Non-Verbal (Sign Language) To Verbal Language Translator Using Convolutional Neural Network

Communication is very imperative for daily life. Normal people use verbal language for communication while people with disabilities use sign language for communication. Sign language is a way of communicating by using the hand gestures and parts of the body instead of speaking and listening. As not all people are familiar with sign language, there lies a language barrier. There has been much research in this field to remove this barrier. There are mainly 2 ways in which we can convert the sign language into speech or text to close the gap, i.e. , Sensor based technique,and Image processing. In this paper we will have a look at the Image processing technique, for which we will be using the Convolutional Neural Network (CNN). So, we have built a sign detector, which will recognise the sign numbers from 1 to 10. It can be easily extended to recognise other hand gestures including alphabets (A- Z) and expressions. We are creating this model based on Indian Sign Language(ISL). Keywords: Multi Level Perceptron (MLP), Convolutional Neural Network (CNN), Indian Sign Language(ISL), Region of interest(ROI), Artificial Neural Network(ANN), VGG 16(CNN vision architecture model), SGD(Stochastic Gradient Descent).

Navigating a Diverse Paradigm: A Conceptual Framework for Experimental Framing Effects Research

This review introduces a conceptual framework with three elements to highlight the richness of the framing effects literature, while providing structure to address its fragmented nature. Our first element identifies and discusses the Enduring Issues that confront framing effects researchers. Second, we introduce the Semantic Architecture Model (SAM), which builds on the premise that meaning can be framed at different textual units within a text, which can form the basis of frame manipulations in framing effects experiments. Third, we provide an Inventory of Framing Effects Research Components used in framing effects research illustrated with salient examples from the framing effects literature. By offering this conceptual framework, we make the case for revitalizing framing effects research.

A analytics study Mapping Study of Collaborative business intelligence and self-service

Self-service Business Intelligence (SSBI) is an emerging topic for many companies. Casual users should be enabled to independently build their own analyses and reports. This accelerates and simplifies the decision-making processes. Although recent studies began to discuss parts of a self-service environment, none of these present a comprehensive architecture. Following a design science research approach, this study proposes a new self-service oriented BI architecture in order to address this gap. Starting from an in-depth literature review, an initial model was developed and improved by qualitative data analysis from interviews with 18 BI and IT specialists form companies across different industries. The proposed architecture model demonstrates the interaction between introduced self-service elements with each other and with traditional BI components. For example, we look at the integration of collaboration rooms and a self-learning knowledge database that aims to be a source for a report recommender. Keywords: Business Intelligence, Big Data, Architecture, Self-Service, Analytics

A Study of Analysis and Trends for Embedded Business Intelligence Market

Self-service Business Intelligence (SSBI) is an emerging topic for many companies. Casual users should be enabled to independently build their own analyses and reports. This accelerates and simplifies the decision-making processes. Although recent studies began to discuss parts of a self-service environment, none of these present a comprehensive architecture. Following a design science research approach, this study proposes a new self-service oriented BI architecture in order to address this gap. Starting from an in-depth literature review, an initial model was developed and improved by qualitative data analysis from interviews with 18 BI and IT specialists form companies across different industries. The proposed architecture model demonstrates the interaction between introduced self-service elements with each other and with traditional BI components. For example, we look at the integration of collaboration rooms and a self-learning knowledge database that aims to be a source for a report recommender. Keywords: Business Intelligence, Big Data, Architecture, Self-Service, Analytics

A Digital Twin Architecture Model Applied with MLOps Techniques to Improve Short-Term Energy Consumption Prediction

Using extensive databases and known algorithms to predict short-term energy consumption comprises most computational solutions based on artificial intelligence today. State-of-the-art approaches validate their prediction models in offline environments that disregard automation, quality monitoring, and retraining challenges present in online scenarios. The existing demand response initiatives lack personalization, thus not engaging consumers. Obtaining specific and valuable recommendations is difficult for most digital platforms due to their solution pattern: extensive database, specialized algorithms, and using profiles with similar aspects. The challenges and present personalization tactics have been researched by adopting a digital twin model. This study creates a different approach by adding structural topology to build a new category of recommendation platform using the digital twin model with real-time data collected by IoT sensors to improve machine learning methods. A residential study case with 31 IoT smart meter and smart plug devices with 19-month data (measurements performed each second) validated Digital Twin MLOps architecture for personalized demand response suggestions based on online short-term energy consumption prediction.

