Search

Neural network (i.e. deep learning, NN)-based data analysis techniques have been listed as a pivotal opportunity to protect the integrity and safety of the global food supply chain and forecast $11.2 billion in agriculture markets. As a general-purpose data analytic tool, NN has been applied in several areas of food science, such as food recognition, food supply chain security and omics analysis, and so on. Therefore, given the rapid emergence of NN applications in food safety, this review aims to provide a comprehensive overview of the NN application in food analysis for the first time, focusing on domain-specific applications in food analysis by introducing fundamental methodology, reviewing recent and notable progress, and discussing challenges and potential pitfalls. NN demonstrated that it has a bright future through effective collaboration between food specialist and the broader community in the food field, for example, superiority in food recognition, sensory evaluation, pattern recognition of spectroscopy and chromatography. However, major challenges impeded NN extension including void in the food scientist-friendly interface software package, incomprehensible model behavior, multi-source heterogeneous data, and so on. The breakthrough from other fields proved NN has the potential to offer a revolution in the immediate future. [ABSTRACT FROM AUTHOR]

Radiologic usual interstitial pneumonia (UIP) patterns and concordant clinical characteristics define a diagnosis of idiopathic pulmonary fibrosis (IPF). However, limited expert access and high inter-clinician variability challenge early and pre-invasive diagnostic sensitivity and differentiation of IPF from other interstitial lung diseases (ILDs). We investigated a machine learning-driven software system, Fibresolve, to indicate IPF diagnosis in a heterogeneous group of 300 patients with interstitial lung disease work-up in a retrospective analysis of previously and prospectively collected registry data from two US clinical sites. Fibresolve analyzed cases at the initial pre-invasive assessment. An Expert Clinical Panel (ECP) and three panels of clinicians with varying experience analyzed the cases for comparison. Ground Truth was defined by separate multi-disciplinary discussion (MDD) with the benefit of surgical pathology results and follow-up. Fibresolve met both pre-specified co-primary endpoints of sensitivity superior to ECP and significantly greater specificity (p = 0.0007) than the non-inferior boundary of 80.0%. In the key subgroup of cases with thin-slice CT and atypical UIP patterns (n = 124), Fibresolve's diagnostic yield was 53.1% [CI: 41.3–64.9] (versus 0% pre-invasive clinician diagnostic yield in this group), and its specificity was 85.9% [CI: 76.7–92.6%]. Overall, Fibresolve was found to increase the sensitivity and diagnostic yield for IPF among cases of patients undergoing ILD work-up. These results demonstrate that in combination with standard clinical assessment, Fibresolve may serve as an adjunct in the diagnosis of IPF in a pre-invasive setting. [ABSTRACT FROM AUTHOR]

Quantum imaging exemplifies the fascinating and counter‐intuitive nature of the quantum world, where non‐local correlations are exploited for imaging of objects by remote and non‐interacting photons. The field has exploded of late, driven by advances in our fundamental understanding of these processes, but also by advances in technology, for instance, efficient single photon detectors and cameras. Accelerating the progress is the nascent intersection of quantum imaging with artificial intelligence and machine learning, promising enhanced speed and quality of quantum images. This review provides a comprehensive overview of the rapidly evolving field of quantum imaging with a specific focus on the intersection of quantum ghost imaging with artificial intelligence and machine learning techniques. The seminal advances made to date and the open challenges are highlighted, and the likely trajectory for the future is outlined. [ABSTRACT FROM AUTHOR]

Recent activity in the field of artificial intelligence (AI) has given rise to large language models (LLMs) such as GPT-4 and Bard. These are undoubtedly impressive achievements, but they raise serious questions about appropriation, accuracy, explainability, accessibility, responsibility, and more. There have been pusillanimous and self-exculpating calls for a halt in development by senior researchers in the field and largely self-serving comments by industry leaders around the potential of AI systems, good or bad. Many of these commentaries leverage misguided conceptions, in the popular imagination, of the competence of machine intelligence, based on some sort of Frankenstein or Terminator-like fiction: however, this leaves it entirely unclear what exactly the relationship between human(ity) and AI, as represented by LLMs or what comes after, is or could be. [ABSTRACT FROM AUTHOR]

With 500+ papers and 20+ books spanning many scientific disciplines, Mark Burgin has left an indelible mark and legacy for future explorers of human thought and information technology professionals. In this paper, I discuss his contribution to the evolution of machine intelligence using his general theory of information (GTI) based on my discussions with him and various papers I co-authored during the past eight years. His construction of a new class of digital automata to overcome the barrier posed by the Church–Turing Thesis, and his contribution to super-symbolic computing with knowledge structures, cognizing oracles, and structural machines are leading to practical applications changing the future landscape of information systems. GTI provides a model for the operational knowledge of biological systems to build, operate, and manage life processes using 30+ trillion cells capable of replication and metabolism. The schema and associated operations derived from GTI are also used to model a digital genome specifying the operational knowledge of algorithms executing the software life processes with specific purposes using replication and metabolism. The result is a digital software system with a super-symbolic computing structure exhibiting autopoietic and cognitive behaviors that biological systems also exhibit. We discuss here one of these applications. [ABSTRACT FROM AUTHOR]

Global precipitation is becoming increasingly intense due to the extreme climate. Therefore, creating new technology to manage water resources is crucial. To create a sustainable urban and ecological environment, a water level and water quality control system implementing artificial intelligence is presented in this research. The proposed smart monitoring system consists of four sensors (two different liquid level sensors, a turbidity and pH sensor, and a water oxygen sensor), a control module (an MCU, a motor, a pump, and a drain), and a power and communication system (a solar panel, a battery, and a wireless communication module). The system focuses on low-cost Internet of Things (IoT) devices along with low power consumption and high precision. This proposal collects rainfall from the preceding 10 years in the application region as well as the region's meteorological bureau's weekly weather report and uses artificial intelligence to compute the appropriate water level. More importantly, the adoption of dynamic adjustment systems can reserve and modify water resources in the application region more efficiently. Compared to existing technologies, the measurement approach utilized in this study not only achieves cost savings exceeding 60% but also enhances water level measurement accuracy by over 15% through the successful implementation of water level calibration decisions utilizing multiple distinct sensors. Of greater significance, the dynamic adjustment systems proposed in this research offer the potential for conserving water resources by more than 15% in an effective manner. As a result, the adoption of this technology may efficiently reserve and distribute water resources for smart cities as well as reduce substantial losses caused by anomalous water resources, such as floods, droughts, and ecological concerns. [ABSTRACT FROM AUTHOR]

