Search

Around a third of the total population of Europe suffers from mental disorders. The use of electroencephalography (EEG) together with Machine Learning (ML) algorithms to diagnose mental disorders has recently been shown to be a prominent research area, as exposed by several reviews focused on the field. Nevertheless, previous to the application of ML algorithms, EEG data should be correctly preprocessed and prepared via Feature Engineering (FE). In fact, the choice of FE techniques can make the difference between an unusable ML model and a simple, effective model. In other words, it can be said that FE is crucial, especially when using complex, non-stationary data such as EEG. To this aim, in this paper we present a Systematic Mapping Study (SMS) focused on FE from EEG data used to identify mental disorders. Our SMS covers more than 900 papers, making it one of the most comprehensive to date, to the best of our knowledge. We gathered the mental disorder addressed, all the FE techniques used, and the Artificial Intelligence (AI) algorithm applied for classification from each paper. Our main contributions are: (i) we offer a starting point for new researchers on these topics, (ii) we extract the most used FE techniques to classify mental disorders, (iii) we show several graphical distributions of all used techniques, and (iv) we provide critical conclusions for detecting mental disorders. To provide a better overview of existing techniques, the FE process is divided into three parts: (i) signal transformation, (ii) feature extraction, and (iii) feature selection. Moreover, we classify and analyze the distribution of existing papers according to the mental disorder they treat, the FE processes used, and the ML techniques applied. As a result, we provide a valuable reference for the scientific community to identify which techniques have been proven and tested and where the gaps are located in the current state of the art. [ABSTRACT FROM AUTHOR]

Schizophrenia (SZ) is a prevalent mental disorder characterized by cognitive, emotional, and behavioral changes. Symptoms of SZ include hallucinations, illusions, delusions, lack of motivation, and difficulties in concentration. While the exact causes of SZ remain unproven, factors such as brain injuries, stress, and psychotropic drugs have been implicated in its development. SZ can be classified into different types, including paranoid, disorganized, catatonic, undifferentiated, and residual. Diagnosing SZ involves employing various tools, including clinical interviews, physical examinations, psychological evaluations, the Diagnostic and Statistical Manual of Mental Disorders (DSM), and neuroimaging techniques. Electroencephalography (EEG) recording is a significant functional neuroimaging modality that provides valuable insights into brain function during SZ. However, EEG signal analysis poses challenges for neurologists and scientists due to the presence of artifacts, long-term recordings, and the utilization of multiple channels. To address these challenges, researchers have introduced artificial intelligence (AI) techniques, encompassing conventional machine learning (ML) and deep learning (DL) methods, to aid in SZ diagnosis. This study reviews papers focused on SZ diagnosis utilizing EEG signals and AI methods. The introduction section provides a comprehensive explanation of SZ diagnosis methods and intervention techniques. Subsequently, review papers in this field are discussed, followed by an introduction to the AI methods employed for SZ diagnosis and a summary of relevant papers presented in tabular form. Additionally, this study reports on the most significant challenges encountered in SZ diagnosis, as identified through a review of papers in this field. Future directions to overcome these challenges are also addressed. The discussion section examines the specific details of each paper, culminating in the presentation of conclusions and findings. [ABSTRACT FROM AUTHOR]

The authors suggest to trade-off diagnosis quality versus runtime performance, exploiting learning for constraint ordering and where matrix factorization is used to estimate diagnoses. The final manuscript, "Applying matrix factorization to consistency-based direct diagnosis", authored by Seda Polat Erdeniz et al., deals with diagnosis as a basis for configuration problems when efficient solving is required in real-world applications. Screening all the accepted papers, the top 7 authors of the accepted papers were encouraged to submit their papers for this special issue, asking for substantial extensions to their submissions for creating manuscripts that are appropriate for being published in Applied Intelligence. [Extracted from the article]

With the long-term accumulation of high-quality educational data, artificial intelligence (AI) has shown excellent performance in knowledge tracing (KT). However, due to the lack of interpretability and transparency of some algorithms, this approach will result in reduced stakeholder trust and a decreased acceptance of intelligent decisions. Therefore, algorithms need to achieve high accuracy, and users need to understand the internal operating mechanism and provide reliable explanations for decisions. This paper thoroughly analyzes the interpretability of KT algorithms. First, the concepts and common methods of explainable artificial intelligence (xAI) and knowledge tracing are introduced. Next, explainable knowledge tracing (xKT) models are classified into two categories: transparent models and "black box" models. Then, the interpretable methods used are reviewed from three stages: ante-hoc interpretable methods, post-hoc interpretable methods, and other dimensions. It is worth noting that current evaluation methods for xKT are lacking. Hence, contrast and deletion experiments are conducted to explain the prediction results of the deep knowledge tracing model on the ASSISTment2009 by using three xAI methods. Moreover, this paper offers some insights into evaluation methods from the perspective of educational stakeholders. This paper provides a detailed and comprehensive review of the research on explainable knowledge tracing, aiming to offer some basis and inspiration for researchers interested in the interpretability of knowledge tracing. [ABSTRACT FROM AUTHOR]

Advances in artificial intelligence (AI) have led to its application in many areas of everyday life. In the context of control engineering, reinforcement learning (RL) represents a particularly promising approach as it is centred around the idea of allowing an agent to freely interact with its environment to find an optimal strategy. One of the challenges professionals face when training and deploying RL agents is that the latter often have to run on dedicated embedded devices. This could be to integrate them into an existing toolchain or to satisfy certain performance criteria like real-time constraints. Conventional RL libraries, however, cannot be easily utilised in conjunction with that kind of hardware. In this paper, we present a framework named LExCI, the Learning and Experiencing Cycle Interface, which bridges this gap and provides end-users with a free and open-source tool for training agents on embedded systems using the open-source library RLlib. Its operability is demonstrated with two state-of-the-art RL-algorithms and a rapid control prototyping system. [ABSTRACT FROM AUTHOR]

For humans to trust in artificial intelligence (AI) systems, it is essential for machine learning (ML) models to be interpretable to users. For example, the judicial process requires that AI conclusions must be rigorous and absolutely interpretable. In this paper, we propose a novel approach, VAE-SLIME, for providing stable local interpretable model-agnostic explanations (SLIME) based on a variational autoencoder (VAE). LIME is a technique that explains the predictions of any classifier in an interpretable and faithful manner. Despite the great success of LIME, the most popular method in this category, it has several disadvantages due to its random perturbation-based sampling method. The VAE-SLIME proposed in this paper is specifically designed to address the lack of stability and local fidelity exhibited by LIME for tabular data. VAE-SLIME first employs fixed noise to replace the random Gaussian noise used by the reparameterization trick of the VAE. Then, it uses this new VAE model instead of random perturbation method to generate stable samples. By considering the sequential relationship and flipping of features, a novel explanation stability evaluation metric, the feature sequence stability index (FSSI), is introduced to accurately evaluate the stability of explanations. In a comparison with 6 state-of-the-art approaches on 7 commonly used tabular datasets, the experimental results show beyond doubt that the explanations produced by our approach are most stable, and its local fidelity is 65.17% higher than that of other approaches on average. [ABSTRACT FROM AUTHOR]

