Sensor Inputs Research Articles

Automated Gesture Recognition Using African Vulture Optimization with Deep Learning for Visually Impaired People on Sensory Modality Data

Gesture recognition for visually impaired persons (VIPs) is a useful technology for enhancing their communications and increasing accessibility. It is vital to understand the specific needs and challenges faced by VIPs when planning a gesture recognition model. But, typical gesture recognition methods frequently depend on the visual input (for instance, cameras); it can be vital to discover other sensory modalities for input. The deep learning (DL)-based gesture recognition method is effective for the interaction of VIPs with their devices. It offers a further intuitive and natural way of relating with technology, creating it more available for everybody. Therefore, this study presents an African Vulture Optimization with Deep Learning-based Gesture Recognition for Visually Impaired People on Sensory Modality Data (AVODL-GRSMD) technique. The AVODL-GRSMD technique mainly focuses on the utilization of the DL model with hyperparameter tuning strategy for a productive and accurate gesture detection and classification process. The AVODL-GRSMD technique utilizes the primary data preprocessing stage to normalize the input sensor data. The AVODL-GRSMD technique uses a multi-head attention-based bidirectional gated recurrent unit (MHA-BGRU) method for accurate gesture recognition. Finally, the hyperparameter optimization of the MHA-BGRU method can be performed by the use of African Vulture Optimization with Deep Learning (AVO) approach. A series of simulation analyses were performed to demonstrate the superior performance of the AVODL-GRSMD technique. The experimental values demonstrate the better recognition rate of the AVODL-GRSMD technique compared to that of the state-of-the-art models.

A Duo Autoencoder-SVM based Approach for Secure Performance Monitoring of Industrial Conveyor Belt System

Process industries are fascinated by cyber-physical systems because of the potential to integrate physical systems and the cyber realm, resulting in efficient remote monitoring and control. The conveyor belt system has many critical parameters that require continuous attention, necessitating cyber-physical remote monitoring. Due to cloud-based monitoring of parameters, the system is vulnerable to cyber threats. The proposed technique combines a sparse autoencoder and support vector machine (SVM) to detect false data injection attacks (FDIAs) in the presence of sensor bias fault. The sparse autoencoder extracts sparse features and learns anomaly-free dynamics from the input sensor readings. Then, the trained SVM distinguishes attacks and fault by analysing reconstruction residuals of each measurement reading. The residuals also give an idea about the magnitude of abnormality. The proposed method's efficacy is evaluated in terms of accuracy, precision and false-alarm rate with the help of fault and FDIAs models.

What strategies do students use when they are programming a robot to follow a curved line?

During a relatively short period of time, programming has been implemented in the national curriculum of the compulsory school in Sweden. Since 2018, programming is a new content in the technology subject and the research field has discussed some of the challenges teachers and students, who generally have little experiences of programming, face when programming is introduced in teaching. In this study, we have explored what strategies lower secondary school students (ages 13–15) use when they are programming a robot to follow a curved line in technology education class. Data consists of screen recorded films when students are pair programming a robot. Student talks were transcribed verbatim and analysed using Practical Epistemological Analysis. The analysis revealed three different strategies that the students used when programming the robot: (1) sensor—follow the line, searching for a code that automatically would make the robot to follow the route, (2) sensor—wheels, using codes to create a feedback system between sensor and wheels, and (3) rotations—degrees–wheels, using the position of the robot to stepwise fine tune the movement of the wheels. In line with previous research, the students in our study spent much time discussing, testing, and debugging their code, and our findings contribute by showing how these discussions were aligned with the strategy used. Depending on the strategy, students actively looked for and tested codes affecting different aspects of the sensor-wheel system, such as for example sensor input, power, rotations or turning. Implications for teaching is discussed.

