Multi-Scale Memetic Image Registration

Many technological applications of our time rely on images captured by multiple cameras. Such applications include the detection and recognition of objects in captured images, the tracking of objects and analysis of their motion, and the detection of changes in appearance. The alignment of images captured at different times and/or from different angles is a key processing step in these applications. One of the most challenging tasks is to develop fast algorithms to accurately align images perturbed by various types of transformations. The paper reports a new method used to register images in the case of geometric perturbations that include rotations, translations, and non-uniform scaling. The input images can be monochrome or colored, and they are preprocessed by a noise-insensitive edge detector to obtain binarized versions. Isotropic scaling transformations are used to compute multi-scale representations of the binarized inputs. The algorithm is of memetic type and exploits the fact that the computation carried out in reduced representations usually produces promising initial solutions very fast. The proposed method combines bio-inspired and evolutionary computation techniques with clustered search and implements a procedure specially tailored to address the premature convergence issue in various scaled representations. A long series of tests on perturbed images were performed, evidencing the efficiency of our memetic multi-scale approach. In addition, a comparative analysis has proved that the proposed algorithm outperforms some well-known registration procedures both in terms of accuracy and runtime.

PRIMA: general and precise neural network certification via scalable convex hull approximations

Formal verification of neural networks is critical for their safe adoption in real-world applications. However, designing a precise and scalable verifier which can handle different activation functions, realistic network architectures and relevant specifications remains an open and difficult challenge. In this paper, we take a major step forward in addressing this challenge and present a new verification framework, called PRIMA. PRIMA is both (i) general: it handles any non-linear activation function, and (ii) precise: it computes precise convex abstractions involving multiple neurons via novel convex hull approximation algorithms that leverage concepts from computational geometry. The algorithms have polynomial complexity, yield fewer constraints, and minimize precision loss. We evaluate the effectiveness of PRIMA on a variety of challenging tasks from prior work. Our results show that PRIMA is significantly more precise than the state-of-the-art, verifying robustness to input perturbations for up to 20%, 30%, and 34% more images than existing work on ReLU-, Sigmoid-, and Tanh-based networks, respectively. Further, PRIMA enables, for the first time, the precise verification of a realistic neural network for autonomous driving within a few minutes.

Fuzzy-Based Screening System for Determination of Enhanced Oil Recovery (EOR) Method in Reservoir

The petroleum industry is developing technology to increase oil recovery in reservoirs. One of the technologies used is Enhanced Oil Recovery (EOR). Selecting an EOR method for a specific reservoir condition is one of the most challenging tasks for a reservoir engineer. This study tries to build a fuzzy logic-based screening system to determine the EOR method. It created the system intending to be able to assist in selecting and determining the appropriate EOR method used in the field. There are nine input criteria used to screen the EOR criteria, namely: API Gravity, Oil Saturation, Formation Type, Net Thickness, Viscosity, Permeability, Temperature, Porosity, Depth criteria. The output criteria generated from the calculation of the EOR screening criteria are 14 outputs, namely: CO2 MF Miscible Flooding, CO2 IMMF Immiscible Flooding, HC MF Miscible Flooding, HC IMMF Immiscible Flooding, N2 MF Miscible Flooding, N2 IMMF Immiscible Flooding, WAG MF Miscible Flooding , HC+WAG IMMF Immiscible Flooding, Polymer, ASP, Combustion, Steam, Hot Water, Microbial. In this system, 512 rules are generated to produce 14 different outputs of the EOR method, with Mamdani's Fuzzy Inference reasoning. This fuzzy-based screening system has an accuracy rate of 80.95%, so this system is suitable to be used to assist reservoir engineers in determining the appropriate EOR method to be used according to the conditions in the reservoir. The sensitivity level of the system only reaches 53.1%, while the specificity level reaches 94%.

EXPRESS: Dynamic relationships between LMX and employee role-making behaviours: The moderating role of employee emotional ambivalence

We set out to understand how role-making works and what roles employees and leaders play in this process. Employees often make changes to their work roles, such as by negotiating their job responsibilities and seeking challenging tasks. In this study, we suggest that role-making behaviours influence and are influenced by the dyadic relationship between leaders and employees, otherwise known as leader–member exchange (LMX). We collected three waves of survey data from a sample of Chinese employees who were recent college graduates (n = 203). The results from cross-lagged panel analyses showed that 1) LMX and job-change negotiation were reciprocally related to each other and 2) initial LMX was associated with increased challenge-seeking behaviours, although these behaviours did not lead to greater LMX later on. In addition, we found evidence that when employees experienced a high level of emotional ambivalence (a conflicting, mixed, and complex emotional state), the direct and reciprocal relationships between LMX and role-making behaviours were weakened. Our findings advance the understanding of the development of leader–employee relationships in the workplace and have implications for strengthening employee perceptions of high-quality relationships with their leaders by making changes to their workplace roles.

Real Time Face Mask Detection using Google Cloud ML and Flutter

Coronavirus (Covid-19) pandemic has impacted the whole world and has forced health emergencies internationally. The contact of this pandemic has been fallen over almost all the development sectors. A lot of precautionary measures have been taken to control the Covid-19 spread, where wearing a face mask is an essential precaution. Wearing a face mask correctly has been essential in controlling the Covid-19 transmission. Moreover, this research aims to detect the face mask with fine-grained wearing states: face with the correct mask and face without mask. Our work has two challenging tasks due to two main reasons firstly the presence of augmented data set available in the online market and the training of large datasets. This paper represents a mobile application for face mask detection. The fully automated Machine Learning Cloud service known as Google Cloud ML API is used for training the model in TensorFlow file format. This paper highlights the efficiency of the ML model. Additionally, this paper examines the advancement of the cloud technology used for machine learning over the traditional coding methods.

