Prediction of quality of life in people with ALS

Amyotrophic Lateral Sclerosis (ALS) is a rare neurodegenerative disease that causes a rapid decline in motor functions and has a fatal trajectory. ALS is currently incurable, so the aim of the treatment is mostly to alleviate symptoms and improve quality of life (QoL) for the patients. The goal of this study is to develop a Clinical Decision Support System (CDSS) to alert clinicians when a patient is at risk of experiencing low QoL. The source of data was the Irish ALS Registry and interviews with the 90 patients and their primary informal caregiver at three time-points. In this dataset, there were two different scores to measure a person's overall QoL, based on the McGill QoL (MQoL) Questionnaire and we worked towards the prediction of both. We used Extreme Gradient Boosting (XGBoost) for the development of the predictive models, which was compared to a logistic regression baseline model. Additionally, we used Synthetic Minority Over-sampling Technique (SMOTE) to examine if that would increase model performance and SHAP (SHapley Additive explanations) as a technique to provide local and global explanations to the outputs as well as to select the most important features. The total calculated MQoL score was predicted accurately using three features - age at disease onset, ALSFRS-R score for orthopnoea and the caregiver's status pre-caregiving - with a F1-score on the test set equal to 0.81, recall of 0.78, and precision of 0.84. The addition of two extra features (caregiver's age and the ALSFRS-R score for speech) produced similar outcomes (F1-score 0.79, recall 0.70 and precision 0.90).

LDA-LFM

Most of the existing recommender systems are based only on the rating data, and they ignore other sources of information that might increase the quality of recommendations, such as textual reviews, or user and item characteristics. Moreover, the majority of those systems are applicable only on small datasets (with thousands of observations) and are unable to handle large datasets (with millions of observations). We propose a recommender algorithm that combines a rating modeling technique (i.e., Latent Factor Model) with a topic modeling method based on textual reviews (i.e., Latent Dirichlet Allocation), and we extend the algorithm such that it allows adding extra user- and item-specific information to the system. We evaluate the performance of the algorithm using Amazon.com datasets with different sizes, corresponding to 23 product categories. After comparing the built model to four other models, we found that combining textual reviews with ratings leads to better recommendations. Moreover, we found that adding extra user and item features to the model increases its prediction accuracy, which is especially true for medium and large datasets.

Deep learning-based semantic classification of EMF-related scientific literature

Semantic classification of scientific literature using machine learning approaches is challenging due to the difficulties in labeling data and the length of the texts [2, 7]. Most of the work has been done for keyword-based categorization tasks, which take care of occurrence of important terms, whereas semantic classification requires understanding of terms and the meaning of sentences in a context. In this study, we have evaluated neural network models on a semantic classification task using 1091 labeled EMF-related scientific papers listed in the Powerwatch study. The EMF-related papers are labeled into three categories: positive, null finding, and neither. We have conducted neural architecture and hyperparameter search to find the most suitable model for the task. In experiments, we compared the performance of several neural network models in terms of classification accuracy. In addition, we have tested two different types of attention mechanisms. First, a Fully Convolutional Neural Network (FCN) has been used to identify important sentences in the text for the semantic classification. Second, the Transformer, a self-attention-based model, has been tested on the dataset. The experimental result showed that the BiLSTM performed best on both unbalanced and balanced data and the FCN was able to identify important parts in input texts.

A framework for the specification and validation of dynamic reconfigurable systems

We study a framework for the specification and validation of dynamic reconfigurable systems. The framework is based on configuration logic for the description of architecture styles which are families of architectures sharing common connectivity features. We express specifications in the Temporal Configuration Logic (TCL), a linear time temporal logic built from atomic formulas characterizing system configurations and temporal modalities. Two non-trivial benchmarks are introduced to show the adequacy of TCL for the specification of dynamic reconfigurable systems. We study an effective model-checking procedure based on SMT techniques for a non-trivial fragment of TCL which has been implemented in a prototype runtime verification tool. We provide preliminary experimental results illustrating the capabilities of the tool on the considered benchmark systems.