A Wheeled Mobile Robot Obstacles Avoidance for Navigation Control in a Static and Dynamic Environments

This research focuses on the performance of the obstacle avoidance feature implemented on a wheeled mobile robot by using Sugeno Fuzzy Inference System (FIS). The test was done using a simulation software Webots and the layout was first draft out using walls, floors, and objects in order to set a boundary and obstacles for the simulation. To test the effectiveness and efficiency in terms of time and distance, the simulation time and trajectory of the Khepera implementing the Sugeno FIS was recorded and compared with the Khepera without implementing the Sugeno FIS. The inputs of the ultrasonic sensors were also recorded in order to analyze whether if the Khepera detects incoming objects or if Khepera follows the rules set in the algorithm.

Navigating to objects in the real world.

Semantic navigation is necessary to deploy mobile robots in uncontrolled environments such as homes or hospitals. Many learning-based approaches have been proposed in response to the lack of semantic understanding of the classical pipeline for spatial navigation, which builds a geometric map using depth sensors and plans to reach point goals. Broadly, end-to-end learning approaches reactively map sensor inputs to actions with deep neural networks, whereas modular learning approaches enrich the classical pipeline with learning-based semantic sensing and exploration. However, learned visual navigation policies have predominantly been evaluated in sim, with little known about what works on a robot. We present a large-scale empirical study of semantic visual navigation methods comparing representative methods with classical, modular, and end-to-end learning approaches across six homes with no prior experience, maps, or instrumentation. We found that modular learning works well in the real world, attaining a 90% success rate. In contrast, end-to-end learning does not, dropping from 77% sim to a 23% real-world success rate because of a large image domain gap between sim and reality. For practitioners, we show that modular learning is a reliable approach to navigate to objects: Modularity and abstraction in policy design enable sim-to-real transfer. For researchers, we identify two key issues that prevent today's simulators from being reliable evaluation benchmarks-a large sim-to-real gap in images and a disconnect between sim and real-world error modes-and propose concrete steps forward.

Learning deep feature fusion for traffic light detection

Traffic light detection in real-world conditions is challenging because of the positioning of lights, variety in shapes and scales, and similarity with other objects. The paper presents a deep learning-based traffic light detection system by learning the fusion of handcrafted features. The handcrafted features for object detection focus on specific attributes such as shape, color, or texture. The objective of this work is to incorporate handcrafted features into the network learning process such that the resulting detector parameters are robust to input variations, sensor noise, and atmospheric noise. The proposed detection framework is based on the latest You only look once (YOLO) architecture, trained with the fusion of different information channels in the Integral Channel Features (ICF). The approach demonstrates a qualitative approach for identifying the optimal layer for additional feature injection in the network, and the selection of ICF channels to be applied for fusion. The validation of the proposed detector on the Bosch small traffic light dataset achieved the best mAP score of 55.7 % on the testing set. Further, a qualitative comparison of the proposed detector’s performance with that of other recent methods is presented, along with an analysis using auxiliary experiments.

Evaluating and Improving Interactions with Hazy Oracles

Many AI systems integrate sensor inputs, world knowledge, and human-provided information to perform inference. While such systems often treat the human input as flawless, humans are better thought of as hazy oracles whose input may be ambiguous or outside of the AI system's understanding. In such situations it makes sense for the AI system to defer its inference while it disambiguates the human-provided information by, for example, asking the human to rephrase the query. Though this approach has been considered in the past, current work is typically limited to application-specific methods and non-standardized human experiments. We instead introduce and formalize a general notion of deferred inference. Using this formulation, we then propose a novel evaluation centered around the Deferred Error Volume (DEV) metric, which explicitly considers the tradeoff between error reduction and the additional human effort required to achieve it. We demonstrate this new formalization and an innovative deferred inference method on the disparate tasks of Single-Target Video Object Tracking and Referring Expression Comprehension, ultimately reducing error by up to 48% without any change to the underlying model or its parameters.

