Extending electronic shot counters with machine learning-based ammunition discrimination for targeted maintenance

This paper investigates the effects of using erasure information in Reed Solomon (RS) coded parallel combinatorial spread spectrum (PC/SS) communication systems over AWGN and Rayleigh fading channels. The PC/SS system is an advanced multicode direct sequence spread spectrum (DS/SS) system for high-speed data transmission. Our previous works have shown that the RS coded PC/SS systems provide significant improvement in error rate performance over conventional DS/SS systems. To achieve further performance improvement in the PC/SS systems, error-and-erasure decoding techniques are implemented in an RS coded PC/SS receiver. To obtain the erasure location information, a threshold test for the squared ratio of the correlator outputs is applied. Simulation results show that the coded PC/SS system using the erasure information provides significant improvement in word error rate (WER) and bit error rate (BER). With errors-only decoding, the PC/SS systems cannot improve the error rate performance because of large SNR penalty introduced by coding. On the contrary, error-and-erasure decoding using erasure information still improves the performance of PC/SS systems.

This paper investigates the effects of using error-and-erasure decoding in coded parallel combinatorial spread spectrum (PC/SS) systems over Rayleigh fading channels. The PC/SS system is an advanced multi-code direct sequence spread spectrum system for high-speed data transmission. Our previous works have shown that the Reed-Solomon (RS) coded PC/SS systems provide significant improvement in error rate performance over conventional DS/SS systems. To achieve further performance improvement in the PC/SS systems, error-and-erasure decoding techniques are implemented in the RS coded PC/SS receiver. To obtain the erasure location information, a threshold for the signal-to-noise ratio is set at the correlator output. Numerical results show that the coded PC/SS systems with error-and-erasure decoding provides significant improvement in the bit error rate (BER). With errors-only decoding, the PC/SS systems cannot improve the error rate performance because of large SNR penalty introduced by coding. On the contrary, error-and erasure decoding still improves the performance of PC/SS systems under multiple access environment.

Leveraging digitilisation and machine learning for improved railway operations and maintenance

The operation and maintenance of buildings has seen several advances in recent years. Multiple information and communication technology (ICT) solutions have been introduced to better manage building maintenance. However, maintenance practices in buildings remain less efficient and lead to significant energy waste. In this paper, a predictive maintenance framework based on machine learning techniques is proposed. This framework aims to provide guidelines to implement predictive maintenance for building installations. The framework is organised into five steps: data collection, data processing, model development, fault notification and model improvement. A sport facility was selected as a case study in this work to demonstrate the framework. Data were collected from different heating ventilation and air conditioning (HVAC) installations using Internet of Things (IoT) devices and a building automation system (BAS). Then, a deep learning model was used to predict failures. The case study showed the potential of this framework to predict failures. However, multiple obstacles and barriers were observed related to data availability and feedback collection. The overall results of this paper can help to provide guidelines for scientists and practitioners to implement predictive maintenance approaches in buildings.

In military simulations, software agents are used to represent individuals, weapon platforms or aggregates thereof. Modeling the behavioral capabilities and limitations of such agents may be time-consuming, requiring extensive interaction with subject matter experts and complicated scripts, but nevertheless resulting in rigid, predictable performance. Autonomous agents that learn desired behaviors themselves using Machine Learning (ML) techniques can overcome these shortcomings. However, such techniques are not yet widely used and perhaps underappreciated. In this context, the latin expression multum in parvo (much in little) denotes that ML agents are able to yield a large variety of behavior, despite their compactness in terms of code and usage of physical memory. This paper attempts to provide some background on applicable Machine Learning solutions and their potential military application. The paper is based on the work of the NATO Research Task Group IST-121 Machine Learning Techniques for Autonomous Computer Generated Entities.

Recent progress on machine learning techniques for flow field optimization toward performance and commercial scale proton exchange membrane fuel cell: A systematic review

This study examines the relationship between effective leadership, emotional intelligence (EI), and maintenance efficiency. It investigates the effects of leadership and EI initiatives on maintenance efficiency in three production facilities situated in Nigeria’s Niger Delta region. Important metrics such as Mean Time Between Failure (MTBF), Mean Time to Repair (MTTR), Downtime hours (DT), and Failure rate (λ) were employed in this study. Results reveal significant improvements in the employed metrics across all three facilities following the implementation of effective leadership and EI strategies. The case study facilities, EOC, OPP, and KGP experienced average improvement values of -73.25, -89.75, and -75.00 respectively. Despite variations in the level of improvement, the facilities witnessed enhancements in MTTR, MTBF, DT, and λ. The negative average improvement values signify improvements in maintenance efficiency post-implementation. The findings emphasize the positive impact of leadership and EI initiatives on maintenance practices and continuous improvement in organizations. By investing in leadership development and EI training, organizations can improve operational efficiency, optimal reliability, and cost reduction. The integration of these skills has significantly enhanced maintenance efficiency in the facilities studied, highlighting their significance in maintenance-intensive industries.

