This work addresses four aspects of the English translation model: consistency, model structure, semantic understanding, and knowledge fusion. To solve the problem of lack of personality consistency in the responses generated by neural networks in English translation models, an English translation model with fuzzy semantic optimal control of neural networks is proposed in this study. The model uses a fuzzy semantic optimal control retrieval mechanism to obtain appropriate information from an externally set English information table; to further improve the effectiveness of the model in retrieving correct information, this work adopts a two-stage training method, using ordinary English translation data for model pretraining and then fine-tuning the model using English translation data with optimal control containing fuzzy semantic information. The model consists of two parts, a sequence generation network that can output the probability distribution of words and an evaluation network that can predict future whole-sentence returns. In particular, the evaluation network can evaluate the impact of currently generated words on whole sentences using deep inheritance features so that the model can consider not only the optimal solution for the current words, as in other generative models, but also the optimal solution for future generated whole sentences. The experimental results show that the English translation model with fuzzy semantic optimal control of the neural network proposed in this study can obtain better semantic feature representation by using a novel bidirectional neural network and a masked language model to train sentence vectors; the combination of semantic features and fuzzy semantic similarity features can obtain higher scoring accuracy and better model generalization. In English translation applications, there are large improvements in scoring accuracy and generality.

/pdf/construction-of-english-translation-model-based-on-neural-m5ew3rn9.pdf

Construction of English Translation Model Based on Neural Network Fuzzy Semantic Optimal Control

Sentiment analysis is a method that uses peer-reviewed literature to address issues from a variety of specialised scientific viewpoints. It's crucial to read reviews before purchasing a product so that you're aware of the benefits and drawbacks of the items you want to use; for example, you may learn whether or not a certain cosmetic brand is of a usable quality by reading reviews of the product. In order to make an informed decision about a cosmetics purchase, shoppers should read reviews and testimonials from other customers who have tried the product in question. It's clear that people are becoming more wary of review sites due to the sheer volume of reviews available. The reviews stop being useful at some point. So that readers may locate reliable product comparisons quickly, the writers categorise using both positive and negative classifications. Support Vector Machine (SVM) and Nave Bayes (NB) algorithms may both benefit from the adoption of Particle Swarm Optimization (PSO) with Genetic Algorithm (GA) optimization, resulting in more accurate and optimum solutions to the review categorization issue. In a head-to-head comparison using this data set, an SVM algorithm achieves an accuracy of 89.20% and an area under the curve (AUC) of 0.973, whereas an SVM based on PSO achieves an accuracy of 94.60% and an AUC of 0.985. Testing the data using the NB algorithm yielded an accuracy of 88.50% and an AUC of 0.536; next, the accuracy was compared to that of the PSO-based NB method, which was 0.692. These numbers show that PSO optimization may be used to increase precision and provide better answers.

Sentiment Analysis based optimization approach

By transferring knowledge from the source domain labeled data to the target domain, cross-domain sentiment analysis can predict sentiment polarity in the lacking of labeled data in the target domain. However, most existing cross-domain sentiment analysis methods establish the relationship of domains by extracting domain-invariant (pivot) features. These methods ignore domain-specific (non-pivot) features or introduce a lot of noisy features to make domain adaptability weak. Hence, we propose a cross-domain reinforcement learning framework for sentiment analysis. We extract pivot and non-pivot features separately to fully mine sentiment information. To avoid the Hughes phenomena caused by the feature redundancy, the proposed framework applies a multi-level policy to select appropriate features extracted from the data. And a sentiment predictor is applied to calculate delayed reward for policy improvement and predict the sentiment polarity. The decision-making capacity of reinforcement learning can effectively tackle the problem of noisy feature data and improve domain adaptability. Extensive experiments on the Amazon review datasets demonstrate that the proposed model for cross-domain sentiment analysis outperforms state-of-the-art methods. 

