Explore the vast range of titles available.

The vigorous development of Time Series Neural Network in recent years has brought many potential possibilities to the application of financial technology. This research proposes a stock trend prediction model that combines Gate Recurrent Unit and Attention mechanism. In the proposed framework, the model takes the daily opening price, closing price, highest price, lowest price and trading volume of stocks as input, and uses technical indicator transition prediction as a label to predict the possible rise and fall probability of future trading days. The research results show that the proposed model and labels designed by this research can effectively predict important stock price fluctuations and can be effectively applied to financial commodity trading strategies.

This study presents a comparative analysis of two advanced attention-based deep learning models—Attention-LSTM and Attention-GRU—for predicting Bitcoin price movements. The significance of this research lies in integrating moving average technical indicators with deep learning models to enhance sensitivity to market momentum, and in normalizing these indicators to accurately reflect market trends and reversals. Utilizing historical OHLCV data along with four key technical indicators (SMA, EMA, TEMA, and MACD), the models classify trends into uptrend, downtrend, and neutral categories. Experimental results demonstrate that the inclusion of technical indicators, particularly MACD, significantly improves prediction accuracy. Furthermore, the Attention-GRU model offers computational efficiency suitable for real-time applications, while the Attention-LSTM model excels in capturing long-term dependencies. These findings contribute valuable insights for financial forecasting, providing practical tools for cryptocurrency traders and investors.

In view of the great need for quality assurance in radiotherapy, this paper proposes a stitching-based detector (SBD) technique and a set of intelligent algorithms that can reconstruct the information of projected particle beams. The reconstructed information includes the intensity, sigma value, and location of the maximum intensity of the beam under test. To verify the effectiveness of the proposed technique and algorithms, this research study adopts the pencil beam scanning (PBS) form of proton beam therapy (PBT) as an example. Through the SBD technique, it is possible to utilize 128 × 128 ionization chambers, which constitute an ionization plate of 25.6 cm2, with an acceptable number of 4096 analog-to-digital converters (ADCs) and a resolution of 0.25 mm. Through simulation, the proposed SBD technique and intelligent algorithms are proven to exhibit satisfactory and practical performance. By using two kinds of maximum intensity definitions, sigma values ranging from 10 to 120, and two definitions in an erroneous case, the maximum error rate is found to be 3.95%, which is satisfactorily low. Through analysis, this research study discovers that most errors occur near the symmetrical and peripheral boundaries. Furthermore, lower sigma values tend to aggravate the error rate because the beam becomes more like an ideal particle, which leads to greater imprecision caused by symmetrical sensor structures as its sigma is reduced. However, because proton beams are normally not projected onto the border region of the sensed area, the error rate in practice can be expected to be even lower. Although this research study adopts PBS PBT as an example, the proposed SBD technique and intelligent algorithms are applicable to any type of particle beam reconstruction in the field of radiotherapy, as long as the particles under analysis follow a Gaussian distribution.

Alzheimer’s disease (AD) is the most prevalent neurodegenerative disease in the elderly. Zinc (Zn) ion interacts with the pathogenic hallmark, amyloid-β (Aβ), and is enriched in senile plaques in brain of AD patients. To understand Zn-chelated Aβ (ZnAβ) species, here we systematically characterized ZnAβ aggregates by incubating equimolar Aβ with Zn. We found ZnAβ40 and ZnAβ42 both form spherical oligomers with a diameter of ~12–14 nm composed of reduced β-sheet content. Oligomer assembly examined by analytical ultracentrifugation, hydrophobic exposure by BisANS spectra, and immunoreactivity of ZnAβ and Aβ derived diffusible ligands (ADDLs) are distinct. The site-specific 13 C labeled solid-state NMR spectra showed that ZnAβ40 adopts β-sheet structure as in Aβ40 fibrils. Interestingly, removal of Zn by EDTA rapidly shifted the equilibrium back to fibrillization pathway with a faster kinetics. Moreover, ZnAβ oligomers have stronger toxicity than ADDLs by cell viability and cytotoxicity assays. The ex vivo study showed that ZnAβ oligomers potently inhibited hippocampal LTP in the wild-type C57BL/6JNarl mice. Finally, we demonstrated that ZnAβ oligomers stimulate hippocampal microglia activation in an acute Aβ-injected model. Overall, our study demonstrates that ZnAβ rapidly form toxic and distinct off-pathway oligomers. The finding provides a potential target for AD therapeutic development.