This research aims to develop a diagnostic tool that can quickly and accurately detect prostate cancer using electronic nose technology and a neural network trained on a dataset of urine samples from patients diagnosed with both prostate cancer and benign prostatic hyperplasia, which incorporates a unique data redundancy method. By analyzing signals from these samples, we were able to significantly reduce the number of unnecessary biopsies and improve the classification method, resulting in a recall rate of 91% for detecting prostate cancer. The goal is to make this technology widely available for use in primary care centers, to allow for rapid and non-invasive diagnoses. [ABSTRACT FROM AUTHOR]

For decades, playing Go at a professional level has counted among those things that, in Dreyfus's words, 'computers still can't do'. This changed dramatically in early March 2016, at the Four Seasons Hotel in Seoul, South Korea, when AlphaGo, the most sophisticated Go program at the time, beat Lee Sedol, an internationally top-ranked Go professional, by four games to one. A documentary movie has captured and crafted the unfolding drama and, since AlphaGo 's momentous win, the drama has been retold in myriad variations. Yet the exhibition match as a technology demonstration—in short, the ' AlphaGo show '—has not received much scrutiny in STS, notwithstanding or precisely because of all the media frenzy, game commentary, and 'AI' expertise in its wake. This article therefore revisits the second game's 'move 37', its surprise delivery by AlphaGo on stage, and the subsequent line of commentary by the attending experts, initiated by the news-receipt token 'ooh'. Drawing upon a reflexive video analysis, the article explicates the Go move's scenic intelligibility—its embodied delivery as part of the technology demonstration—as the contingent result of intricate 'human/machine interfacing'. For mainstream media to report on AlphaGo 's 'superhuman intelligence', it both relied upon and effaced such interfacing work. In turn, the article describes and discusses how 'object agency' and 'algorithmic drama' both trade on skillfully embodied play as a pivotal interfacing practice, informing the exhibition match from within its livestream broadcast. [ABSTRACT FROM AUTHOR]

Maintaining computer network security has long been an essential component of computer administration. Network security has become essential to companies' safety and steady development in real-time implementation for diverse physical domains employing computers. Establishing a specific physical domain has consistently included a priority job of improving the safety of computer systems management. Study results on the practical implementation of machine intelligence in network security maintenance. Specifically, this paper examines and offers security management techniques for computer network data protection to establish an all-encompassing security shield for networked computers, with the ultimate goal of improving the safety and reliability of the net-worked computers used in commercial settings. Furthermore, the comprehensive research analysis determines an architectural model for machine intelligence-based network security maintenance (MI-NSM), implying an intrusion detection scheme with a novel neural network system. Labelling important properties of objects or data points and searching for commonalities allows the auto-mobile's AI to distinguish between a human, the street, another car, and the sky. The simulation evaluation is performed using the NS2 simulator and observes the security maintenance efficiency over the current security solutions. [ABSTRACT FROM AUTHOR]

In this work, we present a perspective on the role machine intelligence can play in supporting human abilities. In particular, we consider research in rehabilitation technologies such as prosthetic devices, as this domain requires tight coupling between human and machine. Taking an agent-based view of such devices, we propose that human–machine collaborations have a capacity to perform tasks which is a result of the combined agency of the human and the machine. We introduce communicative capital as a resource developed by a human and a machine working together in ongoing interactions. Development of this resource enables the partnership to eventually perform tasks at a capacity greater than either individual could achieve alone. We then examine the benefits and challenges of increasing the agency of prostheses by surveying literature which demonstrates that building communicative resources enables more complex, task-directed interactions. The viewpoint developed in this article extends current thinking on how best to support the functional use of increasingly complex prostheses, and establishes insight toward creating more fruitful interactions between humans and supportive, assistive, and augmentative technologies. [ABSTRACT FROM AUTHOR]

This article provides an overview of the application of the intelligent technology in healthcare especially in the various specialities of dentistry and how much it has enhanced the quality of care being provided. Artificial intelligence is widely gaining popularity in various other sectors and is thought to be useful in the healthcare industry for diagnostic purposes and eventually with time programming, the technology to help healthcare personnels to carry out less invasive procedures. [ABSTRACT FROM AUTHOR]

Jeff Hawkins is one of those rare individuals who speaks the languages of both AI and neuroscience. In his recent book, "A Thousand Brains: A New Theory of Intelligence", Hawkins proposes that current learning algorithms lack four attributes which will be necessary for true machine intelligence. Here we demonstrate that a minimal learning system which satisfies all four points can be constructed using only simple, classical machine learning techniques. We illustrate that such a system falls short of biological intelligence in some important ways. We suggest that Hawkins' list is a useful model, but the "recipe" for true intelligence—if there is one—may not be so easily defined. [ABSTRACT FROM AUTHOR]

This research aims to develop a diagnostic tool that can quickly and accurately detect prostate cancer using electronic nose technology and a neural network trained on a dataset of urine samples from patients diagnosed with both prostate cancer and benign prostatic hyperplasia, which incorporates a unique data redundancy method. By analyzing signals from these samples, we were able to significantly reduce the number of unnecessary biopsies and improve the classification method, resulting in a recall rate of 91% for detecting prostate cancer. The goal is to make this technology widely available for use in primary care centers, to allow for rapid and non-invasive diagnoses. [ABSTRACT FROM AUTHOR]