Distributed adaptive cooperative control via command filters for multi-agent systems including input unmodeled dynamics and sensor faults

This study focuses on the topic of distributed adaptive cooperative tracking control (CTC) for non-strict feedback multi-agent systems (MASs) including input unmodeled dynamics, prescribed performance, sensor faults and unknown control directions. An adaptive neural CTC tactic is raised via command filtered backstepping technique. With the help of the property of Gaussian function, the barriers produced by the non-strict feedback terms and partial sensor faults are handled. Moreover, the prescribed performance on measured synchronization error is considered by designing a finite-time performance function. By introducing normalization signals and adjusting parameters, the problems caused by input unmodeled dynamics are resolved. The compensation signals and normalization signals are integrated into the whole Lyapunov function in the stability analysis. All the variables in the controlled system are turned out to be semi-globally uniformly ultimately bounded (SGUUB). Meanwhile, the synchronization errors never exceed to predefined boundary. A simulation example is employed to confirm the viability of the constructed control method.

Fault‐tolerant control of multi‐agent systems with input delay and sensor failure

AbstractThe problem of fault‐tolerant control (FTC) for a multi‐agent system (MAS) with input delay and sensor failures is addressed in this study. The topology of communication is an undirected subgraph having directed connections between the followers and leader. The Lyapunov approach is used to identify sufficient criteria for consensus control. We propose a fault‐tolerant controller based on observed descriptors. On the basis of proposed fault‐tolerant control, actuator problems, sensor faults, and state estimations can be solved. To minimize the size of the data, the Artstein–Kwon–Pearson reduction method is applied. Based on a Lyapunov functional predictive descriptor observer architecture, sufficient conditions are derived to guarantee the asymptotic stability. To demonstrate the theoretical results, numerical examples are provided.

ADAS USING TOUCH SENSOR

EPS systems integrate Advanced Driver Assistance Systems (ADAS) while the driver controls the steering wheel. Touch sensors, torque, and position sensors improve driver involvement, safety, and control in EPS. ADAS features like lane-keeping assistance and adaptive cruise control are activated by the driver’s steering wheel touch. EPS with driver-enabled ADAS integration, using touch sensors, empowers drivers while leveraging enhanced automation. The vehicle model design incorporates touch sensors, Arduino, and motor drivers to enable Advanced Driver Assistance Systems (ADAS) exclusively when the driver holds the steering wheel. The touch sensors detect the driver’s touch on the steering wheel, triggering the ADAS functionalities and allowing the vehicle to move. The Arduino microcontroller, equipped with embedded C code, processes the touch sensor inputs and communicates with the motor drivers to initiate vehicle propulsion. The embedded C code facilitates real-time monitoring and control of the touch sensor inputs, enabling a seamless integration between driver interaction and vehicle movement, thereby enhancing both safety and user experience

SBFEM and Bayesian inference for efficient multiple flaw detection in structures

Bayesian inference is a powerful technique for damage/flaw detection in critical structures. This paper explores the application of Bayesian inference to identify the flaws (voids/inclusions) and its parameters, assuming no information about the flaws is known a priori. Multiple flaws are represented by a parameter vector that contains the locations and the geometric information. In the inverse problem framework, the Scaled Boundary Finite Element Method (SBFEM) with quadtree decomposition is used to solve the forward problem. The flaw parameters are statistically quantified using the Bayesian inference. The likelihood function and prior information update the joint distribution of the number of flaws and their corresponding flaw parameters. The sampling to estimate the posterior distribution of the flaw parameters is based on the trans-dimensional Reversible Jump Markov Chain Monte Carlo (RJMCMC). Also, the impact of additive Gaussian noise on the observed data is investigated. Numerical examples include identifying multiple voids of different shapes such as circle and ellipse and identifying voids and inclusions, using the proposed approach with input sensor data at different noise levels.

