arXiv Computer Science @arxiv_cs@qoto.org

The article proposes a universal dual-axis intelligent systems assessment scale. The scale considers the properties of intelligent systems within the environmental context, which develops over time. In contrast to the frequent consideration of the 'mind' of artificial intelligent systems on a scale from 'weak' to 'strong', we highlight the modulating influences of anticipatory ability on their 'brute force'. In addition, the complexity, the 'weight' of the cognitive task and the ability to critically assess it beforehand determine the actual set of cognitive tools, the use of which provides the best result in these conditions. In fact, the presence of 'common sense' options is what connects the ability to solve a problem with the correct use of such an ability itself. The degree of 'correctness' and 'adequacy' is determined by the combination of a suitable solution with the temporal characteristics of the event, phenomenon, object or subject under study.

Existing work on fairness typically focuses on making known machine learning algorithms fairer. Fair variants of classification, clustering, outlier detection and other styles of algorithms exist. However, an understudied area is the topic of auditing an algorithm's output to determine fairness. Existing work has explored the two group classification problem for binary protected status variables using standard definitions of statistical parity. Here we build upon the area of auditing by exploring the multi-group setting under more complex definitions of fairness.

Usage-based insurance is becoming the new standard in vehicle insurance; it is therefore relevant to find efficient ways of using insureds' driving data. Applying anomaly detection to vehicles' trip summaries, we develop a method allowing to derive a "routine" and a "peculiarity" anomaly profile for each vehicle. To this end, anomaly detection algorithms are used to compute a routine and a peculiarity anomaly score for each trip a vehicle makes. The former measures the anomaly degree of the trip compared to the other trips made by the concerned vehicle, while the latter measures its anomaly degree compared to trips made by any vehicle. The resulting anomaly scores vectors are used as routine and peculiarity profiles. Features are then extracted from these profiles, for which we investigate the predictive power in the claim classification framework. Using real data, we find that features extracted from the vehicles' peculiarity profile improve classification.

Finding claims that researchers have made considerable progress in artificial intelligence over the last several decades is easy. However, our everyday interactions with cognitive systems quickly move from intriguing to frustrating. The root of those frustrations rests in a mismatch between the expectations we have due to our inherent, folk-psychological theories and the real limitations we see in existing computer programs. To address the discordance, we find ourselves building mental models of how each unique tool works: how we address Apple's Siri may differ from how we address Amazon's Alexa, the prompts that create striking images in Midjourney may produce unsatisfactory renderings in OpenAI's DALL-E. Emphasizing intentionality in research on cognitive systems provides a way to reduce these discrepancies, bringing system behavior closer to folk psychology. This paper scrutinizes the propositional attitude of intention to clarify this claim. That analysis is joined with broad methodological suggestions informed by recent practices within large-scale research programs. The overall goal is to identify a novel approach for measuring and making progress in artificial intelligence.

This paper is simply a collection of process diagrams for further use and reference. These are diagrams about different approaches to research.

Missing value is a very common and unavoidable problem in sensors, and researchers have made numerous attempts for missing value imputation, particularly in deep learning models. However, for real sensor data, the specific data distribution and data periods are rarely considered, making it difficult to choose the appropriate evaluation indexes and models for different sensors. To address this issue, this study proposes a multistage imputation framework based on deep learning with adaptability for missing value imputation. The model presents a mixture measurement index of low- and higher-order statistics for data distribution and a new perspective on data imputation performance metrics, which is more adaptive and effective than the traditional mean squared error. A multistage imputation strategy and dynamic data length are introduced into the imputation process for data periods. Experimental results on different types of sensor data show that the multistage imputation strategy and the mixture index are superior and that the effect of missing value imputation has been improved to some extent, particularly for the large segment imputation problem. The codes and experimental results have been uploaded to GitHub.