Depression diagnosis is a challenging clinical task currently conducted mostly using subjective criteria. It is well known that depression alters the neural activity in the brain, so that the corresponding neurophysiological signature may be measured using non-invasive electroencephalography (EEG) signals. These, in turn, may be possible to decode using machine learning algorithms. Despite the extensive literature, the existing techniques rely on several channels and obtrusive systems. In this paper, and for the first time, the diagnostic power of each EEG channel for depression detection is analyzed using Neighborhood Component Analysis (NCA). Our results indicate that a mere two features collected from one EEG channel suffice for reliable diagnosis. To evaluate the performance of the proposed method, a dataset comprising seven minutes of EEG recording from 84 subjects is used. The data was divided into two separate sets, one for feature selection and one for diagnostic classification. We delineate brain regions that have the strongest discriminative power linked to depression diagnosis. Thus, we identified one electrode (i.e., AF4) located on the frontal lobe, which can be used to diagnose depression with high accuracy. After evaluation of a series of shallow machine learning methods, we achieved the classification accuracy of 80.8%, sensitivity of 60% and specificity of 99.7% with two features from one electrode. We also achieved the highest classification accuracy of 91.8%, the specificity of 93.5%, and sensitivity of 90% with two electrodes and three features. Our findings show that it is possible to significantly reduce the complexity of algorithms to diagnose depression with the motivation of use in highly accessible wearable devices. [ABSTRACT FROM AUTHOR]

Fog-integrated cloud (FiC) contains a fair amount of heterogeneity, leading to uncertainty in the resource provisioning. An admission control manager (ACM) is proposed, using a modified fuzzy inference system (FiS), to place a request based on the request's parameters, e.g., CPU, memory, storage, and few categorical parameters, e.g., job priority and time sensitivity. The ACM considers the extended three-layer architecture of FiC. FiC nodes are classified into three computing nodes: fog node, aggregated fog node, and cloud node using modified FiS model. For performance study, extensive simulation experiments have been carried out on real Google trace. Different batches on the number of relevant rules are created and compared on metrics of job execution time, memory overhead, accuracy, and hit ratio with the modified rules. The proposed work has also been compared with the state of the art. The results have been encouraging and exhibit the benefits of the proposed model apart from being it lightweight with reduced number of rules, especially suited for the FiC. [ABSTRACT FROM AUTHOR]

This paper explores criticality-based real-time scheduling of neural-network-based machine inference pipelines in cyber-physical systems (CPS) to mitigate the effect of algorithmic priority inversion. We specifically focus on the perception subsystem, an important subsystem feeding other components (e.g., planning and control). In general, priority inversion occurs in real-time systems when computations that are of lower priority are performed together with or ahead of those that are of higher priority. In current machine perception software, significant priority inversion occurs because resource allocation to the underlying neural network models does not differentiate between critical and less critical data within a scene. To remedy this problem, in recent work, we proposed an architecture to partition the input data into regions of different criticality, then formulated a utility-based optimization problem to batch and schedule their processing in a manner that maximizes confidence in perception results, subject to criticality-based time constraints. This journal extension matures the work in several directions: (i) We extend confidence maximization to a generalized utility optimization formulation that accounts for criticality in the utility function itself, offering finer-grained control over resource allocation within the perception pipeline; (ii) we further instantiate and compare two different criticality metrics (distance-based and relative velocity-based) to understand their relative advantages; and (iii) we explore the limitations of the approach, specifically how inaccuracies in criticality-based attention cueing affect performance. All experiments are conducted on the NVIDIA Jetson AGX Xavier platform with a real-world driving dataset. [ABSTRACT FROM AUTHOR]

This study proposes a robust depth map framework based on a convolutional neural network (CNN) to calculate disparities using multi-direction epipolar plane images (EPIs). A combination of three-dimensional (3D) and two-dimensional (2D) CNN-based deep learning networks is used to extract the features from each input stream separately. The 3D convolutional blocks are adapted according to the disparity of different directions of epipolar images, and 2D-CNNs are employed to minimize data loss. Finally, the multi-stream networks are merged to restore the depth information. A fully convolutional approach is scalable, which can handle any size of input and is less prone to overfitting. However, there is some noise in the direction of the edge. A weighted median filtering (WMF) is used to acquire the boundary information and improve the accuracy of the results to overcome this issue. Experimental results indicate that the suggested deep learning network architecture outperforms other architectures in terms of depth estimation accuracy. [ABSTRACT FROM AUTHOR]

This article is dedicated to study the impact of machine intelligence (MI) methods viz. various types of Neural models for investigating dynamical systems arising in interdisciplinary areas. Different types of artificial neural network (ANN) methods, viz., recurrent neural network, functional‐link neural network, convolutional neural network, symplectic artificial neural network, genetic algorithm neural network, and so on, are addressed by different researchers to investigate these problems. Although various traditional methods have been developed by researchers to solve these dynamical problems but the existing traditional methods may sometimes be problem dependent, require repetitions of the simulations, and fail to solve nonlinearity behavior. In this regard, neural network model based methods are more general and solutions are continuous over the given domain of integration, self‐adaptive and can be used as a black box. As such, in this article, we have reviewed and analyzed different MI methods, which are applied to investigate these problems. This article is categorized under:Technologies > Computational IntelligenceTechnologies > Machine LearningApplication Areas > Science and Technology [ABSTRACT FROM AUTHOR]

