Bangla Sign Language (BdSL) Alphabets and Numerals Classification Using a Deep Learning Model

A real-time Bangla Sign Language interpreter can enable more than 200 k hearing and speech-impaired people to the mainstream workforce in Bangladesh. Bangla Sign Language (BdSL) recognition and detection is a challenging topic in computer vision and deep learning research because sign language recognition accuracy may vary on the skin tone, hand orientation, and background. This research has used deep machine learning models for accurate and reliable BdSL Alphabets and Numerals using two well-suited and robust datasets. The dataset prepared in this study comprises of the largest image database for BdSL Alphabets and Numerals in order to reduce inter-class similarity while dealing with diverse image data, which comprises various backgrounds and skin tones. The papers compared classification with and without background images to determine the best working model for BdSL Alphabets and Numerals interpretation. The CNN model trained with the images that had a background was found to be more effective than without background. The hand detection portion in the segmentation approach must be more accurate in the hand detection process to boost the overall accuracy in the sign recognition. It was found that ResNet18 performed best with 99.99% accuracy, precision, F1 score, sensitivity, and 100% specificity, which outperforms the works in the literature for BdSL Alphabets and Numerals recognition. This dataset is made publicly available for researchers to support and encourage further research on Bangla Sign Language Interpretation so that the hearing and speech-impaired individuals can benefit from this research.

Compensating for Soft-Tissue Artifact Using the Orientation of Distal Limb Segments During Electromagnetic Motion Capture of the Upper Limb

Most motion capture measurements suffer from soft-tissue artifacts (STA). Especially affected are rotations about the long axis of a limb segment, such as humeral internal-external rotation (HIER) and forearm pronation-supination (FPS). Unfortunately, most existing methods to compensate for STA were designed for optoelectronic motion capture systems. We present and evaluate a STA compensation method that 1) compensates for STA in HIER and/or FPS, 2) is developed specifically for electromagnetic motion capture systems, and 3) does not require additional calibration or data. To compensate for STA, calculation of HIER angles rely on forearm orientation, and calculation of FPS angles rely on hand orientation. To test this approach, we recorded whole-arm movement data from eight subjects and compared their joint angle trajectories calculated according to progressive levels of STA compensation. Compensated HIER and FPS angles were significantly larger than uncompensated angles. Although the effect of STA compensation on other joint angles (besides HIER and FPS) was usually modest, significant effects were seen in certain DOF under some conditions. Overall, the method functioned as intended during most of the range of motion of the upper limb, but it becomes unstable in extreme elbow extension and extreme wrist flexion-extension. Specifically, this method is not recommended for movements within 20° of full elbow extension, full wrist flexion, or full wrist extension. Since this method does not require additional calibration of data, it can be applied retroactively to data collected without the intent to compensate for STA.

INTELLIGENT SYSTEM FOR CHOOSING A FUTURE PROFESSION

Finding a professional field in which a person is going to develop all his life is not easy, especially when a person does not have the tools to make accurate and informed choices. When we talk about professional orientation, we mean the psychological and pedagogical process, which aims to help choose a profession that corresponds to the skills and moods of man. On the other hand, orientation not only intends to look for a job, but also to know what motivates a person or who he would like to see himself in a few years. Professional discrimination is a process that creates controversy among young people, who often do not immediately get a higher education or decide to change careers due to lack of professional orientation. People are struck by the uncertainty about how to choose the right future profession: according to interests, according to employment opportunities, or according to the usefulness of this career. Another important factor is the future salary we will earn. Our vocation and our abilities are also factors to consider, as they will ultimately motivate us to continue our studies. To make the best decision about choosing a future career, a professional test will be the most useful tool with which a person can determine their capabilities. As modern technologies are increasingly used to analyze data around the world, it is an expected task to translate testing from a general cohort of psychological techniques into the digital world. For best results, it was decided to solve this problem using an artificial neural network. Scientists who have studied and continue to study neural networks believe that they are an almost indispensable tool in the work of analysts, because they allow you to work with both qualitative and quantitative characteristics. The main function of the developed system is to advise students and entrants on the choice of future profession, as well as to provide information in a form convenient for analyzing the results of career guidance work.

