How AI chatbots have reshaped the frontline interface in China: examining the role of sales–service ambidexterity and the personalization–privacy paradox

PurposeThis study serves two purposes: (1) to evaluate the effects of organizational ambidexterity by examining how the balanced and the combined sales–service configurations of chatbots differ in their abilities to enhance customer experience and patronage and (2) to apply information boundary theory to assess the contingent role that chatbot sales–service ambidexterity can play in adapting to customers' personalization–privacy paradox.Design/methodology/approachAn online survey of artificial intelligence chatbots users was conducted, and a mixed-methods research design involving response surface analysis and polynomial regression was adopted to address the research aim.FindingsThe results of polynomial regressions on survey data from 507 online customers indicated that as the benefits of personalization decreased and the risk to privacy increased, the inherently negative (positive) effects of imbalanced (combined) chatbots' sales–service ambidexterity had an increasing (decreasing) influence on customer experience. Furthermore, customer experience fully mediated the association of chatbots' sales–service ambidexterity with customer patronage.Originality/valueFirst, this study enriches the literature on frontline ambidexterity and extends it to the setting of human–machine interaction. Second, the study contributes to the literature on the personalization–privacy paradox by demonstrating the importance of frontline ambidexterity for adapting to customer concerns. Third, the study examines the conduit between artificial intelligence (AI) chatbots' ambidexterity and sales performance, thereby helping to reconcile the previously inconsistent evidence regarding this relationship.

Highly Sensitive Flexible Modulus Sensor for Softness Perception and Clinical Application

The wearable sensors for softness measuring are emerging as a solution of softness perception, which is an intrinsic function of human skin, for electronic skin and human-machine interaction. However, these wearable sensors suffer from a key challenge: the modulus of an object can not be characterized directly, which originates from the complicated transduction mechanism. To address this key challenge, we developed a flexible and wearable modulus sensor that can simultaneously measure the pressure and modulus without mutual interference. The modulus sensing was realized by merging the electrostatic capacitance response from the pressure sensor and the ionic capacitance response from the indentation sensor. Via the optimized structure, our sensor exhibits high modulus sensitivity of 1.9 × 102 in 0.06 MPa, a fast dynamic response time of 100 ms, and high mechanical robustness for over 2500 cycles. We also integrated the sensor onto a prosthetic hand and surgical probe to demonstrate its capability for pressure and modulus sensing. This work provides a new strategy for modulus measurement, which has great potential in softness sensing and medical application.

Integrated Temperature and Position Sensors in a Shape-Memory Driven Soft Actuator for Closed-Loop Control

Soft actuators are a promising option for the advancing fields of human-machine interaction and dexterous robots in complex environments. Shape memory alloy wire actuators can be integrated into fiber rubber composites for highly deformable structures. For autonomous, closed-loop control of such systems, additional integrated sensors are necessary. In this work, a soft actuator is presented that incorporates fiber-based actuators and sensors to monitor both deformation and temperature. The soft actuator showed considerable deformation around two solid body joints, which was then compared to the sensor signals, and their correlation was analyzed. Both, the actuator as well as the sensor materials were processed by braiding and tailored fiber placement before molding with silicone rubber. Finally, the novel fiber-rubber composite material was used to implement closed-loop control of the actuator with a maximum error of 0.5°.

Taxonomy of Object Detection methods: A Survey

Object detection (OD) within a video is one of the relevant and critical research areas in the computer vision field. Due to the widespread of Artificial Intelligence, the basic principle in real life nowadays and its exponential growth predicted in the epochs to come, it will transmute the public. Object Detection has been extensively implemented in several areas, including human-machine Interaction, autonomous vehicles, security with video surveillance, and various fields that will be mentioned further. However, this augmentation of OD tackles different challenges such as occlusion, illumination variation, object motion, without ignoring the real-time aspect that can be quite problematic. This paper also includes some methods of application to take into account these issues. These techniques are divided into five subcategories: Point Detection, segmentation, supervised classifier, optical flow, a background modeling. This survey decorticates various methods and techniques used in object detection, as well as application domains and the problems faced. Our study discusses the cruciality of deep learning algorithms and their efficiency on future improvement in object detection topics within video sequences.