With the development of technology, the importance of the research on speech emotion recognition and semantic analysis has increased. The research is primarily applied in companion robot, technology products and medical purpose. In this research, a communication system with speech emotion recognition is proposed. The system pre-process speech with sound data enhancing method in speech emotion recognition and transform the sound into spectrogram by MFCC (Mel Frequency Cepstral Coefficient). Then, GoogLeNet of CNN (Convolutional Neural Network) is applied to recognize the five emotions, which are peace, happy, sad, angry and fear, and the top accuracy of recognition is 79.81%. When applying semantic analysis, the training texts are divided into two categories, positive and negative, and the chatting conversations are conducted in the framework Seq2Seq of RNN (Recurrent Neural Network). The systematic framework of this research has two parts, the client and the server. The former one is developed on Android system to be used in Application, and the latter one is established by Ubuntu Linux system and combined with the web server. With the bi-terminal framework system, the users can record voice in APP one his/her cellphone and upload the voice file to the server. Then, the voice undergoes speech emotion recognition by CNN and semantic analysis by RNN to function as a chatting machine that can respond positively or negatively based on the detected emotion and show the results on APP of the user’s cell phone. The main contributions of this research are: 1) This study introduces the Chinese word vector to the robot dialogue system, effectively improving dialogue tolerance and semantic interpretation, 2) The traditional method of emotion identification must first tokenize the Chinese words, analyze the clauses and part of speech, and capture the emotional keywords before being interpreted by the expert system. Different from the traditional method, this study classifies the input directly through the convolutional neural network after the input sentence is converted into a spectrogram by MFCC, and 3) in addition to implementing the companion robot, the user’s emotional index can be collected for analysis by the back-end care organization. In addition, compared with other commercial humanoid companion robots, this study is presented in an App, which is easier to use and economical.

In recent years, the use of Artificial Intelligence for emotion recognition has attracted much attention. The industrial applicability of emotion recognition is quite comprehensive and has good development potential. This research uses voice emotion recognition technology to apply it to Chinese speech emotion recognition. The main purpose of this research is to transform gradually popularized smart home voice assistants or AI system service robots from a touch-sensitive interface to a voice operation. This research proposed a specifically designed Deep Neural Network (DNN) model to develop a Chinese speech emotion recognition system. In this research, 29 acoustic characteristics in acoustic theory are used as the training attributes of the proposed model. This research also proposes a variety of audio adjustment methods to amplify datasets and enhance training accuracy, including waveform adjustment, pitch adjustment, and pre-emphasize. This study achieved an average emotion recognition accuracy of 88.9% in the CASIA Chinese sentiment corpus. The results show that the deep learning model and audio adjustment method proposed in this study can effectively identify the emotions of Chinese short sentences and can be applied to Chinese voice assistants or integrated with other dialogue applications.

The Snail transcription factor plays as a master regulator of epithelial mesenchymal transition (EMT), one of the steps of tumor metastasis. Snail enhances expressions of a lot of mesenchymal genes including the matrix degradation enzyme matrix metalloproteinases 9 (MMP9) and the EMT transcription factor zinc finger E-box binding homeobox 1 (ZEB1), however, the underlying mechanisms are not clarified. Herein, we investigated how Snail upregulated transcription of ZEB1 and MMP9 induced by the tumor promoter 12-O-tetradecanoyl-phorbol 13-acetate (TPA) in hepatoma cell HepG2. According to deletion mapping and site directed mutagenesis analysis, the TPA-responsive elements on both MMP9 and ZEB1 promoters locate on a putative EGR1 and SP1 overlapping region coupled with an upstream proposed Snail binding motif TCACA. Consistently, chromatin immunoprecipitation (ChIP) assay showed TPA triggered binding of Snail, EGR1 and SP1 on MMP9 and ZEB1 promoters. Double ChIP further indicated TPA induced association of Snail with EGR1 and SP1 on both promoters. Also, electrophoresis mobility shift assay revealed TPA enhanced binding of Snail with a MMP9 promoter fragment. According to shRNA techniques, Snail was essential for gene expression of both ZEB1 and MMP9. In conclusion, Snail transactivates genes involved in tumor progression via direct binding to a specific promoter region.

