicine often falls short in leveraging prior knowledge and adapting to the complexities of biomedical literature mining. Entity recognition, a fundamental task in information extraction, also provides data support for Natural Language Processing (NLP) downstream tasks. Bovine Viral Diarrhea Virus (BVDV) results in considerable economic losses in the cattle industry due to calf diarrhea, bovine respiratory syndrome, and cow abortion. This study aims to extract information on BVDV from relevant literature and build a knowledge base. It enhances feature extraction in the BioBERT pre-trained model using the Machine Reading Comprehension (MRC) framework for information fusion and bi-directionally extracts corpus information through the Bi-LSTM network, followed by a CRF layer for decoding and prediction. The results show the construction of a BVDV Corpus with 22 biomedical entities and introduce the BioBERT-Bi-LSTM-CRF Integrated with MRC (BBCM) model for Named Entity Recognition (NER), combining prior knowledge and the reading comprehension framework (MRC). The BBCM model achieves F 1 -scores of 78.79% and 76.3% on the public datasets JNLPBA and GENIA, respectively, and 67.52% on the BVDV Corpus, outperforming other models. This research presents a targeted NER method for BVDV, effectively identifying related entities and exploring their relationships, thus providing valuable data support for NLP's downstream tasks. [ABSTRACT FROM AUTHOR]

To better combat the devastation of the protected forests in Côte d'Ivoire, a study was conducted to create a technique for detecting the acoustic signals produced by chainsaws deployed to fell trees in these areas. To improve the recognition rate of chainsaw sounds in a forest environment and increase the detection range of the recognition system, we are implementing the maximum ratio combining (MRC) technique on a microphone array. Therefore, the employment of an identification system is compared using one (01) microphone against the outcomes obtained by adopting system with three (03), six (06), and twelve (12) microphones. The use of MRC is then contrasted with an alternative recombining approach, designated as simple summation (SS). The SS is characterised by the simple addition of the signals acquired by the microphone array in the frequency domain. The MRC was employed on various microphone arrangements, accounting for varying degrees of attenuation experienced by chainsaw sounds. The K-Nearest Neighbors, in combination with Mel Frequency Cepstral Coefficients (MFCC), was employed to detect chainsaw sounds within the 16 kHz central frequency octave band. MRC applied to microphone arrays provided superior outcomes than simple summation. The enhancement in terms of classification rate ranged from [18; 51], favouring MRC. Moreover, it extended the chainsaw detection range from 520 m (using one microphone) to 1210 m (using a 12-microphone array). Taking into account the criteria for selecting an optimum microphone array, including classification rate, number of microphone nodes, information processing time and detection range, the six-microphone array was chosen as the best configuration. This configuration boasts a theoretical detection range of 1040 meters. [ABSTRACT FROM AUTHOR]

Machine Reading Comprehension (MRC) is a task that enables machines to mirror key cognitive processes involving reading, comprehending a text passage, and answering questions about it. There has been significant progress in this task for English in recent years, where recent systems not only surpassed human-level performance but also demonstrated advancements in emulating complex human cognitive processes. However, the development of Arabic MRC has not kept pace due to language challenges and the lack of large-scale, high-quality datasets. Existing datasets are either small, low quality or released as a part of large multilingual corpora. We present the Arabic Question Answering Dataset (ArQuaD), a large MRC dataset for the Arabic language. The dataset comprises 16,020 questions posed by language experts on passages extracted from Arabic Wikipedia articles, where the answer to each question is a text segment from the corresponding reading passage. Besides providing various dataset analyses, we fine-tuned several pre-trained language models to obtain benchmark results. Among the compared methods, AraBERTv0.2-large achieved the best performance with an exact match of 68.95% and an F1-score of 87.15%. However, the significantly higher performance observed in human evaluations (exact match of 86% and F1-score of 95.5%) suggests a significant margin of possible improvement in future research. We release the dataset publicly at https://github.com/RashaMObeidat/ArQuAD to encourage further development of language-aware MRC models for the Arabic language. [ABSTRACT FROM AUTHOR]

The deployment of cooperative communication inside a cell-Free mMIMO system can improve both the spectral efficiency SE performance as well as the energy efficiency EE performance. This increase is due to the increase in the signal to interference plus noise ratio SINR. In fact, the SINR can be greatly improved when the cognitive radio theory is applied due to its capability of interference mitigation. In this manuscript, the cognitive intelligent reflecting surfaces IRSs are distributed inside a cell-Free mMIMO system in order to improve the SE as well as the EE performance. Moreover, the cognitive radio can raise each user SINR. In this manuscript, the authors try to carry out the suitable mathematical model for the fore-mentioned system. Moreover, the system will be simulated. Subsequently, the simulation results will be explained. It is obvious that the implantation of cognitive IRSs inside, cell-Free mMIMO systems can greatly increase the system performance. [ABSTRACT FROM AUTHOR]