Travel Time Prediction and Explanation with Spatio-Temporal Features: A Comparative Study

Travel time information is used as input or auxiliary data for tasks such as dynamic navigation, infrastructure planning, congestion control, and accident detection. Various data-driven Travel Time Prediction (TTP) methods have been proposed in recent years. One of the most challenging tasks in TTP is developing and selecting the most appropriate prediction algorithm. The existing studies that empirically compare different TTP models only use a few models with specific features. Moreover, there is a lack of research on explaining TTPs made by black-box models. Such explanations can help to tune and apply TTP methods successfully. To fill these gaps in the current TTP literature, using three data sets, we compare three types of TTP methods (ensemble tree-based learning, deep neural networks, and hybrid models) and ten different prediction algorithms overall. Furthermore, we apply XAI (Explainable Artificial Intelligence) methods (SHAP and LIME) to understand and interpret models’ predictions. The prediction accuracy and reliability for all models are evaluated and compared. We observed that the ensemble learning methods, i.e., XGBoost and LightGBM, are the best performing models over the three data sets, and XAI methods can adequately explain how various spatial and temporal features influence travel time.

Hunger Effects on Option Quality for Hedonic and Utilitarian Food Products

Multiple studies have examined the extent to which consumers’ hunger levels predict their food choices and preference patterns. These investigations often involve making binary choices between hedonic and utilitarian foods. However, most consumers entering a grocery store are not restricted to solely selecting either hedonic or utilitarian foods. Rather, they typically choose both hedonic and utilitarian food options. Moreover, little is known about the effects of hunger on the quality of these food choices or consumers’ cognitive performance in food contexts. To address these gaps, the current study explored (1) whether experimentally induced hunger (vs. satiation) influenced the option quality of consumers’ chosen food items (i.e., the match between actual choices and stated preferences); (2) whether this potential interplay was contingent on the food category (hedonic vs. utilitarian); and (3) whether hungry (vs. satiated) consumers’ performance differed on cognitively challenging tasks. The results revealed that hunger did not lead to a generalized decrease in consumers’ option quality. However, option quality was inferior for utilitarian—but not hedonic—foods among hungry participants, whereas no such differences were found for satiated participants. Hungry (vs. satiated) consumers also performed significantly worse on cognitively demanding tasks, underscoring the far-reaching consequences of hunger on consumers’ decision-making. Together, the current research offers a novel way of testing whether and how hunger influences the quality of consumers’ chosen food items in both hedonic and utilitarian food categories.

Selection of the Key Segment Position for Trapezoidal Tapered Rings and Calculation of the Range of Jack Stroke Differences with a Predetermined Key Segment Position

It is generally accepted that selecting the key segment position for trapezoidal tapered rings and controlling the shield machine advancement are challenging tasks for shield tunneling projects. In this work, we propose a method for calculating the key segment position based on the shield tail gap, jack stroke difference, and lining trend. To calculate all possible key segment positions other than that corresponding to the straight joint configuration, the shield tail gap that remains after segment assembly and the jack stroke difference corresponding to the advancement of the segmental lining and lining trend were computed; then, values and importance coefficients were assigned to these factors according to current operating conditions. To ensure that the segmental lining can be assembled successfully with the calculated key position, we established a model to calculate the change in the shield tail gap before and after shield machine advancement based on the spatial relationships of the shield machine, the currently installed segmental rings, and the segment to be installed. Further, we propose a method for calculating the range of jack stroke differences when the predetermined “permitted shield tail gap” and key position are provided. The method is based on the change in the shield tail gap calculated with the above model and the positional relationship between the shield machine’s actual axis and the designed tunnel axis after the current segmental ring has been assembled. The calculated range of jack stroke differences may then be used to control the advancement of the shield machine. We validated the viability of our methods by using the data of Phase 1 works on Line 2 of the Ningbo Rail Transit system.

The Undergraduate English Students’ Perception, Plan, and Implementation of Critical Thinking Skills in Their Presentation

Previous studies shows that several learning strategies have been used to promote critical thinking skills for students at the university level, the most frequently used is presentation. The students in the third semester of the English department in IAIN Pekalongan have distinctive responses regarding their critical thinking skills in their presentation. This study aimed to explain students’ perception, plan and implementation in their use of critical thinking skills in their presentation. This study was qualitative case study. The data gathered by classroom observation, questionnaires, and interviews. The findings showed (1) The students positively perceived their use of critical thinking skills in their presentation, they believed that critical thinking skills help them to enable their presentation, English skills, and performance (2) the students plan their critical thinking skills by preparing the schema, skills, and practicing (3) the implementation of critical thinking skills in students' presentation by combining students' awareness, activeness, and learning style. Theoretically, critical thinking skills are fundamental to be implemented in higher education students. Practically, the result of this study gave benefit for the lecturer in giving students challenging tasks that encourage them to use their critical thinking skills. Pedagogically, the implementation of critical thinking skills in students’ presentations needs a student-lecturer relationship.