Intelligent Objects Research Articles

Self-Attention-Based Convolutional GRU for Enhancement of Adversarial Speech Examples

Recent research has identified adversarial examples which are the challenges to DNN-based ASR systems. In this paper, we propose a new model based on Convolutional GRU and Self-attention U-Net called [Formula: see text] to improve adversarial speech signals. To represent the correlation between neighboring noisy speech frames, a two-Layer GRU is added in the bottleneck of U-Net and an attention gate is inserted in up-sampling units to increase the adversarial stability. The goal of using GRU is to combine the weights sharing technique with the use of gates to control the flow of data across multiple feature maps. As a result, it outperforms the original 1D convolution used in [Formula: see text]. Especially, the performance of the model is evaluated by explainable speech recognition metrics and its performance is analyzed by the improved adversarial training. We used adversarial audio attacks to perform experiments on automatic speech recognition (ASR). We saw (i) the robustness of ASR models which are based on DNN can be improved using the temporal features grasped by the attention-based GRU network; (ii) through adversarial training, including some additive adversarial data augmentation, we could improve the generalization power of Automatic Speech Recognition models which are based on DNN. The word-error-rate (WER) metric confirmed that the enhancement capabilities are better than the state-of-the-art [Formula: see text]. The reason for this enhancement is the ability of GRU units to extract global information within the feature maps. Based on the conducted experiments, the proposed [Formula: see text] increases the score of Speech Transmission Index (STI), Perceptual Evaluation of Speech Quality (PESQ), and the Short-term Objective Intelligibility (STOI) with adversarial speech examples in speech enhancement.

DCT based densely connected convolutional GRU for real-time speech enhancement

Over the past ten years, deep learning has enabled significant advancements in the improvement of noisy speech. Due to the short time stability of speech signal, previous speech enhancement (SE) methods concentrated only on magnitude estimation, and these methods added a phase of the mixture in reconstructing the speech. The performance is limited in these approaches since the phase will also carry some of the speech information. Some of the speech enhancement approaches were developed later to jointly estimate both magnitudes as well as phases. Recently, complex-valued models, like deep complex convolution recurrent network (DCCRN), are proposed, but the computation of the model is very huge. In this work, we propose a Discrete Cosine Transform-based Densely Connected Convolutional Gated Recurrent Unit (DCTDCCGRU) model using dilated dense block and stacked GRU. The dense connectivity strengthens the gradient propagation by concatenating features from previous layers at the input. The advantage of the dense block is that at various resolutions, the dilated convolutions aid with context aggregation, and the dense connectivity provides a feature map with more precise target information by passing through multiple layers. To represent the correlation between neighboring noisy speech frames, a two Layer GRU is added in the bottleneck of U-Net. The experimental findings demonstrate that the proposed model outperformed the other existing models in terms of STOI (short-time objective intelligibility), PESQ (perceptual evaluation of the speech quality), and output SNR (signal-to-noise ratio).

An Adaptive Hybrid Attention Based Convolutional Neural Net for Intelligent Transportation Object Recognition

An Adaptive Hybrid Attention Based Convolutional Neural Net for Intelligent Transportation Object Recognition

Real-time Mixed Reality (MR) and Artificial Intelligence (AI) object recognition integration for digital twin in Industry 4.0

In the digital era, real-time object recognition and inspection, based on Artificial Intelligence (AI), have become vitally important in a wide range of applications. With the evolution of Industry 4.0, the integration of digital informatics and decisions is crucial for smart manufacturing, Logistics 4.0, and supply chain digitization. However, much of digital content lacks interconnection. As such, the Digital Twin (DT) was proposed to promote the integration of physical machines and devices with the digital space. Augmented reality (AR) usually works in conjunction with the DT network to collect and provide real-time data. In fact, most of the AR devices are not fully connected in DT as the decision support from AI is disconnected. On the other hand, human-machines and object interactions are still complicated in AR, thus limiting applications. In order to achieve digital twinning for object recognition and human-machine interaction, we proposed a DT architecture for integrating the latest Mixed Reality (MR) device for real-time data streaming. Object recognition is empowered by the AI algorithm in the backend cloud computing and database. The entire system integrates the informatics between physical machines and devices and the digital content using an AI algorithm. Our proposed method achieved real-time informatics integration of MR and AI, while the warehouse is used as a case scenario with simulations. Industrial informatics integration can be applied for smart manufacturing, smart warehouse, and many Industry 4.0 applications.

