The symbolism, connectionism and behaviorism approaches of artificial intelligence have achieved a lot of successes in various tasks, while we still do not have a clear definition of "intelligence" ...with enough consensus in the community (although there are over 70 different "versions" of definitions). The nature of intelligence is still in darkness. In this work we do not take any of these three traditional approaches, instead we try to identify certain fundamental aspects of the nature of intelligence, and construct a mathematical model to represent and potentially reproduce these fundamental aspects. We first stress the importance of defining the scope of discussion and granularity of investigation. We carefully compare human and artificial intelligence, and qualitatively demonstrate an information abstraction process, which we propose to be the key to connect perception and cognition. We then present the broader idea of "concept", separate the idea of self model out of the world model, and construct a new model called world-self model (WSM). We show the mechanisms of creating and connecting concepts, and the flow of how the WSM receives, processes and outputs information with respect to an arbitrary type of problem to solve. We also consider and discuss the potential computer implementation issues of the proposed theoretical framework, and finally we propose a unified general framework of intelligence based on WSM.
With recent developments, the performance of automotive radar has improved significantly. The next generation of 4D radar can achieve imaging capability in the form of high-resolution point clouds. ...In this context, we believe that the era of deep learning for radar perception has arrived. However, studies on radar deep learning are spread across different tasks, and a holistic overview is lacking. This review paper attempts to provide a big picture of the deep radar perception stack, including signal processing, datasets, labelling, data augmentation, and downstream tasks such as depth and velocity estimation, object detection, and sensor fusion. For these tasks, we focus on explaining how the network structure is adapted to radar domain knowledge. In particular, we summarise three overlooked challenges in deep radar perception, including multi-path effects, uncertainty problems, and adverse weather effects, and present some attempts to solve them.
In this work, we proposed a method of extracting feature parameters for deep neural network prediction based on the vectorgraph storage format, which can be applied to the design of electromagnetic ...metamaterials with sandwich structures. Compared to current methods of manually extracting feature parameters, this method can automatically and precisely extract the feature parameters of arbitrary two-dimensional surface patterns of the sandwich structure. The position and size of surface patterns can be freely defined, and the surface patterns can be easily scaled, rotated, translated, or transformed in other ways. Compared to the pixel graph feature extraction method, this method can adapt to very complex surface pattern design in a more efficient way. And the response band can be easily shifted by scaling the designed surface pattern. To illustrate and verify the method, a 7-layer deep neural network was built to design a metamaterial broadband polarization converter. Prototype samples were fabricated and tested to verify the accuracy of the prediction results. In general, the method is potentially applicable to the design of different kinds of sandwich-structure metamaterials, with different functions and in different frequency bands.
CNNs have achieved remarkable image classification and object detection results over the past few years. Due to the locality of the convolution operation, although CNNs can extract rich features of ...the object itself, they can hardly obtain global context in images. It means the CNN-based network is not a good candidate for detecting objects by utilizing the information of the nearby objects, especially when the partially obscured object is hard to detect. ViTs can get a rich context and dramatically improve the prediction in complex scenes with multi-head self-attention. However, it suffers from long inference time and huge parameters, which leads ViT-based detection network that is hardly be deployed in the real-time detection system. In this paper, firstly, we design a novel plug-and-play attention module called mix attention (MA). MA combines channel, spatial and global contextual attention together. It enhances the feature representation of individuals and the correlation between multiple individuals. Secondly, we propose a backbone network based on mix attention called MANet. MANet-Base achieves the state-of-the-art performances on
ImageNet
and
CIFAR
. Last but not least, we propose a lightweight object detection network called
CAT-YOLO
, where we make a trade-off between precision and speed. It achieves the
AP
of 25.7% on
COCO 2017 test-dev
with only 9.17 million parameters, making it possible to deploy models containing ViT on hardware and ensure real-time detection. CAT-YOLO could better detect obscured objects than other state-of-the-art lightweight models.
Despite significant progress in vision-based detection methods, the task of detecting traffic objects at night remains challenging. Visual information of medium and small stationary objects is ...deteriorated due to poor lighting conditions. And the visual information is important for traffic investigations. For meeting the needs of night traffic investigations, this study focuses on presenting a nighttime multi-object detection framework based on Single Shot MultiBox Detector (SSD). Considering the need of traffic investigations, the applicable detection framework is presented for detecting traffic objects, especially medium and small stationary objects. In the framework, the Dense Convolutional Network (DenseNet) and deconvolutional layers are introduced to enhance the feature reuse, and the effectiveness of the optimization is finally verified. In this paper, qualitative and quantitative experiments are presented. The results show that our presented framework has better detection performance for medium and small stationary objects. Moreover, the results show that presented framework has better performance for nighttime traffic investigations at intersections.
