Search results

The goal of this research is to develop a dynamic step path planning algorithm based on the rapidly exploring random tree (RRT) algorithm that combines Q-learning with the Gaussian distribution of obstacles. A route for autonomous vehicles may be swiftly created using this algorithm.

The path planning issue is divided into three key steps by the authors. First, the tree expansion is sped up by the dynamic step size using a combination of Q-learning and the Gaussian distribution of obstacles. The invalid nodes are then removed from the initially created pathways using bidirectional pruning. B-splines are then employed to smooth the predicted pathways.

The algorithm is validated using simulations on straight and curved highways, respectively. The results show that the approach can provide a smooth, safe route that complies with vehicle motion laws.

An improved RRT algorithm based on Q-learning and obstacle Gaussian distribution (QGD-RRT) is proposed for the path planning of self-driving vehicles. Unlike previous methods, the authors use Q-learning to steer the tree's development direction. After that, the step size is dynamically altered following the density of the obstacle distribution to produce the initial path rapidly and cut down on planning time even further. In the aim to provide a smooth and secure path that complies with the vehicle kinematic and dynamical restrictions, the path is lastly optimized using an enhanced bidirectional pruning technique.

The purpose of this paper is to propose an attention alignment method for opinion mining of massive open online course (MOOC) comments. Opinion mining is essential for MOOC applications. In this study, the authors analyze some of bidirectional encoder representations from transformers (BERT’s) attention heads and explore how to use these attention heads to extract opinions from MOOC comments.

The approach proposed is based on an attention alignment mechanism with the following three stages: first, extracting original opinions from MOOC comments with dependency parsing. Second, constructing frequent sets and using the frequent sets to prune the opinions. Third, pruning the opinions and discovering new opinions with the attention alignment mechanism.

The experiments on the MOOC comments data sets suggest that the opinion mining approach based on an attention alignment mechanism can obtain a better F1 score. Moreover, the attention alignment mechanism can discover some of the opinions filtered incorrectly by the frequent sets, which means the attention alignment mechanism can overcome the shortcomings of dependency analysis and frequent sets.

To take full advantage of pretrained language models, the authors propose an attention alignment method for opinion mining and combine this method with dependency analysis and frequent sets to improve the effectiveness. Furthermore, the authors conduct extensive experiments on different combinations of methods. The results show that the attention alignment method can effectively overcome the shortcomings of dependency analysis and frequent sets.

The purpose of this paper is to describe a new approach to sentence representation learning leading to text classification using Bidirectional Encoder Representations from Transformers (BERT) embeddings. This work proposes a novel BERT-convolutional neural network (CNN)-based model for sentence representation learning and text classification. The proposed model can be used by industries that work in the area of classification of similarity scores between the texts and sentiments and opinion analysis.

The approach developed is based on the use of the BERT model to provide distinct features from its transformer encoder layers to the CNNs to achieve multi-layer feature fusion. To achieve multi-layer feature fusion, the distinct feature vectors of the last three layers of the BERT are passed to three separate CNN layers to generate a rich feature representation that can be used for extracting the keywords in the sentences. For sentence representation learning and text classification, the proposed model is trained and tested on the Stanford Sentiment Treebank-2 (SST-2) data set for sentiment analysis and the Quora Question Pair (QQP) data set for sentence classification. To obtain benchmark results, a selective training approach has been applied with the proposed model.

On the SST-2 data set, the proposed model achieved an accuracy of 92.90%, whereas, on the QQP data set, it achieved an accuracy of 91.51%. For other evaluation metrics such as precision, recall and F1 Score, the results obtained are overwhelming. The results with the proposed model are 1.17%–1.2% better as compared to the original BERT model on the SST-2 and QQP data sets.

The novelty of the proposed model lies in the multi-layer feature fusion between the last three layers of the BERT model with CNN layers and the selective training approach based on gated pruning to achieve benchmark results.

The rapid rise of large language models (LLMs) has propelled them to the forefront of applications in natural language processing (NLP). This paper aims to present a comprehensive examination of the research landscape in LLMs, providing an overview of the prevailing themes and topics within this dynamic domain.