PurposeThe cost of residential building maintenance can harmfully affect low-income earners' expenditure if not checked. A customised maintenance concept via a framework will ensure efficient and proper building maintenance operations. The outcome may keep the life cycle cost down. Studies concerning the low-cost housing (LCH) maintenance concept through a framework are scarce in Malaysia. Thus, the study aims to investigate the state of LCH and develop a framework to improve LCH maintenance practices in Malaysia.Design/methodology/approachThe study adopted a soft system methodology (SSM) to comprehend Malaysia's LCH building maintenance practices. The SSM allowed an alternative approach to improve LCH maintenance practices via a developed framework. Virtual interviews were conducted with experts, and findings were presented. It was in line with the SSM seven steps.FindingsThe findings show that apart from the poor state of LCH maintenance, there is the absence of a framework to improve maintenance practices, especially in LCH across Malaysia's cities. The findings developed a framework that would reposition the joint management body and management corporation in collaboration with the proposed maintenance agency for better service delivery via substantive, technical and administrative aspects.Research limitations/implicationsThis study's data collection is restricted to Pulau Pinang, Kuala Lumpur and Johor through a qualitative research design approach. Future research is needed to consider more extensive coverage and validate the developed framework from this study via a quantitative research design.Practical implicationsApart from the conceptual model that was developed, the suggested framework can be employed by Malaysia's maintenance practitioners and policymakers as a guideline to improve LCH building maintenance practices across the cities.Originality/valueThis study examined Malaysia's LCH maintenance practices via SSM to identify the state of the houses, identify the information required and propose a suitable framework to improve Malaysia's LCH maintenance practices.

In terms of the availability and accuracy of positioning, navigation, and timing (PNT), the traditional Global Navigation Satellite System (GNSS) algorithms and models perform well under good signal conditions. In order to improve their robustness and performance in less than optimal signal environments, many researchers have proposed machine learning (ML) based GNSS models (ML models) as early as the 1990s. However, no study has been done in a systematic way to analyze the extent of the research on the utilization of ML models in GNSS and their performance. In this study, we perform a systematic review of studies from 2000 to 2021 in the literature that utilizes machine learning techniques in GNSS use cases. We assess the performance of the machine learning techniques in the existing literature on their application to GNSS. Furthermore, the strengths and weaknesses of machine learning techniques are summarized. In this paper, we have identified 213 selected studies and ten categories of machine learning techniques. The results prove the acceptable performance of machine learning techniques in several GNSS use cases. In most cases, the models using the machine learning techniques in these GNSS use cases outperform the traditional GNSS models. ML models are promising in their utilization in GNSS. However, the application of ML models in the industry is still limited. More effort and incentives are needed to facilitate the utilization of ML models in the PNT context. Therefore, based on the findings of this review, we provide recommendations for researchers and guidelines for practitioners.

Systematic literature review of machine learning based software development effort estimation models

본 논문에서는 어떠한 이진 입력 이산 퀀텀채널(quantum channel)이 주어지더라도 대칭 용량을 달성할 수 있는 qubit(quantum bit)를 생성하기 위해, 극(polar) 퀌텀 채널 코딩이라 부르는 퀀텀 채널의 결합과 분리 형태를 제시한다. 현재의 용량은 동등 확률을 갖는 임의의 qubit 입력에 따라서 결정된다. 퀀텀채널의 분극은 대칭채널이 1 에 근접하면 rate 1 로 아니면 rate 0 으로 전송하는 채널을 통해 퀀텀 데이터를 부분적으로 전송하는 퀀텀 오류정정 부호화에 아주 적합하다.

Legged robots are a class of biologically inspired robots that use articulated leg mechanisms for locomotion. Legged motion is very complex and requires specialized actuation mechanisms and complicated motion control systems to operate. Traditional legged robots were controlled by purely physics-based, however, recent developments of artificial intelligence (AI), and machine learning (ML) techniques have opened new opportunities to train locomotion skills in a legged robot in a much more efficient way than the traditional physics-based controllers. In this chapter, the authors study how machine learning techniques are used to train quadruped robots in basic locomotion skills, evaluate training accuracy, training speed, and also discussed performance, simulation environment, trajectory control, and how the authors achieved accurate tracking of trajectories. Furthermore, this chapter delves into the details of the actual quadruped robot that the authors built to evaluate locomotion policies and some challenges that were faced in building the real robot.