• Previous groundwater intelligent models often overlook the inherent limitations. • Integrating data, humans and machines can enhance groundwater modeling. • Multisource data serves as the training basis and insight generator. • Human expertise acts as the source of intelligence and collaborative catalyst. • Machine intelligence is the cornerstone of high accuracy and efficiency. Groundwater models are essential for understanding aquifer systems behavior and effective water resources spatio-temporal distributions, yet they are often hindered by challenges related to model assumptions, parametrization, uncertainty, and computational efficiency. Machine intelligence, especially deep learning, promises a paradigm shift in overcoming these challenges. A critical examination of existing machine-driven methods reveals the inherent limitations, particularly in terms of the interpretability and the ability to generalize findings. To overcome these challenges, we develop a ternary framework that synergizes the valuable insights from multisource data, human expertise, and machine intelligence. This framework capitalizes on the distinct strengths of each element: the value and relevance of multisource data, the innovative capacity of human expertise, and the analytical efficiency of machine intelligence. Our goal is to conceptualize sustainable water management practices and enhance our understanding and predictive capabilities of groundwater systems. Unlike approaches that rely solely on abundant data, our framework emphasizes the quality and strategic use of available data, combined with human intellect and advanced computing, to overcome current limitations and pave the way for more realistic groundwater simulations. [Display omitted] [ABSTRACT FROM AUTHOR]

Virtual reality (VR) has advanced as a collaborative, realistic, and creative computation technique in recent decades. With organizations becoming digitally more focused and employees' experience changed by technology, manager's face and continue to confront several obstacles in the digital transformation process. Recent advances in information integration have been made possible by implementing the improved digital twin (DT) paradigm and its use in the workspace. To solve these problems, simulated convergence, realistic dynamic computational decision-making, and other tools are effective. This helps to complete activities with physical models and records. Thereby, this paper presents a Visually Improved Digital Media Communication Framework (VIDMCF) using VR technology and DT. Incorporating all information, displaying the whole procedure, avoiding challenges, closing loops, optimizing repetitive processes, and making complex decisions in real-time can be aided by reproducing physical systems in the virtual design and adding VR and digital mirror twin to the output of digital media. The proposed model can achieve connectivity and convergence among the realistic atmosphere and the digital environment's virtual system in cyber-real-space harmony over the life cycle. [ABSTRACT FROM AUTHOR]

Wind power forecasting is a field characterised by sudden weather-related events, turbine failures and constraints imposed by the electricity grid. Nowadays, different energy markets add the extra challenge of requiring predictions at the minute level a day forward for bidding-processes. This is to avoid trading energy as a bulk and match demand. In this context, we present a novel approach to predict power generation at high frequencies one day in advance, which handles constraints such as curtailment and turbine degradation. This has been tested over historical data from SCADA systems and historical forecasts from wind speed providers for eight windfarm locations in Ireland over two years. Our work was performed in two phases. First, we undertook a preliminary study to analyse the relationship between all combinations of observed wind, forecasted wind and electrical power. Secondly, a wide variety of Machine Learning algorithms were run over each of the locations in order to assess the degrees of predictability of different algorithms and regions. Most of the algorithms benchmarked improve linear wind to power mappings besides the high degree of noise in this domain. Our analysis and experimental results show how boosting ensembles are a cost-effective solution in terms of runtime among other Machine Learning algorithms predicting wind power a day ahead. [ABSTRACT FROM AUTHOR]

The failure of complex artificial intelligence (AI) systems seems ubiquitous. To provide a model to describe these shortcomings, we define complexity in terms of a system’s sensors and the number of environments or situations in which it performs. The complexity is not looked at in terms of the difficulty of design, but in the final performance of the system as a function of the sensor and environmental count. As the complexity of AI, or any system, increases linearly the contingencies increase exponentially and the number of possible design performances increases as a compound exponential. In this worst case scenario, the exponential increase in contingencies makes the assessment of all contingencies difficult and eventually impossible. As the contingencies grow large, unexpected and undesirable contingencies are all expected to increase in number. This, the worst case scenario, is highly connected, or conjunctive. Contingencies grow linearly with respect to complexity for systems loosely connected, or disjunctive. Mitigation of unexpected outcomes in either case can be accomplished using tools such as design expertise and iterative redesign informed by intelligent testing. [ABSTRACT FROM AUTHOR]

If we human beings are successful at enhancing our intelligence through technology, will this count as spiritual advance? No. Intelligence alone—whether what we are born with or what is superseded by artificial intelligence or intelligence amplification—has no built-in moral compass. Christian spirituality values love more highly than intelligence, because love orients us toward God, toward the welfare of the neighbor, and toward the common good. Spiritual advance would require orienting our enhanced intelligence toward loving God and neighbor with heart, mind (or intelligence), and soul. [ABSTRACT FROM AUTHOR]

Bench press training seems to be the most common exercise for increasing upper-body strength and control among athletes, fitness enthusiasts, and wellness buffs. Bench presses are usually done by lying down on the bench with the back, shoulders, and buttocks in touch. The bench press training surveillance systems with technical advancements are rarely seen in the research domain. Therefore, this paper presents a novel bench press training monitoring method (BPTMM) by evaluating mechanical joint rotational friction using Internet of Things (IoT) sensors. The bench press is a common upper body strength-building and muscle-building conditioning exercise. The bench press and the squat and deadlift are the three primary lifts performed in powerlifting competitions. Artificial intelligence aids in risk prediction and suggests possible positions. There is a 96.8% accuracy rate in surveillance and categorization, according to the findings of the experiments. [ABSTRACT FROM AUTHOR]

Emotion plays a significant role in human understanding and generally connected with rational decision making, attitudes, human activity, and human intelligence. To create realistic emotional relations between human beings and machines, the research community's increasing interests need reliable and deployable solutions to recognize human emotional conditions. Automatic emotion detection is one of the main obstacles in providing innovative methods for more comfortable and more objective diagnosis, communication and analysis. Hence in this paper, an Artificial intelligence-assisted emotion prediction model (AIEPM) has been proposed to evaluate the probability of digital representation, identification and estimation of feelings, their state-of-the-art methods and primary research guidance. The proposed AIEPM analyses the effect on multimodal detection of emotional models. This paper presents emerging works based on language, sound, image, film, and physiological signals using current methods such as machine intelligence for recognizing human emotion. The proposed emphasis on this cutting-edge analysis reflects elements like the form and presentation of emotional stimulation, the sample's scale. The numerical outcome suggested AIEPM, according to age, behaviour classification according to age (95.2%), emotions state recognition high probability in satisfaction compared to the proposed method, accuracy ratio (89.6%), performance ratio (94.5%) and recognition outcomes of existing and proposed work (98.2%) compared to other existing approaches improve behaviour classification. [ABSTRACT FROM AUTHOR]

