Search

The paper introduces a natural language processing system designed to answer natural language questions across knowledge graphs for scientific data applications where no prior training data in the form of question-answer pairs is available. 59 papers, submitted by 243 authors from over 20 countries/regions to SSDBM 2021, have showcased the pervasiveness of AI/ML in the field of scientific and statistical data management, which covered a variety of related topics (among others) including: In-database machine learning. Recent advancement in deep neural networks, combined with the high performance computing power and Big Data, has profoundly brought artificial intelligence (AI) to nearly all fields of scientific disciplines. [Extracted from the article]

De-mining operations are of critical importance for humanitarian efforts and safety in conflict-affected regions. In this paper, we address the challenge of enhancing the accuracy and efficiency of mine detection systems. We present an innovative Deep Learning architecture tailored for pulse induction-based Metallic Mine Detectors (MMD), so called DL-MMD. Our methodology leverages deep neural networks to distinguish amongst nine distinct materials with an exceptional validation accuracy of 93.5%. This high level of precision enables us not only to differentiate between anti-personnel mines, without metal plates but also to detect minuscule 0.2-g vertical paper pins in both mineralized soil and non-mineralized environments. Moreover, through comparative analysis, we demonstrate a substantial 3% and 7% improvement (approx.) in accuracy performance compared to the traditional K-Nearest Neighbors and Support Vector Machine classifiers, respectively. The fusion of deep neural networks with the pulse induction-based MMD not only presents a cost-effective solution but also significantly expedites decision-making processes in de-mining operations, ultimately contributing to improved safety and effectiveness in these critical endeavors. [ABSTRACT FROM AUTHOR]

The first issue of Artificial Intelligence and Law journal was published in 1992. This paper provides commentaries on landmark papers from the first decade of that journal. The topics discussed include reasoning with cases, argumentation, normative reasoning, dialogue, representing legal knowledge and neural networks. [ABSTRACT FROM AUTHOR]

The retinal impulse signal is the basic carrier of visual information. It records the distribution of light on the retina. However, its direct conversion to a scene image is difficult due to the nonlinear characteristics of its distribution. Therefore, the use of artificial neural network to reconstruct the scene from retinal spikes has become an important research area. This paper proposes the architecture of a neural network based on vector quantization, where the feature vectors of spike trains are extracted, compressed, and stored using a feature extraction and compression network. During the decoding process, the nearest neighbour search method is used to find the nearest feature vector corresponding to each feature vector in the feature map. Finally, a reconstruction network is used to decode a new feature map composed of matching feature vectors to obtain a visual scene. This paper also verifies the impact of vector quantization on the characteristics of pulse signals by comparing experiments and visualizing the characteristics before and after vector quantization. The network delivers promising performance when evaluated on different datasets, demonstrating that this research is of great significance for improving relevant applications in the fields of retinal image processing and artificial intelligence. [ABSTRACT FROM AUTHOR]

Deep Neural Networks (DNN's) present some of the leading applications of Artificial Intelligence (AI) which have proven suitability on various machine-learning use cases. Forecasting demand of intermittent on-line sales is a task which needs to be carried out automatically for a large number of Stock Keeping Units (SKU's). This paper discusses the intermittent online sales and proposes an AI-based model for forecasting demand. We provide empirical evidence by utilizing data from 17 different sellers with approximately 3000 orders in total. Our findings indicate that thanks to their multi-layered learning structure, the DNN's can provide up to 35% better accuracy than the classic models such as Moving Average, Exponential Smoothing, Croston's method and ARIMA. Also, it was revealed that the time between orders' arrivals follow Exponential distribution and the order sizes also generally follow Exponential distribution. Thus, most of the time, Poisson Exponential distribution can be used for modelling intermittent sales process through online platforms. The analyses show that Poisson Exponential distribution can generate values close to real sales with less than 7% error margin with real data. [ABSTRACT FROM AUTHOR]

The rising population of millennials, coupled with Digital Assistants (DA) and online purchasing trends among consumers have gained increasing attention by global marketers. The study evaluates the influence of DA attributes on the purchasing intention (PUI) of millennials. A combined approach of PLS-SEM, Artificial Neural Network (ANN) and Fuzzy-set Qualitative Comparative Analysis (fsQCA) is used to predict the PUI of 345 millennials. Also, multi-group analysis is employed to uncover the influence of gender on the relationship between PUI and DA attributes. The findings suggest that DA attributes may amplify purchasing intention among millennials, especially through perceived interactivity and anthropomorphism. Further, the moderating role of gender was found significant on the inter-relationship of perceived interactivity and PUI. This research is a pioneer study in the area of artificial intelligence, conversational commerce, DA and AI-powered chatbots. This study will help marketers and practitioners to predict millennial purchasing intentions. An evaluation of this paper may help them to foster immersive and effective engagement through DA. [ABSTRACT FROM AUTHOR]

To investigate how the petroleum industry evaluates and selects powerful cloud service providers, first, an evaluation index system including 25 indices such as scalability and private data protection is built. This index system can systematically examine the comprehensive strengths of cloud service providers. Aiming to solve the problems that the traditional expert evaluation method has high requirements on expert experience and is easily affected by subjective factors, a novel artificial intelligence evaluation model named TentISSA-BPNN is proposed. The objective evaluation ability of this model can be effectively used in evaluation research on cloud service providers for petroleum enterprises. In this model, the SSA algorithm is optimized by Tent chaotic mapping and adaptive inertia weight; an algorithm, TentISSA, that has good stability and fast convergence speed is designed and proposed; and the BPNN is improved with TentISSA to obtain more accurate evaluation results. To evaluate the performance of the TentISSA algorithm, nine unimodal and multimodal functions are selected in this paper to test the convergence accuracy. Then, seven models are selected as the control groups to validate the effectiveness and performance of the TentISSA-BPNN evaluation model proposed in this paper. Finally, the preprocessed data of the candidate cloud service providers are input into the trained neural network model proposed in this paper for evaluation. Based on the ranking of the evaluation scores, the comprehensive strengths of the cloud service providers are obtained to provide a decision-making reference for managers of petroleum enterprises in the process of choosing cloud service providers. [ABSTRACT FROM AUTHOR]