Object detection; Night condition; SSD; Medium object; Small object.
Wearable sound detectors require strain sensors that are stretchable, sensitive, and capable of adhering conformably to the skin, and toward this end, 2D materials hold great promise. However, the ...vibration of vocal cords and muscle contraction are complex and changeable, which can compromise the sensing performance of devices. By combining deep learning and 2D MXenes, an MXene‐based sound detector is prepared successfully with improved recognition and sensitive response to pressure and vibration, which facilitate the production of a high‐recognition and resolution sound detector. By training and testing the deep learning network model with large amounts of data obtained by the MXene‐based sound detector, the long vowels and short vowels of human pronunciation are successfully recognized. The proposed scheme accelerates the application of artificial throat devices in biomedical fields and opens up practical applications in voice control, motion monitoring, and many other fields.
The flexible sensor based on MXene can detect the movement signal of neck muscles caused by human pronunciation. Combining a large number of detected signals with convolutional neural networks can classify and recognize different pronunciation contents, which is conducive to the development of advanced wearable artificial larynx.
We demonstrate the construction of the optical system in the atomic clock-beyond atomic fountain based on
87
Rb atom. The optical system includes a high-stability laser system and an optical lattice. ...The high-stability laser system with the new scheme of frequency locking and shift is introduced in detail, which is an important laser source for laser cooling. The optimized frequency and intensity stability are achieved to 4 × 10
–14
τ
−
1
/
2
(
τ
is the averaging time) and 4 × 10
–5
τ
−
1
/
2
, respectively, which are highly stable. On the basis of the conventional atomic fountain clock, the optical lattice is specially investigated along the direction of gravity and its characteristics are studied systematically. For the optimized and novel exploration, we predict the achievable stability of
3.6
×
10
−
14
τ
−
1
/
2
and it has the potential to be improved to
3.6
×
10
−
15
τ
−
1
/
2
. The realizability of the construction due to the stabilized laser and optical lattice makes the beyond fountain promising candidate for the next-generation high performance microwave atomic clock.
3D point clouds are a crucial type of data collected by LiDAR sensors and widely used in transportation applications due to its concise descriptions and accurate localization. Deep neural networks ...(DNNs) have achieved remarkable success in processing large amount of disordered and sparse 3D point clouds, especially in various computer vision tasks, such as pedestrian detection and vehicle recognition. Among all the learning paradigms, Self-Supervised Learning (SSL), an unsupervised training paradigm that mines effective information from the data itself, is considered as an essential solution to solve the time-consuming and labor-intensive data labeling problems via smart pre-training task design. This paper provides a comprehensive survey of recent advances on SSL for point clouds. We first present an innovative taxonomy, categorizing the existing SSL methods into four broad categories based on the pretexts’ characteristics. Under each category, we then further categorize the methods into more fine-grained groups and summarize the strength and limitations of the representative methods. We also compare the performance of the notable SSL methods in literature on multiple downstream tasks on benchmark datasets both quantitatively and qualitatively. Finally, we propose a number of future research directions based on the identified limitations of existing SSL research on point clouds.
This paper considers (in general form) the problem of recovering information (size and material parameters) about the scattering object from far-field measurements. The order of solution and ...functions of each equation for the fields inside and outside the scattering object are discussed. Using well-known mathematical theorems, a simple equation has been derived that connects the far-field data on one side to the near-field data on the other side. Consequently, this equation has been used in an optimization procedure to find the parameters of the dielectric cylinder.
A low-profile, high-gain, and low cross-polarization omnidirectional antenna is proposed. The antenna structure is pretty concise with convenient probe feeding and sandwich-structure design. The ...characteristic mode analysis shows that the antenna can excite quasi-TM01 and quasi-TM02 modes in a broadband and, thus, results in monopole radiation mode and low cross polarization in a broad operating band. The full-wave simulation and experiments were performed to verify the antenna design. The fabricated prototype antenna showed <2 dB unroundness and <−25 dB cross polarization in (4.8-11.1) GHz, with a relative bandwidth of 79.2% and a peak gain of 8.4 dBi at 9 GHz.