High-level Description Research Articles

REAL-TIME FOREGROUND SEGMENTATION FOR SURVEILLANCE APPLICATIONS IN NRCS LIDAR SEQUENCES

Abstract. In this paper, we propose a point-level foreground-background separation technique for the segmentation of measurement sequences of a Non-repetitive Circular Scanning (NRCS) Lidar sensor, which is used as a 3D surveillance camera mounted in a fixed position. We show that by applying the NRCS Lidar technology, we can overcome various limitations of rotating multi-beam Lidar sensors, such as low vertical measurement resolution, which is disadvantageous in surveillance applications. As the main challenge, we need to efficiently balance between the spatial and the temporal resolution of the recorded range data. For this reason, we automatically generate and maintain a very high-resolution background model of the sensor’s Field of View, while for enabling real-time analysis of dynamic objects we use low integration time to extract the consecutive time frames. As a result, the laser reflections from foreground objects reflect sparse, but geometrically accurate samples of the silhouettes providing valuable input for higher-level shape description or event analysis steps. We demonstrate the efficiency of the new approach in different realistic NRCS Lidar measurements sequences, obtaining a 0.76 overall F1-score on the measured dataset.

Impact analysis of keyword extraction using contextual word embedding.

A document’s keywords provide high-level descriptions of the content that summarize the document’s central themes, concepts, ideas, or arguments. These descriptive phrases make it easier for algorithms to find relevant information quickly and efficiently. It plays a vital role in document processing, such as indexing, classification, clustering, and summarization. Traditional keyword extraction approaches rely on statistical distributions of key terms in a document for the most part. According to contemporary technological breakthroughs, contextual information is critical in deciding the semantics of the work at hand. Similarly, context-based features may be beneficial in the job of keyword extraction. For example, simply indicating the previous or next word of the phrase of interest might be used to describe the context of a phrase. This research presents several experiments to validate that context-based key extraction is significant compared to traditional methods. Additionally, the KeyBERT proposed methodology also results in improved results. The proposed work relies on identifying a group of important words or phrases from the document’s content that can reflect the authors’ main ideas, concepts, or arguments. It also uses contextual word embedding to extract keywords. Finally, the findings are compared to those obtained using older approaches such as Text Rank, Rake, Gensim, Yake, and TF-IDF. The Journals of Universal Computer (JUCS) dataset was employed in our research. Only data from abstracts were used to produce keywords for the research article, and the KeyBERT model outperformed traditional approaches in producing similar keywords to the authors’ provided keywords. The average similarity of our approach with author-assigned keywords is 51%.

TagSeq: Malicious behavior discovery using dynamic analysis.

In recent years, studies on malware analysis have noticeably increased in the cybersecurity community. Most recent studies concentrate on malware classification and detection or malicious patterns identification, but as to malware activity, it still relies heavily on manual analysis for high-level semantic descriptions. We develop a sequence-to-sequence (seq2seq) neural network, called TagSeq, to investigate a sequence of Windows API calls recorded from malware execution, and produce tags to label their malicious behavior. We propose embedding modules to transform Windows API function parameters, registry, filenames, and URLs into low-dimension vectors, while still preserving the closeness property. Moreover, we utilize an attention mechanism to capture the relations between generated tags and certain API invocation calls. Results show that the most possible malicious actions are identified by TagSeq. Examples and a case study demonstrate that the proposed embedding modules preserve semantic-physical relations and that the predicted tags reflect malicious intentions. We believe this work is suitable as a tool to help security analysts recognize malicious behavior and intent with easy-to-understand tags.