Robust fixed-order [formula omitted] controller synthesis for multi-phase converters with input voltage feed-forward

Generated DC voltages of batteries, fuel cells, or supercapacitors as power sources connected in series with DC-DC converters change according to operating conditions. In such cases, the output voltage stability of the multi-phase DC-DC converters is an issue, particularly being subject to noises in the input voltage and load current disturbances. Input voltage feed-forward (IVFF) compensation approaches can improve the output voltage stability of the DC-DC converters in such scenarios. This paper proposes a robust fixed-order H∞ based IVFF control framework by considering sensor noise, input voltage, and load current disturbances to improve output voltage stability and reference tracking performance. The mismatched disturbance transfer functions depending on parasitic resistances are derived to include in the controller synthesis process. An iterative convex-concave optimization-based robust fixed-order controller design algorithm is proposed to optimize the feedback and feed-forward controllers under the stability and performance constraints. This algorithm allows the designing of the controllers simultaneously. The feed-forward controller, whose structure is independent of the system transfer functions, is optimized without any model inversion or extra design steps. The performance of the proposed controller is compared with an integral linear quadratic regulator controller, a sliding mode PID controller augmented with a nonlinear disturbance observer, and a fixed-order robust controller designed with non-smooth techniques. Real-time implementation of the fixed-order control systems is performed on a 2-leg 200 W interleaved boost converter. The performances are discussed under external disturbance effects to show the validity of the proposed control approach.

Greenhouse Farm Monitoring is Automated with Smart Controls

In the modern day, greenhouses have emerged as a well-liked option for sustainable agriculture due to the growing worry about climate change and the rising demand for food production. Because of the growing concern about climate change and the increased demand for food production, greenhouses are becoming a preferred approach for sustainable agriculture. To get around these problems, clever control systems using Arduino microcontrollers have been developed to automatically monitor and regulate the ambient conditions within the greenhouse. Before a problem arises, intelligent control systems can identify and mitigate possible hazards. A more ecologically friendly and productive approach to farming may be achieved via the use of sophisticated management systems in greenhouses. The major objective of the project is to build greenhouses that provide a suitable environment with a high production capacity, protect endangered plants, and conserve peoples time and energy. We ll use the Arduino to help us automate this process. The Arduino is a device that has outputs that are used in greenhouses and inputs (sensors) that can be programmed in C++ on a computer. The tools and materials we utilize for the project are an Arduino, a fan, a spray can, a humidity sensor, a lighting sensor, and a temperature sensor. The temperature sensor in our project is utilized to measure temperature. It will send a sensor to Arduino when the temperature rises or falls. To maintain a temperature that is comfortable for the plants, the fan or air conditioner is switched on. When there is insufficient light, the light sensor sends a signal to the Arduino to switch on the lights. It measures the moisture content of the soil. It will be transmitted to Arduino if the soil needs water. Through a DC motor, water flows. In order to provide an appropriate climate for plants without a human to take care of them, a smart control of greenhouse utilizing Arduino is used.

Virtual metrology in long batch processes using machine learning

ABSTRACT A long batch process typically runs for several hours to produce different process outcomes. During the entire duration of the process, several sensor data are recorded involving complicated non-linear dynamics among process constituents, which are difficult to model. The users are often interested in predicting the eventual process outcomes well before the completion of the process so that the process can be terminated in case the predicted outcome is not as desired. Virtual Metrology (VM), a virtual property estimation procedure, has gained importance over the years as a supporting tool to address this problem. In this paper, we have proposed a generalized VM pipeline including a deep-learning model that can be scaled to support high-dimensional input sensors and outputs. The developed model is able to predict the end-results for an industrial problem with less than 10% error after about one-fifth of the total process-time.

