Transfer Learning for Human & AI

Current RF sensors lack the computational resources to support practical, in-situtraining for intelligent signal classification . Deepdelay Loop Reservoir Computing (DLR) delivers reductions in form factor, hardware complexity and latency compared to the State-ofthe- Art (SoA) neural nets . DLR enables mobile edge platforms to authenticate andthen track emitters with fast SEI retraining .…

This paper proposes a mechanism to assess the safety of autonomous cars . It assesses the car’s safety in scenarios where the car must avoid collision with an adversary . Core to this mechanism is a safety measure, called Safe-KamikazeDistance (SKD), which computes the average similarity between sets of safeadversary’s trajectories and kamikazes close to the safetrajectories .…

Understanding students’ programming misconceptions is critical . We propose catalogs ofantipatterns for two programming languages: C and Python . We analyzed the codes of 166 CS1 engineering students when they were codingsolutions to programming exercises . We catalog 41 CS1antipAtterns from 95 cataloged misconceptions in C and .…

A Convolutional Neural Network (CNN) model is able to accuratelydiscriminate between 4 different phases of neurological status in a non-Electroencephalogram(EEG) dataset recorded in an experiment in which subjects are exposed to physical, cognitive and emotional stress . We show that CNN models outperformstradic classification methods such as SVM, and RF, in comparison to other methods, in robustnessto noise by 97.46% accuracy on a noisy dataset .…

In nominal mission scenarios, geostationary satellites perform end-of-lifeorbit maneuvers to reach suitable disposal orbits . This research investigates the long-term orbitevolution of decommissioned geostations . The model accounts for all the relevant harmonics of the gravity field and solar radiation pressure and third-body perturbations caused by the Moon and the Sun .…

Social networks seeded, crystallized and structured by large-scale social platforms exhibit complicated epistemic structures and dynamics that arise from the nature of interactive knowledge that users/participants possess, share and shape . We use a novel approach to characterize knowledge statesand flows in social networks, based on epistemic networks, or epinets, to study the relationship between the structure of platforms and the structures of socialnetworks that form on them .…

Research evaluations and comparison of the assessments of academic institutions are among themajor issues in recent years in higher education systems . In this paper we introduce a natural geometric way to compare these assessments by introducing an ad hoc distance from the performance of an institution to the best possible achievable assessment .…

Conventional works that learn grasping affordance from demonstrations need to explicitly predict grasping configurations . We propose a contrastive learning framework that consists of a Siameseencoder and a trajectory decoder . We further introduce a coupled triplet lossto encourage the discovered affordance cues to be more affordance-relevant .…

Formal Methods for the Informal Engineer (FMIE) was a workshop held at the Broad Institute of MIT and Harvard in 2021 to explore the potential role of verified software in the biomedical software ecosystem . The motivation for FMIE was the recognition that the life sciences and medicine areundergoing a transition from being passive consumers of software and AI/ML technologies to fundamental drivers of new platforms, including those which will need to be mission and safety-critical .…

Software has always been considered as malleable. Changes to softwarerequirements are inevitable during the development process. Despite manysoftware engineering advances over several decades, requirements changes are asource of project risk . In theory, change control policies and formal processes are consideredas a natural strategy to deal with requirements changes.…

We present a new approach to proving non-termination of non-deterministic integer programs . Our technique is rather simple but efficient . It relies on apurely syntactic reversal of the program’s transition system followed by aconstraint-based invariant synthesis with constraints coming from both the original and reversed transition system .…

We present a novel reformulation of balanced truncation, a classical model reduction method . The principal innovation comes through theuse of system response data that has been either measured or computed, withoutreference to any prescribed realization of the original model .…

The difficulty of optimal control problems has classically been characterized in terms of system properties such as minimum eigenvalues ofcontrollability/observability gramians . We revisit these characterizations in the context of the increasing popularity of data-driven techniques likereinforcement learning (RL) and in control settings where input observationsare high-dimensional images and transition dynamics are unknown .…

This paper proposes a deep learning framework for classification of BBC television programmes using audio . The audio is firstly transformed intospectrograms, which are fed into a pre-trained convolutional Neural Network . We achieve an average classification accuracy of 93.7% over 14-fold cross validation .…

Energy modeling can enable energy-aware software development and assist thedeveloper in meeting an application’s energy budget . The model accounts for the Frequency, PreFetch, andWaitState processor configurations which all have a significant impact on the execution time and energy consumption of edge computing applications .…

In this paper, we pose the current state-of-the-art voice conversion (VC)systems as two-encoder-one-decoder models . After comparing these models, we combine the best features and propose Assem-VC . This paper also introduces the GTAfinetuning in VC, which significantly improves the quality and the speakersimilarity of the outputs .…

Generative Rerank Network (GRN) has outperformed state-of-the-art point-wise and list-wise methods . GRN has achieved a performanceimprovement of 5.2% on PV and 6.1% on IPV metric after the successfuldeployment in one popular recommendation scenario of Taobao application . Empirical resultsshow that GRN consistently and significantly outperforms state- of theartpoint-wise .…