The development of a new energy generation industry, represented by wind power generation, constitutes a crucial endeavor in attaining the dual carbon goal. Nonetheless, the high-dimensional, nonlinear, and stochastic nature of wind speed sequences imposes substantial demands on power systems' peak regulation capability. To address the limitations of traditional prediction methods, which struggle to provide probabilistic prediction outcomes and exhibit poor generalizability, this paper introduces a fusion of fuzzy theory and advanced artificial intelligence algorithms. The proposed approach, termed the fuzzification-forecasting-optimization ensemble system (FFOES), enables both point and interval predictions of wind speed, thereby complementing the emerging literature on power system dispatch. By leveraging fuzzy set theory and the concept of information granulation, the original sequence is initially divided into manageable particles of smaller scales. Subsequently, the computational efficiency of shallow neural networks and the automatic feature extraction capability of deep learning are harnessed to construct a comprehensive and integrated strategy for wind speed prediction. The numerical results demonstrate that the FFOES achieves a superior balance between prediction accuracy and stability compared to that of 15 benchmark models. Notably, the system's robust performance across distinct sites and time intervals underscores the significant potential of the FFOES in the realm of wind system risk management. [ABSTRACT FROM AUTHOR]

As the use of drones continues to increase, their capabilities pose a threat to airspace safety when they are misused. Deploying AI models for intercepting these unwanted drones becomes crucial. However, these AI models, such as deep learning models, often operate as "black boxes", making it hard to trust their decision-making system. This also affects end-users' confidence in these AI systems. In this paper, the explainability of deep reinforcement learning is investigated and a deep reinforcement learning (DRL) method, double deep Q-network with dueling architecture and prioritized experience replay is applied to train the AI models. To make the AI model decisions more transparent and to understand the reasoning behind the AI decisions for counter-drone systems, Shapley Additive Explanations (SHAP) method is implemented. After training the DRL agent, experience replay is visualized, and the absolute SHAP values are calculated to explain the key factors that influence the deep reinforcement learning agent's choices. The integration of DRL with explainable AI methods such as SHAP demonstrates significant potential for the advancement of robust and efficient counter-drone systems. [ABSTRACT FROM AUTHOR]

This paper critically examines model compression techniques within the machine learning (ML) domain, emphasizing their role in enhancing model efficiency for deployment in resource-constrained environments, such as mobile devices, edge computing, and Internet of Things (IoT) systems. By systematically exploring compression techniques and lightweight design architectures, it is provided a comprehensive understanding of their operational contexts and effectiveness. The synthesis of these strategies reveals a dynamic interplay between model performance and computational demand, highlighting the balance required for optimal application. As machine learning (ML) models grow increasingly complex and data-intensive, the demand for computational resources and memory has surged accordingly. This escalation presents significant challenges for the deployment of artificial intelligence (AI) systems in real-world applications, particularly where hardware capabilities are limited. Therefore, model compression techniques are not merely advantageous but essential for ensuring that these models can be utilized across various domains, maintaining high performance without prohibitive resource requirements. Furthermore, this review underscores the importance of model compression in sustainable artificial intelligence (AI) development. The introduction of hybrid methods, which combine multiple compression techniques, promises to deliver superior performance and efficiency. Additionally, the development of intelligent frameworks capable of selecting the most appropriate compression strategy based on specific application needs is crucial for advancing the field. The practical examples and engineering applications discussed demonstrate the real-world impact of these techniques. By optimizing the balance between model complexity and computational efficiency, model compression ensures that the advancements in AI technology remain sustainable and widely applicable. This comprehensive review thus contributes to the academic discourse and guides innovative solutions for efficient and responsible machine learning practices, paving the way for future advancements in the field. [ABSTRACT FROM AUTHOR]

Intelligent systems, such as driving assistance systems, can assist drivers by providing basic traffic, road blockage and possible route information to enable safe driving. The goal of scene text tracking in driver assistance systems is to locate and track scene text, milestone signs, traffic panels and road signs in real time. Therefore, the accuracy and real-time performance of scene text localization tracking play vital roles in intelligent driving assistance systems. However, traffic video text tracking often has the problems of missed and false detections because of illumination occlusion and similar appearances. In this paper, we propose a new Swin transformer-based traffic video text tracking method, known as STVT, which is composed of a Siamese SwinDC transformer module, a deformable text detection module, and a text matching module. The STVT method employs the Siamese SwinDC transformer module, which performs text detection by considering both temporal and spatial dimensions, mitigating the issue of missed detections caused by occlusion. The text matching module combines the semantic, visual, and geometric features of text instances to effectively differentiate visually similar text instances. Extensive experiments demonstrated that our proposed STVT method outperformed the state-of-the-art methods on various benchmark datasets. On the ICDAR2015 dataset, compared with those of the Free method, the mostly matched (MM) result increased by 32.0% (702 vs. 926), and the mostly lost (ML) result decreased by 33.2% (568 vs. 850). The visualization results demonstrated that the proposed STVT model can accurately detect and track occluded text instances in traffic videos. On the ICDAR2023 dataset, our method achieved a 6.01% improvement in MOTA compared to that of the TransDETR method, demonstrating that our proposed method is effective for small and dense text detection problems. In addition, qualitative and quantitative analyses confirmed the effectiveness and real-time performance of our proposed STVT method. [ABSTRACT FROM AUTHOR]

This paper addresses the evaluation of multi-step point forecasting models. Currently, deep learning models for multi-step forecasting are evaluated on datasets by selecting one error metric that is aggregated across the time series and the forecast horizon. This approach hides insights that would otherwise be useful for practitioners when evaluating and selecting forecasting models. We propose four novel metrics to provide additional insights when evaluating models: 1) a win-loss metric that shows how models perform across time series in the dataset , allowing the practitioner to check whether the model is superior for all series or just a subset of series. 2) a variance weighted metric that accounts for differences in variance across the seasonal period. It can be used to evaluate models for seasonal datasets such as rush hour traffic prediction, where it is desirable to select the model that performs best during the periods of high uncertainty. 3) a delta horizon metric measuring how much models update their forecast for a period in the future over the forecast horizon. Less change to the forecast means more stability over time and is desirable for most forecasting applications. 4) decomposed errors that relate the forecasting error to trend, seasonality, and noise. Decomposing the errors allows the practitioners to identify for which components the model is making more errors and adjust the model accordingly. To show the applicability of the proposed metrics, we implement four deep learning architectures and conduct experiments on five benchmark datasets. We highlight several use cases for the proposed metrics and discuss the applicability in light of the empirical results. [ABSTRACT FROM AUTHOR]