Green nephrology has emerged as a crucial strategy to address the health care sector’s role in the climate crisis, particularly due to the high carbon intensity of dialysis-related services. Aligned with global net-zero commitments, sustainable kidney care can reduce environmental impact while maintaining high standards of patient care. This viewpoint paper proposes a net-zero carbon emissions kidney care center model to address global climate change challenges and advance health care sustainability goals. Based on the United Nations Sustainable Development Goals, we developed a 4D framework: digital transformation, low-carbon health care, circular economy, and preventive medicine. The digital transformation dimension features a precision kidney health system integrating acute and chronic kidney injury digital care models. The low-carbon health care dimension focuses on increasing the rates of kidney transplantation and choosing optimal dialysis modality. The circular economy dimension involves dialysis wastewater recycling, repurposing of medical materials, and integration of renewable energy into facility operations. The preventive medicine dimension incorporates telehealth education, behavioral interventions, and health inequality improvements. This net-zero carbon emissions kidney care model represents an environmental, social, and governance approach to ensuring implementation and continual improvement. It also provides actionable steps for implementing sustainable kidney care and serves as a reference model for net-zero emissions health care systems.

Male predominance in active tuberculosis (TB) is widely-reported globally. Gender inequalities in socio-cultural status are frequently regarded as contributing factors for disparities in sex in active TB. The disparities of sex in the prevalence of latent TB infection (LTBI) are less frequently investigated and deserve clarification. In this cross-sectional study conducted in a TB endemic area, we enrolled patients at high-risk for LTBI and progression from LTBI to active TB from 2011 to 2012. Diagnosis of LTBI was made by QuantiFERON-TB Gold In-Tube (QFT-GIT). Differences in sex in terms of prevalence of LTBI and clinical predictors for LTBI were investigated. Associations among age, smoking status, and sex disparities in LTBI were also analyzed. A total of 1018 high-risk individuals with definite QFT-GIT results were included for analysis, including 534 males and 484 females. The proportion of LTBI was significantly higher in males than in females (32.6% vs. 25.2%, p = 0.010). Differences in the proportion of LTBI between sexes were most prominent in older patients (age ≥ 55 years). In multivariate analysis, independent clinical factors associated with LTBI were age (p = 0.014), smoking (p = 0.048), and fibro-calcified lesions on chest radiogram (p = 0.009). Male sex was not an independent factor for LTBI (p = 0.88). When stratifying patients according to the smoking status, the proportion of LTBI remained comparable between sexes among smokers and non-smokers. In conclusion, although the proportion of LTBI is higher in men, there is no significant disparity in terms of sex in LTBI among high-risk individuals after adjusting for age, smoking status, and other clinical factors.

Hepatocellular carcinoma (HCC) is among the most lethal cancers. Mounting studies highlighted the essential role of the HGF/c-MET axis in driving HCC tumor progression. Therefore, c-Met is a potential therapeutic target for HCC. However, several concerns remain unresolved in c-Met targeting. First, the status of active c-Met in HCC must be screened to determine patients suitable for therapy. Second, resistance and side effects have been observed frequently when using conventional c-Met inhibitors. Thus, a preclinical system for screening the status of c-Met signaling and identifying efficient and safe anti-HCC agents is urgently required. In this study, immunohistochemical staining of phosphorylated c-Met (Tyr1234) on tissue sections indicated that HCCs with positive c-Met signaling accounted for approximately 46% in 26 cases. Second, many patient-derived HCC cell lines were established and characterized according to motility and c-Met signaling status. Moreover, LZ8, a medicinal peptide purified from the herb Lingzhi, featuring immunomodulatory and anticancer properties, was capable of suppressing cell migration and slightly reducing the survival rate of both c-Met positive and negative HCCs, HCC372, and HCC329, respectively. LZ8 also suppressed the intrahepatic metastasis of HCC329 in SCID mice. On the molecular level, LZ8 suppressed the expression of c-Met and phosphorylation of c-Met, ERK and AKT in HCC372, and suppressed the phosphorylation of JNK, ERK, and AKT in HCC329. According to receptor array screening, the major receptor tyrosine kinase activated in HCC329 was found to be the epidermal growth factor receptor (EGFR). Moreover, tyrosine-phosphorylated EGFR (the active EGFR) was greatly suppressed in HCC329 by LZ8 treatment. In addition, LZ8 blocked HGF-induced cell migration and c-Met-dependent signaling in HepG2. In summary, we designed a preclinical trial using LZ8 to prevent the tumor progression of patient-derived HCCs with c-Met-positive or -negative signaling.