In recent years, neuroscientists have been interested to the development of brain-computer interface (BCI) devices. Patients with motor disorders may benefit from BCIs as a means of communication and for the restoration of motor functions. Electroencephalography (EEG) is one of most used for evaluating the neuronal activity. In many computer vision applications, deep neural networks (DNN) show significant advantages. Towards to ultimate usage of DNN, we present here a shallow neural network that uses mainly two convolutional neural network (CNN) layers, with relatively few parameters and fast to learn spectral-temporal features from EEG. We compared this models to three other neural network models with different depths applied to a mental arithmetic task using eye-closed state adapted for patients suffering from motor disorders and a decline in visual functions. Experimental results showed that the shallow CNN model outperformed all the other models and achieved the highest classification accuracy of 90.68%. It's also more robust to deal with cross-subject classification issues: only 3% standard deviation of accuracy instead of 15.6% from conventional method.

Conventional automatic doors cannot distinguish between people wishing to pass through the door and people passing by the door, so they often open unnecessarily. This leads to the need to adopt new systems in both commercial and non-commercial environments: smart doors. In particular, a smart door system predicts the intention of people near the door based on the social context of the surrounding environment and then makes rational decisions about whether or not to open the door. This work proposes the first position paper related to smart doors, without bells and whistles. We first point out that the problem not only concerns reliability, climate control, safety, and mode of operation. Indeed, a system to predict the intention of people near the door also involves a deeper understanding of the social context of the scene through a complex combined analysis of proxemics and scene reasoning. Furthermore, we conduct an exhaustive literature review about automatic doors, providing a novel system formulation. Also, we present an analysis of the possible future application of smart doors, a description of the ethical shortcomings, and legislative issues.

We present sMolBoxes, a dataflow representation for the exploration and analysis of long molecular dynamics (MD) simulations. When MD simulations reach millions of snapshots, a frame-by-frame observation is not feasible anymore. Thus, biochemists rely to a large extent only on quantitative analysis of geometric and physico-chemical properties. However, the usage of abstract methods to study inherently spatial data hinders the exploration and poses a considerable workload. sMolBoxes link quantitative analysis of a user-defined set of properties with interactive 3D visualizations. They enable visual explanations of molecular behaviors, which lead to an efficient discovery of biochemically significant parts of the MD simulation. sMolBoxes follow a node-based model for flexible definition, combination, and immediate evaluation of properties to be investigated. Progressive analytics enable fluid switching between multiple properties, which facilitates hypothesis generation. Each sMolBox provides quick insight to an observed property or function, available in more detail in the bigBox View. The case study illustrates that even with relatively few sMolBoxes, it is possible to express complex analyses tasks, and their use in exploratory analysis is perceived as more efficient than traditional scripting-based methods.

3D flash LIDAR is an alternative to the traditional scanning LIDAR systems, promising precise depth imaging in a compact form factor, and free of moving parts, for applications such as self-driving cars, robotics and augmented reality (AR). Typically implemented using single-photon, direct time-of-flight (dToF) receivers in image sensor format, the operation of the devices can be hindered by the large number of photon events needing to be processed and compressed in outdoor scenarios, limiting frame rates and scalability to larger arrays. We here present a 64x32 pixel (256x128 SPAD) dToF imager that overcomes these limitations by using pixels with embedded histogramming, which lock onto and track the return signal. This reduces the size of output data frames considerably, enabling maximum frame rates in the 10 kFPS range or 100 kFPS for direct depth readings. The sensor offers selective readout of pixels detecting surfaces, or those sensing motion, leading to reduced power consumption and off-chip processing requirements. We demonstrate the application of the sensor in mid-range LIDAR.

Let $\mathscr C$ be a hereditary class of graphs. Assume that for every $p$ there is a hereditary NIP class $\mathscr D_p$ with the property that the vertex set of every graph $G\in\mathscr C$ can be partitioned into $N_p=N_p(G)$ parts in such a way that the union of any $p$ parts induce a subgraph in $\mathscr D_p$ and $\log N_p(G)\in o(\log |G|)$. We prove that $\mathscr C$ is (monadically) NIP. Similarly, if every $\mathscr D_p$ is stable, then $\mathscr C$ is (monadically) stable. Results of this type lead to the definition of decomposition horizons as closure operators. We establish some of their basic properties and provide several further examples of decomposition horizons.