Introduction: The emergence of automated machine learning or AutoML has raised an interesting trend of no-code and low-code machine learning where most tasks in the machine learning pipeline can possibly be automated without support from human data scientists. While it sounds reasonable that we should leave repetitive trial-and-error tasks of designing complex network architectures and tuning a lot of hyperparameters to AutoML, leading research using AutoML is still scarce. Thereby, the overall purpose of this case study is to investigate the gap between current AutoML frameworks and practical machine learning development. Case description: First, this paper confirms the increasing trend of AutoML via an indirect indicator of the numbers of search results in Google trend, IEEE Xplore, and ACM Digital Library during 2012–2021. Then, the three most popular AutoML frameworks (i.e., Auto-Sklearn, AutoKeras, and Google Cloud AutoML) are inspected as AutoML's representatives; the inspection includes six comparative aspects. Based on the features available in the three AutoML frameworks investigated, our case study continues to observe recent machine learning research regarding the background of image-based machine learning. This is because the field of computer vision spans several levels of machine learning from basic to advanced and it has been one of the most popular fields in studying machine learning and artificial intelligence lately. Our study is specific to the context of image-based road health inspection systems as it has a long history in computer vision, allowing us to observe solution transitions from past to present. Discussion and evaluation: After confirming the rising numbers of AutoML search results in the three search engines, our study regarding the three AutoML representatives further reveals that there are many features that can be used to automate the development pipeline of image-based road health inspection systems. Nevertheless, we find that recent works in image-based road health inspection have not used any form of AutoML in their works. Digging into these recent works, there are two main problems that best conclude why most researchers do not use AutoML in their image-based road health inspection systems yet. Firstly, it is because AutoML's trial-and-error decision involves much extra computation compared to human-guided decisions. Secondly, using AutoML adds another layer of non-interpretability to a model. As these two problems are the major pain points in modern neural networks and deep learning, they may require years to resolve, delaying the mass adoption of AutoML in image-based road health inspection systems. Conclusions: In conclusion, although AutoML's utilization is not mainstream at this moment, we believe that the trend of AutoML will continue to grow. This is because there exists a demand for AutoML currently, and in the future, more demand for no-code or low-code machine learning development alternatives will grow together with the expansion of machine learning solutions. Nevertheless, this case study focuses on selected papers whose authors are researchers who can publish their works in academic conferences and journals. In the future, the study should continue to include observing novice users, non-programmer users, and machine learning practitioners in order to discover more insights from non-research perspectives. [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]

Recently, skin cancer is one of the spread and dangerous cancers around the world. Early detection of skin cancer can reduce mortality. Traditional methods for skin cancer detection are painful, time-consuming, expensive, and may cause the disease to spread out. Dermoscopy is used for noninvasive diagnosis of skin cancer. Artificial Intelligence (AI) plays a vital role in diseases' diagnosis especially in biomedical engineering field. The automated detection systems based on AI reduce the complications in the traditional methods and can improve skin cancer's diagnosis rate. In this paper, automated early detection system for skin cancer dermoscopic images using artificial intelligent is presented. Adaptive snake (AS) and region growing (RG) algorithms are used for automated segmentation and compared with each other. The results show that AS is accurate and efficient (accuracy = 96%) more than RG algorithm (accuracy = 90%). Artificial Neural networks (ANN) and support vector machine (SVM) algorithms are used for automated classification compared with each other. The proposed system with ANN algorithm shows high accuracy (94%), precision (96%), specificity (95.83%), sensitivity (recall) (92.30%), and F1-score (0.94). The proposed system is easy to use, time consuming, enables patients to make early detection for skin cancer and has high efficiency. [ABSTRACT FROM AUTHOR]

With the continuous development and combined application of cloud computing and artificial intelligence, some new methods have emerged to reduce task execution time for training neural network models in a cloud-edge collaborative environment. The most attractive method is neural network model segmentation. However, many factors affect the segmentation point, such as resource allocation, system energy consumption, load balancing, and network Bandwidth allocation. Some segmentation methods consider the shortest task execution time, which ignores the utilization of resources at the edge and can result in resource waste. Additionally, these factors are difficult to measure, which presents a challenge in calculating the best segmentation point to achieve the goal of maximum resource utilization and minimum task execution time. To solve this problem, this paper proposes a cloud-edge collaborative task scheduling method based on model segmentation (CECMS). This method first analyzes the factors affecting the segmentation point of the model and then obtains accurate factors that affect the segmentation point calculation through the pre-execution method. Furthermore, a multi-objective solution algorithm is improved to calculate the optimal model segmentation point. And tasks are separately offloaded to the edge and cloud based on the optimal model segmentation point. Finally, the experiments are conducted to verify the effectiveness of this method. Finally, the effectiveness of the CECMS method was verified through simulation experiments. Compared with the Dynamic Adaptive DNN Surgery (DADS) method and an adaptive DNN inference acceleration framework algorithm with end–edge–cloud collaborative computing algorithm (ADC), CECMS achieves the same effectiveness as DADS and ADC in optimizing task execution time by comprehensively considering the utilization of edge resources and minimizing task execution time, while also effectively ensuring resource utilization. [ABSTRACT FROM AUTHOR]