Cross-Domain Reinforcement Learning for Sentiment Analysis

Nowadays, people always use online promotions to know about best shops to buy the best products. This shopping experience and shopper’s opinion about the shop can be observed by the customer-experience shared on social media. A new customer when searching a shop needs information about manufacturing date (MRD) and manufacturing price (MRP), offers, quality, and suggestions which are only provided by the previous customer experience. Several approaches were used previously for predicting the product details, but no one approach provides accurate information. To overcome these issues, Reviewer Reliability and XGboost whale Optimized Sentiment Analysis for Online Product Recommendation is proposed in this manuscript.Initially, Amazon Product recommendation datathe data are preprocessed and given to XGboost Classifier that classifies the product recommendation result as, good, bad and average. Generally the XGboost Classifier does not reveal any adoption of optimization techniques for computing the optimal parameters for assuring accurate classification of product recommendation. Therefore in this work, proposed Whale optimization algorithm utilized to optimize the weight parameters of the XGboost. Then the proposed model is implemented in MATLAB. The proposed method attains 18.31%, 12.81%, 45.75%, 26.97% and 25.55% lower Mean Absolute error, 18.31%, 12.81%, 27.97%, 25.97%, and 25.55% higher Mean absolute percentage error and 15.31%, 10.33%, 25.86%, 22.86% and 15.22% lower Mean Square Error than the existing methods.

Reviewer reliability and XGboost whale optimized sentiment analysis for online product recommendation

Radioactive source localization algorithms have been widely used in the detection of nuclear accident areas. But some shortcomings, such as complex algorithm structure, slow localization speed and poor accuracy, were obviously performed to affect mobile robot locating autonomously. In this paper, a potential alternative method was investigated to be a new usage of locating leaks, just via specifying the change of exposure rate. In this model, several key factors, such as gamma ray attenuation, scattering factor, travel angle guide, spatial discretization, etc., were taken into consideration, to demonstrate the effectiveness of the algorithm, which is appropriated in unknown areas of the radioactive waste repository. Since there are three factors with different contribution, such as position, quantity of the source and gamma ray energy, which considered to demonstrate its impact on success. So, a hybrid adaptive grey wolf algorithm (HAGWO) has been adopted and implemented to develop a novel rapid method of radioactive leak location. Three aspects, including the good point set initialization in population size, balanced convergence function, and self-adaptive greedy strategy for population update, were optimized and merged into the locating model. To investigate the effectiveness of the algorithm, results of HAGWO are compared with grey wolf algorithm (GWO), good point set initialization strategy GWO(GGWO) and adaptive head wolf strategy GWO (ALGWO) in convergence speed, accuracy, stability and positioning error of single and double leak points. It is observed that convergence speed is increased by 37.93 ± 2% at the highest; the convergence accuracy is increased by 92.42 ± 2% at the most; the stability is improved by 30% ∼ 50%. The positioning error of single leak point is within 1.08%, and the positioning error of double leak point is less than 8.90%. Besides, compared with GWO, GGWO and ALGWO, the single-point accuracy is improved by 1.36 percentage points (to GWO), and the double-point accuracy is improved by 40.35 percentage points (to ALGWO) at most. It is observed that HAGWO performs the best in locating leaks, with a faster convergence, stronger stability and more accuracy.

Rapid localization of radioactive leaks based on hybrid adaptive grey wolf algorithm

Sentiment analysis is the most frequently adopted technique and is also termed as opinion mining. A numerous data is generated by the E-Commerce portals. These data will assist the online retailers for knowing the expectation of customers. From the numerous sources, sentiment analysis can process huge amount of online opinions. This paper develops a novel sentiment classification approach, named BH-GWO-Fuzzy, in E-commerce application for framing an efficient recommendation system. The proposed model undergoes five processing steps, such as (a) Data acquisition, (b) Pre-processing, (c) Feature extraction, (d) Weighted feature extraction, and (e) Classification. The pre-processing is done by three steps, namely stop word removal, stemming, and blank space removal. Further, the feature extraction is performed by measuring the joint similarity score and cross similarity score for the positive, negative and neutral keywords from the tweets. From the resultant features, the weighted feature extraction is carried out, in which the weight is multiplied with the features to attain the better scalable feature suitable for classification. Here, the weight is tuned or optimized by the hybrid Black Hole-based Grey Wolf Optimization (BH-GWO). The BH-GWO is developed by integrating BH and GWO algorithms. After that, the extracted features are subjected to Adaptive Fuzzy Classifier, in which the membership function is optimized by the same hybrid BH-GWO algorithm. Finally, the sentiment classification for recommendation system will be empirically evaluated against the gathered benchmark dataset using diverse machine learning algorithms.The accuracy of the BH-GWO-Fuzzy is 11.7% better than Fuzzy, 28.3% better than K-Nearest Neighbor (KNN), 20.2% better than Support Vector Machine (SVM), and 18.75% better than Neural Network (NN) at learning percentage 45 for dataset 1.