Quantifying means-end reasoning skills in simulation-based training: a logic-based approach

We develop a logic-based approach for designing simulation-based training scenarios. Our methodology embodies a concise definition of the scenario concept and integrates the notions of training goals, acceptable versus unacceptable actions and performance scoring. The approach applies classical artificial intelligence (AI) planning to extract coherent plays from a causal description of the training domain. The domain- and task-specific parts are defined in a high-level action description language [Formula: see text]. Generic causal and temporal logic is added when the causal theory is compiled into the underlying Answer Set Programming (ASP) language. The ASP representation is used to derive a scoring function that reflects the quality of a play or training session, based on a distinction of states and actions into green (acceptable) and red (unacceptable) ones. To that end, we add to the casual theory a set of norms that specify an initial assignment of colors. The ASP engine uses these norms as axioms and propagates colors by consulting the causal theory. We prove that any set of such norms constitutes a conservative extension of the underlying causal theory. With this work, we hope to lay the foundation for the development of design and analysis tools for exercise managers. We envision a software system that lets an exercise manager view all plays of a tentative scenario design, with expediency information and scores for each possible play. Our approach is applicable to any domain in which means-ends reasoning is pertinent. We illustrate the approach in the domain of crisis response and management.

Mammogram Image Retrieval System Using Texture and Semantic Features

Image retrieval systems might help radiologists in aiding their diagnostic decision-making by giving a way to discover and identify similar images from databases. Keyword-based search became the dominant paradigm for searching multimedia datasets in the early years of image retrieval. However, using keywords alone has numerous drawbacks: human annotation is time-consuming and intrinsically incomplete, and the relationship between words and concepts is sometimes complicated. These significant challenges have motivated research in the field of Content-Based Image Retrieval (CBIR). However, using visual content has its own set of restrictions, owing to the Semantic Gap, which describes the disparity between low-level information that can be extracted quickly from images and high-level descriptions that are meaningful to users. As a result, a system with integrated approaches is important. In this paper a mammogram image retrieval system based on low level visual features and high-level semantic features has been proposed. Based upon the proposed framework, a prototype of mammogram image retrieval system has been developed. The proposed framework for retrieval of mammograms consists of two phases. The system first exploits the textual features and then further refines the search using visual features. Further, if the user is unsatisfied with the search results, he or she can send Relevance Feedback (RF) to the retrieval system, which has methods to learn about the user’s information needs. A system like this might be utilised for Computer Aided Diagnosis, medical education, and research. The framework established is generalizable and adaptable to a variety of anatomic and diagnostic circumstances. The proposed system’s performance is demonstrated by the experimental findings.

Schaeffer's Solfège, Percussion, Audio Descriptors: Towards an Interactive Musical System

Pierre Schaeffer's typomorphology (1966) proposes seven criteria of musical perception for the identification and qualification of sound objects, which form the basis of his musical theory. This Solfège fits well into contexts where pitch is not the dominant dimension. Relying on similarities between the practice of reduced listening and the utilization of low-level audio descriptors, we present the first version of a real-time setup in which these descriptors are applied to qualify percussive sounds. The paper describes the tools and strategies used for addressing different criteria: envelope followers with different window sizes and filtering; detection of transients and amplitude modulations; extraction and counting of spectral components; estimation of intrinsic dissonance and spectral distribution; among others. The extracted data is subjected to simple statistical analysis, producing scalar values associated with each segmented object. Finally, we present a variety of examples.

Efficient color image retrieval method using deep stacked sparse autoencoder

The recent advancement in deep learning-based approaches vastly outperforms the traditional image descriptors. Deep learning models, such as residual networks (ResNet), are well known for finding salient features. Although effective, high-level description often has a high dimensionality that increases computational overhead. The autoencoders find the useful approximation of the input data without losing critical information. Considering this, we propose a content-based image retrieval system for natural color images using a deep stacked sparse autoencoder (DSSA). The DSSA model learns latent features in an unsupervised way from the high-level description obtained using ResNet. The DSSA model achieves a nearly 50% reduction in size compared with the full-length features for the simple distance-based retrieval approach while increasing accuracy. The image retrieval efficacy of the learned latent features is also evaluated for two classifier-based methods using a Softmax classifier. Further, this study investigates the impact of unsupervised feature learning on retrieval using three benchmark natural color image databases of varying complexities, viz., Corel-1K, Corel-10K, and Canadian Institute for Advanced Research (CIFAR)-10. The latent features learned by the DSSA model with the fuzzy class membership-based retrieval method achieve promising improvements and yield a highly competitive retrieval performance with the large-size CIFAR-10 database.

