Aspect Term Extraction (ATE) is a critical task in aspect-level sentiment analysis, and extraction and annotation costs are extremely high. When training and testing samples come from different domains, the performance of traditional methods often degrades significantly owing to the differences between the two samples. Existing methods focus on domain adaptation techniques based on rich semantic information within local contexts to achieve cross-domain ATE. However, they overlook the potential global long-range dependency relationships of aspect terms within the text, thereby limiting the performance, scalability, and robustness of the models. To address these issues, this study proposes a cross-domain ATE model known as CBiLSTM, which does not require additional manual labeling and integrates global and local semantic information. The model leverages semantic information as a pivot and first incorporates external semantic information into word embeddings to construct pivot information for both the source and target domains. It then performs parallel encoding of the global and local contextual semantic information, thereby better capturing comprehensive semantic features and bridging the gap between the source and target domains to achieve cross-domain ATE. CBiLSTM achieves an average F1-score of 53.87%, outperforming the current state-of-the-art model by 0.49 percentage points, on three benchmark datasets. Experimental results demonstrate the superior performance and lower computational cost of CBiLSTM.
Stock price prediction presents significant challenges owing to the highly volatile and nonlinear nature of financial markets, which are influenced by various factors including macroeconomic conditions, policy changes, and market sentiment. Traditional prediction models such as ARIMA and classic linear regression models are often inadequate for capturing the complex dynamics of stock prices. The advent of deep learning has led to substantial improvements in prediction accuracy, with various recurrent neural networks widely employed for representation learning from stock sequences. However, recurrent networks such as LSTM and GRU may exhibit susceptibility to overfitting the training data, leading to suboptimal performance in real-world predictions due to the inherent noise and volatility of stock market data. Recent research has demonstrated that temporal convolutional networks (TCN) exhibit impressive capabilities in stock price prediction. A TCN can achieve extensive sequence memory by utilizing dilated convolutions, enabling it to capture long-term dependencies in time-series data, as well as causal convolution, ensuring that the model does not utilize future information when predicting future values, which is particularly crucial for time-series prediction. Nevertheless, stock market data typically contain substantial noise to which TCNs may be overly sensitive, thereby affecting the accuracy of the predictions. To address this issue, we propose a novel stock price prediction method based on the Generative Adversarial Networks (GANs) framework, utilizing an Attentive Temporal Convolutional Network (ATCN) as the generator, termed Attentive Temporal Convolution-based Generative Adversarial Network (ATCGAN). This approach employs a GAN framework to generate stock price data using an attentive temporal convolutional network as a generator, whereas a CNN-based discriminator evaluates the authenticity of the data. Adversarial training facilitates the model’s learning of the complex distribution of stock price data. Within the GAN framework, the TCN effectively captures long-term dependencies, combined with an attention mechanism for generating representative feature combinations, thereby enhancing prediction accuracy. Compared to the traditional ARIMA forecasting method, ACTGAN achieved a 78.29% reduction in Mean Absolute Error (MAE). Furthermore, when compared to the deep learning method GRU, ACTGAN reduced the Mean Absolute Error (MAE) by 51.01%. The experimental results demonstrate that the proposed GAN-based approach significantly outperforms the traditional methods and deep learning techniques.
Ernie Suryati Jefri, Mohd Hafidzal Mohd Hanafi, Nurul Hanim Razak
et al.
Polylactic Acid (PLA) has received considerable attention worldwide due to its ability to act as biodegradable material that has a lot of similarity towards petrochemically derived products. However, PLA still experience drawbacks such as high brittleness and low toughness that require further research. These limitations can be addressed through plasticization, polymer blending and crosslinking mechanism. The incorporation of vegetable oil-based plasticizer in PLA has been found to enhance its mechanical properties due to high lubricity, high index viscosity and good solvency characteristic. These contributes to increase in ductility, tensile strength, stability and toughness. In parallel, addition of composite materials further strengthens PLA by redistributing stress from polymer matrix to reinforcing phases and improving interfacial adhesion. This review emphasis on the effect of plasticizer and composite material in modifying PLA mechanical properties focusing on tensile strength, flexural strength and elongation at break, while other aspects are reserved for future studies. The aim is to advance PLA as a sustainable material with performance comparable to petrochemically derived product. Plasticizer that being discussed in this review are epoxidized jatropha oil (EJO), epoxidized chia seed oil (ECO), epoxidized soybean oil (ESO), epoxidized palm oil (EPO) and epoxidized waste cooking oil (EWCO). Meanwhile, composite material reviewed are kenaf fibre, zinc oxide nanoparticles (ZnO NPs), and 3-aminophenylboronic acid (APBA). The results showed that EPO promotes stronger hydrogen bonding within the PLA matrix due to higher oxirane oxygen content, thereby increase the tensile strength efficiently. The study also revealed that APBA helps to form borate ester linkage through interaction between boric acid groups and hydroxyl groups in PLA, that contributes to higher elongation at break. ZnO NPs additions introduce new functional properties which is antibacterial traits, while increasing tensile strength. The ability of epoxy group in EWCO to insert themselves between PLA chains helps to reduce van der Waals and hydrogen bonding, that leads to increase in flexural strength. This paper present findings on the effect of vegetable oil-based plasticizer and composite material towards PLA mechanical performance for wider applications as a sustainable product.
