International Journal on Artificial Intelligence Tools

The problem of vehicle redeployment in multi-period systems is studied in this paper. It is a sequential decision making problem that involves optimizing an objective over some planning horizon composed of multiple periods. In this work, the problem is handled with a hybrid local search and Q-learning algorithm. It integrates local search into the Dyna-Q algorithm and combines the system’s tactical and operational decision levels to find a multi-period policy for sharing vehicles between stations while optimizing the objective. Tests were carried out on synthetic and real instances, and the obtained results show how local search integration can improve the basic Dyna-Q algorithm.

We consider the problem of the semantic representation of words based on explicit basis word vectors. We focus on explicit semantic vectors in which each basis vector is equivalent to a unique word. In this paper, we propose a new approach to represent semantic vectors explicitly. The approach consists of three steps: First, we introduce two new factors called word similarity (WS) and the number of zeroes (NZ) for choosing informative context words. Second, we propose a dependency distance method by incorporating the syntactic relations of the words in the sentences. This means that the method uses not only semantic information but also syntactic one. Third, we propose two shifting methods based on WF and WS factors to eliminate the bias of the PPMI matrix. In this work, we use the ukWaC corpus to select context words and compute co-occurrence matrices. Then, we examine the results on MEN, RG-65, SimLex-999, and WordSim353 test sets. We report the performance in comparison with a Baseline in which, the word frequency has been used. The Baseline method uses a window to fix the influence of the neighboring words. Our approach improves the Spearman correlation coefficient for MEN, RG-65, SimLex-999, and WordSim353 datasets by 3.87%, 10.25%, 5.04%, and 5.24%, respectively. So, the experiment results show that the proposed context words selection, incorporating dependency distance, and using the WF-based shifting method significantly improve the performance.

This work implements argumentation as the basis for modeling the relevant EU legislation concerning medical devices classification. Stakeholders can consult a web application for determining the risk-based class of a medical device based on the relevant legislation. The described approach is generally applicable to any other analogous cases of decision-making based on legislative regulations. One of the main advantages of using argumentation is the explainability and the high modularity of software permitting the extension and/or modification of the code when new relevant regulations become available.

In Internet of Things (IoT) business applications, healthcare records and medical web service management have emerging technologies tremendous amount of data in daily transactions. The cloud service providers have attracted the attention of a huge number of user requests based on different Quality of Service (QoS) factors. The data gained researchers attention to predict user behavior through the production of IoT applications. Artificial Intelligence (AI)-based techniques have a great impact on analyzing and detection of web service segmentation and user behavior in selecting and allocating online services and online stores with wireless communications and smart devices. This research improves the Redundancy, Frequency, and Maintenance value (RFM) model to evaluate healthcare records using a hybrid Grouping Genetic Algorithm (GGA) and Density-based Spatial Clustering of Applications with Noise (DBSCAN) algorithms. In this hybrid method, using the GGA algorithm, the features selection is applied to find the optimal features for healthcare records of customer segmentation. After that, by applying the RFM model on the data output of the genetic algorithm, the data are clustered. Finally, by applying the DBSCAN algorithm, the most suitable case for clustering will be selected. The simulation results show that the accuracy of the genetic algorithm is 97% and the final clustering accuracy is 92%.

The novel Coronavirus (COVID-19) has affected the normal life of people around the world and has forced them to maintain social distance, self-quarantine and closing of many businesses. So, the people wish to share the information regarding the pandemic through social media e.g. Twitter. The key objective of this paper is to identify the sentiment associated with the pandemic by utilizing the tweets regarding the Coronavirus (COVID-19) and by using the python libraries to perform the task. We analyze the sentiment of people when Coronavirus has attained a peak level using the machine, deep learning techniques and TextBlob. We have classified the sentiments into positive and negative classes using the Machine Learning (NB, SVM, Logistic regression) approaches and deep learning-based Bi-LSTM model. The Bi-LSTM approach has achieved better accuracy (0.87) compared to the traditional machine learning models for Twitter sentiment classification. From the overall analysis, we could conclude that people are confident and they express more positivity towards the recovery from the COVID-19 pandemic. Such an analysis will help the policy and decision-makers to address the needs of the public appropriately.

In recent times, marine fish species recognition becomes an important research area to protect the ocean environment. It is a tough and time-consuming operation to manually detect marine fish species on the ocean floor. Depending on the situation, extensive sample efforts may be required. These efforts might be harmful to the marine ecosystem. Automated classification methods are capable of properly classifying these fish on a consistent basis. An increasing number of people are becoming interested in utilizing electronic monitoring and reporting with artificial intelligence for the aim of fish identification and enhancing present techniques. It is becoming more usual to use video and pictures of fish (either underwater or on ships) in fishing operations. These techniques are operational, transportable, and non-invasive, and they provide high-quality pictures at a lower cost than traditional approaches. Automated image processing techniques such as Deep Learning (DL) and Machine Learning (ML) are now available, and they may be customized to perform efficient fish species identification and segmentation. In this aspect, this paper presents an Intelligent DL based Marine Fish Species Classification (IDL-MFSC) technique. The proposed IDL-MFSC technique involves three major processes such as pre-processing, fish detection and fish classification. Primarily, Weiner filtering-based noise removal process takes place as a pre-processing step. In addition, Mask R-CNN (Mask Region Based Convolutional Neural Networks) with Residual Network as a backbone network is used for fish detection. Moreover, Optimal Deep Kernel Extreme Learning Machine (ODKELM) based classification method is employed for determining the class labels of the marine fish species in which the parameter tuning of the DKELM model takes place using Water Wave Optimization (WWO) technique. The performance of the proposed method is tested using an openly accessible Fish4Knowledge dataset. The experimental result highlights the supremacy of the IDL-MFSC technique over the recent techniques with respect to various measures.

By using of Gated Recurrent Unit and Graph Convolution network model, this work, based on remote sensing water quality measurement data, forecast the water quality which observed by the index of the chlorophyll A value and total nitrogen at the chosen observation points. The data is decomposed and reconstructed in time series in the light of the spatio-temporal correlation. The dependence of the processed sample is obviously decreased. The prediction results reflect the temporal and spatial changes of water quality data, and have faster processing speed and stronger computing power than other models.

Mixed-initiative systems for interactive optimization allow the user to add preferences to find satisfactory solutions. Industries use them as decision-support tools in order to take into consideration unexpected events or characteristics not stated in the optimization model. We present a design of an interactive optimization system that allows users to quickly find a new optimal solution when the user changes the values of decision variables. It anticipates the actions of the user and precomputes the solutions that satisfy the preferences by using both the capacities of the optimization software and a novel custom technique based on the kernel of the constraint matrix. This system is tested on a softwood lumber-drying planning problem and returns promising results for future use in wood industries.