Development and Evaluation of a Dual-Layer-Offset PET Detector Constructed with Different Reflectors

Dual-layer-offset or multi-layer-offset design of a PET detector can improve spatial resolution while maintaining high sensitivity. In this study, three dual-layer-offset LYSO detectors with three different reflectors (ESR, Toray, and BaSO4) were developed. The top layer consisted of a 17 × 17 array of crystals 1 × 1 × 6.5 mm3 in size and the bottom layer consisted of an 18 × 18 array of crystals 1 × 1 × 9.5 mm3 in size. Neither light guides nor optical glue were used between the two layers of crystals. A custom-designed electronics system, composed of a 6 × 6 SiPM array, two FPC cables, and a custom-designed data processing module, was used to read out signals. An optimized interaction-decoding algorithm using the center of gravity to determine the position and threshold of analog signals for timing methods was applied to generate decoding flood histograms. The detector performances, in terms of peak to valley ratio of the flood histograms and energy resolutions, were calculated and compared. The dual-layer-offset PET detector constructed with BaSO4 reflectors performed much better than the other two reflectors in both crystal identification and energy resolution. The average peak-to-valley ratio and the energy resolution were approximately 7 and 11%, respectively. In addition, the crystals in the bottom layer showed better performance at crystal identification than those in the top layer. This study can act as a reference providing guidance in choosing scintillator reflectors for multi-layer dedicated DOI detectors designed for small-animal PET imaging.

Copying and Recreation Methods of Painting Works Relying on Mobile Digital Multimedia Big Data Analysis

In order to improve the effect of copying and recreation of painting works, this paper combines mobile digital multimedia big data technology to improve the image coding algorithm, identify the characteristics of existing works, apply the algorithm to the detailed analysis of painting works, and construct the main functional structure modules of the system. Moreover, this paper combines the existing hardware equipment to construct the painting works’ recreation system and obtains the image processing module. After the system is constructed, the effect of copying and recreating painting works is analyzed through the mobile digital multimedia big data analysis technology. Finally, this paper constructs the system of this paper through simulation methods and uses experiments to calculate the feature recognition effect and copy effect of the painting works of the system. Through experimental analysis, it can be known that the copying and recreation system of painting works based on mobile digital multimedia big data analysis proposed in this paper can help painters effectively improve the effect of recreation.

Machine-Learning Classifiers for Malware Detection Using Data Features

The spread of ransomware has risen exponentially over the past decade, causing huge financial damage to multiple organizations. Various anti-ransomware firms have suggested methods for preventing malware threats. The growing pace, scale and sophistication of malware provide the anti-malware industry with more challenges. Recent literature indicates that academics and anti-virus organizations have begun to use artificial learning as well as fundamental modeling techniques for the research and identification of malware. Orthodox signature-based anti-virus programs struggle to identify unfamiliar malware and track new forms of malware. In this study, a malware evaluation framework focused on machine learning was adopted that consists of several modules: dataset compiling in two separate classes (malicious and benign software), file disassembly, data processing, decision making, and updated malware identification. The data processing module uses grey images, functions for importing and Opcode n-gram to remove malware functionality. The decision making module detects malware and recognizes suspected malware. Different classifiers were considered in the research methodology for the detection and classification of malware. Its effectiveness was validated on the basis of the accuracy of the complete process.

Graphical Interface for the Recommendation System

Today, mathematics plays a huge part of our everyday life. But due to the poor school education and lack of open access resources, many students find it difficult to be fully prepared for the independent external evaluation in mathematics, especially geometry. Although much has already been done to conduct higher knowledge results, lots of students still have gaps in understanding simple problem solving. Clearly, geometry requires a more fundamental and visual implementation to the studying process than algebra in order to increase the overall knowledge level of Ukrainian applicants for higher education. Students often do not have access to innovative studying instruments in their schools necessary for successful completion of geometry classes, which is why they receive weak results in tests.In the research, we are concentrating on the planimetry problems, because they can be easily produced in a written form. After analyzing all types of describing a problem, the best option for the system is the open-type problems with the short answer.The article concentrates on creating a graphical interface module, implementing it to the existing language processing module, and introducing a recommendation system that demonstrates a new fundamental instrument that can change the learning technique and give a comprehensive way of explaining geometry problems.The created system receives an open-type planimetry problem in Ukrainian language, processes it using the NLP module, and transfers the data directly to the interface module, which creates an image of the problem. Then the student can try to draw all the required figures, while the system continuously checks the progress. Recommendations (hints) can be applied during the process by the system.Interface and the NLP modules were created separately, independently, and using different programming languages. For that purpose, we use an intermediate stage – JSON file, which is used to transfer the processed information.

Web technologies in cartographic support of geological exploration

Web technologies are now an integral part of the implementation of research work in various branches of science. The geological and geophysical direction is no exception, where the planning and execution of geological and geophysical surveys depend on the accuracy, reliability and relevance of the transmitted information.The article deals with the possibilities of web technologies for cartographic support of geological exploration – a complex of scientific and production works, designed to determine the industrial significance of mineral deposits (ore, hydrocarbon, etc.). Examples are given of the use of geoportal solutions for the publication of data on the territory of study.Taking into account the current level of web technologies development, a proprietary web-service was created to provide operational access to geodata during geological and geophysical work. The presented solution is implemented using PostgreSQL DBMS, PostGIS geospatial data processing module, Leaflet JavaScript library. The resulting interactive map allows to perform operational monitoring of field crews during seismic exploration, provides information on the stages of data processing and interpretation. Also it allows to implement a unified geoinformation space for joint work of specialists from different industries.