Drawing from an extensive corpus of 198 records published between 1996 to 2023 from the relevant academic database encompassing journal articles, books, book chapters, conference papers and selected working papers, this study delves deep into the multifaceted world of LLM research. In this study, the authors employed the BERTopic algorithm, a recent advancement in topic modeling, to conduct a comprehensive analysis of the data after it had been meticulously cleaned and preprocessed. BERTopic leverages the power of transformer-based language models like bidirectional encoder representations from transformers (BERT) to generate more meaningful and coherent topics. This approach facilitates the identification of hidden patterns within the data, enabling authors to uncover valuable insights that might otherwise have remained obscure. The analysis revealed four distinct clusters of topics in LLM research: “language and NLP”, “education and teaching”, “clinical and medical applications” and “speech and recognition techniques”. Each cluster embodies a unique aspect of LLM application and showcases the breadth of possibilities that LLM technology has to offer. In addition to presenting the research findings, this paper identifies key challenges and opportunities in the realm of LLMs. It underscores the necessity for further investigation in specific areas, including the paramount importance of addressing potential biases, transparency and explainability, data privacy and security, and responsible deployment of LLM technology.

The analysis revealed four distinct clusters of topics in LLM research: “language and NLP”, “education and teaching”, “clinical and medical applications” and “speech and recognition techniques”. Each cluster embodies a unique aspect of LLM application and showcases the breadth of possibilities that LLM technology has to offer. In addition to presenting the research findings, this paper identifies key challenges and opportunities in the realm of LLMs. It underscores the necessity for further investigation in specific areas, including the paramount importance of addressing potential biases, transparency and explainability, data privacy and security, and responsible deployment of LLM technology.

This classification offers practical guidance for researchers, developers, educators, and policymakers to focus efforts and resources. The study underscores the importance of addressing challenges in LLMs, including potential biases, transparency, data privacy, and responsible deployment. Policymakers can utilize this information to shape regulations, while developers can tailor technology development based on the diverse applications identified. The findings also emphasize the need for interdisciplinary collaboration and highlight ethical considerations, providing a roadmap for navigating the complex landscape of LLM research and applications.

This study stands out as the first to examine the evolution of LLMs across such a long time frame and across such diversified disciplines. It provides a unique perspective on the key areas of LLM research, highlighting the breadth and depth of LLM’s evolution.

Normalization is an important step in all the natural language processing applications that are handling social media text. The text from social media poses a different kind of problems that are not present in regular text. Recently, a considerable amount of work has been done in this direction, but mostly in the English language. People who do not speak English code mixed the text with their native language and posted text on social media using the Roman script. This kind of text further aggravates the problem of normalizing. This paper aims to discuss the concept of normalization with respect to code-mixed social media text, and a model has been proposed to normalize such text.

The system is divided into two phases – candidate generation and most probable sentence selection. Candidate generation task is treated as machine translation task where the Roman text is treated as source language and Gurmukhi text is treated as the target language. Character-based translation system has been proposed to generate candidate tokens. Once candidates are generated, the second phase uses the beam search method for selecting the most probable sentence based on hidden Markov model.

Character error rate (CER) and bilingual evaluation understudy (BLEU) score are reported. The proposed system has been compared with Akhar software and RB\_R2G system, which are also capable of transliterating Roman text to Gurmukhi. The performance of the system outperforms Akhar software. The CER and BLEU scores are 0.268121 and 0.6807939, respectively, for ill-formed text.

It was observed that the system produces dialectical variations of a word or the word with minor errors like diacritic missing. Spell checker can improve the output of the system by correcting these minor errors. Extensive experimentation is needed for optimizing language identifier, which will further help in improving the output. The language model also seeks further exploration. Inclusion of wider context, particularly from social media text, is an important area that deserves further investigation.

The practical implications of this study are: (1) development of parallel dataset containing Roman and Gurmukhi text; (2) development of dataset annotated with language tag; (3) development of the normalizing system, which is first of its kind and proposes translation based solution for normalizing noisy social media text from Roman to Gurmukhi. It can be extended for any pair of scripts. (4) The proposed system can be used for better analysis of social media text. Theoretically, our study helps in better understanding of text normalization in social media context and opens the doors for further research in multilingual social media text normalization.

Existing research work focus on normalizing monolingual text. This study contributes towards the development of a normalization system for multilingual text.