Across the globe, governments are developing policies and strategies to reduce carbon emissions to address climate change. Monitoring the impact of governments' carbon reduction policies can significantly enhance our ability to combat climate change and meet emissions reduction targets. One promising area in this regard is the role of artificial intelligence (AI) in carbon reduction policy and strategy monitoring. While researchers have explored applications of AI on data from various sources, including sensors, satellites, and social media, to identify areas for carbon emissions reduction, AI applications in tracking the effect of governments' carbon reduction plans have been limited. This study presents an AI framework based on long short-term memory (LSTM) and statistical process control (SPC) for the monitoring of variations in carbon emissions, using UK annual CO2 emission (per capita) data, covering a period between 1750 and 2021. This paper used LSTM to develop a surrogate model for the UK's carbon emissions characteristics and behaviours. As observed in our experiments, LSTM has better predictive abilities than ARIMA, Exponential Smoothing and feedforward artificial neural networks (ANN) in predicting CO2 emissions on a yearly prediction horizon. Using the deviation of the recorded emission data from the surrogate process, the variations and trends in these behaviours are then analysed using SPC, specifically Shewhart individual/moving range control charts. The result shows several assignable variations between the mid-1990s and 2021, which correlate with some notable UK government commitments to lower carbon emissions within this period. The framework presented in this paper can help identify periods of significant deviations from a country's normal CO2 emissions, which can potentially result from the government's carbon reduction policies or activities that can alter the amount of CO2 emissions. [ABSTRACT FROM AUTHOR]

Artificial neural networks (ANNs), inspired by the human brain's network of neurons and synapses, enable computing machines and systems to execute cognitive tasks, thus embodying artificial intelligence (AI). Since the performance of ANNs generally improves with the expansion of the network size, and also most of the computation time is spent for matrix operations, AI computation have been performed not only using the general-purpose central processing unit (CPU) but also architectures that facilitate parallel computation, such as graphic processing units (GPUs) and custom-designed application-specific integrated circuits (ASICs). Nevertheless, the substantial energy consumption stemming from frequent data transfers between processing units and memory has remained a persistent challenge. In response, a novel approach has emerged: an in-memory computing architecture harnessing analog memory elements. This innovation promises a notable advancement in energy efficiency. The core of this analog AI hardware accelerator lies in expansive arrays of non-volatile memory devices, known as resistive processing units (RPUs). These RPUs facilitate massively parallel matrix operations, leading to significant enhancements in both performance and energy efficiency. Electrochemical random-access memory (ECRAM), leveraging ion dynamics in secondary-ion battery materials, has emerged as a promising candidate for RPUs. ECRAM achieves over 1000 memory states through precise ion movement control, prompting early-stage research into material stacks such as mobile ion species and electrolyte materials. Crucially, the analog states in ECRAMs update symmetrically with pulse number (or voltage polarity), contributing to high network performance. Recent strides in device engineering in planar and three-dimensional structures and the understanding of ECRAM operation physics have marked significant progress in a short research period. This paper aims to review ECRAM material advancements through literature surveys, offering a systematic discussion on engineering assessments for ion control and a physical understanding of array-level demonstrations. Finally, the review outlines future directions for improvements, co-optimization, and multidisciplinary collaboration in circuits, algorithms, and applications to develop energy-efficient, next-generation AI hardware systems. [ABSTRACT FROM AUTHOR]

Shale gas reservoirs are contributing a major role in overall hydrocarbon production, especially in the United States, and due to the intense development of such reservoirs, it is a must thing to learn the productive methods for modeling production and performance evaluation. Consequently, one of the most adopted techniques these days for the sake of production performance analysis is the utilization of artificial intelligence (AI) and machine learning (ML). Hydrocarbon exploration and production is a continuous process that brings a lot of data from sub-surface as well as from the surface facilities. Availability of such a huge data set that keeps on increasing over time enhances the computational capabilities and performance accuracy through AI and ML applications using a data-driven approach. The ML approach can be utilized through supervised and unsupervised methods in addition to artificial neural networks (ANN). Other ML approaches include random forest (RF), support vector machine (SVM), boosting technique, clustering methods, and artificial network-based architecture, etc. In this paper, a systematic literature review is presented focused on the AI and ML applications for the shale gas production performance evaluation and their modeling. [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 Internet of things (IoT) is emerging as a prime area of research in the modern era. The significance of IoT in the daily life is increasing due to the increase in objects or things connected to the internet. In this paper, routing protocol for low power and lossy networks (RPL) is examined on the Contiki operating system. This paper used RPL attack framework to simulate three RPL attacks, namely hello-flood, decreased-rank and increased-version. These attacks are simulated in a separate and simultaneous manner. The focus remained on the detection of these attacks through artificial neural network (ANN)-based supervised machine learning approach. The accurate detection of the malicious nodes prevents the network from the severe effects of the attack. The accuracy of the proposed model is computed with hold-out approach and tenfold cross-validation technique. The hyperparameters have been optimized through parameter tuning. The model presented in this paper detected the aforesaid attacks simultaneously as well as individually with 100% accuracy. This work also investigated other performance measures like precision, recall, F1-score and Mathews correlation coefficient (MCC). [ABSTRACT FROM AUTHOR]

Due to digitalization, small and medium-sized enterprises (SMEs) have significantly enhanced their efficiency and productivity in the past few years. The process to automate SME transaction execution is getting highly multifaceted as the number of stakeholders of SMEs is connecting, accessing, exchanging, adding, and changing the transactional executions. The balanced lifecycle of SMEs requires partnership exchanges, financial management, manufacturing, and productivity stabilities, along with privacy and security. Interoperability platform issue is another critical challenging aspect while designing and managing a secure distributed Peer-to-Peer industrial development environment for SMEs. However, till now, it is hard to maintain operations of SMEs' integrity, transparency, reliability, provenance, availability, and trustworthiness between two different enterprises due to the current nature of centralized server-based infrastructure. This paper bridges these problems and proposes a novel and secure framework with a standardized process hierarchy/lifecycle for distributed SMEs using collaborative techniques of blockchain, the internet of things (IoT), and artificial intelligence (AI) with machine learning (ML). A blockchain with IoT-enabled permissionless network structure is designed called "B-SMEs" that provides solutions to cross-chain platforms. In this, B-SMEs address the lightweight stakeholder authentication problems as well. For that purpose, three different chain codes are deployed. It handles participating SMEs' registration, day-to-day information management and exchange between nodes, and analysis of partnership exchange-related transaction details before being preserved on the blockchain immutable storage. Whereas AI-enabled ML-based artificial neural networks are utilized, the aim is to handle and optimize day-to-day numbers of SME transactions; so that the proposed B-SMEs consume fewer resources in terms of computational power, network bandwidth, and preservation-related issues during the complete process of SMEs service deliverance. The simulation results present highlight the benefits of B-SMEs, increases the rate of ledger management and optimization while exchanging information between different chains, which is up to 17.3%, and reduces the consumption of the system's computational resources down to 9.13%. Thus, only 14.11% and 7.9% of B-SME's transactions use network bandwidth and storage capabilities compared to the current mechanism of SMEs, respectively. [ABSTRACT FROM AUTHOR]

