Assistive Technology based Solution for Hearing Impairment using Smartphone

Developing a system for sign language recognition becomes essential for the deaf as well as a mute person. The recognition system acts as a translator between a disabled and an able person. This eliminates the hindrances in the exchange of ideas. Most of the existing systems are very poorly designed with limited support for the needs of their day to day facilities. The proposed system embedded with gesture recognition capability has been introduced here which extracts signs from a video sequence and displays them on screen. On the other hand, a speech to text as well as text to speech system is also introduced to further facilitate the grieved people. To get the best out of a human-computer relationship, the proposed solution consists of various cutting-edge technologies and Machine Learning based sign recognition models that have been trained by using TensorFlow and Keras library. The proposed architecture works better than several gesture recognition techniques like background elimination and conversion to HSV

A Graph Optimization-Based Acoustic SLAM Edge Computing System Offering Centimeter-Level Mapping Services with Reflector Recognition Capability

Robots can use echo signals for simultaneous localization and mapping (SLAM) services in unknown environments where its own camera is not available. In current acoustic SLAM solutions, the time of arrival (TOA) in the room impulse response (RIR) needs to be associated with the corresponding reflected wall, which leads to an echo labelling problem (ELP). The position of the wall can be derived from the TOA associated with the wall, but most of the current solutions ignore the effect of the cumulative error in the robot’s moving state measurement on the wall position estimation. In addition, the estimated room map contains only the shape information of the room and lacks position information such as the positions of doors and windows. To address the above problems, this paper proposes a graph optimization-based acoustic SLAM edge computing system offering centimeter-level mapping services with reflector recognition capability. In this paper, a robot equipped with a sound source and a four-channel microphone array travels around the room, and it can collect the room impulse response at different positions of the room and extract the RIR cepstrum feature from the room impulse response. The ELP is solved by using the RIR cepstrum to identify reflectors with different absorption coefficients. Then, the similarity of the RIR cepstrum vectors is used for closed-loop detection. Finally, this paper proposes a method to eliminate the cumulative error of robot movement by fusing IMU data and acoustic echo data using graph-optimized edge computation. The experiments show that the acoustic SLAM system in this paper can accurately estimate the trajectory of the robot and the position of doors, windows, and so on in the room map. The average self-localization error of the robot is 2.84 cm, and the mapping error is 4.86 cm, which meet the requirement of centimeter-level map service.

3D Recognition Based on Sensor Modalities for Robotic Systems: A Survey

3D visual recognition is a prerequisite for most autonomous robotic systems operating in the real world. It empowers robots to perform a variety of tasks, such as tracking, understanding the environment, and human–robot interaction. Autonomous robots equipped with 3D recognition capability can better perform their social roles through supportive task assistance in professional jobs and effective domestic services. For active assistance, social robots must recognize their surroundings, including objects and places to perform the task more efficiently. This article first highlights the value-centric role of social robots in society by presenting recently developed robots and describes their main features. Instigated by the recognition capability of social robots, we present the analysis of data representation methods based on sensor modalities for 3D object and place recognition using deep learning models. In this direction, we delineate the research gaps that need to be addressed, summarize 3D recognition datasets, and present performance comparisons. Finally, a discussion of future research directions concludes the article. This survey is intended to show how recent developments in 3D visual recognition based on sensor modalities using deep-learning-based approaches can lay the groundwork to inspire further research and serves as a guide to those who are interested in vision-based robotics applications.

Recognition capability of one’s own skilled movement is dissociated from acquisition of motor skill memory

When we have rehearsed a movement using an object, we can reproduce the movement without holding the object. However, the reproduced movement sometimes differs from the movement holding a real object, likely because movement recognition is inaccurate. In the present study, we tested whether the recognition capability was dissociated from the acquisition of motor skill memory. Twelve novices were asked to rotate two balls with their right hand as quickly as possible; they practiced the task for 29 days. To evaluate recognition capability, we calculated the difference in coordination pattern of all five digits between the ball-rotation movement and the reproduced movement without holding balls. The recognition capability did not change within the first day, but improved after one week of practice. On the other hand, performance of the ball rotation significantly improved within the first day. Since improvement of performance is likely associated with acquisition of motor skill memory, we suggest that recognition capability, which reflects the capability to cognitively access motor skill memory, was dissociated from the acquisition of motor skill memory. Therefore, recognition of one’s own skilled movement would rely on a hierarchical structure of acquisition of motor skill memory and cognitive access to that memory.

