Large amount of data are generated from in-situ monitoring of additive manufacturing (AM) processes which is later used in prediction modelling for defect classification to speed up quality inspection of products. A high volume of this process data is defect-free (majority class) and a lower volume of this data has defects (minority class) which result in the class-imbalance issue. Using imbalanced datasets, classifiers often provide sub-optimal classification results i.e. better performance on the majority class than the minority class. However, it is important for process engineers that models classify defects more accurately than the class with no defects since this is crucial for quality inspection. Hence, we address the class-imbalance issue in manufacturing process data to support in-situ quality control of additive manufactured components.  For this, we propose cluster-based adaptive data augmentation (CADA) for oversampling to address the class-imbalance problem. Quantitative experiments are conducted to evaluate the performance of the proposed method and to compare with other selected oversampling methods using AM datasets from an aerospace industry and a publicly available casting manufacturing dataset. The results show that CADA outperformed random oversampling and the SMOTE method and is similar to random data augmentation and cluster-based oversampling. Furthermore, the results of the statistical significance test show that there is a significant difference between the studied methods.  As such, the CADA method can be considered as an alternative method for oversampling to improve the performance of models on the minority class. 

We evaluate Forward Error Correction (FEC) codes in the context of a novel routing protocol HDARP+ for airborne networks. HDARP+ uses directional antennas and dynamic FEC coding to avoid detection by adversaries. The use of FEC coding is dynamic in the sense that different FEC codes, or no FEC code, will be used depending on the relative position of friendly and adversary aircraft. Due to the real-time restrictions in airborne networks, encoding and decoding must be fast and done through table lookup. Since we use table lookup, the FEC codes must be short. We evaluate two types of short FEC codes: Reed-Solomon (RS) codes, and FEC codes found using greedy search (called GS codes). The results show that the RS codes are better than the GS codes at handling error bursts. However, the GS codes are more flexible when it comes to finding attractive trade-offs between the code's ability to increase the number of the cases when hostile detection can be avoided (related to the coding gain), the code rate and the amount of memory required for implementing lookup tables.

With the rapid growth of internet technologies, IT businesses are transferring to cloud-based systems, and cloud-based services are in high demand among internet users. Therefore, appropriate allocation of resources in cloud computing environments is essential. The companies can reduce costs by saving energy by dynamically scaling up or down the number of active servers. In this context, this study presents a machine learning-based model for accurate prediction of CPU utilization. Previous studies employed timestamp-based data to predict CPU utilization in cloud computing, while the proposed work uses incoming user requests to predict CPU workload so that a timely decision can be made to scale up or scale down the servers in a cloud computing environment. The proposed model is based on several machine learning algorithms that are stacked into a single model called the stacking model for CPU workload prediction. The effectiveness of the proposed stacking model was tested on several evaluation metrics to validate its performance. Furthermore, the performance of the proposed stacking model is also compared with other state-of-the-art machine learning models such as support vector machines (SVM), decision trees (DT), random forests (RF), gradient boosting, and extreme gradient boosting (XGBoost). 

Using a novel method and tool in the form of a Python program, we present a bibliometric study based on 46,937 documents related to smart cities from the Scopus database. The study identifies important research directions and trends during the time period 2014 to 2023. We also present the growth of smart city research for five geographic regions. Citation analysis for research directions and regions is also performed. The results show that smart city research in general stopped growing around 2019. However, some research directions are still growing, e.g., smart city research related to machine learning and AI. India is the only geographic region where smart city research still is growing. We also see that the number of citations of a smart city document from North America is on average a factor 3.74 larger than the number of citations to a document from India. © 2024 IEEE.

We present a method, including tool support, for bibliometric mining of trends in large and dynamic research areas. The method is applied to the machine learning research area for the years 2013 to 2022. A total number of 398,782 documents from Scopus were analyzed. A taxonomy containing 26 research directions within machine learning was defined by four experts with the help of a Python program and existing taxonomies. The trends in terms of productivity, growth rate, and citations were analyzed for the research directions in the taxonomy. Our results show that the two directions, Applications and Algorithms, are the largest, and that the direction Convolutional Neural Networks is the one that grows the fastest and has the highest average number of citations per document. It also turns out that there is a clear correlation between the growth rate and the average number of citations per document, i.e., documents in fast-growing research directions have more citations. The trends for machine learning research in four geographic regions (North America, Europe, the BRICS countries, and The Rest of the World) were also analyzed. The number of documents during the time period considered is approximately the same for all regions. BRICS has the highest growth rate, and, on average, North America has the highest number of citations per document. Using our tool and method, we expect that one could perform a similar study in some other large and dynamic research area in a relatively short time.

Here we present a novel routing protocol HDARP+ for airborne tactical networks that use directional antennas. HDARP+ extends the existing protocol HDARP (Hostile-Direction Aware Routing Protocol) by reducing the risk for detection by adversary aircraft even further. Compared to HDARP, the extension in HDARP+ introduces dynamic Forward Error Correction (FEC) coding. The FEC code is dynamic in the sense that different FEC codes, or no FEC code, will be used depending on the relative position of the receiver and adversary aircraft. We evaluate three different Reed-Solomon FEC codes based on three criteria: the ability to transmit in the presence of adversaries without being detected, the reduction of the effective communication bandwidth, and the implementation cost in terms of the sizes of lookup tables for encoding and decoding. We argue that (variations of) HDARP+ will be implemented in future airborne tactical networks. This paper was originally presented at the NATO Science and Technology Organization Symposium (ICMCIS) organized by the Information Systems Technology (IST) Panel, IST-205-RSY - the ICMCIS, held in Koblenz, Germany, 23-24 April 2024. 

In this report we explain an alternative computational analysis to the detection diabetes Type 2 from voice, which is an end-to-end pipeline, the input to which is a speech file and the output is a prediction about its category(diseased or control), and it consists of 1) a feature extraction script to obtain richer representation of the speech signal (6000 parameters in placeof less than 20), and 2) learning and testing of a classification functionthat assigns a category to a new sample. The feature extraction can be usedtogether with the classical statistical analysis currently considered to be thegold standard in the literature on diabetes detection from voice.

In many cases, e.g., when performing systematic literature reviews, one need to find documents related to a certain document or to a certain set of documents. Historically, traditional databas esearches based on keywords has been the main way of doing this. For a number of years these traditional search methods have been complemented with so called snowballing. Backward snowballing starting from a document A means that we look at the (older) documents that are cited by A, and forward snowballing means that we look at (newer) documents that cite A. Snowballing and traditional database searches can also be combined in hybridsearch strategies (Wohlin et al 2022). Here we define a way to generalize snowballing, to something we refer to as family searching.Compared to traditional backward and forward snowballing there are two clear advantages with family searching: (i) family searches find a larger number of related documents compared to backward and forward snowballing, and (ii) family searches rank the related documents based on how closely related to the starting document (or set of documents) they are.

Contemporary airborne radio networks are usually implemented using omnidirectional antennas. Unfortunately, such networks suffer from disadvantages such as easy detection by hostile aircraft and potential information leakage. In this paper, we present a novel mobile ad hoc network (MANET) routing protocol based on directional antennas and situation awareness data that utilizes adaptive multihop routing to avoid sending information in directions where hostile nodes are present. Our protocol is implemented in the OMNEST simulator and evaluated using two realistic flight scenarios involving 8 and 24 aircraft, respectively. The results show that our protocol has significantly fewer leaked packets than comparative protocols, but at a slightly higher cost in terms of longer packet lifetime.