Computer-aided sports analysis is demanded by coaches and the media. Image processing and machine learning techniques that allow for “live” recognition and tracking of players exist. But these methods are far from collecting and analyzing event data fully autonomously. To generate accurate results, human interaction is required at different stages including system setup, calibration, supervision of classifier training, and resolution of tracking conflicts. Furthermore, the real-time constraints are challenging: in contrast to other object recognition and tracking applications, we cannot treat data collection, annotation, and learning as an offline task. A semi-automatic labeling of training data and robust learning given few examples from unbalanced classes are required. We present a real-time system acquiring and analyzing video sequences from soccer matches. It estimates each player’s position throughout the whole match in real-time. Performance measures derived from these raw data allow for an objective evaluation of physical and tactical profiles of teams and individuals. The need for precise object recognition, the restricted working environment, and the technical limitations of a mobile setup are taken into account. Our contribution is twofold: (1) the deliberate use of machine learning and pattern recognition techniques allows us to achieve high classification accuracy in varying environments. We systematically evaluate combinations of image features and learning machines in the given online scenario. Switching between classifiers depending on the amount of training data and available training time improves robustness and efficiency. (2) A proper human–machine interface decreases the number of required operators who are incorporated into the system’s learning process. Their main task reduces to the identification of players in uncertain situations. Our experiments showed high performance in the classification task achieving an average error rate of 3 % on three real-world datasets. The system was proved to collect accurate tracking statistics throughout different soccer matches in real-time by incorporating two human operators only. We finally show how the resulting data can be used instantly for consumer applications and discuss further development in the context of behavior analysis.

Research has shown the importance of Electronic Health Records (EHR) and in-home sensor data for continuous health tracking and health risk predictions. With the increased computational capabilities and advances in machine learning techniques, we have new opportunities to use multi-modal health big data to develop accurate health tracking models. This dissertation describes the development, evaluation, and testing of systems for predicting functional health and fall risks in community-dwelling older adults using health data and machine learning techniques. In an initial study, we focused on organizing and de-identifying EHR data for analysis using HIPAA regulations. The dataset contained nine years of structured and unstructured EHR data obtained from TigerPlace, a senior living facility at Columbia, MO. The de-identification of this data was done using custom automated algorithms. The de-identified EHR data was used in several studies described in this dissertation. We then developed personalized functional health tracking models using geriatric assessments in the EHR data. Studies show that higher levels of functional health in older adults lead to a higher quality of life and improves the ability to age-in-place. Even though several geriatric assessments capture several aspects of functional health, there is limited research in longitudinally tracking the personalized functional health of older adults using a combination of these assessments. In this study, data from 150 older adult residents were used to develop a composite functional health prediction model using Activities of Daily Living (ADL), Instrumental Activities of Daily Living (IADL), Mini-Mental State Examination (MMSE), Geriatric Depression Scale (GDS), and Short Form 12 (SF12). Tracking functional health objectively could help clinicians to make decisions for interventions in case of functional health deterioration. We next constructed models for fall risk prediction in older adults using geriatric assessments, demographic data, and GAITRite assessment data. A 6-month fall risk prediction model was developed with data from 93 older adult residents. Explainable AI techniques were used to provide explanations to the model predictions, such as which specific features increased the risk of fall in a particular model prediction. Such explanations to model predictions provide valuable insights for targeted interventions. In another study, we developed deep neural network models to predict fall risk from de-identified nursing notes data from 162 older adult residents from TigerPlace. Clinical nursing notes have been shown to contain valuable information related to fall risk factors. This analysis provides the groundwork for future experiments to predict fall risk in older adults using clinical notes. In addition to using EHR data to predict functional health and fall risk in older adults, two studies were conducted to predict fall and functional health from in-home sensor data. Models for in-home fall prediction using depth sensor imagery have been successfully used at TigerPlace. However, the model is prone to false fall alarms in several scenarios, such as pillows thrown on the floor and pets jumping from couches. A secondary fall analysis was performed by analyzing fall alert videos to further identify and remove false alarms. In the final study, we used in-home sensor data streaming from depth sensors and bed sensors to predict functional health and absolute geriatric assessment values. These prediction models can be used to predict the functional health of residents in absence of sparse and infrequent geriatric assessments. This can also provide continuous tracking of functional health in older adults using the streaming in-home sensor data.

Mid-infrared spectroscopy as a real-time diagnostic tool for chronic endometritis: A preliminary study.