Glioblastoma (GBM) is a highly morbid and lethal disease with poor prognosis. Their emergent properties such as cellular heterogeneity, therapy resistance, and self-renewal are largely attributed to the interactions between a subset of their population known as glioblastoma-derived stem cells (GSCs) and their microenvironment. Identifying causal patterns in the developmental trajectories between GSCs and the mature, well-differentiated GBM phenotypes remains a challenging problem in oncology. The paper presents a blueprint of complex systems approaches to infer attractor dynamics from the single-cell gene expression datasets of pediatric GBM and adult GSCs. These algorithms include Waddington landscape reconstruction, GANs (Generative Adversarial Networks), and fractal dimension analysis. Here I show, a Rössler-like strange attractor with a fractal dimension of roughly 1.7 emerged in all n = 12 patients’ GAN-reconstructed patterns. The findings suggest a strange attractor may be driving the complex dynamics and adaptive behaviors of GBM in signaling state-space. [ABSTRACT FROM AUTHOR]

Purpose: The electronic nose is an array of chemical or gas sensors and associated with a pattern-recognition framework competent in identifying and classifying odorant or non-odorant and simple or complex gases. Despite more than 30 years of research, the robust e-nose device is still limited. Most of the challenges towards reliable e-nose devices are associated with the non-stationary environment and non-stationary sensor behaviour. Data distribution of sensor array response evolves with time, referred to as non-stationarity. The purpose of this paper is to provide a comprehensive introduction to challenges related to non-stationarity in e-nose design and to review the existing literature from an application, system and algorithm perspective to provide an integrated and practical view. Design/methodology/approach: The authors discuss the non-stationary data in general and the challenges related to the non-stationarity environment in e-nose design or non-stationary sensor behaviour. The challenges are categorised and discussed with the perspective of learning with data obtained from the sensor systems. Later, the e-nose technology is reviewed with the system, application and algorithmic point of view to discuss the current status. Findings: The discussed challenges in e-nose design will be beneficial for researchers, as well as practitioners as it presents a comprehensive view on multiple aspects of non-stationary learning, system, algorithms and applications for e-nose. The paper presents a review of the pattern-recognition techniques, public data sets that are commonly referred to as olfactory research. Generic techniques for learning in the non-stationary environment are also presented. The authors discuss the future direction of research and major open problems related to handling non-stationarity in e-nose design. Originality/value: The authors first time review the existing literature related to learning with e-nose in a non-stationary environment and existing generic pattern-recognition algorithms for learning in the non-stationary environment to bridge the gap between these two. The authors also present details of publicly available sensor array data sets, which will benefit the upcoming researchers in this field. The authors further emphasise several open problems and future directions, which should be considered to provide efficient solutions that can handle non-stationarity to make e-nose the next everyday device. [ABSTRACT FROM AUTHOR]

From early days, a key and controversial question inside the artificial intelligence community was whether Artificial General Intelligence (AGI) is achievable. AGI is the ability of machines and computer programs to achieve human-level intelligence and do all tasks that a human being can. While there exist a number of systems in the literature claiming they realize AGI, several other researchers argue that it is impossible to achieve it. In this paper, we take a different view to the problem. First, we discuss that in order to realize AGI, along with building intelligent machines and programs, an intelligent world should also be constructed which is on the one hand, an accurate approximation of our world and on the other hand, a significant part of reasoning of intelligent machines is already embedded in this world. Then we discuss that AGI is not a product or algorithm, rather it is a continuous process which will become more and more mature over time (like human civilization and wisdom). Then, we argue that pre-trained embeddings play a key role in building this intelligent world and as a result, realizing AGI. We discuss how pre-trained embeddings facilitate achieving several characteristics of human-level intelligence, such as embodiment, common sense knowledge, unconscious knowledge and continuality of learning, by machines. [ABSTRACT FROM AUTHOR]

Digital systems have been playing a vital role in various applications such as banking, finance, healthcare, manufacturing, security and so on. Also, their role and applications are becoming wider and more crucial. In many such applications, identifying and recognizing a character, or a digit accurately, plays a significant role, especially in banking and financial sectors and other sectors where an error can cause much loss or damage. This, technically, is called the optical character recognition (OCR) problem. In this context, contribution of this paper is of two folds. First, we propose a multi-layer perceptron (MLP) neural network architecture that includes an input layer, hidden layers and an output layer to develop an effective method for OCR. The architecture builds a model that learns representations from the input data and further these representations are used for classifying the unknown data. This proposed method MLP, which recognizes optical characters, is compared to existing nearest neighborhood methods such as condensed nearest neighbor (CNN), modified condensed nearest neighbor (MCNN) and other class nearest neighbor (OCNN), in performance. Posterior probabilities and conditional probabilities pertaining to recognition are computed, estimated and validated on the test data (OCR and Pendigits) for all the afore-mentioned methods. Using these posterior probabilities, probabilities of detection of the newly drawn character or digits can be estimated. The proposed model in this paper outperforms existing methods. The second contribution is as follows. In certain critical applications, it is very important to achieve the highest possible accuracy even if it is expensive. To achieve this a multi-pronged approach using multiple methods is developed based on these four methods, in order to improve and estimate the accuracy, in cases when multiple methods concur or otherwise. [ABSTRACT FROM AUTHOR]