Inner Retinal neurons are a most essential part of the retina and they are supplied with blood via retinal vessels. This paper primarily focuses on the segmentation of retinal vessels using a triple preprocessing approach. DRIVE database was taken into consideration and preprocessed by Gabor Filtering, Gaussian Blur, and Edge Detection by Sobel and Pruning. Segmentation was driven out by 2 proposed U-Net architectures. Both the architectures were compared in terms of all the standard performance metrics. Preprocessing generated varied interesting results which impacted the results shown by the UNet architectures for segmentation. This real-time deployment can help in the efficient pre-processing of images with better segmentation and detection.

Functional connectivity network (FCN) data from functional magnetic resonance imaging (fMRI) is increasingly used for the diagnoses of brain disorders. However, state-of-the-art studies used to build the FCN using a single brain parcellation atlas at a certain spatial scale, which largely neglected functional interactions across different spatial scales in hierarchical manners. In this study, we propose a novel framework to perform multiscale FCN analysis for brain disorder diagnosis. We first use a set of well-defined multiscale atlases to compute multiscale FCNs. Then, we utilize biologically meaningful brain hierarchical relationships among the regions in multiscale atlases to perform nodal pooling across multiple spatial scales, namely "Atlas-guided Pooling". Accordingly, we propose a Multiscale-Atlases-based Hierarchical Graph Convolutional Network (MAHGCN), built on the stacked layers of graph convolution and the atlas-guided pooling, for a comprehensive extraction of diagnostic information from multiscale FCNs. Experiments on neuroimaging data from 1792 subjects demonstrate the effectiveness of our proposed method in the diagnoses of Alzheimer's disease (AD), the prodromal stage of AD (i.e., mild cognitive impairment [MCI]), as well as autism spectrum disorder (ASD), with accuracy of 88.9%, 78.6%, and 72.7% respectively. All results show significant advantages of our proposed method over other competing methods. This study not only demonstrates the feasibility of brain disorder diagnosis using resting-state fMRI empowered by deep learning, but also highlights that the functional interactions in the multiscale brain hierarchy are worth being explored and integrated into deep learning network architectures for better understanding the neuropathology of brain disorders.

The recent availability of large datasets in bio-medicine has inspired the development of representation learning methods for multiple healthcare applications. Despite advances in predictive performance, the clinical utility of such methods is limited when exposed to real-world data. Here we develop model diagnostic measures to detect potential pitfalls during deployment without assuming access to external data. Specifically, we focus on modeling realistic data shifts in electrophysiological signals (EEGs) via data transforms, and extend the conventional task-based evaluations with analyses of a) model's latent space and b) predictive uncertainty, under these transforms. We conduct experiments on multiple EEG feature encoders and two clinically relevant downstream tasks using publicly available large-scale clinical EEGs. Within this experimental setting, our results suggest that measures of latent space integrity and model uncertainty under the proposed data shifts may help anticipate performance degradation during deployment.

Recently, there has been extensive use of artificial Intelligence (AI) in the field of material engineering. This can be attributed to the development of high performance computing and thereby feasibility to test deep learning models with large parameters. In this article we tried to review some of the latest developments in the applications of AI in material engineering.

Multiple business scenarios require an automated generation of descriptive human-readable text from structured input data. Hence, fact-to-text generation systems have been developed for various downstream tasks like generating soccer reports, weather and financial reports, medical reports, person biographies, etc. Unfortunately, previous work on fact-to-text (F2T) generation has focused primarily on English mainly due to the high availability of relevant datasets. Only recently, the problem of cross-lingual fact-to-text (XF2T) was proposed for generation across multiple languages alongwith a dataset, XALIGN for eight languages. However, there has been no rigorous work on the actual XF2T generation problem. We extend XALIGN dataset with annotated data for four more languages: Punjabi, Malayalam, Assamese and Oriya. We conduct an extensive study using popular Transformer-based text generation models on our extended multi-lingual dataset, which we call XALIGNV2. Further, we investigate the performance of different text generation strategies: multiple variations of pretraining, fact-aware embeddings and structure-aware input encoding. Our extensive experiments show that a multi-lingual mT5 model which uses fact-aware embeddings with structure-aware input encoding leads to best results on average across the twelve languages. We make our code, dataset and model publicly available, and hope that this will help advance further research in this critical area.