Monocular Depth Perception on Microcontrollers for Edge Applications

Depth estimation is crucial in several computer vision applications, and a recent trend in this field aims at inferring such a cue from a single camera. Unfortunately, despite the compelling results achieved, state-of-the-art monocular depth estimation methods are computationally demanding, thus precluding their practical deployment in several application contexts characterized by low-power constraints. Therefore, in this paper, we propose a lightweight Convolutional Neural Network based on a shallow pyramidal architecture, referred to as <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mu $ </tex-math></inline-formula> PyD-Net, enabling monocular depth estimation on microcontrollers. The network is trained in a peculiar self-supervised manner leveraging proxy labels obtained through a traditional stereo algorithm. Moreover, we propose optimization strategies aimed at performing computations with quantized 8-bit data and map the high-level description of the network to low-level layers optimized for the target microcontroller architecture. Exhaustive experimental results on standard datasets and an in-depth evaluation with a device belonging to the popular Arm Cortex-M family confirm that obtaining sufficiently accurate monocular depth estimation on microcontrollers is feasible. To the best of our knowledge, our proposal is the first one enabling such remarkable achievement, paving the way for the deployment of monocular depth cues onto the tiny end-nodes of distributed sensor networks.

Genetic circuit design automation with Cello 2.0.

Cells interact with their environment, communicate among themselves, track time and make decisions through functions controlled by natural regulatory genetic circuits consisting of interacting biological components. Synthetic programmable circuits used in therapeutics and other applications can be automatically designed by computer-aided tools. The Cello software designs the DNA sequences for programmable circuits based on a high-level software description and a library of characterized DNA parts representing Boolean logic gates. This process allows for design specification reuse, modular DNA part library curation and formalized circuit transformations based on experimental data. This protocol describes Cello 2.0, a freely available cross-platform software written in Java. Cello 2.0 enables flexible descriptions of the logic gates' structure and their mathematical models representing dynamic behavior, new formal rules for describing the placement of gates in a genome, a new graphical user interface, support for Verilog 2005 syntax and a connection to the SynBioHub parts repository software environment. Collectively, these features expand Cello's capabilities beyond Escherichia coli plasmids to new organisms and broader genetic contexts, including the genome. Designing circuits with Cello 2.0 produces an abstract Boolean network from a Verilog file, assigns biological parts to each node in the Boolean network, constructs a DNA sequence and generates highly structured and annotated sequence representations suitable for downstream processing and fabrication, respectively. The result is a sequence implementing the specified Boolean function in the organism and predictions of circuit performance. Depending on the size of the design space and users' expertise, jobs may take minutes or hours to complete.

Hardware Acceleration of Video Edge Detection with Hight Level Synthesis on the Xilinx Zynq Platform

The study conducted in the current paper consists of validating an original design flow for the rapid prototyping of real-time image and video processing applications on FPGAs. A video application for edge detection with Simulink HDL coder and Vivado High-Level Synthesis (HLS) has been designed as if the code was going to be executed on a conventional processor. The developed tools will automatically translate the code into VHDL hardware language using an advanced compilation technique. This amounts to embedding processors on Xilinx Zynq-7000 System on-Chip (SoC) device in an optimal manner. This automated hardware design flow reduces the time to create a prototype since only the high-level description is required. The design of the video edge detection system is implemented on Xilinx Zynq-7000 platform. The result of the implementation gave effective resource utilization and a good frame rate (95 FPS) under 170MHz frequency.

Evaluating the Impact of Voice Activity Detection on Speech Emotion Recognition for Autistic Children