Attribution of paintings is a critical problem in art history. This study extends machine learning analysis to surface topography of painted works. A controlled study of positive attribution was designed with paintings produced by a class of art students. The paintings were scanned using a chromatic confocal optical profilometer to produce surface height data. The surface data were divided into virtual patches and used to train an ensemble of convolutional neural networks (CNNs) for attribution. Over a range of square patch sizes from 0.5 to 60 mm, the resulting attribution was found to be 60–96% accurate, and, when comparing regions of different color, was nearly twice as accurate as CNNs using color images of the paintings. Remarkably, short length scales, even as small as a bristle diameter, were the key to reliably distinguishing among artists. These results show promise for real-world attribution, particularly in the case of workshop practice. [ABSTRACT FROM AUTHOR]

Attribution of paintings is a critical problem in art history. This study extends machine learning analysis to surface topography of painted works. A controlled study of positive attribution was designed with paintings produced by a class of art students. The paintings were scanned using a chromatic confocal optical profilometer to produce surface height data. The surface data were divided into virtual patches and used to train an ensemble of convolutional neural networks (CNNs) for attribution. Over a range of square patch sizes from 0.5 to 60 mm, the resulting attribution was found to be 60–96% accurate, and, when comparing regions of different color, was nearly twice as accurate as CNNs using color images of the paintings. Remarkably, short length scales, even as small as a bristle diameter, were the key to reliably distinguishing among artists. These results show promise for real-world attribution, particularly in the case of workshop practice. [ABSTRACT FROM AUTHOR]

Background: Current intra-tumoral heterogeneous feature extraction in radiology is limited to the use of a single slice or the region of interest within a few context-associated slices, and the decoding of intra-tumoral spatial heterogeneity using whole tumor samples is rare. We aim to propose a mathematical model of space-filling curve-based spatial correspondence mapping to interpret intra-tumoral spatial locality and heterogeneity. Methods: A Hilbert curve-based approach was employed to decode and visualize intra-tumoral spatial heterogeneity by expanding the tumor volume to a two-dimensional (2D) matrix in voxels while preserving the spatial locality of the neighboring voxels. The proposed method was validated using three-dimensional (3D) volumes constructed from lung nodules from the LIDC-IDRI dataset, regular axial plane images, and 3D blocks. Results: Dimensionality reduction of the Hilbert volume with a single regular axial plane image showed a sparse and scattered pixel distribution on the corresponding 2D matrix. However, for 3D blocks and lung tumor inside the volume, the dimensionality reduction to the 2D matrix indicated regular and concentrated squares and rectangles. For classification into benign and malignant masses using lung nodules from the LIDC-IDRI dataset, the Inception-V4 indicated that the Hilbert matrix images improved accuracy (85.54% vs. 73.22%, p < 0.001) compared to the original CT images of the test dataset. Conclusions: Our study indicates that Hilbert curve-based spatial correspondence mapping is promising for decoding intra-tumoral spatial heterogeneity of partial or whole tumor samples on radiological images. This spatial-locality-preserving approach for voxel expansion enables existing radiomics and convolution neural networks to filter structured and spatially correlated high-dimensional intra-tumoral heterogeneity. [ABSTRACT FROM AUTHOR]

The future network is expected to support extremely large bandwidth, ultra-low latency or deterministic delay, extremely high reliability, and massive connectivity for novel forward-looking scenarios. As one of the most fundamental parts of the network, routing plays a vital role in a well-performed network. Recently, some new techniques using machine intelligence to optimize the network routing have been proposed. Although they have demonstrated great potential to improve the network performance, it is still a great challenge to apply machine intelligence-based routing in real network environment due to the limitations of current network architectures and protocols. Fortunately, the future network research program is on-going for designing new network paradigms, which provides an opportunity to address those limitations. In this paper, we investigate state-of-the-art techniques in machine intelligence-enabled network routing and discuss the development trends of machine intelligence-enabled routing optimization techniques for the future network. [ABSTRACT FROM AUTHOR]

Frequent itemsets mining is an active research problem in the domain of data mining and knowledge discovery. With the advances in database technology and an exponential increase in data to be stored, there is a need for efficient approaches that can quickly extract useful information from such large datasets. Frequent Itemsets (FIs) mining is a data mining task to find itemsets in a transactional database which occur together above a certain frequency. Finding these FIs usually requires multiple passes over the databases; therefore, making efficient algorithms crucial for mining FIs. This work presents a graph-based approach for representing a complete transactional database. The proposed graph-based representation enables the storing of all relevant information (for extracting FIs) of the database in one pass. Later, an algorithm that extracts the FIs from the graph-based structure is presented. Experimental results are reported comparing the proposed approach with 17 related FIs mining methods using six benchmark datasets. Results show that the proposed approach performs better than others in terms of time. [ABSTRACT FROM AUTHOR]

Integrating the Internet of Things (IoT) and edge computing in Edge-IoT systems, converged with machine intelligence, has the potential to enable a wide range of applications in smart homes, factories, and cities. Edge-IoT can connect many diverse devices, and IoT asset owners can run heterogeneous IoT systems supported by various vendors or service providers (SPs), using either cloud or local edge computing (or both) for resource assistance. The existing methods typically manage the systems as separate vertical silos, or in a vendor-/SP-centric way, which suffers from significant challenges. In this article, we present a novel owner-centric management paradigm named ORCA to address the gaps left by the owner-centric paradigm and empower IoT asset owners to effectively identify and mitigate potential issues in their own network premises, regardless of vendors'/SPs' situations. ORCA aims to be scalable and extensible in assisting IoT owners to perform intelligent management through a behavior-oriented and data-driven approach. ORCA is an ongoing project, and the preliminary results indicate that it can significantly empower IoT system owners to better manage their IoT assets. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to demonstrate the principle and practical applications of hyperspectral object detection, carry out the problem we now face and the possible solution. Also some challenges in this field are discussed. Design/methodology/approach: First, the paper summarized the current research status of the hyperspectral techniques. Then, the paper demonstrated the development of underwater hyperspectral techniques from three major aspects, which are UHI preprocess, unmixing and applications. Finally, the paper presents a conclusion of applications of hyperspectral imaging and future research directions. Findings: Various methods and scenarios for underwater object detection with hyperspectral imaging are compared, which include preprocessing, unmixing and classification. A summary is made to demonstrate the application scope and results of different methods, which may play an important role in the application of underwater hyperspectral object detection in the future. Originality/value: This paper introduced several methods of hyperspectral image process, give out the conclusion of the advantages and disadvantages of each method, then demonstrated the challenges we face and the possible way to deal with them. [ABSTRACT FROM AUTHOR]