Transformers have resulted in remarkable achievements in the field of image processing. Inspired by this great success, the application of Transformers to 3D point cloud processing has drawn more and more attention. This paper presents a novel point cloud representational learning network, 3D Point Cloud Transformer with Dual Self-attention (3DPCT) and an encoder-decoder structure. Specifically, 3DPCT has a hierarchical encoder, which contains two local-global dual-attention modules for the classification task (three modules for the segmentation task), with each module consisting of a Local Feature Aggregation (LFA) block and a Global Feature Learning (GFL) block. The GFL block is dual self-attention, with both point-wise and channel-wise self-attention to improve feature extraction. Moreover, in LFA, to better leverage the local information extracted, a novel point-wise self-attention model, named as Point-Patch Self-Attention (PPSA), is designed. The performance is evaluated on both classification and segmentation datasets, containing both synthetic and real-world data. Extensive experiments demonstrate that the proposed method achieved state-of-the-art results on both classification and segmentation tasks.

Deep Reinforcement Learning (DRL) is employed to develop autonomously optimized and custom-designed heat-treatment processes that are both, microstructure-sensitive and energy efficient. Different from conventional supervised machine learning, DRL does not rely on static neural network training from data alone, but a learning agent autonomously develops optimal solutions, based on reward and penalty elements, with reduced or no supervision. In our approach, a temperature-dependent Allen-Cahn model for phase transformation is used as the environment for the DRL agent, serving as the model world in which it gains experience and takes autonomous decisions. The agent of the DRL algorithm is controlling the temperature of the system, as a model furnace for heat-treatment of alloys. Microstructure goals are defined for the agent based on the desired microstructure of the phases. After training, the agent can generate temperature-time profiles for a variety of initial microstructure states to reach the final desired microstructure state. The agent's performance and the physical meaning of the heat-treatment profiles generated are investigated in detail. In particular, the agent is capable of controlling the temperature to reach the desired microstructure starting from a variety of initial conditions. This capability of the agent in handling a variety of conditions paves the way for using such an approach also for recycling-oriented heat treatment process design where the initial composition can vary from batch to batch, due to impurity intrusion, and also for the design of energy-efficient heat treatments. For testing this hypothesis, an agent without penalty on the total consumed energy is compared with one that considers energy costs. The energy cost penalty is imposed as an additional criterion on the agent for finding the optimal temperature-time profile.

Let $P$ be a set of points in the plane and let $T$ be a maximum-weight spanning tree of $P$. For an edge $(p,q)$, let $D_{pq}$ be the diametral disk induced by $(p,q)$, i.e., the disk having the segment $\overline{pq}$ as its diameter. Let $\cal{D_T}$ be the set of the diametral disks induced by the edges of $T$. In this paper, we show that one point is sufficient to pierce all the disks in $\cal{D_T}$, thus, the set $\cal{D_T}$ is Helly. Actually, we show that the center of the smallest enclosing circle of $P$ is contained in all the disks of $\cal{D_T}$, and thus the piercing point can be computed in linear time.

In this report, we describe our submitted system for track 2 of the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22). We fuse a variety of good-performing models ranging from supervised models to self-supervised learning(SSL) pre-trained models. The supervised models, trained using VoxCeleb-2 dev data, consist of ECAPA-TDNN and Res2Net in a very deep structure. The SSL pre-trained models, wav2vec and wavLM, are trained using large scale unlabeled speech data up to million hours. These models are cascaded with ECAPA-TDNN and further fine-tuned in a supervised fashion to extract the speaker representations. All 13 models are applied with score normalization and calibration and then fused into the the submitted system. We also explore the audio quality measures in the calibration stage such as duration, SNR, T60, and MOS. The best submitted system achieves 0.073 in minDCF and 1.436% in EER on the VoxSRC-22 evaluation set.