Neural Correlates of Hand–Object Congruency Effects during Action Planning

Selecting hand actions to manipulate an object is affected both by perceptual factors and by action goals. Affordances may contribute to “stimulus–response” congruency effects driven by habitual actions to an object. In previous studies, we have demonstrated an influence of the congruency between hand and object orientations on response times when reaching to turn an object, such as a cup. In this study, we investigated how the representation of hand postures triggered by planning to turn a cup was influenced by this congruency effect, in an fMRI scanning environment. Healthy participants were asked to reach and turn a real cup that was placed in front of them either in an upright orientation or upside–down. They were instructed to use a hand orientation that was either congruent or incongruent with the cup orientation. As expected, the motor responses were faster when the hand and cup orientations were congruent. There was increased activity in a network of brain regions involving object-directed actions during action planning, which included bilateral primary and extrastriate visual, medial, and superior temporal areas, as well as superior parietal, primary motor, and premotor areas in the left hemisphere. Specific activation of the dorsal premotor cortex was associated with hand–object orientation congruency during planning and prior to any action taking place. Activity in that area and its connectivity with the lateral occipito-temporal cortex increased when planning incongruent (goal-directed) actions. The increased activity in premotor areas in trials where the orientation of the hand was incongruent to that of the object suggests a role in eliciting competing representations specified by hand postures in lateral occipito-temporal cortex.

Development of arabic sign language dictionary using 3D avatar technologies

<span>The arabic sign language (ArSL) is the natural language of the deaf community in Arabic countries. ArSL suffers from a lack of resources such as unified dictionaries and corpora. In this work, a dictionary of Arabic language to ArSL has been constructed as a part of a translation system. The Arabic words are converted into hamburg notation system (HamNoSys) using eSign editor Software. HamNoSys was used to create manual parameters (handshape, hand orientation, hand location, and hand movement), while non-manual parameters (facial expressions, shoulder raising, mouthing gesture, head tilting, and body movement) added by using (mouth, face, and limbs) in the eSign editor software. The sign then converted to the sign gesture markup language (SiGML) file, and later 3D avatar interprets the SiGML file scripts to the animated sign. The constructed dictionary has three thousand signs; therefore, it can be adopted for the translation system in which written text can be transformed into sign language and can be utilized for the education of deaf people. The dictionary will be available as a free resource for researchers. It is hard and time-consuming work, but it is an essential step in machine translation of whole Arabic text to ArSL with 3D animations. </span>

Neural correlates of hand-object congruency effects during action planning

Selecting hand actions to manipulate an object is affected both by perceptual factors and by action goals. Affordances are associated with the automatic potentiation of motor representations to an object, independent of the goal of the actor. In previous studies, we have demonstrated an influence of the congruency between hand and object orientations on response times when reaching to turn an object, such as a cup. In this study, we investigated how the representation of hand postures triggered by planning to turn a cup were influenced by this congruency effect, in an fMRI scanning environment. Healthy participants were asked to reach and turn a real cup that was placed in front of them either in an upright orientation or upside down. They were instructed to use a hand orientation that was either congruent or incongruent with the cup orientation. As expected, the motor responses were faster when the hand and cup orientations were congruent. There was increased activity in a network of brain regions involving object-directed actions during action planning, which included bilateral primary and extrastriate visual, medial and superior temporal areas, as well as superior parietal, primary motor and premotor areas in the left hemisphere. Specific activation of the dorsal premotor cortex (PMd) was associated with hand-object orientation congruency during planning, and prior to any action taking place. Activity in that area and its connectivity with the lateral occipito-temporal cortex (LOTC) increased when planning incongruent actions. The increased activity in premotor areas in trials where the orientation of the hand was incongruent to that of the object suggests a role in eliciting competing representations specified by hand postures in LOTC.