Speech emotion recognition (SER) has gained significant attention due to its several application fields, such as mental health, education, and human-computer interaction. However, the accuracy of SER systems is hindered by high-dimensional feature sets that may contain irrelevant and redundant information. To overcome this challenge, this study proposes an iterative feature boosting approach for SER that emphasizes feature relevance and explainability to enhance machine learning model performance. Our approach involves meticulous feature selection and analysis to build efficient SER systems. In addressing our main problem through model explainability, we employ a feature evaluation loop with Shapley values to iteratively refine feature sets. This process strikes a balance between model performance and transparency, which enables a comprehensive understanding of the model's predictions. The proposed approach offers several advantages, including the identification and removal of irrelevant and redundant features, leading to a more effective model. Additionally, it promotes explainability, facilitating comprehension of the model's predictions and the identification of crucial features for emotion determination. The effectiveness of the proposed method is validated on the SER benchmarks Toronto emotional speech set (TESS), Berlin Database of Emotional Speech (EMO-DB), Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), and Surrey Audio-Visual Expressed Emotion (SAVEE) dataset, outperforming state-of-the-art methods. These results highlight the potential of the proposed technique in developing accurate and explainable SER systems. To the best of our knowledge, this is the first work to incorporate model explainability into an SER framework. The source code of this paper is publicly available via this https://github.com/alaaNfissi/Unveiling-Hidden-Factors-Explainable-AI-for-Feature-Boosting-in-Speech-Emotion-Recognition. [ABSTRACT FROM AUTHOR]

Within the federated learning (FL) framework, the client collaboratively trains the model in coordination with a central server, while the training data can be kept locally on the client. Thus, the FL framework mitigates the privacy disclosure and costs related to conventional centralized machine learning. Nevertheless, current surveys indicate that FL still has problems in terms of communication efficiency and privacy risks. In this paper, to solve these problems, we develop an FL framework with communication-efficient and privacy-preserving (FLCP). To realize the FLCP, we design a novel compression algorithm with efficient communication, namely, adaptive weight compression FedAvg (AWC-FedAvg). On the basis of the non-independent and identically distributed (non-IID) and unbalanced data distribution in FL, a specific compression rate is provided for each client, and homomorphic encryption (HE) and differential privacy (DP) are integrated to provide demonstrable privacy protection and maintain the desirability of the model. Therefore, our proposed FLCP smoothly balances communication efficiency and privacy risks, and we prove its security against "honest-but-curious" servers and extreme collusion under the defined threat model. We evaluate the scheme by comparing it with state-of-the-art results on the MNIST and CIFAR-10 datasets. The results show that the FLCP performs better in terms of training efficiency and model accuracy than the baseline method. [ABSTRACT FROM AUTHOR]

Our generation is quite obsessed with technology and we like to share our personal information such as photos and videos on the internet via different social networking websites i.e. Facebook, Snapchat, Instagram, etc. Therefore, it becomes easier for others to breach our privacy and harm us in a direct or indirect way. Now, computerized systems have advanced due to the improvements in Machine Learning (ML) algorithms and Artificial Intelligence (AI). These algorithms can extract sensitive information such as face attributes, text information, etc. from images or videos and can be used for privacy breaching. In this paper, we propose a novel privacy protection method by adding intelligent noise to the image while preserving image aesthetics and attributes. We determine multiple attributes for an image such as baldness, smiling, gender, etc. and we intelligently add noise to particular regions of the image that define a particular attribute using the visual explanation technique i.e. GradCam++, thereby preserving the other attributes. The addition of noise is based on the idea of Fast Gradient Sign Method (FGSM) that maximizes the gradients of the loss of an input image to create a new adversarial image. We integrate FGSM adversarial image and GradCam++ output to affect particular attributes only and hence keeping the image human imperceptible. The experiment results show that our attack outperforms the existing attacks including naive FGSM, Projected Gradient Descent (PGD), Momentum Iterative Method (MIM), Shadow Attack (SA), and Fast Minimum Norm (FMN) in terms of preserving attributes and image visual quality, when evaluated on CelebA dataset. [ABSTRACT FROM AUTHOR]

In recent years, a number of backdoor attacks against deep neural networks (DNN) have been proposed. In this paper, we reveal that backdoor attacks are vulnerable to image compressions, as backdoor instances used to trigger backdoor attacks are usually compressed by image compression methods during data transmission. When backdoor instances are compressed, the feature of backdoor trigger will be destroyed, which could result in significant performance degradation for backdoor attacks. As a countermeasure, we propose the first compression-resistant backdoor attack method based on feature consistency training. Specifically, both backdoor images and their compressed versions are used for training, and the feature difference between backdoor images and their compressed versions are minimized through feature consistency training. As a result, the DNN treats the feature of compressed images as the feature of backdoor images in feature space. After training, the backdoor attack will be robust to image compressions. Furthermore, we consider three different image compressions (i.e., JPEG, JPEG2000, WEBP) during the feature consistency training, so that the backdoor attack can be robust to multiple image compression algorithms. Experimental results demonstrate that when the backdoor instances are compressed, the attack success rate of common backdoor attack is 6.63% (JPEG), 6.20% (JPEG2000) and 3.97% (WEBP) respectively, while the attack success rate of the proposed compression-resistant backdoor attack is 98.77% (JPEG), 97.69% (JPEG2000), and 98.93% (WEBP) respectively. The compression-resistant attack is robust under various parameters settings. In addition, extensive experiments have demonstrated that even if only one image compression method is used in the feature consistency training process, the proposed compression-resistant backdoor attack has the generalization ability to resist multiple unseen image compression methods. [ABSTRACT FROM AUTHOR]

The growing relevance of artificial intelligence (AI) for technical systems offers significant potential for the realization and operation of autonomous systems in complex and potentially unknown environments. However, unlike classical solution approaches, the functionality of an AI system cannot be verified analytically, which is why data-driven approaches such as scenario-based testing are used. With the increasing complexity of the required functionality of the AI-based system, the quantity, and quality of the data needed for development and validation also increase. To meet this demand, data generated synthetically using simulation is increasingly being used. Compared to the acquisition of real-world reference data, simulation offers the major advantage that it can be configured to test specific scenarios of interest. This paper presents an architecture for the systematic generation of virtual test scenarios to establish synthetically generated test data as an integral part of the development and validation process for AI systems. Key aspects of this architecture are the consistent use of digital twins as virtual 1-to-1 replicas and a simulation infrastructure that enables the generation of training and validation data for AI-based systems in appropriate quantity, quality, and time. In particular, this paper focuses on the application of the architecture in the context of two use cases from different application domains. [ABSTRACT FROM AUTHOR]