Machine reading comprehension is introduced to improve machines' readability and understandability of human languages. This sophisticated version of natural language processing is used for testing and improving the machine's efficiency for reading and responding to the input texts for appropriate queries. In this article, a persistent comprehensive model using query reconstruction is introduced to address the "Cloze Style" issue in text reading. This issue results in multiple output delivery that serves as irrelevant for different input queries. Therefore, the query reconstruction using the possible combination, reducing the aforementioned issue, is introduced in this model. The possible query keywords are replaced using the maximum individual combinations. The combinations are swapped using deep learning through keyword training and substitution processes. This process is persistent until the maximum text output (answer/ response) is obtained from the machine. The output is used for analyzing the understandability of the machine based on which the training intensity is tuned for successive iterations. Therefore, the proposed model scrutinizes output accuracy by reducing errors under controlled combination time. [ABSTRACT FROM AUTHOR]

Implementation of an eRehabilitation intervention named Fit After Stroke @Home (Fast@home) – including cognitive/physical exercise applications, activity-tracking, psycho-education – after stroke resulted in health-related improvements. This study investigated what worked and why in the implementation. Implementation activities (information provision, integration of Fast@home, instruction and motivation) were performed for 14 months and evaluated, using the Medical Research Council framework for process evaluations which consists of three evaluation domains (implementation, mechanisms of impact and contextual factors). Implementation activities were evaluated by field notes/surveys/user data, it's mechanisms of impact by surveys and contextual factors by field notes/interviews among 11 professionals. Surveys were conducted among 51 professionals and 73 patients. User data (n = 165 patients) were extracted from the eRehabilitation applications. Implementation activities were executed as planned. Of the professionals trained to deliver the intervention (33 of 51), 25 (75.8%) delivered it. Of the 165 patients, 82 (49.7%) were registered for Fast@home, with 54 patient (65.8%) using it. Mechanisms of impact showed that professionals and patients were equally satisfied with implementation activities (median score 7.0 [IQR 6.0–7.75] versus 7.0 [6.0–7.5]), but patients were more satisfied with the intervention (8.0 [IQR 7.0–8.0] versus 5.5 [4.0–7.0]). Guidance by professionals was seen as most impactful for implementation by patients and support of clinical champions and time given for training by professionals. Professionals rated the integration of Fast@home as insufficient. Contextual factors (financial cutbacks and technical setbacks) hampered the implementation. Main improvements of the implementation of eRehabilitation are related to professionals' perceptions of the intervention, integration of eRehabilitation and contextual factors. To increase the use of eRehabilitation by patients, patients should be supported by their healthcare professional in their first time use and during the rehabilitation process. To increase the use of eRehabilitation by healthcare professionals, healthcare professionals should be (1) supported by a clinical champion and (2) provided with sufficient time for learning to work and getting familiar with the eRehabilitation program. Integration of eRehabilitation in conventional stroke rehabilitation (optimal blended care) is an important challenge and a prerequisite for the implementation of eRehabilitation in the clinical setting. [ABSTRACT FROM AUTHOR]

In an advanced wireless communication system, a smart receiver trims down the fading effect. From a practical point of view, performance such receiver depends not only on the estimation of channels but also system accuracy. This paper derives the general expression of average bit error rate (BER) and outage probability for dual-branch Maximum Ratio Combining (2-MRC) over Fluctuating Two Ray (FTR) fading channels with Imperfect Channel Estimation. Communication channels encountered in Fifth-Generation Millimeter-Wave communication is represented accurately by the FTR fading channels. A 2-MRC receiver is considered because of its performance advantage and less complexity. The probability density function of the output signal-to-noise ratio is obtained for 2-MRC receiver with channel estimation error over the FTR fading model. The mathematical description of average BER for both non-coherent and binary coherent modulation is derived. The impact of the fading parameters and the error estimation on the system efficiency are assessed through numerical analysis of the generated equations. [ABSTRACT FROM AUTHOR]

We experimentally demonstrate the transmission of 20-Gbaud QPSK millimeter-wave signals within a 1.2-km wireless range at 128-GHz using constant-modulus-algorithm (CMA) and the maximum ratio combining (MRC) technology with over 2.2-dB gain in a photonics-assisted millimeter wave (MMW) 1 × 2 Single Input Multi Output (SIMO) communication system. MRC is applied for SIMO signal merging which leads to Signal to Noise Ratio (SNR) enhancement and significant Bit Error Rate (BER) reduction. The comparison which is performed for Single Input Single Output (SISO) and SIMO system, demonstrates the BER improvement. To the best of our knowledge, this is the first experimental demonstration of high gain in a D-band MMW 1 × 2 SIMO system by using these technologies. [ABSTRACT FROM AUTHOR]

Peripheral nerve injuries are common and remain a significant health challenge. Outcome measurements are used to evaluate injury, monitor recovery after nerve repair, and compare scientific advances. Clinical judgement is required to determine which available tools are most applicable, which requires a vast understanding of the available outcome measurements. In this article we discuss the highest yield tools available for clinical application., Competing Interests: Financial disclosure Dr K.C. Chung receives funding from the National Institutes of Health, United States and book royalties from Wolters Kluwer and Elsevier., (Published by Elsevier Inc.)