Observer-Based Adaptive Fuzzy Quantized Fault-Tolerant Control of Nonstrict-Feedback Nonlinear Systems With Sensor Fault

This paper focuses on the problem of adaptive quantized fault tolerant tracking control for a class of uncertain nonstrict-feedback nonlinear systems in the presence of input and output quantization and sensor fault. The main technical challenges come from how to deal with the input and output quantization errors and the partial loss of sensors' effectiveness. Firstly, a new observer including the quantized input and output signals and the estimation of fault parameter is designed to reconstruct the unavailable states, and some special techniques are developed to deal with the sector-bounded quantization errors. Furthermore, based on the cubic absolute-value Lyapunov function, the adaptive fault compensation strategy is presented to make up for the influence from sensor fault upon the control performance. Then, with the aid of fuzzy logic system (FLS) approximation method and backstepping technique, a novel output feedback adaptive fuzzy fault tolerant control (FTC) scheme is proposed for this class of systems, such that all signals in the closed-loop are semi-globally uniformly ultimately bounded (SGUUB) while the tracking error remains in a small vicinity of the origin. Finally, the effectiveness and applicability of the proposed control scheme are validated by conducting two simulation examples.

Bayesian Networks for the Driver Overtaking Assistance System on Two-lane Roads

Unsuccessful overtaking maneuvers on two-lane rural roads are one of the major causes of road accidents in the 21st century. The complexity of this maneuver merits the adoption of a thorough method for developing a proposed assistance system to prevent accidents and consequently reduce the high number of fatalities and the associated economic costs. This study aims to introduce an intelligent Driver Overtaking Assistance System (DOAS) to assist drivers in performing overtaking maneuvers safely. The study also will introduce a method to assess the impact of all the influential variables related to the driver, vehicle, traffic, road, and the surrounding environment. In momentary driving situations, the DOAS uses the communicated information via Hello beacon messages (HBM) and a set of input sensors to measure the possibility of overtaking the preceding vehicle(s) proactively by considering whether the distance gap to the oncoming vehicle is sufficient for overtaking. Besides, the proposed system is a vehicle-based safety system based on the collection of contextual information from the driving vicinity to acquire all relevant information regarding the ambient driving environment and the vehicles involved in the overtaking. To do this, DOAS uses a Bayesian Network (BN) to model overtaking maneuvers. The work presented shows high accuracy and promising results in aiding safe overtaking, with significant improvements to overtaking maneuvers on two-lane rural roads.

Calibration Measurements and Computational Models of Sensors Used in Autonomous Vehicles

Unsuccessful overtaking maneuvers on two-lane rural roads are one of the major causes of road accidents in the 21st century. The complexity of this maneuver merits the adoption of a thorough method for developing a proposed assistance system to prevent accidents and consequently reduce the high number of fatalities and the associated economic costs. This study aims to introduce an intelligent Driver Overtaking Assistance System (DOAS) to assist drivers in performing overtaking maneuvers safely. The study also will introduce a method to assess the impact of all the influential variables related to the driver, vehicle, traffic, road, and the surrounding environment. In momentary driving situations, the DOAS uses the communicated information via Hello beacon messages (HBM) and a set of input sensors to measure the possibility of overtaking the preceding vehicle(s) proactively by considering whether the distance gap to the oncoming vehicle is sufficient for overtaking. Besides, the proposed system is a vehicle-based safety system based on the collection of contextual information from the driving vicinity to acquire all relevant information regarding the ambient driving environment and the vehicles involved in the overtaking. To do this, DOAS uses a Bayesian Network (BN) to model overtaking maneuvers. The work presented shows high accuracy and promising results in aiding safe overtaking, with significant improvements to overtaking maneuvers on two-lane rural roads.

Prediction of oxygen uptake kinetics during heavy-intensity cycling exercise by machine-learning analysis.