Complex visual question answering holds the potential to enhance artificial intelligence proficiency in understanding natural language, stimulate advances in computer vision technologies, and expand the range of practical applications. However, achieving desirable answers is often hindered by factors such as inconsistent form and content of pre-training and fine-tuning tasks, and the involvement of external knowledge. In this paper, we propose a complex visual question answering model based on uniform form and content, which aims to achieve better feature consistency and enhance model performance. To guide the question answering task and compensate for inconsistencies in the form of pre-training and downstream tasks, an encoding and decoding model is employed to generate auto-prompt tuning templates with masks. Moreover, the intermediate process between pre-training and the downstream task, which is similar to the downstream task, helps to further bridge the content gap between the two modalities. Based on this foundation, we propose a novel APT-CVQA model that incorporates a hybrid architecture and a joint loss function for cross-entropy and SIMCLR. On the complex scenario KR-VQA dataset, the accuracy of our model surpasses the optimal performance by 2.45 % . On the universal dataset GQA, our model performs 6.87 % better than the optimal performance of the compared models. The whole process is divided into three phases. Phase-1 generates auto-prompt tuning templates, Phase-2 facilitates the creation of intermediate pre-trained checkpoints, and Phase-3 is used for fine-tuning. [ABSTRACT FROM AUTHOR]

The cost of collecting and annotating large-scale datasets is expensive, thus the valuable datasets can be considered as the intellectual property (IP) of the dataset creator. To date, all the copyright protection methods for deep learning focus on the copyright protection of the models, while there are no researches on copyright protection of the dataset. Protecting the intellectual property of dataset is a brand new topic which is very challenging. In this paper, we propose an authorization control method to actively protect the dataset from being used to train Deep Neural Network (DNN) models without authorization. To the best of our knowledge, this is the first work on IP protection for dataset. We generate feature space adversarial examples for clean images. Then, we utilize the modified Reversible Image Transformation to hide the clean images into the corresponding feature space adversarial examples to generate the protected images. For the unauthorized users, the model directly trained on the protected dataset will have poor inference accuracy. For the authorized users, the model can be trained on the recovered dataset and will have normal inference accuracy. Experimental results on CIFAR-10 and TinyImageNet datasets demonstrate the effectiveness of the proposed method. It is also demonstrated that the proposed method has an excellent transferability across different models. Moreover, the proposed method is robust to the adaptive attack. [ABSTRACT FROM AUTHOR]

The topology optimization of crash structures in automotive and aeronautical applications is challenging. Purely mathematical methods struggle due to the complexity of determining the sensitivities of the relevant objective functions and restrictions according to the design variables. For this reason, the Graph- and Heuristic-based Topology optimization (GHT) was developed, which controls the optimization process with rules derived from expert knowledge. In order to extend the collected expert rules, the use of reinforcement learning (RL) agents for deriving a new optimization rule is proposed in this paper. This heuristic is designed in such a way that it can be applied to many different models and load cases. An environment is introduced in which agents interact with a randomized graph to improve cells of the graph by inserting edges. The graph is derived from a structural frame model. Cells represent localized parts of the graph and delineate the areas where agents can insert edges. A newly developed shape preservation metric is presented to evaluate the performance of topology changes made by agents. This metric evaluates how much a cell has deformed by comparing its shape in the deformed and undeformed state. The training process of the agents is described and their performance is evaluated in the training environment. It is shown how the agents and the environment can be integrated as a new heuristic into the GHT. An optimization of the frame model and a vehicle rocker model with the enhanced GHT is carried out to assess its performance in practical optimizations. [ABSTRACT FROM AUTHOR]

In this era of e-commerce, many companies are moving towards subscription-based invoicing platforms to maintain their electronic invoices. Unfortunately, fraudsters are using these platforms for different types of malicious activities. Identifying fraudsters is often challenging for many companies due to the limitation of time and other resources. A fully automated fraud detection model can be useful, but it creates a risk of false-positive identification. This paper proposed a hybrid fraud detection framework when only a small set of labelled (fraud/non-fraud) data is available, and human input is required in the final decision-making step. This framework used a combination of unsupervised and supervised machine learning, red-flag prioritization, and an augmented AI approach containing a human-in-the-loop process. It also proposed a weighted center based on the feature importance scores for the fraud risk cluster and used it in the red-flag prioritization process. Finally, the approach is illustrated using a case study to identify fraudulent users in an invoicing platform. Our hybrid framework showed promising results in identifying fraudulent users and improving human performance when human input is required to make the final decision. [ABSTRACT FROM AUTHOR]

Training automated trading agents is a long-standing topic that has been widely discussed in artificial intelligence for the quantitative finance. Reinforcement learning (RL) is designed to solve the sequential decision-making tasks, like the stock trading. The output of the RL is the policy which can be presented as the probability values of the possible actions based on a given state. The policy is optimized by the reward function. However, even if the profit is considered as the natural reward function, a trading agent equipped with an RL model has several serious problems. Specifically, profit is only obtained after executing sell action, different profits exist at the same time step due to the varying-length transactions and the hold action deals with two opposite states, empty or nonempty position. To alleviate these shortcomings, in this paper, we introduce a new trading action called wait for the empty position status and design the appropriate rewards to all actions. Based on the new action space and reward functions, a novel approach named Transaction-aware Inverse Reinforcement Learning (TAIRL) is proposed. TAIRL rewards all trading actions for avoiding the reward bias and dilemma. TAIRL is evaluated by backtesting on 12 stocks of US, UK and China stock markets, and compared against other state-of-art RL methods and moving average trading methods. The experimental results show that the agent of TAIRL achieves the state-of-art performance in profitability and anti-risk ability. [ABSTRACT FROM AUTHOR]

Automated Machine Learning-based systems' integration into a wide range of tasks has expanded as a result of their performance and speed. Although there are numerous advantages to employing ML-based systems, if they are not interpretable, they should not be used in critical or high-risk applications. To address this issue, researchers and businesses have been focusing on finding ways to improve the explainability of complex ML systems, and several such methods have been developed. Indeed, there are so many developed techniques that it is difficult for practitioners to choose the best among them for their applications, even when using evaluation metrics. As a result, the demand for a selection tool, a meta-explanation technique based on a high-quality evaluation metric, is apparent. In this paper, we present a local meta-explanation technique which builds on top of the truthfulness metric, which is a faithfulness-based metric. We demonstrate the effectiveness of both the technique and the metric by concretely defining all the concepts and through experimentation. [ABSTRACT FROM AUTHOR]