Neural network pruning offers great prospects for facilitating the deployment of deep neural networks on computational resource limited devices. Neural architecture search (NAS) provides an efficient way to automatically seek appropriate neural architecture design for compressed model. It is observed that, for existing NAS-based pruning methods, there is usually a lack of layer information when searching the optimal neural architecture. In this paper, we propose a new NAS approach, namely, differentiable channel pruning method guided via attention mechanism (DCP-A), where the adopted attention mechanism is able to provide layer information to guide the optimization of the pruning policy. The training process is differentiable with Gumbel-softmax sampling, while parameters are optimized under a two-stage training procedure. The neural network block with the shortcut is dedicatedly designed, which is of help to prune the network not only on its width but also on its depth. Extensive experiments are performed to verify the applicability and superiority of the proposed method. Detailed analysis with visualization of the pruned model architecture shows that our proposed DCP-A learns explainable pruning policies. [ABSTRACT FROM AUTHOR]

As Artificial Intelligence (AI) becomes increasingly prevalent, Deep Neural Networks (DNNs) have become a crucial tool for developing and advancing AI applications. Considering limited computing and energy resources on mobile devices (MDs), it is a challenge to perform compute-intensive DNN tasks on MDs. To attack this challenge, mobile edge computing (MEC) provides a viable solution through DNN partitioning and task offloading. However, as the communication conditions between different devices change over time, DNN partitioning on different devices must also change synchronously. This is a dynamic process, which aggravates the complexity of DNN partitioning. In this paper, we delve into the issue of jointly optimizing energy and delay for DNN partitioning and task offloading in a dynamic MEC scenario where each MD and the server adopt the pre-trained DNNs for task inference. Taking advantage of the characteristics of DNN, we first propose a strategy for layered partitioning of DNN tasks to divide the task of each MD into subtasks that can be either processed on the MD or offloaded to the server for computation. Then, we formulate the trade-off between energy and delay as a joint optimization problem, which is further represented as a Markov decision process (MDP). To solve this, we design a DNN partitioning and task offloading (DPTO) algorithm utilizing deep reinforcement learning (DRL), which enables MDs to make optimal offloading decisions. Finally, experimental results demonstrate that our algorithm outperforms existing non-DRL and DRL algorithms with respect to processing delay and energy consumption, and can be applied to different DNN types. [ABSTRACT FROM AUTHOR]

Virtue ethics has many times been suggested as a promising recipe for the construction of artificial moral agents due to its emphasis on moral character and learning. However, given the complex nature of the theory, hardly any work has de facto attempted to implement the core tenets of virtue ethics in moral machines. The main goal of this paper is to demonstrate how virtue ethics can be taken all the way from theory to machine implementation. To achieve this goal, we critically explore the possibilities and challenges for virtue ethics from a computational perspective. Drawing on previous conceptual and technical work, we outline a version of artificial virtue based on moral functionalism, connectionist bottom–up learning, and eudaimonic reward. We then describe how core features of the outlined theory can be interpreted in terms of functionality, which in turn informs the design of components necessary for virtuous cognition. Finally, we present a comprehensive framework for the technical development of artificial virtuous agents and discuss how they can be implemented in moral environments. [ABSTRACT FROM AUTHOR]

Artificial neural network is revolutionizing business and everyday life, bringing us to the next level in artificial intelligence. It has a unique ability to extract meaning from complex data to find patterns and detect trends that are too convoluted for the human brain. This paper analyzes the artificial neural network impact on different computational organizations by using the innovative structure of bipolar complex spherical fuzzy relation which is any subset of the Cartesian product of two bipolar complex spherical fuzzy sets. This notion has a comprehensive structure that consists of membership grade, abstinence grade, and non-membership grade. Furthermore, various kinds of bipolar complex spherical fuzzy relation with suitable examples are given and some authentic results also have been proved. These newly defined structures are used to investigate the impact of artificial neural network work on a variety of organizations. The innovative framework is also compared with the existing structure in the field of fuzzy set theory to prove its superiority. [ABSTRACT FROM AUTHOR]

The practice of using deep learning methods in safety critical vision systems such as autonomous driving has come a long way. As vision systems supported by deep learning methods become ubiquitous, the possible security threats faced by these systems have come into greater focus. As it is with any artificial intelligence system, these deep neural vision networks are first trained on a data set of interest, once they start performing well, they are deployed to a real-world environment. In the training stage, deep learning systems are susceptible to data poisoning attacks. While deep neural networks have proved to be versatile in solving a host of challenges. These systems have complex data ecosystems especially in computer vision. In practice, the security threats when training these systems are often ignored while deploying these models in the real world. However, these threats pose significant risks to the overall reliability of the system. In this paper, we present the fundamentals of data poisoning attacks when training deep learning vision systems and discuss countermeasures against these types of attacks. In addition, we simulate the risk posed by a real-world data poisoning attack on a deep learning vision system and present a novel algorithm MOVCE--Model verification with Convolutional Neural Network and Word Embeddings which provides an effective countermeasure for maintaining the reliability of the system. The countermeasure described in this paper can be used on a wide variety of use cases where the risks posed by poisoning the training data are similar. [ABSTRACT FROM AUTHOR]