Semantic field of falling in Russian sign language

This paper presents an analysis of the semantic fi eld of falling in Russian Sign Language (RSL). In this domain, RSL makes use of a particular group of signs usually referred to as ‘classifi er predicates’ [Zwitserlood 2012]. These signs are highly iconic and do not have correlates in spoken languages. Separate structural components of classifi er predicates, i.e. the handshape, the hand orientation, the trajectory and the direction of movement etc., describe diff erent aspects of falling. For example, the handshape determines the type of the trajector, and the direction of movement indicates the start versus end-point locations of the trajector. While some of these aspects are typically marked in both sign and spoken languages, others are unique for the languages of the visual modality. The paper gives a detailed description of the internal structure of the classifier predicates occurring in this semantic fi eld and discusses the implications these data provide for the theory of lexical typology. In particular, we explain the differences in lexicalization strategies between RSL and the spoken languages by two conceptualization modes RSL uses in this domain, i.e. the cognitive and the (purely) visual conceptualization. While the former is guided by cognitive processes and, therefore, is shared by sign and spoken languages, the latter is unique for the languages of the visual modality; it is responsible for the aspects of lexicalization based exclusively on the visual characteristics of the object/situation.

Hand Posture Recognition Using Skeletal Data and Distance Descriptor

In this paper, a method for the recognition of static hand postures based on skeletal data was presented. A novel descriptor was proposed. It encodes information about distances between particular hand points. Five different classifiers were tested, including four common methods and a proposed modification of nearest neighbor classifier, which can distinguish between posture classes differing mostly in hand orientation. The experiments were performed using three challenging datasets of gestures from Polish and American Sign Languages. The proposed method was compared with other approaches found in the literature. It outperforms every compared method, including our previous work, in terms of recognition rate.

How Organizational Training Affects Employee Performance: A Case on Bangladesh Private Banking Sector

Employees are one of the leading assets of any organization and the vigorous role they play towards an organisation’s success cannot be undervalued. Accordingly, equipping these unique assets through effective training becomes imperative in order to maximize the job performance. Also position them to take on the challenges of the today’s competitive business climate. In this regard, the purpose of this study is to determine the effect of organization’s training on employee performance. The nature of this study was quantitative and data for this study had been collected through structured questionnaire by conducting survey. A total 200 respondents were selected through convenience sampling technique from the different private banks, mainly from Chattogram. All the data of this study were processed and analyzed through SPSS software (version 24). The value of Cronbach Alpha was 0.796 which means that the data of this study is reliable according to Nunnaly, (1978). Hypotheses were tested by employing the multiple regression analysis. From the findings, it was found that organization’s training has significant effect on the performance of their employees. More precisely, out of four hypotheses, three hypotheses such as Foundation Training, On the Job Training, Career Development Training, have significant effect on Employee Performance, on the other hand, Orientation Training has no significant effect on Employee Performance. Eventually, this study was concluded by providing few recommendations for managerial implication.

Realization of Natural User Interface for Computer Control With KNN Classifier Enhanced Smart Glove

Gesture interaction is a commonly used solution when introducing Natural User Interface (NUI), a kind of user interface where the interaction is direct and consistent with natural heuristic behaviors. In this paper, a smart glove with efficient real-time hand orientation calculation and accurate static hand gesture prediction is proposed. This custom-built wireless glove consists of flex sensors, an Inertial Measurement Unit (IMU) sensor, a microcontroller with multi-channel ADC/AMP (analog to digital converter and amplifier), a Bluetooth module, and an Arduino Micro Pro. K-Nearest-Neighbor (KNN) classifier is implemented to assist static hand gesture prediction with the validated accuracy exceeding 97%. This supervised machine learning algorithm allows a highly customizable smart glove which the input gestures, input number of gestures, and the associated activating functions are all easily changeable by the users any time. To show the benefits of combining the NUI and supervised machine learning, a validation experiments, computer control, were conducted.