There are many machine learning approaches available and commonly used today, however, the extreme learning machine is appraised as one of the fastest and, additionally, relatively efficient models. Its main benefit is that it is very fast, which makes it suitable for integration within products that require models taking rapid decisions. Nevertheless, despite their large potential, they have not yet been exploited enough, according to the recent literature. Extreme learning machines still face several challenges that need to be addressed. The most significant downside is that the performance of the model heavily depends on the allocated weights and biases within the hidden layer. Finding its appropriate values for practical tasks represents an NP-hard continuous optimization challenge. Research proposed in this study focuses on determining optimal or near optimal weights and biases in the hidden layer for specific tasks. To address this task, a multi-swarm hybrid optimization approach has been proposed, based on three swarm intelligence meta-heuristics, namely the artificial bee colony, the firefly algorithm and the sine–cosine algorithm. The proposed method has been thoroughly validated on seven well-known classification benchmark datasets, and obtained results are compared to other already existing similar cutting-edge approaches from the recent literature. The simulation results point out that the suggested multi-swarm technique is capable to obtain better generalization performance than the rest of the approaches included in the comparative analysis in terms of accuracy, precision, recall, and f1-score indicators. Moreover, to prove that combining two algorithms is not as effective as joining three approaches, additional hybrids generated by pairing, each, two methods employed in the proposed multi-swarm approach, were also implemented and validated against four challenging datasets. The findings from these experiments also prove superior performance of the proposed multi-swarm algorithm. Sample code from devised ELM tuning framework is available on the GitHub.

/pdf/multi-swarm-algorithm-for-extreme-learning-machine-1yttweju.pdf

Multi-Swarm Algorithm for Extreme Learning Machine Optimization

The economic model derived from the supply and demand of crude oil prices is a significant component that measures economic development and sustainability. Therefore, it is essential to mitigate crude oil price volatility risks by establishing models that will effectively predict prices. A promising approach is the application of long short-term memory artificial neural networks for time-series forecasting. However, their ability to tackle complex time series is limited. Therefore, a decomposition-forecasting approach is taken. Furthermore, machine learning model accuracy is highly dependent on hyper-parameter settings. Therefore, in this paper, a modified version of the salp swarm algorithm is tasked with determining satisfying parameters of the long short-term memory model to improve the performance and accuracy of the prediction algorithm. The proposed approach is validated on real-world West Texas Intermediate (WTI) crude oil price data throughout two types of experiments, one with the original time series and one with the decomposed series after applying variation mode decomposition. In both cases, models were adjusted to conduct one, three, and five-steps ahead predictions. According to the findings of comparative analysis with contemporary metaheuristics, it was concluded that the proposed hybrid approach is promising for crude oil price forecasting, outscoring all competitors.

/pdf/multi-step-crude-oil-price-prediction-based-on-lstm-approach-2k9ksh09.pdf

Multi-Step Crude Oil Price Prediction Based on LSTM Approach Tuned by Salp Swarm Algorithm with Disputation Operator

Objective To determine the capabilities of ChatGPT for rapidly generating, rewriting, and evaluating (via diagnostic and triage accuracy) sets of clinical vignettes. Design We explored the capabilities of ChatGPT for generating and rewriting vignettes. First, we gave it natural language prompts to generate 10 new sets of 10 vignettes, each set for a different common childhood illness. Next, we had it generate 10 sets of 10 vignettes given a set of symptoms from which to draw. We then had it rewrite 15 existing pediatric vignettes at different levels of health literacy. Fourth, we asked it to generate 10 vignettes written as a parent, and rewrite these vignettes as a physician, then at a grade 8 reading level, before rewriting them from the original parent's perspective. Finally, we evaluated ChatGPT for diagnosis and triage for 45 clinical vignettes previously used for evaluating symptom checkers. Setting and participants ChatGPT, a publicly available, free chatbot. Main outcome measures Our main outcomes for de novo vignette generation were whether ChatGPT followed vignette creation instructions consistently, correctly, and listed reasonable symptoms for the disease being described. For generating vignettes from pre-existing symptom sets, we examined whether the symptom sets were used without introducing extra symptoms. Our main outcome for rewriting existing standardized vignettes to match patient demographics, and rewriting vignettes between styles, was whether symptoms were dropped or added outside the original vignette. Finally, our main outcomes examining diagnostic and triage accuracy on 45 standardized patient vignettes were whether the correct diagnosis was listed first, and if the correct triage recommendation was made. Results ChatGPT was able to quickly produce varied contexts and symptom profiles when writing vignettes based on an illness name, but overused some core disease symptoms. It was able to use given symptom lists as the basis for vignettes consistently, adding one additional (though appropriate) symptom from outside the list for one disease. Pediatric vignettes rewritten at different levels of health literacy showed more complex symptoms being dropped when writing at low health literacy in 87.5% of cases. While writing at high health literacy, it added a diagnosis to 80% of vignettes (91.7% correctly diagnosed). Symptoms were retained in 90% of cases when rewriting vignettes between viewpoints. When presented with 45 vignettes, ChatGPT identified illnesses with 75.6% (95% CI, 62.6% to 88.5%) first-pass diagnostic accuracy and 57.8% (95% CI, 42.9% to 72.7%) triage accuracy. Its use does require monitoring and has caveats, which we discuss. Conclusions ChatGPT was capable, with caveats and appropriate review, of generating, rewriting, and evaluating clinical vignettes.