The purpose of this paper is to address the challenge of opinion mining in text documents to perform further analysis such as community detection and consistency control. More specifically, we aim to identify and extract opinions from natural language documents and to represent them in a structured manner to identify communities of opinion holders based on their common opinions. Another goal is to rapidly identify similar or contradictory opinions on a target issued by different holders.

For the opinion extraction problem we opted for a supervised approach focusing on the feature selection problem to improve our classification results. On the community detection problem, we rely on the Infomap community detection algorithm and the multi-scale community detection framework used on a graph representation based on the available opinions and social data.

The classification performance in terms of precision and recall was significantly improved by adding a set of “meta-features” based on grouping rules of certain part of speech (POS) instead of the actual words. Concerning the evaluation of the community detection feature, we have used two quality metrics: the network modularity and the normalized mutual information (NMI). We evaluated seven one-target similarity functions and ten multi-target aggregation functions and concluded that linear functions perform poorly for data sets with multiple targets, while functions that calculate the average similarity have greater resilience to noise.

Although our solution relies on existing approaches, we managed to adapt and integrate them in an efficient manner. Based on the initial experimental results obtained, we managed to integrate original enhancements to improve the performance of the obtained results.

Studies on mining text and generating intelligence on human resource documents are rare. This research aims to use artificial intelligence and machine learning techniques to facilitate the employee selection process through latent semantic analysis (LSA), bidirectional encoder representations from transformers (BERT) and support vector machines (SVM). The research also compares the performance of different machine learning, text vectorization and sampling approaches on the human resource (HR) resume data.

LSA and BERT are used to discover and understand the hidden patterns from a textual resume dataset, and SVM is applied to build the screening model and improve performance.

Based on the results of this study, LSA and BERT are proved useful in retrieving critical topics, and SVM can optimize the prediction model performance with the help of cross-validation and variable selection strategies.

The technique and its empirical conclusions provide a practical, theoretical basis and reference for HR research.

The novel methods proposed in the study can assist HR practitioners in designing and improving their existing recruitment process. The topic detection techniques used in the study provide HR practitioners insights to identify the skill set of a particular recruiting position.

To the best of the authors’ knowledge, this research is the first study that uses LSA, BERT, SVM and other machine learning models in human resource management and resume classification. Compared with the existing machine learning-based resume screening system, the proposed system can provide more interpretable insights for HR professionals to understand the recommendation results through the topics extracted from the resumes. The findings of this study can also help organizations to find a better and effective approach for resume screening and evaluation.

To analyze the impact of agricultural sector on the economy of North Cyprus, which suffers from political problems and drought over the years.

Annual data covering 1975‐2002 period has been used to find the direction of causality in Granger sense between agricultural growth and economic growth after employing unit root tests to see if the variables under consideration are stationary.

Results of the present study first suggest that agricultural output growth and economic growth as measured by real gross domestic product growth are stationary at their levels, thus, they are naturally co‐integrated. They are in long run equilibrium relationship. And secondly, there is feedback relationship between these variables that indicates bidirectional causation among them in the long run period.

A more expanded data can be used for further comparison. Furthermore, a future study can be done for other islands to make comparison across themselves.

This study has shown that although North Cyprus suffers from political problems and drought in the agriculture sector, this sector still has an impact on the economy. Thus, effective policies related with this sector should be developed by authorities. Building pipelines from Turkey, which are at the agenda of North Cyprus and Turkish governments over the years should immediately put into action. This will have enormous impact on both sides of the island on the way to a solution in Cyprus problem.

This study is the first of its kind which analyzes the relationship between agricultural output and economic growth in a small island which has a closed economy and is politically non‐recognized state. Furthermore, it is a rare study made for small islands.

The purpose of this paper is three-fold: to review the categories explaining mainly optimization algorithms (techniques) in that needed to improve the generalization performance and learning speed of the Feedforward Neural Network (FNN); to discover the change in research trends by analyzing all six categories (i.e. gradient learning algorithms for network training, gradient free learning algorithms, optimization algorithms for learning rate, bias and variance (underfitting and overfitting) minimization algorithms, constructive topology neural networks, metaheuristic search algorithms) collectively; and recommend new research directions for researchers and facilitate users to understand algorithms real-world applications in solving complex management, engineering and health sciences problems.