Potential benefits of precision medicine in cardiovascular disease (CVD) include more accurate phenotyping of individual patients with the same condition or presentation, using multiple clinical, imaging, molecular and other variables to guide diagnosis and treatment. An approach to realising this potential is the digital twin concept, whereby a virtual representation of a patient is constructed and receives real-time updates of a range of data variables in order to predict disease and optimise treatment selection for the real-life patient. We explored the term digital twin, its defining concepts, the challenges as an emerging field, and potentially important applications in CVD. A mapping review was undertaken using a systematic search of peer-reviewed literature. Industry-based participants and patent applications were identified through web-based sources. Searches of Compendex, EMBASE, Medline, ProQuest and Scopus databases yielded 88 papers related to cardiovascular conditions (28%, n = 25), non-cardiovascular conditions (41%, n = 36), and general aspects of the health digital twin (31%, n = 27). Fifteen companies with a commercial interest in health digital twin or simulation modelling had products focused on CVD. The patent search identified 18 applications from 11 applicants, of which 73% were companies and 27% were universities. Three applicants had cardiac-related inventions. For CVD, digital twin research within industry and academia is recent, interdisciplinary, and established globally. Overall, the applications were numerical simulation models, although precursor models exist for the real-time cyber-physical system characteristic of a true digital twin. Implementation challenges include ethical constraints and clinical barriers to the adoption of decision tools derived from artificial intelligence systems. [ABSTRACT FROM AUTHOR]

The health management of railway signal equipment in the high-speed railway is a key link between intelligent operation and maintenance. Accurately predicting the health state of compensation capacitors is of great significance to ensure the reliable work of track circuits. This paper proposes an improved deep neural network algorithm focusing on the problem of long-term accurate health forecasts for compensation capacitors. First, establishing a transmission state model for degradation mechanism mining, the difference function that can quantitatively evaluate features is defined by piecewise processing cab signaling receiving voltage. Introducing the degradation model, predictive driving under both model and data is implemented. Then, the convolutional neural networks and bidirectional long–short-term memory are combined and improved to construct a novel artificial intelligence combination strategy, while parameters are optimized based on the sparrow search algorithm. Finally, facing the conditional repair of compensation capacitors, we set a reasonable threshold for the occurrence of hidden dangers to complete fault warning. This novel and practical approach effectively explores the procedure of prognosis and health management, while the refined maintenance will better utilize current monitoring information, helping the intelligence and accuracy of safety control decision-making. [ABSTRACT FROM AUTHOR]

We present here an artificial intelligence model based on deep learning for semantic segmentation of dermatoscopic images of skin neoplasms. The model was trained using an annotated image database. This paper discusses the challenge of increasing diagnostic accuracy using a two-level procedure based on artificial intelligence: 1) first, the object of medical interest is segmented; 2) the object is then classified. The present work is proposed as part of the first stage. Experimental studies (training set 583 images, test set 73 images) demonstrated high segmentation accuracy (Jaccard index 0.93) as compared with known methods. The approach proposed here can be used to recognize skin diseases using neural network technologies. [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]

Solar energy-based technologies have developed rapidly in recent years, however, the inability to appropriately estimate solar energy resources is still a major drawback for these technologies. In this study, eight different artificial intelligence (AI) models namely; convolutional neural network (CNN), artificial neural network (ANN), long short-term memory recurrent model (LSTM), eXtreme gradient boost algorithm (XG Boost), multiple linear regression (MLR), polynomial regression (PLR), decision tree regression (DTR), and random forest regression (RFR) are designed and compared for solar irradiance prediction. Additionally, two hybrid deep neural network models (ANN-CNN and CNN-LSTM-ANN) are developed in this study for the same task. This study is novel as each of the AI models developed was used to estimate solar irradiance considering different timesteps (hourly, every minute, and daily average). Also, different solar irradiance datasets (from six countries in Africa) measured with various instruments were used to train/test the AI models. With the aim to check if there is a universal AI model for solar irradiance estimation in developing countries, the results of this study show that various AI models are suitable for different solar irradiance estimation tasks. However, XG boost has a consistently high performance for all the case studies and is the best model for 10 of the 13 case studies considered in this paper. The result of this study also shows that the prediction of hourly solar irradiance is more accurate for the models when compared to daily average and minutes timestep. The specific performance of each model for all the case studies is explicated in the paper. [ABSTRACT FROM AUTHOR]

Machine learning and logical reasoning have been the two foundational pillars of Artificial Intelligence (AI) since its inception, and yet, until recently the interactions between these two fields have been relatively limited. Despite their individual success and largely independent development, there are new problems on the horizon that seem solvable only via a combination of ideas from these two fields of AI. These problems can be broadly characterized as follows: how can learning be used to make logical reasoning and synthesis/verification engines more efficient and powerful, and in the reverse direction, how can we use reasoning to improve the accuracy, generalizability, and trustworthiness of learning. In this perspective paper, we address the above-mentioned questions with an emphasis on certain paradigmatic trends at the intersection of learning and reasoning. Our intent here is not to be a comprehensive survey of all the ways in which learning and reasoning have been combined in the past. Rather we focus on certain recent paradigms where corrective feedback loops between learning and reasoning seem to play a particularly important role. Specifically, we observe the following three trends: first, the use of learning techniques (especially, reinforcement learning) in sequencing, selecting, and initializing proof rules in solvers/provers; second, combinations of inductive learning and deductive reasoning in the context of program synthesis and verification; and third, the use of solver layers in providing corrective feedback to machine learning models in order to help improve their accuracy, generalizability, and robustness with respect to partial specifications or domain knowledge. We believe that these paradigms are likely to have significant and dramatic impact on AI and its applications for a long time to come. [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]

In recent years, order-reduction techniques based on artificial intelligence algorithms have become a topic of interest in the structural dynamics community. In this paper, we describe a new artificial intelligence technique based on the artificial neural network used to reduce a large interval system. Applied to reduce the degree of the polynomial numerator and denominator each separately, by allowing them to learn automatically from the original system, this machine learning phase allows the algorithm to improve over time and control performance of the approximation, maintaining as much as possible the stability of the dynamic system, and reducing errors between the original system and the reduced system that are presented as a very acceptable approximation, a comparison study is presented between existing works and the proposed technique, with the help of examples from literature. [ABSTRACT FROM AUTHOR]