A novel recommendation system enabled by adaptive fuzzy aided sentiment classification for E-commerce sector using black hole-based grey wolf optimization

A mobile wireless sensor network (MWSN) is a self-configuring network that does not require a fixed structure, which minimizes its operation time. At the same time, every node in this network is free to move and make the network change its topology frequently. Several routing algorithms designed for MWSNs are established on every node that forwards data packets in the network. However, in real time, some of the nodes may act as selfish nodes. Those selfish nodes use the network and its services but do not cooperate with other nodes. Therefore, detecting these nodes is essential for the WSN. Thus, this approach, “sensor node communication-based selfish node detection” (CSND) in MWSN, is proposed. In this approach, it can be verified that the node communicates based on the route request and reply messages sent within the communication network. The article's objective is to distinguish the selfish node in WSNs. This approach elects the forwarder node based on the highest energy level and node communication ratio (RNC). The BS is noticing the behaviour of every communication in the MWSN. The simulation illustrates that it enhances delivery and drop rates and improves energy efficiency during data transmission.

Sensor Node Communication based Selfish Node Detection in Mobile Wireless Sensor Networks

The sentimental analysis is processed according to structural detection, extraction, quantification, and evaluation of impacts and information present in natural language processing, biometric data, computer-language society, and text analysis. Advanced implementations in data analytics occur, which allows for identifying the underlining trends based on certain efficient computational models. Some of the social and e-commerce platforms consist of numerous reviews regarding the online products that are posted by the end-users. This helps the developers to understand priceless insight during the process of product design. The most significant aim of this work is to develop a Heuristic-based sentimental analysis for E-Commerce data. Here, the pre-processing of input E-Commerce data is performed by blank space removal, stop word removal, and stemming. Here, the statistical features are extracted using Cross Similarity Score (CSS) and Joint Similarity Score (JSS) regarding “positive, negative, and neutral keywords”. In addition, the word2vec features are also extracted. From the two sets of features, “Convolutional Neural Network (CNN) with Bidirectional Long Short Term Memory (BiLSTM)” is separately used that is named as Optimal Hybrid CNN-BiLSTM (OH-CNN-BiLSTM), and performed the hybridization of two models for the sentimental analysis. The designed CNN-BiLSTM technique is ensured better outcomes when processing long text as it provides advantages through the ability of CNN to extract the features and superiority of Bi-LSTM in learning the bidirectional dependencies of the long-term text. The main novelty of this work is to develop an improved Galactic Swarm Optimization (IGSO) algorithm for improving the hybridized model, as it provides faster convergence when getting the accurate solution on a wide range of dimensional space and is also able to solve the optimization issues with multimodal benchmark data. The evaluation of the suggested algorithm is done with various E-Commerce data and secures high accuracy on sentimental analysis and prediction while comparing with the traditional models. 

N Ramshankar

Papers

A novel recommendation system enabled by adaptive fuzzy aided sentiment classification for E-commerce sector using black hole-based grey wolf optimization

Reviewer reliability and XGboost whale optimized sentiment analysis for online product recommendation

Sensor Node Communication based Selfish Node Detection in Mobile Wireless Sensor Networks

Automated sentimental analysis using heuristic-based CNN-BiLSTM for E-commerce dataset