Predicting students' performance in distance courses is a very relevant task to help teachers identify students who need reinforcement or extension activities. Nevertheless, identifying the student's progress is highly complicated due to the large number of students and the lack of direct interaction. Artificial intelligence algorithms contribute to overcoming this problem by automatically analyzing the features and interactions of each student with the e-learning platform. The main limitations of the previous proposals are that they do not consider a ranking between the different marks obtained by students and the most accurate models are usually black boxes without comprehensibility. This paper proposes to use an optimized ordinal classification algorithm, FlexNSLVOrd, that performs a prediction of student's performance in four ranking classes (Withdrawn < Fail < Pass < Distinction) by generating highly understandable models. The experimental study uses the OULA dataset and compares 10 state-of-the-art methods on 7 different courses and 3 classical classification metrics. The results, validated with statistical analysis, show that FlexNSLVOrd has higher performance than the other models and achieves significant differences with the rest of the proposals. In addition, the interpretability of FlexNSLVOrd is compared with other rule-based models, and simpler and more representative rules are obtained. [ABSTRACT FROM AUTHOR]

Generative Adversarial Networks (GAN) show excellent performance in various problems of computer vision, computer graphics, and machine learning, but require large amounts of data and huge computational resources. There is also the issue of unstable training. If the generator and discriminator diverge during the training process, the GAN is subsequently difficult to converge. In order to tackle these problems, various transfer learning methods have been introduced; however, mode collapse, which is a form of overfitting, often arises. Moreover, there were limitations in learning the distribution of the training data. In this paper, we provide a comprehensive review of the latest transfer learning methods as a solution to the problem, propose the most effective method of fixing some layers of the generator and discriminator, and discuss future prospects. The model to be used for the experiment is StyleGAN, and the performance evaluation uses Fréchet Inception Distance (FID), coverage, and density. Results of the experiment revealed that the proposed method did not overfit. The model was able to learn the distribution of the training data relatively well compared to the previously proposed methods. Moreover, it outperformed existing methods at the Stanford Cars, Stanford Dogs, Oxford Flower, Caltech-256, CUB-200–2011, and Insect-30 datasets. [ABSTRACT FROM AUTHOR]

Over recent decades, research in Artificial Intelligence (AI) has developed a broad range of approaches and methods that can be utilized or adapted to address complex optimization problems. As real-world problems get increasingly complicated, this requires an effective optimization method. Various meta-heuristic algorithms have been developed and applied in the optimization domain. This paper used and ameliorated a promising meta-heuristic approach named Crow Search Algorithm (CSA) to address numerical optimization problems. Although CSA can efficiently optimize many problems, it needs more searchability and early convergence. Its positioning updating process was improved by supporting two adaptive parameters: flight length (fl) and awareness probability (AP) to tackle these curbs. This is to manage the exploration and exploitation conducts of CSA in the search space. This process takes advantage of the randomization of crows in CSA and the adoption of well-known growth functions. These functions were recognized as exponential, power, and S-shaped functions to develop three different improved versions of CSA, referred to as Exponential CSA (ECSA), Power CSA (PCSA), and S-shaped CSA (SCSA). In each of these variants, two different functions were used to amend the values of fl and AP. A new dominant parameter was added to the positioning updating process of these algorithms to enhance exploration and exploitation behaviors further. The reliability of the proposed algorithms was evaluated on 67 benchmark functions, and their performance was quantified using relevant assessment criteria. The functionality of these algorithms was illustrated by tackling four engineering design problems. A comparative study was made to explore the efficacy of the proposed algorithms over the standard one and other methods. Overall results showed that ECSA, PCSA, and SCSA have convincing merits with superior performance compared to the others. [ABSTRACT FROM AUTHOR]

Vehicle routing (VRP) and traveling salesman problems (TSP) are classical and interesting NP-hard routing combinatorial optimization (CO) with practical significance. While moving forward with artificial intelligence, researchers are paying more and more attention to applying machine learning to classical CO problems. However, traditional reinforcement learning faces challenges like reward sparsity and unstable training, so it is necessary to assist agents in finding high-quality routings in the initial model training stage to obtain more positive feedback. This paper proposes a novel Monte Carlo Tree Search (MCTS)-based two-stage multi-agent reinforcement learning training pipeline (MCRL) in which we also design a multifunctional reward function, improving efficiency, accuracy, and diversity to guide agents to learn the routings over graphs better. Besides, previous approaches are frequently too sluggish in runtime to be useful in contexts with sparsely connected networks and uncertain traffic. As an alternative, we design a model based on graph neural networks that can execute multi-agent routing in a sparsely connected graph with constantly changing traffic circumstances. Also, the agents are better equipped to collaborate online and adjust to changes thanks to our learned communication module. [ABSTRACT FROM AUTHOR]

We are witnessing the digitalization era, where artificial intelligence (AI)/machine learning (ML) models are mandatory to transform this data deluge into actionable information. However, these models require large, high-quality datasets to predict high reliability/accuracy. Even with the maturity of Internet of Things (IoT) systems, there are still numerous scenarios where there is not enough quantity and quality of data to successfully develop AI/ML-based applications that can meet market expectations. One such scenario is precision agriculture, where operational data generation is costly and unreliable due to the extreme and remote conditions of numerous crops. In this paper, we investigated the generation of synthetic data as a method to improve predictions of AI/ML models in precision agriculture. We used generative adversarial networks (GANs) to generate synthetic temperature data for a greenhouse located in Murcia (Spain). The results reveal that the use of synthetic data significantly improves the accuracy of the AI/ML models targeted compared to using only ground truth data. [ABSTRACT FROM AUTHOR]

In recent years, artificial intelligence has drawn the attention of the world, and the contributions of deep learning is enormous. The convolution neural network (CNN) provides more opportunities and better choices for our work. This paper explores the potential of deep neural networks in single image super-resolution (SR). In fact, some models based on deep neural networks have achieved remarkable performance in the reconstruction accuracy of individual images, but there is more room for development. In this paper, we removed the bicubic interpolation operation which is handcraft up-sampling and not intelligent enough. And we introduced deconvolution layer instead of up-sampling layer. In addition, we designed the local polymorphic parallel network and many-to-many connections. On the basis of this theory, we have carried out a simulation experiment to prove the excellent effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