HIDE-Healthcare IoT Data Trust ManagEment: Attribute centric intelligent privacy approach

The cloud-based Internet of Things (IoTs) storage enables patients to monitor their health remotely and offers services for physicians of various Medical Institutions (MIs) to diagnose and treat them on time. As a matter of trust, patients are legally expected to hide their real identity and ensure data privacy in the cross-domain of IoT-healthcare, whether it is stored correctly or modified due to external and internal attacks in the cloud. Additionally, physicians treat patients and continuously store duplicated data in cloud storage, which increases the cost of computing. In this context, this paper presents HIDE-Healthcare IoT Data privacy trust management framework, focusing on attributes. Patients’ attributes are used to encrypt and decrypt sensory data between patients and different entities by incorporating the idea of trustworthy and secure shared keys. HIDE uses an intelligent object’s pointer to store the same patient’s sensory data in various versions to prevent data duplication, which will help track MIs that treat patients. An intelligent content-based emergency data access control is developed to monitor multiple patient health criticalities in HIDE. The security analysis and experimental evaluation attest to the benefits of the proposed HIDE framework, considering security and privacy metrics.

The anatomo-politics of affect: An investigation of affective governmentality

The present inquiry concerns ‘affective governmentality’ and is guided by the following question: How did affects become intelligible objects of knowledge and what enabled a scientific conception of affect to turn into a distinctive government of affect? In answering this question, the article first outlines how a lineage of thinkers used the speculative tools of geometry to conceptualize and deduce human affects. Through an analysis of Spinoza’s Political Treatise, the article then investigates how this geometric conception of affect enabled a productive and indirect government of affect. The article’s contribution to the study of affective governmentality is twofold: First, it advances the methodological claim that the proper register to study affects in governmentality is anatomo-political rather than biopolitical. Second, the analysis of the Political Treatise exemplifies, nuances and substantiates our understanding of how desires and affects were reconceptualized geometrically to conceive a government of bodies and souls.

Fast and accurate object detector for autonomous driving based on improved YOLOv5

Autonomous driving is an important branch of artificial intelligence, and real-time and accurate object detection is key to ensuring the safe and stable operation of autonomous vehicles. To this end, this paper proposes a fast and accurate object detector for autonomous driving based on improved YOLOv5. First, the YOLOv5 algorithm is improved by using structural re-parameterization (Rep), enhancing the accuracy and speed of the model through training-inference decoupling. Additionally, the neural architecture search method is introduced to cut redundant branches in the multi-branch re-parameterization module during the training phase, which ameliorates the training efficiency and accuracy. Finally, a small object detection layer is added to the network and the coordinate attention mechanism is added to all detection layers to improve the recognition rate of the model for small vehicles and pedestrians. The experimental results show that the detection accuracy of the proposed method on the KITTI dataset reaches 96.1%, and the FPS reaches 202, which is superior to many current mainstream algorithms and effectively improves the accuracy and real-time performance of unmanned driving object detection.

Accurate Movement Detection of Artificially Intelligent Security Objects

A number of intelligent applications demand multiple item detection and tracking as vital elements. Although object search links the identified object through a series of frames, object detection pinpoints the thing's location in a scene. Over the last few decades, a wide range of approaches has been created, which may be divided into 2D and stereo-based 3D techniques. When used in limited circumstances, most of these strategies yield trustworthy findings. These limiting presumptions are used to determine the number of complex elements that object detection and tracking naturally entail. Environmental factors, object appearance, flow density, backdrop colour intensity information, the amount of time an object is present in the scene, object occlusion, a scene's maximum number of things, etc., are among the most often held presumptions. In real-time applications, these approaches' dependability is not assured. A modern surveillance system needs reliable object identification and tracking in an open area.

Is the Concept of Industry 4.0 Still Interesting for Scientists due to the Emergence of Industry 5.0? Bibliometric Analysis