Chemical engineering, Computer engineering. Computer hardware
Abstract Steganography aims to embed and extract secret information in digital media for enhancing information security, which is widely applied to covert communication, copyright and privacy protection, digital forensics, etc. To resist steganalysis detection, generative steganography is one of the most promising techniques with embedding secret information into a generated image. Although existing generative steganographic methods could perform well with low hiding capacity, most of them encode the secret information in non-distribution-preserving manners, leading to poor security performance against steganalyzers when hiding more secret information. Meanwhile, the secret information tends to be difficult to be extracted with these methods because the secret-to-image transformations are irreversible. To tackle these issues, in this paper, we propose a reversible generative steganography with distribution-preserving scheme, which is mainly composed of a secret message mapping strategy with distribution-preserving and a reversible Glow model. To improve the anti-detectability against steganalyzers, the message mapping strategy with distribution-preserving is customized to encode the secret information into latent vectors which follow the Gaussian distribution as they are usually done in typical image generation models. The Glow model is then trained with reversible transformation to map the latent vectors into the generated stego-images with information hiding. Owing to the distribution-preserving and reversibility of the message mapping and Glow model, the proposed generative steganographic method achieves superior security performance and accurate extraction of secret message. Extensive experimental results demonstrate that the proposed method outperforms several state-of-the-art methods in terms of information extraction accuracy and anti-detectability, especially for high hiding capacity (up to 4.0 bpp).
The paper presents selected results of the analysis of thermal and mass flow transient processes within the containments of the WWER-440 and the WWER-1000 nuclear reactors during Loss-of-Coolant Accidents based on the mathematical model and computer code for LOCA simulation. General assumptions of the mathematical model (with lumped parameters) are briefly presented. Changes of thermal variables (temperature, pressure etc.) are governed by the fundamental thermodynamic equations. All these equations have the nonlinear, integral form. The whole area of the containment is divided into several control volumes. Control volumes are joined in a given mode (orifices, valves, siphon closures etc.) . The liquid phase (water) and the gaseous phase (air, steam and hydrogen) can appear in a control volume. Thermal equilibrium within an individual phase and a non-equilibrium state between phases is assumed. Heat accumulation in the walls and internal structures of the containment is taken into account and heat transfer between liquid and gaseous phases is also considered. The working mathematical model can be used for the analysis of different scenarios of LOCA within the containment of the PWR and BWR reactors. Later on the sample results of calculations of changes of pressure and temperature within the containment of the WWER-440 nuclear reactor and within the full containment of the WWER-1000 reactor are presented.
Computer engineering. Computer hardware, Mechanics of engineering. Applied mechanics
Thermal ignition for a reactive viscous flow between two symmetrically heated walls is investigated. The second order nonlinear boundary value problem governing the problem is obtained and solved analytically using a special type of Hermite-Padé approximation technique. We obtained very accurately the critical conditions for thermal ignition together with the two solution branches. It has been observed that an increase in viscous heating due to viscous dissipation can cause a rapid decrease in the magnitude of thermal ignition critical conditions.
Computer engineering. Computer hardware, Mechanics of engineering. Applied mechanics
Recent neural network research has demonstrated a significant benefit in machine learning compared to conventional algorithms based on handcrafted models and features. In regions such as video, speech and image recognition, the neural network is now widely adopted. But the high complexity of neural network inference in computation and storage poses great differences on its application. These networks are computer-intensive algorithms that currently require the execution of dedicated hardware. In this case, we point out the difficulty of Adders (MOAs) and their high-resource utilization in a CNN implementation of FPGA .to address these challenge a parallel self-time adder is implemented which mainly aims at minimizing the amount of transistors and estimating different factors for PASTA, i.e. field, power, delay.