/pdf/chatgpt-for-clinical-vignette-generation-revision-and-25tkkfsk.pdf

ChatGPT for Clinical Vignette Generation, Revision, and Evaluation

Can ChatGPT be used in oral and maxillofacial surgery?

Today, chatbots are being employed across a wide range of businesses. The researchers will present the outcome of the literature exploration on attributes of chatbots that later become a reference to build a new chatbot for banking use. The goal is to use human natural language as an interaction medium to aid humans in doing any prescribed activity. It is important to think about how people engage with chatbots in order to create a viable and high-quality chatbot solution. The authors aim to help the chatbot community by determining what qualities a chatbot should have and how to build a chatbot for a bank. For the purpose of compiling useful chatbot characteristics, the researchers searched through a group of linked papers. The survey was done on a small group of chatbot end users in order to get a sense of what functionalities are most important to the end users. On the basis of a summary of the literature research and data from a survey, a set of chatbot functional features is proposed. This research intended to provide a quality feature criterion for creating a chatbot application. 

Features requirement elicitation process for designing a chatbot application

Big data are regarded as a tremendous technology for processing a huge variety of data in a short time and with a large storage capacity. The user’s access over the internet creates massive data processing over the internet. Big data require an intelligent feature selection model by addressing huge varieties of data. Traditional feature selection techniques are only applicable to simple data mining. Intelligent techniques are needed in big data processing and machine learning for an efficient classification. Major feature selection algorithms read the input features as they are. Then, the features are preprocessed and classified. Here, an algorithm does not consider the relatedness. During feature selection, all features are misread as outputs. Accordingly, a less optimal solution is achieved. In our proposed research, we focus on the feature selection by using supervised learning techniques called grey wolf optimization (GWO) with decomposed random differential grouping (DrnDG-GWO). First, decomposition of features into subsets based on relatedness in variables is performed. Random differential grouping is performed using a fitness value of two variables. Now, every subset is regarded as a population in GWO techniques. The combination of supervised machine learning with swarm intelligence techniques produces best feature optimization results in this research. Once the features are optimized, we classify using advanced kNN process for accurate data classification. The result of DrnDG-GWO is compared with those of the standard GWO and GWO with PSO for feature selection to compare the efficiency of the proposed algorithm. The accuracy and time complexity of the proposed algorithm are 98% and 5 s, which are better than the existing techniques. 

/pdf/feature-selection-using-grey-wolf-optimization-with-random-1mcsmtqh.pdf

Feature Selection Using Grey Wolf Optimization with Random Differential Grouping

In recent years, gradual improvements in communication and connectivity technologies have enabled new technical possibilities for the adoption of chatbots across diverse sectors such as customer services, trade, and marketing. The chatbot is a platform that uses natural language processing, a subset of artificial intelligence, to find the right answer to all users’ questions and solve their problems. Advanced chatbot architecture that is extensible, scalable, and supports different services for natural language understanding (NLU) and communication channels for interactions of users has been proposed. The paper describes overall chatbot architecture and provides corresponding metamodels as well as rules for mapping between the proposed and two commonly used NLU metamodels. The proposed architecture could be easily extended with new NLU services and communication channels. Finally, two implementations of the proposed chatbot architecture are briefly demonstrated in the case study of “ADA” and “COVID-19 Info Serbia”.

Extensible Chatbot Architecture Using Metamodels of Natural Language Understanding

A chatbot is an algorithm, a programming script, designed to give users the ability to communicate and interact with it online in order to perform a specific task, without any human factor involvement. In the beginning, chatbots were exclusively programs with which it was possible to correspond by exchanging instant text messages. The main focus of the paper is on the presentation of usage of chatbot ADA (Academic Digital Assistant) based on artificial intelligence. ADA chatbot was developed to provide students with an enhanced study service and the necessary information during their studies. Statistical parameters of the use of chatbot ADA and the analysis of statistics of conversations by channels show growing trend in the use of chatbots in all three surveys of communication channels (Viber, FB Messenger and Website). The conclusions of the analysis of top 10 scenarios and number of conversations are shown that students' interests were in accordance with the school calendar and obligations.

Application of Chatbot at a Higher Education Institution in Republic of Serbia

Students can retrieve information from the website or use the services of an existing information system (provided the information system is on the internet). However, we know from experience that searching a website is time-consuming or even inaccurate, and the functionality of the information system is limited. Chatbot makes it more natural, efficient and faster. Chatbot can understand natural language, i.e. written text and voice messages. It gives precise answers and performs all actions intended by the website and / or the information system. But the website and the information system do not have the richness of language that the chatbot has. You have to log in to the information system and know how to use it, and each new version requires new learning. If you know how Viber or FB Messenger work, you probably know how to use chatbot. The services provided by chatbot are visible on communication platforms used by a large number of users, and thus the quality of these services is better. Due to the use of chats, the human resources of the educational institution are redirected/retrained to more responsible and creative jobs because the workload has been relieved. The paper presents a chatbot called ADA, developed at the Belgrade Business and Arts Academy of Applied Studies (BAPUSS), and shows basic usage statistics. It also points out the importance of chatbots as a communication channel in educational institutions.

Miloš Kabiljo

Papers

Feature Selection Using Grey Wolf Optimization with Random Differential Grouping

Extensible Chatbot Architecture Using Metamodels of Natural Language Understanding

Application of Chatbot at a Higher Education Institution in Republic of Serbia

An example of chatbot in the field of education in the republic of serbia