Abstract Research purpose. Through Industry 4.0, also referred to as the fourth industrial revolution, new technologies or traditional production resources have been transformed into intelligent objects enhanced by the possibility of identification, scanning, and networking. In recent years, the concept of Industry 5.0 has already started to be discussed. However, is Industry 4.0 an uninteresting or sufficiently researched topic for scientists? The main aim of the scientific article is to perform a bibliometric analysis of the Industry 4.0 issue. The aim was supported by six research questions that reflect the publication trend in the years 2012–2022, the most publishing countries, the most used keywords, the Web of Science category, and authors and publishers. Design / Methodology / Approach. The data was obtained from the renowned Web of Science database. The monitored period was 2012–2022 for Industry 4.0 and 2016-2022 for Industry 5.0. The year 2023 was excluded from the analysis, as the year 2023 is not finished. The total number of publications that were used in the bibliometric analysis was 20,151 (I4.0) and 293 (I5.0). VOSviewer and MS Excel were used for graphical data processing. Findings. The oldest publication dedicated to Industry 4.0 in the Web of Science database dates back to 2012. The most scientific articles were seen in 2021, namely 4,326 (I4.0) and 201 in 2022 about I5.0. In 2022, 3848 publications were published. In addition, authors from Germany (2,450), Italy (2,318), China (1,515), and the USA (1,220) address the issue of Industry 4.0. All the countries of the Visegrad Group, Poland (859), the Czech Republic (859), Slovakia (539), and Hungary (282) are most concerned with this problem. If the publications are divided into categories according to the Web of Science database, most of them are included in the categories Engineering Industrial, Engineering Manufacturing, Engineering Electrical Electronic, Computer Science Theory Methods, or Computer Science Information Systems. Publications on Industry 4.0 are published mainly by publishers such as IEEE, Elsevier, Springer, and MDPI. The authors who are most devoted to the mentioned issue are Popkova, Martinek, Rauch, Bogoviz, Silva, and Xu. Originality / Value / Practical implications. The added value of the scientific article is the summarisation of theoretical starting points from the field of Industry 4.0 and Industry 5.0. Likewise, the article is original from the point of view of conducting a bibliometric analysis, focused on the development of the number of publications, the authors who are most devoted to the given topic, the most commonly used keywords, or countries that focus on Industry 4.0 and Industry 5.0 issues the most. The originality of the article also lies in the mapping of the publications of the monitored issue for the entire previous year, 2022.

Do communal narcissists care about intelligence? Associations with high self-assessed and low objective intelligence

Do communal narcissists care about intelligence? Associations with high self-assessed and low objective intelligence

Optimizing robot grasping using soft origami zigzag gripper with artificial intelligence

The covid-19 pandemic leads to an increased need for automation in food industries. Current soft robots require cast moulding, high assembly effort, large actuators, and upfront actuation awareness due to the absence of artificial intelligence. Soft origami structures exhibit high levels of compliance. We developed a 3D print-in-place under-actuated soft origami zigzag gripper using TPU with artificial intelligence object pose estimation to grasp objects with high repeatability of success under different conditions. A self-designed 3D robot arm is used for object grasping. Grasping performance tests were conducted using different gripper designs, robot arm speed, and gripping force on objects with different masses and morphology. The soft origami zigzag gripper has better-grasping performance than the hard gripper as analyzed by paired t-test. The logistic model of the soft origami zigzag gripper’s grasping performance achieved an accuracy of 0.940 and AUC=0.911. Jetson Nano running AI CNN Resnet18, enhanced grasping performance with vision object classification achieved an accuracy of 0.923 and F1 score of 0.956. The AI CNN MobileNetV2 is used for object classification and experimental results showed it had lower accuracy as compared to the AI CNN Resnet18. The object classification using artificial intelligence optimized the robot grasping to improve automation in food processing and food handling to avoid contamination. All these can be used in the automation process in the food industry to overcome health and safety challenges.

LN-Net: Perfusion Pattern-Guided Deep Learning for Lymph Node Metastasis Diagnosis Based on Contrast-Enhanced Ultrasound Videos.

The blood flow in lymph nodes reflects important pathological features. However, most intelligent diagnosis based on contrast-enhanced ultrasound (CEUS) video focuses only on CEUS images, ignoring the process of extracting blood flow information. In the work described here, a parametric imaging method for describing blood perfusion pattern was proposed and a multimodal network (LN-Net) to predict lymph node metastasis was designed. First, the commercially available artificial intelligence object detection model YOLOv5 was improved to detect the lymph node region. Then the correlation and inflection point matching algorithms were combined to calculate the parameters of the perfusion pattern. Finally, the Inception-V3 architecture was used to extract the image features of each modality, with the blood perfusion pattern taken as the guiding factor in fusing the features with CEUS by sub-network weighting. The average precision of the improved YOLOv5s algorithm compared with baseline was improved by 5.8%. LN-Net predicted lymph node metastasis with 84.9% accuracy, 83.7% precision and 80.3% recall. Compared with the model without blood flow feature guidance, accuracy was improved by 2.6%. The intelligent diagnosis method has good clinical interpretability. A static parametric imaging map could describe a dynamic blood flow perfusion pattern, and as a guiding factor, it could improve the classification ability of the model with respect to lymph node metastasis.