Abstract This paper presents a comprehensive evaluation of data pre-processing and word embedding techniques in the context of Arabic document classification in the domain of health-related communication on social media. We evaluate 26 text pre-processings applied to Arabic tweets within the process of training a classifier to identify health-related tweets. For this task we use the (traditional) machine learning classifiers KNN, SVM, Multinomial NB and Logistic Regression. Furthermore, we report experimental results with the deep learning architectures BLSTM and CNN for the same text classification problem. Since word embeddings are more typically used as the input layer in deep networks, in the deep learning experiments we evaluate several state-of-the-art pre-trained word embeddings with the same text pre-processing applied. To achieve these goals, we use two data sets: one for both training and testing, and another for testing the generality of our models only. Our results point to the conclusion that only four out of the 26 pre-processings improve the classification accuracy significantly. For the first data set of Arabic tweets, we found that Mazajak CBOW pre-trained word embeddings as the input to a BLSTM deep network led to the most accurate classifier with F1 score of 89.7%. For the second data set, Mazajak Skip-Gram pre-trained word embeddings as the input to BLSTM led to the most accurate model with F1 score of 75.2% and accuracy of 90.7% compared to F1 score of 90.8% achieved by Mazajak CBOW for the same architecture but with lower accuracy of 70.89%. Our results also show that the performance of the best of the traditional classifier we trained is comparable to the deep learning methods on the first dataset, but significantly worse on the second dataset.
Computer engineering. Computer hardware, Information technology
LI Chao, LI Bo, DING Hongwei, YANG Zhijun, LIU Qianlin
In tactical data link system,the prioritization-based polling access protocol can ensure that information packets in the prioritized sites are sent in time,but the service switching still consumes time.In order to reduce the waiting time and queue length,this paper proposes a Prioritization-based Continuous service Access Control Protocol(PCACP) by using Field Programmable Gate Array(FPGA).The protocol adopts the exhaustive service for the prioritized sites and the limited service for the subordinate sites.The control center adopts the continuous service mode between the sites.The Markov chain and the probabilistic generating function are used to analyze the performance index of the model to obtain the accurate solution of each performance index.The model is simulated by Matlab,and the results show that the proposed protocol can ensure the information packets of the prioritized sites are sent in time,reduce the queue length of the information packets and increase the throughput of the system.
Accurate prediction of Flight Passenger Load Factors(FPLFs) helps in addressing overbooking and overserving of the flight seats.However,traditional time series-based prediction methods only focus on variation feature of recent daily FPLFs and ignore impacts of other factors,leading to limited prediction performance.To address the problem,this paper proposes a recurrent neural network model using multi-granularity temporal attention mechanism named MTA-RNN.The model constructs a hierarchical attention mechanism to acquire the temporal correlation of FPLFs under different temporal granularities.Also,other factors including the properties of a flight,festivals and holidays are introduced into the model to compute the target FPLFs over a certain period in the future.Experimental results on datasets of real historical FPLFs show that the MTA-RNN model has a higher prediction accuracy than ARIMA,LSTM and Seq2seq models.
Ram Agrawal, Bhupendra Gupta, Pradeep Kumar Jhinge
et al.
The heat transfer coefficient of refrigerants R-12 (dichlorodifluoromethane), R-134a (1, 1, 1, 2, tetrafluoroethane) and R-409a (60 % R22, 25 % R124 and 15 % R142b) are compared on the basis of six existing correlations at condensing temperature 45 °C. Heat transfer coefficients are measured for horizontal tube having internal diameter 8 mm, external diameter 9.52 mm and length of 5 m, mass flux varies from 25 to 450 kg/m2sand quality (dryness fraction) varies from 0 to 1. In the comparison of three refrigerants, Bohdal correlation predict that heat transfer coefficient for R-409a is higher than R-134a and R-12 while according to Cavallini and Zecchin, Shah, Traviss, Huang and Park correlation heat transfer coefficient for R-134a is higher than R-409a and R-12.
Chemical engineering, Computer engineering. Computer hardware
In the rapid development of mobile Internet,the security of Android devices becomes more and more prominent,bringing many security risks to mobile Internet users.In this paper,the authors introduce related researches on Android security protection in recent years,point out its advantages and disadvantages,and put forward some improvements.By comparing and analyzing the existing work and related security protection technologies,the challenges and opportunities of Android security protection are given,and the broad prospects of the field of Android security protection are prospected.