In this letter, some peculiarities, challenges, and possible limitations of using ChatGPT in the field of medicine are discussed. [ABSTRACT FROM AUTHOR]

The Turing Test is routinely understood as a behaviourist test for machine intelligence. Diane Proudfoot (Rethinking Turing's Test, Journal of Philosophy, 2013) has argued for an alternative interpretation. According to Proudfoot, Turing's claim that intelligence is what he calls 'an emotional concept' indicates that he conceived of intelligence in response-dependence terms. As she puts it: 'Turing's criterion for "thinking" is...: x is intelligent (or thinks) if in the actual world, in an unrestricted computer-imitates-human game, x appears intelligent to an average interrogator'. The role of the famous test is thus to provide the conditions in which to examine the average interrogator's responses. I shall argue that Proudfoot's analysis falls short. The philosophical literature contains two main models of response-dependence, what I shall call the transparency model and the reference-fixing model. Proudfoot resists the thought that Turing might have endorsed one of these models to the exclusion of the other. But the details of her own analysis indicate that she is, in fact, committed to the claim that Turing's account of intelligence is grounded in a transparency model, rather than a reference-fixing one. By contrast, I shall argue that while Turing did indeed conceive of intelligence in response-dependence terms, his account is grounded in a reference-fixing model, rather than a transparency one. This is fortunate (for Turing), because, as an account of intelligence, the transparency model is arguably problematic in a way that the reference-fixing model isn't. [ABSTRACT FROM AUTHOR]

Twenty years ago in "Turing's Two Tests for Intelligence" I distinguished two distinct tests to be found in Alan Turing's 1950 paper "Computing Machinery and Intelligence": one by then very well-known, the other neglected. I also explained the significance of the neglected test. This paper revisits some of the points in that paper and explains why they are even more relevant today. It also discusses the value of tests for machine intelligence based on games humans play, giving an analysis of some twentieth century TV game shows and how they relate to the tests for machine intelligence in Turing's paper and in some other tests for machine intelligence that have been proposed since. Their value in distinguishing between 'wise' and simply 'clever' AI is discussed. [ABSTRACT FROM AUTHOR]

We define hybrid intelligence (HI) as the combination of human and machine intelligence, augmenting human intellect and capabilities instead of replacing them and achieving goals that were unreachable by either humans or machines. HI is an important new research focus for artificial intelligence, and we set a research agenda for HI by formulating four challenges. [ABSTRACT FROM AUTHOR]

Clear Bright Future is Paul Mason's radical defence of humanity from Trumpist populism and de-globalisation, neo-liberalism, the threat of machine learning and, notwithstanding the book's title (lifted from Trotsky's Testament), Marxism, which, he considers, needs a 'kicking'. Mason redefines Marx's Theses on Feuerbach so that the point of change is to understand the world, or more precisely, for him to understand the world. According to Mason, the declassed, amorphous but nonetheless conscious, yet unconscious, networked individual, who is far more complex, and so essential, than traditional classes, although not a traditional class, and so subjective and not objective, and so not essential, will adopt communism, even though it has not, and implement a new world order, somehow. Mainly it would appear by arguing that machines do not have feelings, but also by rehabilitating the absolute moral philosophy of Thomas Malthus, amongst other things. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to introduce a novel respiration pattern-based biometric prediction system (BPS) by using artificial neural network (ANN). Design/methodology/approach: Respiration patterns were obtained using a knitted piezoresistive smart chest band. The ANN model was implemented by using four hidden layers to help achieve the best complexity to produce an adequate fit for the data. Not only did this study give a detailed distribution of an ANN model construction including the scheme of parameters and network layers, ablation of the architecture and the derivation of back-propagation during the iterations but also engaged a step-based decay to systematically drop the learning rate after specific epochs during training to minimize the loss and increase the model's accuracy as well as to limit the risk of overfitting. Findings: Findings establish the feasibility of using respiratory patterns for biometric identification. Experimental results show that, with a learning rate drop factor = 0.5, the network is able to continue to learn past epoch 40 until stagnation occurs which yielded a classification accuracy of 98 per cent. Out of 51,338 test set, the model achieved 51,557 correctly classified instances and 169 misclassified instances. Practical implications: The findings provide an impetus for possible studies into the application of chest breathing sensors for human machine interfaces in the area of entertainment. Originality/value: This is the first time respiratory patterns have been applied in biometric prediction system design. [ABSTRACT FROM AUTHOR]

While conventional calibrated photometric stereo methods assume that light intensities and sensor exposures are known or unknown but identical across observed images, this assumption easily breaks down in practical settings due to individual light bulb's characteristics and limited control over sensors. This paper studies the effect of unknown and possibly non-uniform light intensities and sensor exposures among observed images on the shape recovery based on photometric stereo. This leads to the development of a “semi-calibrated” photometric stereo method, where the light directions are known but light intensities (and sensor exposures) are unknown. We show that the semi-calibrated photometric stereo becomes a bilinear problem, whose general form is difficult to solve, but in the photometric stereo context, there exists a unique solution for the surface normal and light intensities (or sensor exposures). We further show that there exists a linear solution method for the problem, and develop efficient and stable solution methods. The semi-calibrated photometric stereo is advantageous over conventional calibrated photometric stereo in accurate determination of surface normal, because it relaxes the assumption of known light intensity ratios/sensor exposures. The experimental results show superior accuracy of the semi-calibrated photometric stereo in comparison to conventional methods in practical settings. [ABSTRACT FROM AUTHOR]