B.1.617.2 variant and increasing surge of COVID-19 in Nepal

As the coronavirus disease 2019 (COVID-19) pandemic goes on, there has been an evolution of severe acute respiratory syndrome corona virus 2 (SARS-CoV-2) leading to the mutations. As of May 2021, the B.1.617 variant has become the dominant strain across India and has spread to about 40 nations. Among different strains of B.1.617, the mutations of great concern are E484Q, L452R, P681R and T478K, because of the stronger affinity of the spike protein of these mutants for the Angiotensin Converting Enzyme (ACE) 2 receptor making it more transmissible and infectious, and causing decreased recognition capability of the immune system. Among the sub-variants of B.1.617, the B.1.617.3 shares the L452R and E484Q mutations found in B.1.617.1, whereas B.1.617.2 does not have the mutation E484Q, but it has the T478K mutation, not found in B.1.617.1 and B.1.617.3. With the increasing surge of COVID-19 in India with dominant B.1.617.2 variant, Nepal also witnessed the parallel increasing number of COVID-19 cases starting from the early weeks of April 2021, which could have been triggered by the influx of people due to the long open border of Nepal with neighboring India. Obviously, as of May 2021, the second wave of COVID-19 in Nepal has been linked with this new variant B.1.617.2 of SARS-CoV-2. Despite the challenges imposed by the new variant, the vaccines are likely to remain effective against different variants including B.1.617.2 and to limit severe disease. Moreover, there is an urgent need of an effective locally based system for the testing, contact tracing, and isolation. The risk reduction behavior, such as washing hands frequently, keeping at least 1m distance from others and wearing a mask, should be adapted to the daily habits during this COVID-19 pandemic era. There should be a long term planning for the control of COVID-19 with the effective vaccination and public health measures; otherwise, even after the control of the current surge, the next wave of COVID-19 might be knocking at door in the coming days.

Conceptualized Improvement on Transparent Glass Die for a Robust Manufacturing Process

Glass die are one of the materials used by semiconductor plants during production of specialized quad-flat no-leads (QFN) products. With its transparent appearance and fragile characteristics, several challenges are encountered and analyzed to resolve unwanted issues and to have a robust process manufacturing. This paper will discuss a potential concept of process improvement on the side of the device’s manufacturing with pattern recognition capability as detection and identification of the material to be processed. The paper will also discuss different options that can be selectively considered with respect to the manufacturer’s capability of their process flow.

The Nanopore-Tweezing-Based, Targeted Detection of Nucleobases on Short Functionalized Peptide Nucleic Acid Sequences

The implication of nanopores as versatile components in dedicated biosensors, nanoreactors, or miniaturized sequencers has considerably advanced single-molecule investigative science in a wide range of disciplines, ranging from molecular medicine and nanoscale chemistry to biophysics and ecology. Here, we employed the nanopore tweezing technique to capture amino acid-functionalized peptide nucleic acids (PNAs) with α-hemolysin-based nanopores and correlated the ensuing stochastic fluctuations of the ionic current through the nanopore with the composition and order of bases in the PNAs primary structure. We demonstrated that while the system enables the detection of distinct bases on homopolymeric PNA or triplet bases on heteropolymeric strands, it also reveals rich insights into the conformational dynamics of the entrapped PNA within the nanopore, relevant for perfecting the recognition capability of single-molecule sequencing.

The Nanopore-Tweezing-Based, Targeted Detection of Nucleobases on Short Functionalized Peptide-Nucleic Acid Sequences

Quantum leaps advances in the single-molecule investigative science have been made possible over the past decades through the implication of nanopores, as versatile components on dedicated biosensors. Here, we employed the nanopore-tweezing technique to capture amino acid-functionalized, peptide-nucleic acids (PNA) with -hemolysin-based nanopores, and correlate the ensuing stochastic fluctuations of the ionic current through the nanopore with the composition and order of bases in the PNAs primary structure. We demonstrate that while the system enables detection of distinct bases on homopolymeric PNA or triplet bases on heteropolymeric strands, it also reveals rich insights into the conformational dynamics of the entrapped PNA within the nanopore, relevant for perfecting the recognition capability single-molecule sequencing.

Retina-Inspired Organic Heterojunction-Based Optoelectronic Synapses for Artificial Visual Systems

For the realization of retina-inspired neuromorphic visual systems which simulate basic functions of human visual systems, optoelectronic synapses capable of combining perceiving, processing, and memorizing in a single device have attracted immense interests. Here, optoelectronic synaptic transistors based on tris(2-phenylpyridine) iridium (Ir(ppy)3) and poly(3,3-didodecylquarterthiophene) (PQT-12) heterojunction structure are presented. The organic heterojunction serves as a basis for distinctive synaptic characteristics under different wavelengths of light. Furthermore, synaptic transistor arrays are fabricated to demonstrate their optical perception efficiency and color recognition capability under multiple illuminating conditions. The wavelength-tunability of synaptic behaviors further enables the mimicry of mood-modulated visual learning and memorizing processes of humans. More significantly, the computational dynamics of neurons of synaptic outputs including associated learning and optical logic functions can be successfully demonstrated on the presented devices. This work may locate the stage for future studies on optoelectronic synaptic devices toward the implementation of artificial visual systems.