This study examines an optimal pricing policy for managing deteriorating products in a stochastic inventory system. Customer arrival is formulated as a Poisson process with a fixed rate, and customer demand is probabilistically expressed based on the valuation of the product. Typically, customer interest in items decreases over time because of the declining quality of deteriorating products. A dynamic pricing policy is needed to increase retailer profitability under stochastic scenarios. This paper combines the Hamilton–Jacobi–Bellman (HJB) equation with the Particle Swarm Optimization (PSO) approach to realize an optimal solution for the dynamic pricing strategy with specific boundaries using an analytical approach. Furthermore, an artificial intelligence-based High-Order Neural Network (HONN) model is implemented as an intelligent strategy to approximate the complex dynamic behaviors of the stochastic inventory system. The present study aims to fill the research gap by comparing the analytical solution obtained from the hybrid optimization using HJB–PSO and the intelligent strategy obtained from the HONN model. The proposed approaches bring greater accuracy and efficiency to inventory management tools. The performance difference between the proposed algorithms indicates that the error does not exceed the desired limit (≤ 1%), indicating that the analytical and numerical solutions found can be used interchangeably in practice. Furthermore, all validation tests ensure that the proposed decision support system can aid policymakers in managing stochastic inventory systems with minimal effort and adopting strategies to ensure resilience and customer satisfaction. [ABSTRACT FROM AUTHOR]

Closed Captioning (CC) is a telecommunications service to display textual information equivalent to audio. Although the primary consumer group is Deaf (D) and Hard of Hearing (HOH) viewers, they are typically excluded from the quality assessment process. Including D and HOH viewers for all assessments is nearly impossible and requires enormous effort. One solution is to use machine learning algorithms to replicate human subjective evaluation of the quality of CC. In this paper, a multi-label classifier was trained using an active learning algorithm with D and HOH viewers, predicting human subjective ratings on the various quality of CC. An online user study was conducted to train the multilayer perception with D and HoH participant subjective quality assessment rating data on machine-queried CC encoded to short video clips in various genres. The result revealed the possibilities of using an automated assessment system to predict the human perceived quality of CC, human preferences and perceiving behaviour upon viewing CC with deliberate error inclusion. [ABSTRACT FROM AUTHOR]

Robust model estimation aims to estimate the parameters of a given geometric model, and then separate the outliers and inliers belonging to different model instances into different groups based on the estimated parameters. Robust model estimation is a fundamental task in computer vision and artificial intelligence, and mainly contains two components: data sampling for generating hypotheses and model selection for segmenting data. Over the past decade, a number of guided data sampling algorithms and model selection algorithms have been proposed separately. This results in that the performance of the robust model estimation method is still unsatisfactory. In this paper, we first present a comprehensive study of the above algorithms, by analyzing and comparing them. Then, we propose an efficient and effective robust model estimation method by using preference analysis and information theory principles. Specifically, we first employ our previously proposed data sampling algorithm based on preference analysis to sample data subsets for generating promising hypotheses. Then, we build a discriminative sparse affinity matrix based on the generated hypotheses by using information theory principles. Finally, we segment data by conducting a spectral clustering on the discriminative affinity matrix. Experimental results on the AdelaideRMF and the Hopkins 155 datasets show that the proposed method achieves higher segmentation accuracies than several state-of-the-art model estimation methods. [ABSTRACT FROM AUTHOR]

Stock markets are the result of the interaction of multiple participants, and market makers are one of them. Their main goal is to provide liquidity and market depth to the stock market by streaming bids and offers at both sides of the order book, at different price levels. This activity allows the rest of the participants to have more available prices to buy or sell stocks. In the last years, reinforcement learning market maker agents have been able to be profitable. But profit is not the only measure to evaluate the quality of a market maker. Inventory management arises as a risk source that must be under control. In this paper, we focus on inventory risk management designing an adaptive reward function able to control inventory depending on designer preferences. To achieve this, we introduce two control coefficients, AIIF (Alpha Inventory Impact Factor) and DITF (Dynamic Inventory Threshold Factor), which modulate dynamically the behavior of the market maker agent according to its evolving liquidity with good results. In addition, we analyze the impact of these factors in the trading operative, detailing the underlying strategies performed by these intelligent agents in terms of operative, profitability and inventory management. Last, we present a comparison with other existing reward functions to illustrate the robustness of our approach. [ABSTRACT FROM AUTHOR]

Injecting prior knowledge into the learning process of a neural architecture is one of the main challenges currently faced by the artificial intelligence community, which also motivated the emergence of neural-symbolic models. One of the main advantages of these approaches is their capacity to learn competitive solutions with a significant reduction of the amount of supervised data. In this regard, a commonly adopted solution consists of representing the prior knowledge via first-order logic formulas, then relaxing the formulas into a set of differentiable constraints by using a t-norm fuzzy logic. This paper shows that this relaxation, together with the choice of the penalty terms enforcing the constraint satisfaction, can be unambiguously determined by the selection of a t-norm generator, providing numerical simplification properties and a tighter integration between the logic knowledge and the learning objective. When restricted to supervised learning, the presented theoretical framework provides a straight derivation of the popular cross-entropy loss, which has been shown to provide faster convergence and to reduce the vanishing gradient problem in very deep structures. However, the proposed learning formulation extends the advantages of the cross-entropy loss to the general knowledge that can be represented by neural-symbolic methods. In addition, the presented methodology allows the development of novel classes of loss functions, which are shown in the experimental results to lead to faster convergence rates than the approaches previously proposed in the literature. [ABSTRACT FROM AUTHOR]

In software engineering (SE), code classification and related tasks, such as code clone detection are still challenging problems. Due to the elusive syntax and complicated semantics in software programs, existing traditional SE approaches still have difficulty differentiating between the functionalities of code snippets at the semantic level with high accuracy. As artificial intelligence (AI) techniques have increased in recent years, exploring different machine/deep learning techniques for code classification algorithms has become important. However, most existing machine/deep learning-based approaches often consider using convolutional neural networks (CNNs) or recurrent neural networks (RNNs) to process code texts. However, the two networks inevitably suffer from gradient vanishing problems and fail to capture long-distance dependencies from code statements, resulting in poor performance in downstream tasks. In this paper, we propose the TBCC (Transformer-Based Code Classifier), a novel transformer-based neural network for programming language processing, which can avoid these two problems. Moreover, to capture the important syntactical features from programming languages, we split the deep abstract syntax trees (ASTs) into smaller subtrees that, aim to exploit syntactical information in code statements. We have applied the TBCC to two different common program comprehension tasks to verify its effectiveness: a code classification task for C programs and a code clone detection task for Java programs. The experimental results show that the TBCC achieves state-of-the-art performance, outperforming the baseline methods in terms of accuracy, recall, and F1 score. For subsequent research, the code of TBCC has been released ∗. [ABSTRACT FROM AUTHOR]

According to the first use case scenario, Extended Generalized Graph (EGG) can replace existing data modeling languages for domain-specific data modeling activities. Second, the study presents and implements (for some data modeling languages, including RDF, XML, RDBM, UML, and AOM) a unique approach to measure and compare data modeling languages by mapping their metamodels to the EGG metamodel. Third, the EGG described in this research prevents the transformation of reality to meet the data modeling language requirements because it is sufficiently generic for domain data modeling. [Extracted from the article]