Individuals with autism are known to face challenges with emotion regulation, and express their affective states in a variety of ways. With this in mind, an increasing amount of research on automatic affect recognition from speech and other modalities has recently been presented to assist and provide support, as well as to improve understanding of autistic individuals' behaviours. As well as the emotion expressed from the voice, for autistic children the dynamics of verbal speech can be inconsistent and vary greatly amongst individuals. The current contribution outlines a voice activity detection (VAD) system specifically adapted to autistic children's vocalisations. The presented VAD system is a recurrent neural network (RNN) with long short-term memory (LSTM) cells. It is trained on 130 acoustic Low-Level Descriptors (LLDs) extracted from more than 17 h of audio recordings, which were richly annotated by experts in terms of perceived emotion as well as occurrence and type of vocalisations. The data consist of 25 English-speaking autistic children undertaking a structured, partly robot-assisted emotion-training activity and was collected as part of the DE-ENIGMA project. The VAD system is further utilised as a preprocessing step for a continuous speech emotion recognition (SER) task aiming to minimise the effects of potential confounding information, such as noise, silence, or non-child vocalisation. Its impact on the SER performance is compared to the impact of other VAD systems, including a general VAD system trained from the same data set, an out-of-the-box Web Real-Time Communication (WebRTC) VAD system, as well as the expert annotations. Our experiments show that the child VAD system achieves a lower performance than our general VAD system, trained under identical conditions, as we obtain receiver operating characteristic area under the curve (ROC-AUC) metrics of 0.662 and 0.850, respectively. The SER results show varying performances across valence and arousal depending on the utilised VAD system with a maximum concordance correlation coefficient (CCC) of 0.263 and a minimum root mean square error (RMSE) of 0.107. Although the performance of the SER models is generally low, the child VAD system can lead to slightly improved results compared to other VAD systems and in particular the VAD-less baseline, supporting the hypothesised importance of child VAD systems in the discussed context.

A correct-by-construction AADL runtime for the Ravenscar profile using SPARK2014

Middleware is an integral part of critical software, providing core services for data exchange and manipulation, job execution, and scheduling. Their correctness is central to the correct execution of the software. They must be carefully configured to meet all functional and non-functional requirements. From a set of valid configuration parameters, one then has to demonstrate the implementation is correct and can fulfill its mission. Model-based techniques provide the foundations for correct-by-construction engineering. Most notably, they can be used to model a system, assess its configuration is correct, and then generate the corresponding middleware instance. The SAE AADL language supports the modeling of safety-critical systems and covers its design, configuration, and analysis. In this paper, we present several contributions: the definition of a model of computation aligned with the Ada Ravenscar profile supported by an architectural model expressed using AADL; derivation rules from AADL constructs to middleware services using Ada 2012 and SPARK 2014, and the proof of correctness of the implementation. Our contribution illustrates how one can prove the absence of runtime errors in middleware configured from high-level descriptions. This effort illustrates the positive effect models, programming languages and associated toolsets have on developing high-assurance middleware.

Analyzing Security Vulnerabilities Induced by High-level Synthesis

High-level synthesis (HLS) is essential to map the high-level language (HLL) description (e.g., in C/C++) of hardware design to the corresponding Register Transfer Level (RTL) to produce hardware-independent design specifications with reduced design complexity for ASICs and FPGAs. Adopting HLS is crucial for industrial and government applications to lower development costs, verification efforts, and time-to-market. Current research practices focus on optimizing HLS for performance, power, and area constraints. However, the literature does not include an analysis of the security implications carried through HLS-generated RTL translations (e.g., from an untimed high-level sequential specification to a fully scheduled implementation). This article demonstrates the evidence of security vulnerabilities that emerge during the HLS translation of a high-level description of system-on-chip (SoC) intellectual properties to their corresponding RTL. The evidence provided in this manuscript highlights the need for (a) guidelines for high-level programmers to prevent these security issues at the design time and (b) automated HLS verification solutions that cover security in their optimization flow.

Xor-And-Inverter Graphs for Quantum Compilation

Quantum compilation is the task of translating a high-level description of a quantum algorithm into a sequence of low-level quantum operations. We propose and motivate the use of Xor-And-Inverter Graphs (XAG) to specify Boolean functions for quantum compilation. We present three different XAG-based compilation algorithms to synthesize quantum circuits in the Clifford + T library, hence targeting fault-tolerant quantum computing. The algorithms are designed to minimize relevant cost functions, such as the number of qubits, the T-count, and the T-depth, while allowing the flexibility of exploring different solutions. We present novel resource estimation results for relevant cryptographic and arithmetic benchmarks. The achieved results show a significant reduction in both T-count and T-depth when compared with the state-of-the-art.