A Study on Fault Tolerance Technology of Flight Control Computer for Unmanned Aerial Vehicle

According to the reliability requirement of the Flight Control Computer for Unmanned Aerial Vehicle (UAV), a design scheme is proposed to ensure its reliability by using tri-redundancy technology. Further, by selecting appropriate redundant mode and the architecture model of the triple redundant flight control computer is established in this paper. The multi-channel security level method can give full play to the error tolerance ability of the system and improve the fault tolerance performance of the aircraft. After an extensive analysis and study of the structure of each module, the hardware circuit and software flow chart of the key technologies, such as redundancy strategy and synchronization method are suggested. A channel selection method based on channel security level is proposed. Combined with the comparison technology between channels, the selection of the optimal safe channel is realized.

Traffic Light and Back-light Recognition using Deep Learning and Image Processing with Raspberry Pi

Traffic light detection and back-light recognition are essential research topics in the area of intelligent vehicles because they avoid vehicle collision and provide driver safety. Improved detection and semantic clarity may aid in the prevention of traffic accidents by self-driving cars at crowded junctions, thus improving overall driving safety. Complex traffic situations, on the other hand, make it more difficult for algorithms to identify and recognize objects. The latest state-of-the-art algorithms based on Deep Learning and Computer Vision are successfully addressing the majority of real-time problems for autonomous driving, such as detecting traffic signals, traffic signs, and pedestrians. We propose a combination of deep learning and image processing methods while using the MobileNetSSD (deep neural network architecture) model with transfer learning for real-time detection and identification of traffic lights and back-light. This inference model is obtained from frameworks such as Tensor-Flow and Tensor-Flow Lite which is trained on the COCO data. This study investigates the feasibility of executing object detection on the Raspberry Pi 3B+, a widely used embedded computing board. The algorithm’s performance is measured in terms of frames per second (FPS), accuracy, and inference time.

Energy from the Waves: Integration of a HESS to a Wave Energy Converter in a DC Bus Electrical Architecture to Enhance Grid Power Quality

The need for environmental protection is pushing to a massive introduction of energy production from renewables. Although wind and solar energy present the most mature technologies for energy generation, wave energy has a huge annual energy potential not exploited yet. Indeed, no leading device for wave energy conversion has already been developed. Hence, the future exploitation of wave energy will be strictly related to a specific infrastructure for power distribution and transmission that has to satisfy high requirements to guarantee grid safety and stability, because of the stochastic nature of this source. To this end, an electrical architecture model, based on a common DC bus topology and including a Hybrid Energy Storage System (HESS) composed by Li-ion battery and flywheel coupled to a wave energy converter, is here presented. In detail, this research work wants to investigate the beneficial effects in terms of voltage and current waveforms frequency and transient behavior at the Point of Common Coupling (PCC) introduced by HESS under specific stressful production conditions. Specifically, in the defined simulation scenarios it is demonstrated that the peak value of the voltage wave frequency at the PCC is reduced by 64% to 80% with a faster stabilization in the case of HESS with respect to storage absence, reaching the set value (50 Hz) in a shorter time (by −10% to −42%). Therefore, HESS integration in wave energy converters can strongly reduce safety and stability issues of the main grid relating to intermittent and fluctuating wave production, significantly increasing the tolerance to the expected increasing share of electricity from renewable energy sources.

Reservoir Architecture Modeling at Sub-Seismic Scale for a Depleted Carbonate Reef Reservoir for CO2 Storage in Sarawak Basin, Offshore Malaysia

It is still a challenge to build a numerical static reservoir model, based on limited data, to characterize reservoir architecture that corresponds to the geological concept models. The numerical static reef reservoir model has been evolving from the oversimplified tank-like models, simple multi-layer models to the complex multi-layer models that are more realistic representations of complex reservoirs. A simple multi-layer model for the reef reservoir with proportional layering scheme was applied in the CO2 Storage Development Plan (SDP) study, as the most-likely scenario to match the geological complexity. Model refinement can be conducted during CO2 injection phase with Measurement, Monitoring and Verification (MMV) technologies for CO2 plume distribution tracking. The selected reservoir is a Middle to Late Miocene carbonate reef complex, with three phases of reef growth: 1) basal transgressive phase, 2) lower buildup phase, and 3) upper buildup phase. Three chronostratigraphic surfaces were identified on 3D seismic reflection data as the zone boundaries, which were then divided into sub-zones and layers. Four layering methods were compared, which are ‘proportional’, ’follow top’, ‘follow base’ and ‘follow top with reference surface’. The proportional layering method was selected for the base case of the 3D static reservoir model and the others were used in the uncertainty analysis. Based on the results of uncertainty and risk assessment, a risk mitigation for CO2 injection operation were modeled and three CO2 injection well locations were optimized. The reservoir architecture model would be updated and refined by the difference between the modeled CO2 plume patterns and The MMV results in the future.