Modeling and predicting player behavior is of the utmost importance in game development and matchmaking. A variety of methods have been proposed to build artificial intelligence (AI), human-like players. However, these human-like players have a limited ability to imitate the behavior of individual players. In this paper, we propose a player behavior imitation method using imitation learning under the framework of meta-learning. A generic behavior model of game players was learned from historical records using adversarial imitation learning. Then, we personalized the policy by imitating the behavior of each individual player. Convolutional neural networks were used to construct the feature extractor of game board states. The experiments were conducted using the Reversi game, and 18,000 game records of different players were used to train the generic behavior model. The behavior of each new player was learned using only hundreds of records. The results demonstrate that our method can be utilized to imitate individual behavior in terms of action similarity well. [ABSTRACT FROM AUTHOR]

Uncertainty is of great concern in information fusion and artificial intelligence. Dempster-Shafer theory is a popular tool to deal with uncertainty, but it cannot effectively represent and fuse uncertain information involving non-exclusiveness and incompleteness. In order to solve that problem, an idea of D number theory (DNT) has been proposed. In this paper, the basic theory of DNT for the fusion of non-exclusive and incomplete information is studied to strengthen its theoretical foundation, including concept formalization, uncertainty representation, information modelling and fusion. At first, the non-exclusiveness in DNT is defined formally and its basic properties are discussed. Secondly, new measures of belief and plausibility for D numbers are developed. Thirdly, the combination rule for D numbers is studied by extending the exclusive conflict redistribution rule. Fourthly, a method to combine information-incomplete D numbers is proposed. The proposed concepts, definitions, and methods are analyzed mathematically and exemplified through illustrative examples. [ABSTRACT FROM AUTHOR]

The combination and aggregation of knowledge from multiple neural networks can be commonly seen in the form of mixtures of experts. However, such combinations are usually done using networks trained on the same tasks, with little mention of the combination of heterogeneous pre-trained networks, especially in the data-free regime. The problem of combining pre-trained models in the absence of relevant datasets is likely to become increasingly important, as machine learning continues to dominate the AI landscape, and the number of useful but specialized models explodes. This paper proposes multiple data-free methods for the combination of heterogeneous neural networks, ranging from the utilization of simple output logit statistics, to training specialized gating networks. The gating networks decide whether specific inputs belong to specific networks based on the nature of the expert activations generated. The experiments revealed that the gating networks, including the universal gating approach, constituted the most accurate approach, and therefore represent a pragmatic step towards applications with heterogeneous mixtures of experts in a data-free regime. The code for this project is hosted on github at https://github.com/cwkang1998/network-merging. [ABSTRACT FROM AUTHOR]

Symbolic knowledge representation and reasoning and deep learning are fundamentally different approaches to artificial intelligence with complementary capabilities. The former are transparent and data-efficient, but they are sensitive to noise and cannot be applied to non-symbolic domains where the data is ambiguous. The latter can learn complex tasks from examples, are robust to noise, but are black boxes; require large amounts of –not necessarily easily obtained– data, and are slow to learn and prone to adversarial examples. Either paradigm excels at certain types of problems where the other paradigm performs poorly. In order to develop stronger AI systems, integrated neuro-symbolic systems that combine artificial neural networks and symbolic reasoning are being sought. In this context, one of the fundamental open problems is how to perform logic-based deductive reasoning over knowledge bases by means of trainable artificial neural networks. This paper provides a brief summary of the authors' recent efforts to bridge the neural and symbolic divide in the context of deep deductive reasoners. Throughout the paper we will discuss strengths and limitations of models in term of accuracy, scalability, transferability, generalizabiliy, speed, and interpretability, and finally, will talk about possible modifications to enhance desirable capabilities. More specifically, in terms of architectures, we are looking at Memory-augmented networks, Logic Tensor Networks, and compositions of LSTM models to explore their capabilities and limitations in conducting deductive reasoning. We are applying these models on Resource Description Framework (RDF), first-order logic, and the description logic E L + respectively. [ABSTRACT FROM AUTHOR]

Single image rain streak removal is a significant and challenging task, which is widely applied in many artificial intelligence domains as preprocessing process. Most of existing rain streak removal works focus on designing various deraining unit (e.g., multi-stream dilation convolution) without considering the correlation between different convolution layers, which may lead to large model size. In this paper, we propose a simple and effective deep network architecture for single image rain streak removal based on deep Convolutional Neural Network (CNN). Benefit from the adjacent layers with different dilation factors have similar feature structures, we design a powerful rain streak representation network based on the Layer Similarity Prior Block (LSPB). To better cater to the property of layer similarity prior, the multi-dense-short-connection is developed and it regards every LSPB as a convolution layer, this connection style makes our overall framework to be a layer similarity prior network. To the best of our knowledge, this is the first paper to investigate the effectiveness of exploiting the layer similarity prior and the multi-dense-short-connection. Quantitative and qualitative experimental results demonstrate that the proposed method outperforms other state-of-the-art methods with the least parameters. [ABSTRACT FROM AUTHOR]

Deep neural networks are the driving force of the recent explosion of machine learning applications in everyday life. However, they usually require a lot of training data to work well, and they act as black-boxes, making predictions without any explanation about them. This paper presents Memory Wrap, a module (i.e, a set of layers) that can be added to deep learning models to improve their performance and interpretability in settings where few data are available. Memory Wrap adopts a sparse content-attention mechanism between the input and some memories of past training samples. We show that adding Memory Wrap to standard deep neural networks improves their performance when they learn from a limited set of data, and allows them to reach comparable performance when they learn from the full dataset. We discuss how the analysis of its structure and content-attention weights helps to get insights about its decision process and makes their predictions more interpretable, compared to the same networks without Memory Wrap. We test our approach on image classification tasks using several networks on three different datasets, namely CIFAR10, SVHN, and CINIC10. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have become a major driving force for visual saliency prediction. However, since the features of different layers have diverse characteristics, not all of them are effective for saliency detection, and some even cause interference. To effectively fuse multiscale features from different layers, in this paper, we propose a feature and Gaussian optimization network (FGO-Net) for saliency prediction. Specifically, we first design a novel attention ConvLSTM (ACL) module that contains circular soft layer attention to iteratively reweight multilevel features from different layers. Besides, previous works generally employed Gaussian blur with fixed kernel size after saliency maps generation as post-processing. To this end, we design an adaptive Gaussian blur (AGB) module that can automatically select the appropriate Gaussian kernel size to blur the saliency map without post-processing. Extensive experiments on several public saliency datasets demonstrate that the proposed FGO-Net achieves competitive results in terms of various evaluation metrics. [ABSTRACT FROM AUTHOR]