Development of a method of complex analysis and multidimensional forecasting of the state of intelligence objects

A method of complex analysis and multidimensional forecasting of the state of intelligence objects is proposed to increase the accuracy of their state assessment. The object of research is decision support systems. The subject of research is the process of decision-making in management problems using artificial intelligence methods. The hypothesis of research is to increase the efficiency of decision-making with a given assessment reliability. The proposed method is based on a combination of fuzzy cognitive and temporal models, an advanced cat swarm optimization algorithm and evolving artificial neural networks. The method has the following sequence of actions: ‒ input of initial data; ‒ processing of initial data taking into account uncertainty about the state of heterogeneous intelligence objects; ‒ construction of a fuzzy temporal ontological model of heterogeneous intelligence objects; ‒ conclusion on the state of heterogeneous intelligence objects; ‒ correction of the fuzzy temporal ontological model; ‒ building a fuzzy relational temporal cognitive model of heterogeneous intelligence objects and forecasting the state of the intelligence object; ‒ training knowledge bases on heterogeneous intelligence objects. The training procedure consists in learning the synaptic weights of the artificial neural network, the type and parameters of the membership function, as well as the architecture of individual elements and the architecture of the artificial neural network as a whole. The method makes it possible to increase the efficiency of data processing at the level of 18–25 % by using additional improved procedures. The proposed method should be used to solve the problems of evaluating complex and dynamic heterogeneous intelligence objects, characterized by a high degree of complexity.

Characterization of the Intelligibility of Vowel–Consonant–Vowel (VCV) Recordings in Five Languages for Application in Speech-in-Noise Screening in Multilingual Settings

The purpose of this study is to characterize the intelligibility of a corpus of Vowel–Consonant–Vowel (VCV) stimuli recorded in five languages (English, French, German, Italian and Portuguese) in order to identify a subset of stimuli for screening individuals of unknown language during speech-in-noise tests. The intelligibility of VCV stimuli was estimated by combining the psychometric functions derived from the Short-Time Objective Intelligibility (STOI) measure with those derived from listening tests. To compensate for the potential increase in speech recognition effort in non-native listeners, stimuli were selected based on three criteria: (i) higher intelligibility; (ii) lower variability of intelligibility; and (iii) shallower psychometric function. The observed intelligibility estimates show that the three criteria for application in multilingual settings were fulfilled by the set of VCVs in English (average intelligibility from 1% to 8% higher; SRT from 4.01 to 2.04 dB SNR lower; average variability up to four times lower; slope from 0.35 to 0.68%/dB SNR lower). Further research is needed to characterize the intelligibility of these stimuli in a large sample of non-native listeners with varying degrees of hearing loss and to determine the possible effects of hearing loss and native language on VCV recognition.

Intelligent grandiose narcissists are less likely to exhibit narcissistic rivalry

Grandiose narcissism is considered a multidimensional construct that consists of admiration (self-promotion tendencies) and rivalry (self-defensive tendencies) subdimensions. It has been suggested that admiration is a default narcissistic mode, whereas rivalry is more reactive. Based on two samples, a previous moderation investigation found that at lower levels of objective (sample 1) and subjective (sample 2) intelligence, the association between narcissistic admiration and narcissistic rivalry was stronger, in comparison to at higher levels of intelligence. Given the positive correlation between objectively and subjectively measured intelligence, it remains to be determined if both effects are statistically significant moderators of the association between admiration and rivalry. Based on a mixed sample of undergraduates and community members (N = 422) who completed both the Narcissistic Admiration and Rivalry Questionnaire, as well as a battery of intelligence measures and subjective indicators of intelligence, we found that only objectively measured intelligence moderated negatively (semi-partial r = −0.23) the association between admiration and rivalry. We conclude that beyond an IQ of approximately 115 to 120, the association between narcissistic admiration and rivalry is greatly diminished, suggesting that higher levels of objective intelligence (through greater life achievements) may mitigate the development of narcissistic rivalry in grandiose narcissists.

On the deficiency of intelligibility metrics as proxies for subjective intelligibility

A recent trend in deep neural network (DNN)-based speech enhancement consists of using intelligibility and quality metrics as loss functions for model training with the aim of achieving high subjective speech intelligibility and perceptual quality in real-life conditions. In this study, we analyze a variety of loss functions, including some based on state-of-the-art intelligibility and quality metrics, to train an end-to-end speech enhancement system based on a fully convolutional neural network. The loss functions include perceptual metric for speech quality evaluation (PMSQE), scale-invariant signal-to-distortion ratio (SI-SDR), SI-SDR integrating speech pre-emphasis, short-time objective intelligibility (STOI), extended STOI (ESTOI), spectro-temporal glimpsing index (STGI), and a composite loss function combining STGI and SI-SDR. While DNNs trained with these loss functions produce notable speech intelligibility (and quality) gains according to pertinent objective metrics, we conduct a subjective intelligibility test that contradicts this result, showing no intelligibility improvement. From the results of this study, our conclusion is twofold: (1) subjective intelligibility evaluation is currently not replaceable by objective intelligibility evaluation, and (2) both the development of meaningful intelligibility metrics and DNN-based speech enhancement systems that can consistently improve the intelligibility of noisy speech for human listening remain open problems.