Non-intrusive estimation of oxygen uptake (V̇O2) is possible with wearable sensor technology and artificial intelligence. V̇O2 kinetics have been accurately predicted during moderate exercise using easy-to-obtain sensor inputs. However, V̇O2 prediction algorithms for higher intensity exercise with inherent nonlinearities are still being refined. The purpose of this investigation was to test if a machine learning model can accurately predict dynamic V̇O2 across exercise intensities, including slower V̇O2 kinetics normally observed during heavy- compared to moderate-intensity exercise. Fifteen young healthy adults (7 females; peak V̇O2: 42±5 mL·min-1·kg-1) performed three different pseudorandom binary sequence (PRBS) exercise tests ranging in intensity from low-to-moderate, low-to-heavy, and ventilatory threshold-to-heavy work rates. A temporal convolutional network was trained to predict instantaneous V̇O2, with model inputs including heart rate, percent heart rate reserve, estimated minute ventilation, breathing frequency, and work rate. Frequency domain analyses between V̇O2 and work rate were used to evaluate measured and predicted V̇O2 kinetics. Predicted V̇O2 had low bias (-0.017 L·min-1, 95% limits of agreement: [-0.289, 0.254]), and was very strongly correlated (rrm=0.974, p<0.001) with the measured V̇O2. The extracted indicator of kinetics, mean normalized gain (MNG), was not different between predicted and measured V̇O2 responses (main effect: p=0.374, ηp2=0.01), and decreased with increasing exercise intensity (main effect: p<0.001, ηp2=0.64). Predicted and measured V̇O2 kinetics indicators were moderately correlated across repeated measurements (MNG: rrm=0.680, p<0.001). Therefore, the temporal convolutional network accurately predicted slower V̇O2 kinetics with increasing exercise intensity, enabling non-intrusive monitoring of cardiorespiratory dynamics across moderate- and heavy-exercise intensities.

Strain Virtual Sensing for Structural Health Monitoring under Variable Loads.

Virtual sensing is the process of using available data from real sensors in combination with a model of the system to obtain estimated data from unmeasured points. In this article, different strain virtual sensing algorithms are tested using real sensor data, under unmeasured different forces applied in different directions. Stochastic algorithms (Kalman filter and augmented Kalman filter) and deterministic algorithms (least-squares strain estimation) are tested with different input sensor configurations. A wind turbine prototype is used to apply the virtual sensing algorithms and evaluate the obtained estimations. An inertial shaker is installed on the top of the prototype, with a rotational base, to generate different external forces in different directions. The results obtained in the performed tests are analyzed to determine the most efficient sensor configurations capable of obtaining accurate estimates. Results show that it is possible to obtain accurate strain estimations at unmeasured points of a structure under an unknown loading condition, using measured strain data from a set of points and a sufficiently accurate FE model as input and applying the augmented Kalman filter or the least-squares strain estimation in combination with modal truncation and expansion techniques.

CLONeR: Camera-Lidar Fusion for Occupancy Grid-Aided Neural Representations

Recent advances in neural radiance fields (NeRFs) achieve state-of-the-art novel view synthesis and facilitate dense estimation of scene properties. However, NeRFs often fail for outdoor, unbounded scenes that are captured under very sparse views with the scene content concentrated far away from the camera, as is typical for field robotics applications. In particular, NeRF-style algorithms perform poorly: (1) when there are insufficient views with little pose diversity, (2) when scenes contain saturation and shadows, and (3) when finely sampling large unbounded scenes with fine structures becomes computationally intensive. This paper proposes <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CLONeR</i> , which significantly improves upon NeRF by allowing it to model large unbounded outdoor driving scenes that are observed from sparse input sensor views. This is achieved by decoupling occupancy and color learning within the NeRF framework into separate Multi-Layer Perceptrons (MLPs) trained using LiDAR and camera data, respectively. In addition, this paper proposes a novel method to build differentiable 3D Occupancy Grid Maps (OGM) alongside the NeRF model, and leverage this occupancy grid for improved sampling of points along a ray for volumetric rendering in metric space. Through extensive quantitative and qualitative experiments on scenes from the KITTI dataset, this paper demonstrates that the proposed method outperforms state-of-the-art NeRF models on both novel view synthesis and dense depth prediction tasks when trained on sparse input data.