Deep Learning-Assisted Repurposing of Plant Compounds for Treating Vascular Calcification: An In Silico Study with Experimental Validation.

Background Vascular calcification (VC) constitutes subclinical vascular burden and increases cardiovascular mortality. Effective therapeutics for VC remains to be procured. We aimed to use a deep learning-based strategy to screen and uncover plant compounds that potentially can be repurposed for managing VC. Methods We integrated drugome, interactome, and diseasome information from Comparative Toxicogenomic Database (CTD), DrugBank, PubChem, Gene Ontology (GO), and BioGrid to analyze drug-disease associations. A deep representation learning was done using a high-level description of the local network architecture and features of the entities, followed by learning the global embeddings of nodes derived from a heterogeneous network using the graph neural network architecture and a random forest classifier established for prediction. Predicted results were tested in an in vitro VC model for validity based on the probability scores. Results We collected 6,790 compounds with available Simplified Molecular-Input Line-Entry System (SMILES) data, 11,958 GO terms, 7,238 diseases, and 25,482 proteins, followed by local embedding vectors using an end-to-end transformer network and a node2vec algorithm and global embedding vectors learned from heterogeneous network via the graph neural network. Our algorithm conferred a good distinction between potential compounds, presenting as higher prediction scores for the compound categories with a higher potential but lower scores for other categories. Probability score-dependent selection revealed that antioxidants such as sulforaphane and daidzein were potentially effective compounds against VC, while catechin had low probability. All three compounds were validated in vitro. Conclusions Our findings exemplify the utility of deep learning in identifying promising VC-treating plant compounds. Our model can be a quick and comprehensive computational screening tool to assist in the early drug discovery process.

An OWL-Based Specification of Database Management Systems

In the context of a proliferation of Database Management Systems (DBMSs), we have envisioned and produced an OWL 2 ontology able to provide a high-level machine-processable description of the DBMSs domain. This conceptualization aims to facilitate a proper execution of various software engineering processes and database-focused administration tasks. Also, it can be used to improve the decision-making process for determining/selecting the appropriate DBMS, subject to specific requirements. The proposed model describes the most important features and aspects regarding the DBMS domain, including the support for various paradigms (relational, graph-based, key-value, tree-like, etc.), query languages, platforms (servers), plus running environments (desktop, Web, cloud), specific contexts—i.e., focusing on optimizing queries, redundancy, security, performance, schema vs. schema-less approaches, programming languages/paradigms, and others. The process of populating the ontology with significant individuals (actual DBMSs) benefits from the existing knowledge exposed by free and open machine-processable knowledge bases, by using structured data from Wikipedia and related sources. The pragmatic use of our ontology is demonstrated by two educational software solutions based on current practices in Web application development, proving support for learning and experimenting key features of the actual semantic Web technologies and tools. This approach is also an example of using multiple knowledge from database systems, semantic Web technologies, and software engineering areas.

Supporting Intelligence in Disaggregated Open Radio Access Networks: Architectural Principles, AI/ML Workflow, and Use Cases

Driven by the emerging trend for transparent, open and programmable communications, Open Radio Access Network (O-RAN) constitutes the dominant architectural approach for deploying the future wireless networks. Towards standardizing and specifying the building blocks and principles of O-RAN, a coordinated global effort has been observed, mainly comprised of the O-RAN Alliance, the operators and several research activities. This paper presents the architectural aspects and the current status of O-RAN deployments, integrating both existing and ongoing activities from the O-RAN enablers. Furthermore, since the Artificial Intelligence and Machine Learning (AI/ML) act as key pillars for realizing O-RANs, a comprehensive view on the AI/ML functionality is provided as well. Additionally, a Network Telemetry (NT) architecture is also proposed to ensure end-to-end data collection and real-time analytics. To concretely illustrate the O-RAN supporting mechanisms for hosting AI/ML, we implemented two realistic ML algorithms: (i) a Supervised Learning (SL) based algorithm for cell traffic prediction using the training data of an open dataset and (ii) a Deep Reinforcement Learning (DRL) based algorithm for energy-efficiency maximization using a 5G-compliant simulator to obtain RAN measurements. We schematically demonstrate the AI/ML workflow for both ML-assisted algorithms through the usage of xApps running on the Radio Intelligent Controller (RIC), as well as we outline the role of the O-RAN components involved in the AI/ML loop. Combining the high-level architectural descriptions with a detailed presentation of ML-empowered resource allocation schemes, the paper discusses and summarizes the O-RAN disaggregation principles and the role of AI/ML embedded in future O-RAN deployments.