The FNN has gained much attention from researchers to make a more informed decision in the last few decades. The literature survey is focused on the learning algorithms and the optimization techniques proposed in the last three decades. This paper (Part II) is an extension of Part I. For the sake of simplicity, the paper entitled “Machine learning facilitated business intelligence (Part I): Neural networks learning algorithms and applications” is referred to as Part I. To make the study consistent with Part I, the approach and survey methodology in this paper are kept similar to those in Part I.

Combining the work performed in Part I, the authors studied a total of 80 articles through popular keywords searching. The FNN learning algorithms and optimization techniques identified in the selected literature are classified into six categories based on their problem identification, mathematical model, technical reasoning and proposed solution. Previously, in Part I, the two categories focusing on the learning algorithms (i.e. gradient learning algorithms for network training, gradient free learning algorithms) are reviewed with their real-world applications in management, engineering, and health sciences. Therefore, in the current paper, Part II, the remaining four categories, exploring optimization techniques (i.e. optimization algorithms for learning rate, bias and variance (underfitting and overfitting) minimization algorithms, constructive topology neural networks, metaheuristic search algorithms) are studied in detail. The algorithm explanation is made enriched by discussing their technical merits, limitations, and applications in their respective categories. Finally, the authors recommend future new research directions which can contribute to strengthening the literature.

The FNN contributions are rapidly increasing because of its ability to make reliably informed decisions. Like learning algorithms, reviewed in Part I, the focus is to enrich the comprehensive study by reviewing remaining categories focusing on the optimization techniques. However, future efforts may be needed to incorporate other algorithms into identified six categories or suggest new category to continuously monitor the shift in the research trends.

The authors studied the shift in research trend for three decades by collectively analyzing the learning algorithms and optimization techniques with their applications. This may help researchers to identify future research gaps to improve the generalization performance and learning speed, and user to understand the applications areas of the FNN. For instance, research contribution in FNN in the last three decades has changed from complex gradient-based algorithms to gradient free algorithms, trial and error hidden units fixed topology approach to cascade topology, hyperparameters initial guess to analytically calculation and converging algorithms at a global minimum rather than the local minimum.

The existing literature surveys include comparative study of the algorithms, identifying algorithms application areas and focusing on specific techniques in that it may not be able to identify algorithms categories, a shift in research trends over time, application area frequently analyzed, common research gaps and collective future directions. Part I and II attempts to overcome the existing literature surveys limitations by classifying articles into six categories covering a wide range of algorithm proposed to improve the FNN generalization performance and convergence rate. The classification of algorithms into six categories helps to analyze the shift in research trend which makes the classification scheme significant and innovative.

The stock market generates massive databases of various financial companies that are highly volatile and complex. To forecast daily stock values of these companies, investors frequently use technical analysis or fundamental analysis. Data mining techniques coupled with fundamental and technical analysis types have the potential to give satisfactory results for stock market prediction. In the current paper, an effort is made to investigate the accuracy of stock market predictions by using the combined approach of variables from technical and fundamental analysis for the creation of a data mining predictive model.

We chose 381 companies from the National Stock Exchange of India's CNX 500 index and conducted a two-stage data analysis. The first stage is identifying key fundamental variables and constructing a portfolio based on that study. Artificial neural network (ANN), support vector machines (SVM) and decision tree J48 were used to build the models. The second stage entails applying technical analysis to forecast price movements in the companies included in the portfolios. ANN and SVM techniques were used to create predictive models for all companies in the portfolios. We also estimated returns using trading decisions based on the model's output and then compared them to buy-and-hold returns and the return of the NIFTY 50 index, which served as a benchmark.

The results show that the returns of both the portfolios are higher than the benchmark buy-and-hold strategy return. It can be concluded that data mining techniques give better results, irrespective of the type of stock, and have the ability to make up for poor stocks. The comparison of returns of portfolios with the return of NIFTY as a benchmark also indicates that both the portfolios are generating higher returns as compared to the return generated by NIFTY.

As stock prices are influenced by both technical and fundamental indicators, the current paper explored the combined effect of technical analysis and fundamental analysis variables for Indian stock market prediction. Further, the results obtained by individual analysis have also been compared. The proposed method under study can also be utilized to determine whether to hold stocks for the long or short term using trend-based research.