Nondestructive Detection of Ceramic Products Based on Tapping Sound Signal Feature Recogition

Recent studies on the test of ceramic non-destructive testing are mainly based on high cost technologies, image processing and so on, these method possesses some drawback of low efficiency, high cost and so on. What’s more, detecting whether the ceramic products by human through listening to sound of tapping is also effectless. This paper proposed a non-destructive method for ceramic products to solve this problem. This non-destructive method consists of a tapping device and a signal processing module. The tapping device will be applied to generate the tapping sound signal and the signal processing system will be applied to analysis signal. After the process of signal analysis, sample length and peak of spectrum 2 parameters is extracted, then use these parameters to train SVM, the results will be compared with BP neural network (BPNN). The result of experiment shows that SVM with different kernels of linear, poly, rbf, sigmoid respectively reach the accuracy of 96.29%, 96.29%, 46.29%, 93.82%, while BPNN reaches the accuracy of 93.21%. This result proves that SVM can effectively complete the task of identifying defective ceramics, and its performance is better than BPNN.

A Domain-Independent Generative Adversarial Network for Activity Recognition Using WiFi CSI Data

Over the past years, device-free sensing has received considerable attention due to its unobtrusiveness. In this regard, context recognition using WiFi Channel State Information (CSI) data has gained popularity, and various techniques have been proposed that combine unobtrusive sensing and deep learning to accurately detect various contexts ranging from human activities to gestures. However, research has shown that the performance of these techniques significantly degrades due to change in various factors including sensing environment, data collection configuration, diversity of target subjects, and target learning task (e.g., activities, gestures, emotions, vital signs). This problem, generally known as the domain change problem, is typically addressed by collecting more data and learning the data distribution that covers multiple factors impacting the performance. However, activity recognition data collection is a very labor-intensive and time consuming task, and there are too many known and unknown factors impacting WiFi CSI signals. In this paper, we propose a domain-independent generative adversarial network for WiFi CSI based activity recognition in combination with a simplified data pre-processing module. Our evaluation results show superiority of our proposed approach compared to the state of the art in terms of increased robustness against domain change, higher accuracy of activity recognition, and reduced model complexity.

Towards Explainable Augmented Intelligence (AI) for Crack Characterization

Crack characterisation is one of the central tasks of NDT&E (the Non-Destructive Testing and Evaluation) of industrial components and structures. These days data necessary for carrying out this task are often collected using ultrasonic phased arrays. Many ultrasonic phased array inspections are automated but interpretation of the data they produce is not. This paper offers an approach to designing an explainable AI (Augmented Intelligence) to meet this challenge. It describes a C code called AutoNDE, which comprises a signal-processing module based on a modified total focusing method that creates a sequence of two-dimensional images of an evaluated specimen; an image-processing module, which filters and enhances these images; and an explainable AI module—a decision tree, which selects images of possible cracks, groups those of them that appear to represent the same crack and produces for each group a possible inspection report for perusal by a human inspector. AutoNDE has been trained on 16 datasets collected in a laboratory by imaging steel specimens with large smooth planar notches, both embedded and surface-breaking. It has been tested on two other similar datasets. The paper presents results of this training and testing and describes in detail an approach to dealing with the main source of error in ultrasonic data—undulations in the specimens’ surfaces.

ThamRobot: An Automated Robotic System to Play Thammattama

Sri Lanka has a precious traditional drum music culture that is mainly based on traditional drums. At present, this drum culture is in decline due to a lack of talented drum players. As a result, many Buddhist temples are facing a serious and tragic problem. This article presents the design and implementation of a robotic system named ThamRobot contains two robotic arms that were designed to play pre-programmed three drum tunes of the Thammattama correctly and efficiently like a drum player without any intervention of a human. In the research, nine major characteristics factors of the Thammattama such as music notes, drum locations, approximate stress, frequencies, pitch, drum type, number of sticks, playing technique, distance from stick to drum face were identified. The entire system is comprised of four main modules named motion module, user-operation module, processing module, power supply module. Finally, the system has been tested in a laboratory environment and encouraging results were obtained.

Performance Analysis of Vibration Sensors for Closed-Loop Feedback Health Monitoring of Mechanical Equipment

In this paper, we analyze the performance of mechanical equipment through a closed-loop feedback health monitoring vibration sensor, develop an OTDR optical signal reception and the processing module, and realize the reception, amplification, and filtering of the backscattered optical signal. In terms of vibration signal demodulation, the FPGA signal processing module was developed and debugged to realize the intermodulation with OTDR optical signal reception processing module and the preprocessing of the vibration data stream by taking advantage of the FPGA in parallel high-speed data stream processing. The objective function is constructed based on the dynamic data of the first four vertical frequencies of the modal recognition and the static data of the constant-load cable force of the inclined cable, and the third-order response surface method is applied to fit the response surface function of each correction target. The errors between the corrected FEM calculated values and the measured results are within 5%. The results were compared with the results of static and dynamic corrections, and the results showed that the joint static and dynamic corrections using the third-order response surface could obtain a finite element model that was more comprehensive and closer to the actual engineering response. A 180° feedback gain is set in the mass detection system to reduce the system’s equivalent mass and increase the system resonant frequency. An inverse lock-in amplifier is used instead of a high-frequency bandpass filter to spectrally migrate the useful frequencies and better filter out noise interference. A thin-film microresonant pressure sensor, a cantilever beam microresonant gas sensor, and a microresonant biosensor were designed and developed using the micromachining process. A closed-loop feedback method was used to design a low-frequency detection system, a medium-frequency detection system, and a high-frequency feedback detection based on a phase-locked loop system, completed open-loop and closed-loop detection experiments of the intrinsic frequency of the sensor, through-pressure experiments of the pressure sensor, low and medium frequency gas-sensitive experiments of the gas sensor, and high-frequency detection experiments of the biosensor oxygen absorption/deoxygenation, and measured the mass of individual oxygen molecules.