A Formal Method for Description and Decision of Android Apps Behavior Based on Process Algebra

Android is the most popular mobile platform, and it has become a primary malware target. Existing behavior-based Android malware detection methods suffer from false positive and false negative problems, which lead to low detection accuracy. Formal theory is crucial in studying the behaviors of Android applications characterized by high concurrency, interaction, and mobility. However, existing formal methods mainly focus on specific issues and lack the essential abstraction and high-level description of application behavior. In this study, we propose a formal method for the description and decision of application behavior based on process algebra. First, we propose a formal method for describing application behavior at a component level using process algebra. By extending π-calculus theory, we establish the mapping relationship from the Android application to process algebra, and present the semantics and evolution rules of behavior based on process algebra. Second, we describe the behavior of four types of components in applications and characterize concurrent interactions of components using process algebra expressions. Third, we define the behavior equivalence and simulation mechanism for application behavior analysis and propose the decision rules based on weak simulation. Finally, we discuss a demonstration case, which includes malicious behavior, to demonstrate the feasibility and effectiveness of the proposed method. The results show that our method can accurately describe and analyze application behavior, which provides theoretical support for technologies and methods of behavior-based detection.

A Node Placement Algorithm Utilizing Mobile Nodes in WSN and IoT Networks

The operation of the Internet of Things (IoT) networks and Wireless Sensor Networks (WSN) is often disrupted by a number of problems, such as path disconnections, network segmentation, node faults, and security attacks. A method that gains momentum in resolving some of those issues is the use of mobile nodes or nodes deployed by mobile robots. The use of mobile elements essentially increases the resources and the capacity of the network. In this work, we present a Node Placement Algorithm with two variations, which utilizes mobile nodes for the creation of alternative paths from source to sink. The first variation employs mobile nodes that create locally-significant alternative paths leading to the sink. The second variation employs mobile nodes that create completely individual (disjoint) paths to the sink. We then extend the local variation of the algorithm by also accounting for the energy levels of the nodes as a contributing factor regarding the creation of alternative paths. We offer both a high-level description of the concept and also detailed algorithmic solutions. The evaluation of the solutions was performed in a case study of resolving congestion in the network. Results have shown that the proposed algorithms can significantly contribute to the alleviation of the problem of congestion in IoT and WSNs and can easily be used for other types of network problems.

AIgean : An Open Framework for Deploying Machine Learning on Heterogeneous Clusters

AIgean , pronounced like the sea, is an open framework to build and deploy machine learning (ML) algorithms on a heterogeneous cluster of devices (CPUs and FPGAs). We leverage two open source projects: Galapagos , for multi-FPGA deployment, and hls4ml , for generating ML kernels synthesizable using Vivado HLS. AIgean provides a full end-to-end multi-FPGA/CPU implementation of a neural network. The user supplies a high-level neural network description, and our tool flow is responsible for the synthesizing of the individual layers, partitioning layers across different nodes, as well as the bridging and routing required for these layers to communicate. If the user is an expert in a particular domain and would like to tinker with the implementation details of the neural network, we define a flexible implementation stack for ML that includes the layers of Algorithms, Cluster Deployment &amp; Communication, and Hardware. This allows the user to modify specific layers of abstraction without having to worry about components outside of their area of expertise, highlighting the modularity of AIgean . We demonstrate the effectiveness of AIgean with two use cases: an autoencoder, and ResNet-50 running across 10 and 12 FPGAs. AIgean leverages the FPGA’s strength in low-latency computing, as our implementations target batch-1 implementations.