In machine learning (ML), association patterns in the data, paths in decision trees, and weights between layers of the neural network are often entangled due to multiple underlying causes, thus masking the pattern-to-source relation, weakening prediction, and defying explanation. This paper presents a revolutionary ML paradigm: pattern discovery and disentanglement (PDD) that disentangles associations and provides an all-in-one knowledge system capable of (a) disentangling patterns to associate with distinct primary sources; (b) discovering rare/imbalanced groups, detecting anomalies and rectifying discrepancies to improve class association, pattern and entity clustering; and (c) organizing knowledge for statistically supported interpretability for causal exploration. Results from case studies have validated such capabilities. The explainable knowledge reveals pattern-source relations on entities, and underlying factors for causal inference, and clinical study and practice; thus, addressing the major concern of interpretability, trust, and reliability when applying ML to healthcare, which is a step towards closing the AI chasm. [ABSTRACT FROM AUTHOR]

Background: With the advancement in technology the amount of data generated, in almost every sphere of life, is increasing exponentially. This enormous amount of data needs new powerful tools for analysis and inference drawing. One such process is data mining which is the automated extraction of hidden, previously unknown, and useful knowledge from big data. Data mining is crucial as conventional strategies cannot keep up with the analysis of rapidly accumulating data and they are also inflexible in the wake of new challenges. Animal sciences are no exception to the changing scenario, especially when animal farms are quickly becoming more data intensive. The amount of data generated on the farms is also growing exponentially as farms become more intensive and mechanized. There is thus a need to utilize the knowledge of multidisciplinary fields like advanced statistics, artificial intelligence, machine learning, and database management, for revamping animal sciences. Artificial neural networks (ANNs) offer a lot of promise in this direction since they are motivated by the distributed, massively parallel computation in the brain. ANNs are powerful machine learning tools that offer multiple advantages for data mining over traditional techniques in being fast, accurate, self-organizing, robust, and highly accepting of noisy and imprecise data. Neural networks are being applied successfully for a myriad of supervised and unsupervised learning applications to draw useful hitherto unknown inferences, patterns, and relationships. Neural networks have been used successfully for pattern recognition, clustering, forecasting, prediction, and classification in animal sciences due to their capacity to learn from data, their nonparametric nature, and their ability to generalize well. Today ANN computing is a major element within any data mining tool kit. Popular methods used for neural network computing include feed-forward networks, feedback networks, and self-organization networks. ANN also offers powerful and distributed computing architecture, especially under a scenario where the data are readily available in significant quantity. Short conclusion: This paper gives an overview of ANN and their applications in animal sciences and reviews major research conducted in this new and exciting area of artificial intelligence. Research in many aspects of ANN in Animal Sciences has been conducted globally although there is scope for more research in aspects of animal health, monitoring, breeding as well as nutrition. [ABSTRACT FROM AUTHOR]

This paper focuses on developing a computationally economic lightweight artificial intelligence (AI) technology for smartphones. Until date, no commercial system is available on this technology. Thus the developed breakthrough technology can enhance the capability of users on the field for monitoring the agricultural vehicles (AgV)s health by analyzing the acoustic noise using smartphone's app. This paper can enable the user of AgVs to optimize their farming by management at edge devices: smartphones. Since smartphones use a small integrated computing unit with computational limited resources, thus lighter the system, more favorable to work on. Artificial neural network (ANN) is one of the most favorite AI techniques, but its lightweight architecture—attributed by the number of inputs and hidden layers and neurons—, is one of the most important issues in the context of smartphones. Under the framework of bi-level optimization, we aim to analyze the tournament selection operator based genetic algorithm with hybrid crossover operators, at level-I, to evolve ANN, at level-II to design the lightweight edge device enabled AI technique. The obtained results and numerical evaluative analysis indicate that the optimized design of the lightweight fault detection system responds well to the soundtracks received via microphones. We present the evaluation of the proposed technology on serial programming, parallel programming (PP), GPU programming, and GPU with PP. The results show that PP is enough efficient for the proposed technology and can save the cost of GPU for large scale implementation of the technology. [ABSTRACT FROM AUTHOR]

Integrated circuit (IC) testing presents complex problems that for large circuits are exceptionally difficult to solve by traditional computing techniques. To deal with unmanageable time complexity, engineers often rely on human "hunches" and "heuristics" learned through experience. Training computers to adopt these human skills is referred to as machine intelligence (MI) or machine learning (ML). This survey examines applications of such methods to test analog, radio frequency (RF), digital, and memory circuits. It also summarizes ML applications to hardware security and emerging technologies, highlighting challenges and potential research directions. The present work is an extension of a recent paper from IEEE VLSI Test Symposium (VTS'21), and includes recent applications of artificial neural network (ANN) and principal component analysis (PCA) to automatic test pattern generation (ATPG). [ABSTRACT FROM AUTHOR]

Semantic relatedness is one of the most significant aspects of natural language processing. It has been identified as a critical technology for developing intelligent systems like Siri, Microsoft Ice, Cortana, and Xiaoai. In 2014, SemEval ranked SR as the top task. While many existing studies have focused on analyzing the entailment of single phrases, advancements in deep learning have made it possible to analyze complete sentences or texts. While the natural parallelism of membrane computing has shown promise for data processing, harnessing this potential to advance semantic relatedness remains an open problem yet to be tackled. This paper proposes a novel Siamese Manhattan LSTM-SNP approach (SiMaLSTM-SNP) for the SR problem. The approach uses a collaborative Word2vec and 10-Layer Attention strategy to represent and extract sentence pairs and a Siamese LSTM-SNP structure to calculate the hidden states of sentences. The multi-head self-attention layer identifies text associations and redistributes hidden state weights. The last hidden state is extracted, and the relatedness score is calculated using the Manhattan distance. The experiments demonstrate that SiMaLSTM-SNP outperforms 17 classical SR baselines and 7 novel approaches on the standard datasets SICK and STS in terms of mean square error performance. This indicates that SiMaLSTM-SNP can accurately capture the semantic distinction between two sentences and effectively preserve their semantic information. [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]