Cognitive systems are highly adaptable and flexible, such that action and perception capabilities can be achieved with the body in various ways, and incorporate features of the environment and nonbiological tools. Perceptual learning refers to enduring changes to a system's ability to perceive and respond to environmental stimuli. Here I present an integrative framework for understanding how such capabilities occur in human–machine systems comprising brain–body–tool–environment interactions. Central to this work is the claim that the capacity for high degrees of adaptation, flexibility, and learning are possible because human–machine systems are soft-assembled systems, that is, systems whose material constitution is not rigidly constrained so as to achieve goals via a variety of configurations. I begin by presenting the foundations of the framework on offer: the concepts, methods, and theories of ecological psychology; embodied cognition; dynamical systems theory; and machine intelligence. Next, I apply the framework to the case of visually-guided action. I conclude by explaining how this framework provides the explanatory and investigative tools to understand human–machine perceptual systems as soft-assembled systems that span brains-bodies-tools-environments. [ABSTRACT FROM AUTHOR]

Purpose: An autonomous mobile robot requires efficient perception of the environment to perform various tasks in a challenging environment. The precise sensory information from the range sensors is required to accomplish prerequisites, such as SLAM, path planning and localization. But the accuracy and precision of the sensors become unreliable in harsh environmental conditions because of the effect of rain, dust, humidity, fog and smoke. The purpose of this paper is to generate robust mapping of the environment in harsh environmental conditions. Design/methodology/approach: This paper presents a novel technique, averaging data with short range selection (ADWSRS), to reduce the effect of harsh environmental (rain, wind, humidity, etc.) conditions on sensory information (range) to generate reliable grid mapping. The sensory information on laser and sonar sensors in terms of probability values (occupied/unoccupied cell) in generating grid maps are fused after passing through two newly designed pre-processing filters: laser averaging filter and short range selection filter. This proposed approach relies on various aspects such as averaging laser data analogous to current pose of the sensor, selection of short range with respect to threshold value to remove the effect of specular reflection/crosstalk of sonar and a newly designed apparatus in which dirt cover (glass cover) and air blower are coupled to remove the influence of dirt, rain and humidity. Findings: This proposed approach is tested in different environmental conditions, and to verify the consistency of the proposed approach, qualitative and quantitative analyses are carried out, which shows 42.5 per cent improvement in the probability value of occupied cells in the generated grid map. Originality/value: The proposed ADWSRS approach reduced the effect of harsh environmental conditions such as fog, rain and smoke to generate efficient mapping of the environment, which may be implemented in diverse applications such as autonomous navigation, localization, path planning and mapping. [ABSTRACT FROM AUTHOR]

An inventive scheme for automated tissue segmentation and classification is offered in this paper using Fast Discrete Wavelet Transform (DWT)/Band Expansion Process (BEP), Kernel-based least squares Support Vector Machine (KLS-SVM) and F-score, backed by Principal Component Analysis (PCA). Using input as T1, T2 and Proton Density (PD) scans of patients, CSF (Cerebrospinal Fluid), WM (White matter) and GM (Gray matter) are afforded as output, which act as hallmark for brain atrophy and thus sustaining in diagnosis of Alzheimer's disease (AD) from Mild Cognitive Impairment (MCI) and Healthy Controls (HC). The blending of BEP features from DWT and texture features from Gray Level Co-occurrence Matrix (GLC) promises to be a savior in atrophy revelation of the segmented tissues. Data used for evaluation of this study is taken from the ADNI database that encloses T1-weighted s-MRI (Structural Magnetic Imaging Resonance) scans of 158 patients with AD and 145 HC. Preprocessing steps unearthed five parameters for classification (i.e. cortical thickness, curvature, gray matter volume, surface area, and sulcal depth), in the preliminary step. For challenging the classifier performance, ROC (Receiver operating characteristics) curves are painted and the SVM classifiers of two-dimensional spaces took the top two important features as classification features for separating HC and AD to the maximum extent. The final results revealed that Fast DWT + F-Score + PCA + KLS-SVM + Poly Kernel is giving 100% tissue classification accuracy for test samples under consideration with only 7 input features. [ABSTRACT FROM AUTHOR]

This paper presents the use of an energy recycling technique to extract the intrinsic parameters of lead–acid batteries. The charging and discharging currents of the battery under test are programmed by controlling a bidirectional dc–dc converter to profile the power flow between the battery and a supercapacitor. The sampled battery voltage and current information over the charging and discharging periods are used to estimate the parameters of a high-order electrical battery model with a modified particle swarm optimization algorithm and compare with the battery voltage and current predicted with the extracted parameters.  With the energy recycling mechanism, the proposed parameter extraction process is environment friendly and has low power dissipation, thus increasing the power handling density and allowing long testing duration. A prototype that can extract the intrinsic parameters of eight different types of 12 V, 130 A lead–acid batteries has been built. Its performance has been evaluated with different charging and discharging profiles. The estimated parameters are favorably verified with the theoretical predictions, results obtained by the extended Kalman filter method, and results obtained on a calibrated commercial battery testing system. Results reveal that testing batteries with both charging and discharging processes gives a more accurate prediction of battery performance. [ABSTRACT FROM AUTHOR]

This cross-sectional study (N = 325) investigated the relationship between the Dark Triad personality traits and the perception of artificial intelligence (AI) risk. Narrow AI risk perception was measured based on recently identified perceived risks in the public. Artificial general intelligence (AGI) risk perception was operationalized in terms of plausibility ratings and subjective probability estimates on deceptive AI scenarios developed by Bostrom (2014), in which AI-sided deception is described as a function of intelligence. Machiavellianism and psychopathy predicted narrow AI risk perception above the shared variance of the Dark Triad and above the Big Five. In individuals with self-reported knowledge of machine learning, the Dark Triad traits were associated with AGI risk perception. This study provides evidence for the existence of substantial individual differences in the risk perception of AI. [ABSTRACT FROM AUTHOR]