The codebook design for code-domain non-orthogonal multiple access (CD-NOMA) can be considered as a constellation design for multi-user multi-dimensionalmodulation (MU-MDM) This paper proposes an autoencoder (AE)-basedconstellation design for MU-MDm with the objective of achieving a comparablebit error rate (BER) performance to single-user multidimensional modulation (SU-M) It has been demonstrated that the proposed designachieves a single-users BER bound with only 0.2dB loss, equivalently outperforming the existing CD-NomA designs, while maintaining their overloadingfactor .…

A physical protection system (PPS) integrates people, procedures, and equipment to protect assets or facilities . PPSs have targeted various systems, including airports, rail transport, highways, hospitals, bridges, the electricity grid, dams, power plants, seaports, oil refineries, and water systems .…

The Fisher information matrix plays the role of aRiemannian metric in this framework . This tool helps us obtain Cram\'{e}r-Raolower bound (CRLB) This chapter summarizes the recent results which extend the framework to more general Cram\{e}.r-Rao inequalities . We apply Eguchi’s theory to a generalized form of Czsisz\’ar $f$-divergence to obtain a .general…

The soft error rate (SER) of integrated circuits (ICs) operating in space may vary by several orders of magnitude due to the variable intensity of radiation exposure . To ensure the radiation hardness withoutcompromising the system performance, it is necessary to implement the dynamichardening mechanisms which can be activated under the critical radiation exposure.…

1.3 million household fires, 3,400 civilian deaths, and 23 billion dollars indamage, a fire department is called to respond every 24 seconds . Many firefighters are injured during search and rescue operations due to hiddendangers . Fire-retardant water runoff pollution can threaten human health .…

The DevOps phenomenon is gaining popularity through its ability to supportcontinuous value delivery and ready accommodation of change . However, given therelative immaturity and general confusion about DevOps, a common view of expectations is lacking . Through investigation of online job advertisements, combined with interviews, we identified key Knowledge Areas,Skills and Capabilities for a DevOps role and their relative importance in New Zealand’s job market .…

Study tested feasibility of using ‘off the shelf’ information extraction algorithms to identify medical concepts from Italian clinical notes . We used MetaMap to map medical concepts to the Unified Medical Language System (UMLS) Results in EXP1 showed that theItalian UMLS Metathesaurus sources covered 91% of the medical terms of the’Disorders’ semantic group, as found in the studied dataset .…

There is growing interest in ASR systems that can recognize phones in alanguage-independent fashion . However, there is a paucity of realistic data that can be used to test such systems andtechnologies . This paper presents a publicly available, phoneticallytranscribed corpus of 2255 utterances (words and short phrases) in the endangered Tangkhulic language East Tusom (no ISO 639-3 code), a Tibeto-Burman variety spoken mostly in India .…

This work investigates the use of pulse stretching inverters for monitoring the variation of flux and Linear Energy Transfer (LET) of energetic particles . The basic particle detector consists of two cascaded pulse stretching(skew-sized) inverters designed in CMOS technology . The proposed solution is intended to operate as an on-chip particledetector within the self-adaptive multiprocessing systems .…

Self-supervised learning of speech representations has been a very active research area . Most work is focused on a single domain such as read audiobooks for which there exist large quantities of labeled and unlabeled data . Ourexperiments show that using target domain data during pre-training leads to large performance improvements across a variety of setups .…

Mobile traffic is dominated by content services (e.g., video), which typically use recommendation systems . NFR increase the network performance at the cost of being unfair towards certain contents when compared to the standard recommendations . Fair-NFR can achieve high network gains (similar to non-fair) with little unfairness, authors say .…

We give the first observed communication semantics for a session-typed programming language with general recursion . Polarized SILL is defined using a multiset-rewriting-style substructuraloperational semantics . We show that the “external” simulations coincide with barbedprecongruence . To ensure that our observed communication .…

Social media platforms generate alot of real-time text information regarding public events with differenttopics . Mining social events is challenging because events typically exhibit heterogeneous texture and metadata are often ambiguous . We propose a novel Pairwise Popularity Graph Convolutional Network,named as PP-GCN, based on weighted meta-path instance similarity and textualsemantic representation as inputs .…

We study the problem of aligning the object and environment with a tactile-based feedback insertion policy . The insertion process is modeled as an episodic policy that iterates between insertion attempts followed by pose corrections . We show that the optimalconfiguration of the learning agent (RL + curriculum + tactile flow) exposed to4 training objects yields an insertion policy that inserts 4 novel objects with over 85.0% success rate and within 3~4 attempts .…

The objective speech quality assessment is usually conducted by comparingreceived speech signal with its clean reference . Human beings are capable of evaluating the speech quality without any reference, such as in the meanopinion score (MOS) tests . We propose a novel non-intrusive speech quality measurement model, MetricNet, which combines label distribution learning and joint speech reconstruction learning .…