Internet of Things Energy Consumption Optimization in Buildings: A Step toward Sustainability

The internal components of a smart building interact through a compatible fabric and logic. A smart building integrates systems, structure, services, management, and their interrelationships to create a dynamic and cost-efficient environment. Smart buildings reduce the amount of cooling and heating load required to cool and heat spaces, thereby lowering operating costs and energy consumption without sacrificing occupant comfort. Smart structures are an Internet of Things (IoT) concern. The Internet of Things is a global network that virtualizes commonplace objects. The Internet of Things infuses non-technical objects with technology. IoT development has led to the creation of new protocols based on architectures for wireless sensor networks. Energy conservation extends the life and improves the performance of these networks, while overcoming the limitations of IoT node batteries. This research seeks to develop a data transmission model for routing IoT data in smart buildings. Utilization of intelligent object clustering and particle swarm optimization (PSO), chaotic particle swarm optimization (CPSO), and fractional chaotic order particle swarm optimization (FCPSO) optimization methods. Using the proposed algorithm to minimize energy consumption in the IoT is possible due to the algorithm’s ability to mitigate the problem by considering the number of parameters that can have a significant impact on performance, which is the goal of many optimization approaches.

Intelligent Mining Road Object Detection Based on Multiscale Feature Fusion in Multi-UAV Networks

In complex mining environments, driverless mining trucks are required to cooperate with multiple intelligent systems. They must perform obstacle avoidance based on factors such as the site road width, obstacle type, vehicle body movement state, and ground concavity-convexity. Targeting the open-pit mining area, this paper proposes an intelligent mining road object detection (IMOD) model developed using a 5G-multi-UAV and a deep learning approach. The IMOD model employs data sensors to monitor surface data in real time within a multisystem collaborative 5G network. The model transmits data to various intelligent systems and edge devices in real time, and the unmanned mining card constructs the driving area on the fly. The IMOD model utilizes a convolutional neural network to identify obstacles in front of driverless mining trucks in real time, optimizing multisystem collaborative control and driverless mining truck scheduling based on obstacle data. Multiple systems cooperate to maneuver around obstacles, including avoiding static obstacles, such as standing and lying dummies, empty oil drums, and vehicles; continuously avoiding multiple obstacles; and avoiding dynamic obstacles such as walking people and moving vehicles. For this study, we independently collected and constructed an obstacle image dataset specific to the mining area, and experimental tests and analyses reveal that the IMOD model maintains a smooth route and stable vehicle movement attitude, ensuring the safety of driverless mining trucks as well as of personnel and equipment in the mining area. The ablation and robustness experiments demonstrate that the IMOD model outperforms the unmodified YOLOv5 model, with an average improvement of approximately 9.4% across multiple performance measures. Additionally, compared with other algorithms, this model shows significant performance improvements.

Averroes on Intellect: from Aristotelian Origins to Aquinas’s Critique

<i>Averroes on Intellect: from Aristotelian Origins to Aquinas’s Critique</i>

Speaking in the presence of noise: Consistency of acoustic properties in clear-Lombard speech over time

Individual speakers are often able to modify their speech to facilitate communication in challenging conditions, such as speaking in a noisy environment. Such vocal "enrichments" might include reductions in speech rate or increases in acoustic contrasts. However, it is unclear how consistently speakers enrich their speech over time. This study examined inter-speaker variability in the speech enrichment modifications applied by speakers. The study compared a baseline habitual speaking style to a clear-Lombard style and measured changes in acoustic differences between the two styles over sentence trials. Seventy-eight young adult participants read out sentences in the habitual and clear-Lombard speaking styles. Acoustic differences between speaking styles generally increased nonlinearly over trials, suggesting that speakers require practice before realizing their full speech enrichment potential when speaking clearly in noise with reduced auditory feedback. Using a recent objective intelligibility metric based on glimpses, the study also found that predicted intelligibility increased over trials, highlighting that communicative benefits of the clear-Lombard style are not static. These findings underline the dynamic nature of speaking styles.