The fault monitoring and diagnosis of industrial machineries are very significant in Industry 4.0 revolution but are often complicated and labour intensive. The application of artificial intelligence (AI) techniques have now been an important part of condition monitoring of the mechanical and electrical machines because of its fast computation, higher accuracy, and robustness in performance, reducing the dependence on experienced personnel with expert knowledge. This paper presents a review of applications of AI-based fault diagnosis techniques that have had demonstrated success when applied to various industrial machineries. The important literature published in the last twenty years (i.e., 2000 to 2020) have been reviewed and added. In this work, first, a brief of various AI techniques such as artificial neural networks (ANN), deep learning (DL), fuzzy logic (FL), and support vector machine (SVM) are added. The literature on AI-based diagnostics used for various industrial machines, such as induction motor, bearing, gear, and centrifugal pump, are added and discussed in detail. The observation, research gap, and new ideas have been discussed, followed by a conclusion. [ABSTRACT FROM AUTHOR]

Rock mechanical properties play a crucial role in fracturing design, wellbore stability and in situ stresses estimation. Conventionally, there are two ways to estimate Young's modulus, either by conducting compressional tests on core plug samples or by calculating it from well log parameters. The first method is costly, time-consuming and does not provide a continuous profile. In contrast, the second method provides a continuous profile, however, it requires the availability of acoustic velocities and usually gives estimations that differ from the experimental ones. In this paper, a different approach is proposed based on the drilling operational data such as weight on bit and penetration rate. To investigate this approach, two machine learning techniques were used, artificial neural network (ANN) and support vector machine (SVM). A total of 2288 data points were employed to develop the model, while another 1667 hidden data points were used later to validate the built models. These data cover different types of formations carbonate, sandstone and shale. The two methods used yielded a good match between the measured and predicted Young's modulus with correlation coefficients above 0.90, and average absolute percentage errors were less than 15%. For instance, the correlation coefficients for ANN ranged between 0.92 and 0.97 for the training and testing data, respectively. A new empirical correlation was developed based on the optimized ANN model that can be used with different datasets. According to these results, the estimation of elastic moduli from drilling parameters is promising and this approach could be investigated for other rock mechanical parameters. [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]

Image captioning is a widely known problem in the area of AI. Caption generation from floor plan images has applications in indoor path planning, real estate, and providing architectural solutions. Several methods have been explored in the literature for generating captions or semi-structured descriptions from floor plan images. Since only the caption is insufficient to capture fine-grained details, researchers also proposed descriptive paragraphs from images. However, these descriptions have a rigid structure and lack flexibility, making it difficult to use them in real-time scenarios. This paper offers two models, description synthesis from image cue (DSIC) and transformer-based description generation (TBDG), for text generation from floor plan images. These two models take advantage of modern deep neural networks for visual feature extraction and text generation. The difference between both models is in the way they take input from the floor plan image. The DSIC model takes only visual features automatically extracted by a deep neural network, while the TBDG model learns textual captions extracted from input floor plan images with paragraphs. The specific keywords generated in TBDG and understanding them with paragraphs make it more robust in a general floor plan image. Experiments were carried out on a large-scale publicly available dataset and compared with state-of-the-art techniques to show the proposed model's superiority. [ABSTRACT FROM AUTHOR]

In recent years, artificial intelligence (AI) techniques have been recognized as powerful techniques. In this work, AI techniques such as artificial neural networks (ANNs), support vector machines (SVM), adaptive neuro-fuzzy inference system (ANFIS), genetic algorithms (GA), and particle swarm optimization (PSO), used in water and wastewater treatment processes, are reviewed. This paper describes applications of the mentioned AI techniques for the modelling and optimization of electrochemical processes for water and wastewater treatment processes. Most research in the mentioned scope of study consists of electrooxidation, electrocoagulation, electro-Fenton, and electrodialysis. Also, ANNs have been the most frequent technique used for modelling and optimization of these processes. It was shown that most of the AI models have been built with a relatively low number of samples (< 150) in data sets. This points out the importance of reliability and robustness of the AI models derived from these techniques. We show how to improve the performance and reduce the uncertainty of these developed black-box data-driven models. From the perspectives of both experiment and theory, this review demonstrates how AI techniques can be effectively adapted to electrochemical processes for water and wastewater treatment to model and optimize these processes. [ABSTRACT FROM AUTHOR]

The saturated hydraulic conductivity, ksat, is a crucial variable to describe the hydromechanical behavior of soils. The value of ksat of lateritic soils that are typically found in tropical regions is highly affected by the soil's structure, void ratio, and fine particle aggregation. As a result, the determination of ksat in the field or in the laboratory is complex and involves greater variability, depending on the type of test and on the spatial location of sampling. This paper presents a study of ksat values of lateritic soils, analyzing them using Statistic, Multilayer Perceptron Artificial Neural Networks (ANN) and Decision Trees (CHAID). This study aims to support decision-making regarding the type of test and depth chosen for sampling in laterite soils and understanding the factors influencing the permeability of such soils. An extensive literature review on the ksat values of lateritic soils was performed, providing data for the establishment of a database comprise of 722 registries. According to agronomic and geotechnical soil classifications, the Brazilian lateritic soils presents a "moderate" hydraulic conductivity. A significant variation of permeability values along the depth was identified, particularly for depths between 0.1 and 0.2 m. Regarding the importance of testing variables, the ANN indicated a high dependency on the type of test. The decision tree divided field test and laboratory test automatically, inferring the relevance of the type of test to the determination of ksat. [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]