Non-Human-Machine Interaction for Power Transmission Lines Protection Design and Enhancement of Under Voltage Relay

The continuous monitoring of transmission line protection relay is desirable to ensure the system disturbance such as fault inception is detected in transmission line. Therefore, fault on transmission line needs to be detected, classified, and located accurately to maintain the stability of system. This project presents design enhancement and development under voltage relay in power system protection using MATLAB/Simulink. The under-voltage relay is a relay that has contacts that operate when voltage drops below a set voltage which is used for protection against voltage drops to detect short circuit and others. This study is carried out for all types of faults which only related with one of the parallel lines. For the overall of operation conditions, the sample data were generated for the system by varying the different fault types and fault location. This design system proposes the use of MATLAB/ Simulink based method for fast and reliable fault classification and location for a various type of fault.

Self-healing, Mechanically Robust, and 3D Printable Ionogel for Highly Sensitive and Long-Term Reliable Ionotronics

Flexible sensors which can transduce various stimuli (e.g., strain, pressure, temperature) into electrical signals are highly in demand due to the development of human-machine interaction. However, it is still a...

Autonomous Surgical Robotics at Task and Subtask Levels

The revolution of minimally invasive procedures had a significant influence on surgical practice, opening the way to laparoscopic surgery, then evolving into robotics surgery. Teleoperated master-slave robots, such as the da Vinci Surgical System, has become a standard of care during the last few decades, performing over a million procedures per year worldwide. Many believe that the next big step in the evolution of surgery is partial automation, which would ease the cognitive load on the surgeon, making them possible to pay more attention on the critical parts of the intervention. Partial and sequential introduction and increase of autonomous capabilities could provide a safe way towards Surgery 4.0. Unfortunately, autonomy in the given environment, consisting mostly of soft organs, suffers from grave difficulties. In this chapter, the current research directions of subtask automation in surgery are to be presented, introducing the recent advances in motion planning, perception, and human-machine interaction, along with the limitations of the task-level autonomy.

Usage of Augmented Reality for Improved Human-Machine Interaction and Real-Time Error Correction of Laboratory Units

For future innovations, complex Industry 4.0-technologies need to improve the interaction of humans and technology. Augmented Reality (AR) has a significant potential for this task by introducing more interactivity into modern technical assistance systems. However, AR systems are usually very expensive and thus unsuitable for small and medium-sized enterprises (SMEs). Furthermore, the machine's reliable data transfer to the AR applications and the user activity indication appear to be problematic. This work proposes a solution to these problems. A simple and scalable data transfer from industrial systems to Android applications has been developed.The suggested prototype demonstrates an AR application for troubleshooting and error correction in real-time, even on mobile or wearable devices, while working in a laboratory unit to simulate and solve various errors. The unit components (small garage doors) are equipped with sensors. The information about the state of the system is available in real-time at any given moment and is transmitted to a mobile or wearable device (tablet or smart glass) equipped with AR application. The operator is enabled to preview the required information in a graphical form (marks and cursors). Potential errors are shown and solved with an interactive manual. The system can be used for training purposes to achieve more efficient error correction and faster repairing.

Human Activity Recognition via Hybrid Deep Learning Based Model

In recent years, Human Activity Recognition (HAR) has become one of the most important research topics in the domains of health and human-machine interaction. Many Artificial intelligence-based models are developed for activity recognition; however, these algorithms fail to extract spatial and temporal features due to which they show poor performance on real-world long-term HAR. Furthermore, in literature, a limited number of datasets are publicly available for physical activities recognition that contains less number of activities. Considering these limitations, we develop a hybrid model by incorporating Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) for activity recognition where CNN is used for spatial features extraction and LSTM network is utilized for learning temporal information. Additionally, a new challenging dataset is generated that is collected from 20 participants using the Kinect V2 sensor and contains 12 different classes of human physical activities. An extensive ablation study is performed over different traditional machine learning and deep learning models to obtain the optimum solution for HAR. The accuracy of 90.89% is achieved via the CNN-LSTM technique, which shows that the proposed model is suitable for HAR applications.