Virtual reality (VR) promising to fundamentally transform a broad spectrum of industry sectors and the way humans interact with virtual content . Despite unprecedented progress, current networking and computing infrastructures are incompetent to unlock VR’s full potential . In this paper, we consider delivering the wireless multi-tile VR video service over a mobileedge computing (MEC) network .…

The Council of Europe’s Committee of Ministers adopted the terms of reference for the Ad Hoc Committee on Artificial Intelligence (CAHAI) The CAHAI is charged with examining the feasibility and potential elements of a legal framework for the design, development, and deployment of AI systems .…

This paper presents aframework for SMORES types of modular robots to efficiently self-assemble intotree topologies . These modular robots form kinematic chains that have been shown to be capable of a large variety of manipulation and locomotion tasks . A desired kinematictopology can be mapped onto a planar pattern with optimal module assignment .…

Traffic monitoring cameras are powerful tools for traffic management and essential components of intelligent road infrastructure systems . CAROM processestraffic monitoring videos and converts them to anonymous data structures of vehicle type, 3D shape, position, and velocity for traffic scene reconstructionand replay .…

Event sourced systems are increasing in popularity because they are reliable,flexible, and scalable . In this article, we point a microscope at a softwarearchitecture pattern that is rapidly gaining popularity in industry, but has not received as much attention from the scientific community .…

Most of the existing deep learning based end-to-end video coding (DLEC)architectures are designed specifically for RGB color format . Yet the videocoding standards, including H.264/AVC, H.265/HEVC and H.266/VVC developed over the past few decades, have been designed primarily for YUV 4:2:0 format .…

We address the problem of maximizing user engagement with content with content (in theform of like, reply, retweet, and retweet with comments) We formulate the engagement forecasting task as a multi-label classification problem that captures choice behavior on an unsupervisedclustering of tweet-topics .…

This paper presents an efficient and compact MATLAB code forthree-dimensional stress-based sensitivity analysis . The 146 lines code includes the finite element analysis and p-norm stress sensitivity analysis based on the adjoint method . The complete program for sensitivity analysis is given in the Appendix and is intended for educational purposes only .…

The power-law behavior is ubiquitous in a majority of real-world networks . It has been shown to have a strong effect on various combinatorial, structural,and dynamical properties of graphs . In this paper, we study analytically several combinatorials problems for two power law graphs .…

The Internet of Value (IOV) with its distributed ledger technology (DLT)underpinning has created new forms of lending markets . Lending protocols are gaining traction, holding an aggregate liquidity supply of over $40 billion . We discuss the persisting reliance of DeFi lending on the traditional financial system, and conclude with the outlook of the lending market in the IOV era .…

DataPrep.EDA is a novel task-centric EDA system in Python . It allows data scientists to declaratively specify a widerange of EDA tasks in different granularity with a single function call . It is open-sourced as an EDA component of DataPrep:https://://://www.sfu-db/dataprep.com/svsvsv/dataPrep/dataaprep .…

Archive of Formal Proofs (AFP) is an online repository of formal proofs . It serves as a central location for publishing, discovering, and viewing libraries of proofs . Long-term users of the website are generally satisfied with the AFP but that there are anumber of areas, such as navigation, search and script browsing, that need improvement .…

MimbleWimble (MW) is a privacy-oriented cryptocurrency technology which provides security and scalability properties that distinguish it from other protocols of its kind . We present and discuss those properties and outline thebasis of a model-driven verification approach to address the certification of the correctness of the protocol implementations .…

To reliably model real robot characteristics, interval linear systems ofequations allow to describe families of problems that consider sets of values . This allows to easily account for typical complexities such as sets of jointstates and design parameters uncertainties . For eachclass, reliable and efficient polytope, n-cube, and n-ball inner approximations are presented .…

The key challenge is estimating the segment boundaries of (partially) occluded objects, which areinherently ambiguous when considering only a single frame . We propose Multihypothesis Segmentation Tracking (MST), a novel method forvolumetric segmentation in changing scenes . MST outperforms baselines in all tested scenes, showing it outperforms baselines in all tests .…

The Bayes error-rate is upper bounded bymin(EER,P,1-P), where EER is equal-error-rate and P, 1-P are the priorprobabilities of the competing hypotheses . The EER represents the accuracy of the verifier, while min(P) represents the hardness of the classification problem . We offer some criticism of decisions made by direct score thresholding .…

The visual frontend is a major performance and energy consumption bottleneck in autonomous machine applications . Compared to Nvidia TX1 and Intel i7, ourFPGA-based implementation achieves 5.6x and 3.4x speedup, as well as 3.0x and 34.6X power reduction, respectively. Compared to the Nvidia TX-1, Intel i.7, the implementation achieves 3.5x power reduction .…

Underactuated systems like sea vessels have degrees of motion that are insufficiently matched by a set of independent actuation forces . An online machine learning mechanism based on integral reinforcement learning is proposed to find a solution for a class of nonlinear tracking problems with partial prior knowledge of the system dynamics .…