Data dan informasi adalah sesuatu yang teramat penting dan berharga dalam sebuah organisasi dewasa ini. Pengelolan data dan informasi yang akurat dan cepat dapat membantu tumbuh kembangnya sebuah organisasi. Maka dari itu, pengelolaan data dan informasi dipandang penting demi kelancaran sebuah pekerjaan dan untuk menganalisa perkembangan dari pekerjaan itu sendiri. Untuk pengelolaan data dan informasi dibutuhkan sebuah sistem aplikasi terkomputerisasi. Sistem aplikasi juga sangat dibutuhkan dalam pengelolaan zakat pada Badan Amil Zakat (BAZ) Masjid seperti di Masjid Raya Andalas Padang. Adapun tujuan yang hendak dicapai dalam penulisan tugas akhir adalah menghasilkan sistem aplikasi pengolahan zakat berbasis web pada Masjid Raya Andalas Padang. Dengan adanya sistem aplikasi pengolahan zakat berbasis web pada Masjid Raya Andalas Padang dapat memperbaiki pengolahan data zakat Masjid Raya Andalas Padang serta dapat membantu Masjid Raya Andalas Padang dalam meningkatkan pelayanan kepada umat secara umum, dan kepada muzakki serta mustahik secara khususnya.
Data and information is something that is very important and valuable in an organization today. Management of data and information accurately and quickly can help the growth of an organization. Therefore, the management of data and information deemed essential for the smooth running of a job and to analyze the development of the work itself. For the management of data and information needed a computerized application system. The application system is also needed in the management of zakat in Amil Zakat (BAZ) mosque as Masjid Raya Andalas in Padang. The goals to be achieved in the thesis is generating system zakat web-based application processing at Masjid Raya Andalas Padang. With a system of processing applications on a web-based charity Masjid Raya Andalas Padang can improve the data management at Masjid Raya zakat Andalas Padang and can help Masjid Raya Andalas Padang in improving services to people in general, and to muzakki and mustahik in particular.
YE Ting,CHEN Kefei,SHEN Zhonghua,MENG Qian,ZHANG Wenzheng
Welch-Gong(WG) sequences have good randomness,including long period,balance property,ideal 2-tuple distribution,two-level autocorrelation,three-level cross correlation with m-sequences,and linear complexity increasing exponentially.For the WG transformation,the odd term of polynomial function is studied.Considering the complexity of polynomial function by WG transformation,this paper extends the specific five-term function to general three-term function in WG transformation,and analyzes that the new sequences still have good randomness and low linear complexity.It selects a specific instance to analyze the hardware implementation of WG cipher based on the three-term function,and gives a certain reference value for the design of the algorithm.
Unconventional supports of CoMo catalysts, such as activated carbon, ZrO2 and TiO2 and conventional Al2O3 support in the form of cylindrical extrudates were studied using inverse gas chromatography with single pellet- string column (SPSC) configuration, high pressure mercury porosimetry and nitrogen adsorption methods to assess both the transport and textural characteristics. The supports were saturated from an aqueous slurry of MoO3. MoO3 supported catalysts were promoted from the aqueous slurry of CoCO3.Co(OH)2. The transport and textural parameters of all CoMo catalysts prepared in their both oxidic and sulfide form were compared with that of the parent supports. It was concluded that the support effect, represented in the present work by surface area, CoMo loading and mainly the mean transport-pore radius, govern resultant activity of CoMo catalysts. The increasing mean transport-pore radii either of the support or of the sulfide catalyst correlated well qualitatively with the increasing activity in HDS of 1-benzothiophene in the order: ZrO2 ~ TiO2 < Al2O3 < C. The unconventional ZrO2- and TiO2-supported systems exhibited low microstructural changes in terms of textural and transport characteristics after deposition of CoMo and low HDS activities. In contrast, Al2O3- and C-based systems revealed significant changes in microstructure after deposition of the CoMo phases onto the supports and high HDS activities. The activated carbon supported CoMo catalyst exhibited the highest HDS activity and the mean transport-pore radius despite the highest volume of micropores.
Chemical engineering, Computer engineering. Computer hardware
Removal of lead by untreated coffee grounds was investigated in a packed bed up-flow column. The experiments were conducted to study the effect of important design parameter such as flow rate (5, 7 and 10 mL/min). Data confirmed that the breakthrough curves were dependent on flow rate. At a bed height of 7.5 cm and flow rate of 10 mL min-1, the metal-uptake capacity of coffee grounds for lead was found to be 78.95 mg g-1.
The breakthrough time increased and the saturation time decreased with the increase of flow rate. The Adams–Bohart, Thomas and BDST models were applied to the adsorption under varying experimental conditions to predict the breakthrough curves and to evaluate the model parameters of the fixed-bed column that are useful for process design. The Adams–Bohart model was in good agreement with the experimental data. The untreated coffee grounds column study states the value of the excellent adsorption capacity for the removal of Pb (II) from aqueous solution.
Chemical engineering, Computer engineering. Computer hardware