This paper aims to introduce efficient computer-aided techniques for automated epileptic diagnosis using the features based on improved local pattern transformation methods (LPT). To analyze electroencephalographic (EEG) signal, three techniques, namely one-dimensional local neighbor descriptive count, one-dimensional local gradient count and one-dimensional local binary count, are proposed in this work. Further, a signature point-based improved LPT approach is introduced for effectual classification of EEG signals. The features are computed at the signature points of the EEG signals, which are detected by using the difference of Gaussian pyramid. The features extracted from the signature points of the EEG signals are fed into artificial neural network (ANN) classifier for the discrimination of EEG signals. In this paper, seventeen different classification cases based on six different experimental cases are evaluated using the University of Bonn EEG database. Experimental results show that high classification accuracy for all the cases is achieved using the proposed approach and it also compares favorably to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper proposes a hybrid artificial neural networks-differential evolution (ANN-DE) and wavelet transforms (WTs)-based approach to forecast the short-term electrical load demand data. The input data ranging from 1 h to several days have a significant effect on the accuracy of short-term load forecasting (STLF). Different forecasting methods with good accuracy are developed for solving the STLF problem based on time series analysis and artificial intelligence system. However, there are several disadvantages of ANNs such as falling in trap of local minima during its parameter optimization process. Therefore, to avoid this problem, in this paper, a hybrid approach is developed by combining the ANNs, WTs and evolutionary-based DE algorithm. Here, the ANNs are used to model the nonlinear and complex behavior of electrical load demand. WTs are used to improve the forecasting ability by decreasing the ill-behaved load demand series into a more stable series. The chance of falling into local optimum can be overcome by using the evolutionary-based DE algorithm. In order to show the effectiveness and suitability of the proposed hybrid approach, the load demand data are taken from California Independent System Operator Web site. [ABSTRACT FROM AUTHOR]

In general, the created era of a literary work is significant information for understanding the background and the literary interpretation of the work. However, in the case of literary works of old Korea, especially works created in Hangul, there are few works of which the era of creation are known. In this paper, the created era of old Korean documents was estimated based on artificial intelligence. Hangul, a Korean letter system where one syllable is one character, has more than 10,000 combinations of characters, so it is available to predict changes in the structure or grammar of Hangul by analyzing the frequency of characters. Accordingly, a deep neural network model was constructed based on the term frequency of each character in Hangul. Model training was performed based on 496 documents with known publication years, and the mean-absolute-error of the test set for the entire prediction range from 1447 to 1934 was 13.77 years for test sets and 15.8 years for validation sets, which is less than an error ratio of 3.25% compared to the total year range. In addition, the predicted results of works from which only the approximate creation time was inferred were also within the range, and the predicted creation years for other divisions of the identical novel were similar. These results show that the deep neural network model based on character term frequency predicted the creation era of old Korean documents properly. This study is expected to support the literary history of Korea within the period from 15C to 19C by predicting the period of creation or enjoyment of the work. In addition, the method and algorithm using syllable term frequency are believed to have the potential to apply in other language documents. [ABSTRACT FROM AUTHOR]

In the past decade, social media networks have received much attention among ordinary people, agencies, and research scholars. Twitter is one of the fastest-growing social media tools. By means of the Twitter application on smartphones, users are able to immediately report events happening around them on a real-time basis. The information disseminated by millions of active users every day generates a new version of a dynamic database that contains information about various topics. Twitter data can be utilized as a major traffic data source along with conventional sensors. In this aspect, this paper presents a novel firefly algorithm-based feature selection with a deep learning model for traffic flow analysis (FFAFS-DLTFA) using Twitter data. The goal of FFAFS-DLTFA is to determine the class labels for tweets as relevant to traffic events. The proposed FFAFS-DLTFA encompasses several processes, such as preprocessing, feature extraction, feature selection, and classification. Primarily, tweets are preprocessed in several ways, such as tokenization, removal of stop words, and stemming. At the same time, three types of embedding vectors, unigram, bigram, and POS features, are used. In addition, the firefly algorithm (FFA) is applied for the optimal selection of feature subsets. Finally, a deep neural network (DNN) model is applied for the identification of tweets into three classes, namely, positive, neutral, and negative. The performance validation of FFAFS-DLTFA takes place using the benchmark Kaggle repository, and the results are inspected under different aspects. The experimental values demonstrate the better performance of FFAFS-DLTFA on the other techniques with the maximum accuracy of 98.83%. [ABSTRACT FROM AUTHOR]

In order to realize the full potential of wireless edge artificial intelligence (AI), very large and diverse datasets will often be required for energy-demanding model training on resource-constrained edge devices. This paper proposes a lead federated neuromorphic learning (LFNL) technique, which is a decentralized energy-efficient brain-inspired computing method based on spiking neural networks. The proposed technique will enable edge devices to exploit brain-like biophysiological structure to collaboratively train a global model while helping preserve privacy. Experimental results show that, under the situation of uneven dataset distribution among edge devices, LFNL achieves a comparable recognition accuracy to existing edge AI techniques, while substantially reducing data traffic by >3.5× and computational latency by >2.0×. Furthermore, LFNL significantly reduces energy consumption by >4.5× compared to standard federated learning with a slight accuracy loss up to 1.5%. Therefore, the proposed LFNL can facilitate the development of brain-inspired computing and edge AI. Designing energy-efficient computing solution for the implementation of AI algorithms in edge devices remains a challenge. Yang et al. proposes a decentralized brain-inspired computing method enabling multiple edge devices to collaboratively train a global model without a fixed central coordinator. [ABSTRACT FROM AUTHOR]

The quantification of microstructural properties to optimize battery design and performance, to maintain product quality, or to track the degradation of LIBs remains expensive and slow when performed through currently used characterization approaches. In this paper, a convolution neural network-based deep learning approach (CNN) is reported to infer electrode microstructural properties from the inexpensive, easy to measure cell voltage versus capacity data. The developed framework combines two CNN models to balance the bias and variance of the overall predictions. As an example application, the method was demonstrated against porous electrode theory-generated voltage versus capacity plots. For the graphite|LiMn 2 O 4 chemistry, each voltage curve was parameterized as a function of the cathode microstructure tortuosity and area density, delivering CNN predictions of Bruggeman's exponent and shape factor with 0.97 R 2 score within 2 s each, enabling to distinguish between different types of particle morphologies, anisotropies, and particle alignments. The developed neural network model can readily accelerate the processing-properties-performance and degradation characteristics of the existing and emerging LIB chemistries. [ABSTRACT FROM AUTHOR]