Easy access to audio-visual content on social media, combined with the availability of modern tools such as Tensorflow or Keras, and open-source trained models, along with economical computing infrastructure, and the rapid evolution of deep-learning (DL) methods have heralded a new and frightening trend. Particularly, the advent of easily available and ready to use Generative Adversarial Networks (GANs), have made it possible to generate deepfakes media partially or completely fabricated with the intent to deceive to disseminate disinformation and revenge porn, to perpetrate financial frauds and other hoaxes, and to disrupt government functioning. Existing surveys have mainly focused on the detection of deepfake images and videos; this paper provides a comprehensive review and detailed analysis of existing tools and machine learning (ML) based approaches for deepfake generation, and the methodologies used to detect such manipulations in both audio and video. For each category of deepfake, we discuss information related to manipulation approaches, current public datasets, and key standards for the evaluation of the performance of deepfake detection techniques, along with their results. Additionally, we also discuss open challenges and enumerate future directions to guide researchers on issues which need to be considered in order to improve the domains of both deepfake generation and detection. This work is expected to assist readers in understanding how deepfakes are created and detected, along with their current limitations and where future research may lead. [ABSTRACT FROM AUTHOR]

Recent years have witnessed a rapidly-growing research agenda that explores the combined, integrated, and collective intelligence of humans and machines working together as a team. This paper contributes to the same line of research with three main objectives: a) to introduce the concept of the SMV (Symbols-Meaning-Value) space for describing, understanding, and representing human/machine perception, cognition, and action, b) to revisit the notion of human-machine symbiosis, and c) to outline a conceptual framework of human-machine co-intelligence (i.e., the third intelligence) through human-machine symbiosis in the SMV space. By following the principle of three-way decision as thinking in threes, triads of three things are used for building an easy-to-understand, simple-to-remember, and practical-to-use framework. The three elements of the SMV space, namely, Symbols, Meaning, and Value, are closely related to the three basic human/machine functions of perception, cognition, and action, which can be metaphorically described as the seeing-knowing-doing triad or concretely interpreted as the data-knowledge-wisdom (DKW) hierarchy. Human-machine co-intelligence emerges from human-machine symbiosis in the SMV space. As the third intelligence, human-machine co-intelligence relies on and combines human intelligence and machine intelligence, is a higher level of intelligence above either human intelligence or machine intelligence alone, and is greater than the sum of human intelligence and machine intelligence. There are three basic principles of human-machine symbiosis, i.e., unified oneness, division of labor, and coevolution, for nurturing human-machine co-intelligence. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) is having an enormous impact on the rise of technology in every sector. Indeed, AI-powered systems are monitoring and deciding on sensitive economic and societal issues. The future is moving towards automation, and we must not prevent it. Many people, though, have opposing views because of the fear of uncontrollable AI systems. This concern could be reasonable if it originated from considerations associated with social issues, like gender-biased or obscure decision-making systems. Explainable AI (XAI) is a tremendous step towards reliable systems, enhancing the trust of people in AI. Interpretable machine learning (IML), a subfield of XAI, is also an urgent topic of research. This paper presents a small but significant contribution to the IML community. We focus on a local-based, neural-specific interpretation process applied to textual and time series data. Therefore, the proposed technique, which we call "LioNets", introduces novel approaches to present feature importance-based interpretations. We propose an innovative way to produce counterfactual words in textual datasets. Through a set of quantitative and qualitative experiments, we present competitiveness of LioNets compared to other techniques and suggest its usefulness. [ABSTRACT FROM AUTHOR]

This paper is concerned with a class of neutral-type neural networks with discontinuous activations and time-varying delays. Under the concept of Filippov solution, by applying the differential inclusions and the topological degree theory in set-valued analysis, we employ a novel argument to establish new results on the existence of the periodic solutions for the considered neural networks. After that, we derive some criteria on the uniqueness, global exponential stability of the considered neural networks and convergence of the corresponding autonomous case of the considered neural networks, in terms of nonsmooth analysis theory with Lyapunov-like approach. Without assuming the boundedness (or the growth condition) and monotonicity of the discontinuous neuron activation functions, the results obtained can also be valid. Our results extend previous works on the neutral-type neural networks to the discontinuous cases, some related results in the literature can be enriched and extended. Finally, two typical examples and the corresponding numerical simulations are provided to show the effectiveness and flexibility of the results derived in this paper. [ABSTRACT FROM AUTHOR]

The genome of the novel coronavirus (COVID-19) disease was first sequenced in January 2020, approximately a month after its emergence in Wuhan, capital of Hubei province, China. COVID-19 genome sequencing is critical to understanding the virus behavior, its origin, how fast it mutates, and for the development of drugs/vaccines and effective preventive strategies. This paper investigates the use of artificial intelligence techniques to learn interesting information from COVID-19 genome sequences. Sequential pattern mining (SPM) is first applied on a computer-understandable corpus of COVID-19 genome sequences to see if interesting hidden patterns can be found, which reveal frequent patterns of nucleotide bases and their relationships with each other. Second, sequence prediction models are applied to the corpus to evaluate if nucleotide base(s) can be predicted from previous ones. Third, for mutation analysis in genome sequences, an algorithm is designed to find the locations in the genome sequences where the nucleotide bases are changed and to calculate the mutation rate. Obtained results suggest that SPM and mutation analysis techniques can reveal interesting information and patterns in COVID-19 genome sequences to examine the evolution and variations in COVID-19 strains respectively. [ABSTRACT FROM AUTHOR]

The Cloud paradigm is at a critical point in which the existing energy-efficiency techniques are reaching a plateau, while the computing resources demand at Data Center facilities continues to increase exponentially. The main challenge in achieving a global energy efficiency strategy based on Artificial Intelligence is that we need massive amounts of data to feed the algorithms. This paper proposes a time-series data augmentation methodology based on synthetic scenario forecasting within the Data Center. For this purpose, we will implement a powerful generative algorithm: Generative Adversarial Networks (GANs). Specifically, our work combines the disciplines of GAN-based data augmentation and scenario forecasting, filling the gap in the generation of synthetic data in DCs. Furthermore, we propose a methodology to increase the variability and heterogeneity of the generated data by introducing on-demand anomalies without additional effort or expert knowledge. We also suggest the use of Kullback-Leibler Divergence and Mean Squared Error as new metrics in the validation of synthetic time series generation, as they provide a better overall comparison of multivariate data distributions. We validate our approach using real data collected in an operating Data Center, successfully generating synthetic data helpful for prediction and optimization models. Our research will help optimize the energy consumed in Data Centers, although the proposed methodology can be employed in any similar time-series-like problem. [ABSTRACT FROM AUTHOR]