A cache consolidation design of MLC STT-RAM for energy efficiency enhancement on cyber-physical systems

Owing to the energy-constraint nature of cyber-physical systems (CPS), energy efficiency has become a primary design consideration for CPS. On CPS, owing to the high leakage power issue of SRAM, the major portion of its energy consumption comes from static random-access memory (SRAM)-based processors. Recently, with the emerging and rapidly evolving nonvolatile Spin-Transfer Torque RAM (STT-RAM), STT-RAM is expected to replace SRAM within processors for enhancing the energy efficiency with its near-zero leakage power features. The advances in Magnetic Tunneling Junction (MTJ) technology also realize the multi-level cell (MLC) STT-RAM to pack more cells with the same die area for achieving the memory density. However, the write disturbance issue of MLC STT-RAM prevents STT-RAM from properly resolving the energy efficiency of CPS. Although studies have been proposed to alleviate this issue, previous strategies could induce additional management overhead due to the use of counters or lead to frequent swap operations. Such an observation motivates us to propose an effective and simple strategy to combine direct and split cache mapping designs to enhance the energy efficiency of MLC STT-RAM. A series of experiments have been conducted on an open-source emulator with encouraging results.

Toward accurate platform-aware performance modeling for deep neural networks

In this paper, we provide a fine-grain machine learning-based method, PerfNetV2, which improves the accuracy of our previous work for modeling the neural network performance on a variety of GPU accelerators. Given an application, the proposed method can be used to predict the inference time and training time of the convolutional neural networks used in the application, which enables the system developer to optimize the performance by choosing the neural networks and/or incorporating the hardware accelerators to deliver satisfactory results in time. Furthermore, the proposed method is capable of predicting the performance of an unseen or non-existing device, e.g. a new GPU which has a higher operating frequency with less processor cores, but more memory capacity. This allows a system developer to quickly search the hardware design space and/or fine-tune the system configuration. Compared to the previous works, PerfNetV2 delivers more accurate results by modeling detailed host-accelerator interactions in executing the full neural networks and improving the architecture of the machine learning model used in the predictor. Our case studies show that PerfNetV2 yields a mean absolute percentage error within 13.1% on LeNet, AlexNet, and VGG16 on NVIDIA GTX-1080Ti, while the error rate on a previous work published in ICBD 2018 could be as large as 200%.

CHIEv

Researchers and practitioners in the fields of testing, security assessment and web development seeking to evaluate a given web application often have to rely on the existence of a model of the respective system, which is then used as input to task-specific tools. Such models may include information on HTTP endpoints and their parameters, available user actions/event listeners and required assets. Unfortunately, this data is often unavailable in practice, as only rigorous development practices or manual analysis guarantee their existence and correctness. Crawlers based on static analysis have traditionally been used to extract required information from existing sites. Regrettably, these tools can not accurately account for the dynamic behavior introduced by technologies such as JavaScript that are prevalent on modern sites. While methods based on dynamic analysis exist, they are often not fully capable of identifying event listeners and their effects. In an earlier work, we presented XIEv, an approach for dynamic analysis of web applications that produces an execution trace usable for the extraction of navigation graphs, identification of bugs at runtime and enumeration of resources. It offers improved recognition and selection of event listeners as well as a greater range of observed effects compared to existing approaches. While the evaluation of our research prototype implementation confirmed the capabilities of XIEv, it was generally out-performed by static crawlers in terms of speed. This work introduces CHIEv, an approach that augments XIEv by enabling concurrent processing as well as incorporating the results of a static crawler in real-time. Our results indicate a significant increase in performance, particularly when applied to larger sites.

Detailed black-box monitoring of distributed systems

Modern containerized distributed systems, such as big data storage and processing stacks or micro-service based applications, are inherently hard to monitor and optimize, as resource usage does not directly match hardware resources due to multiple virtualization layers. For instance, interapplication traffic is an important factor in as it directly indicates how components interact, it has not been possible to accurately monitor it in an application independent way and without severe overhead, thus putting it out of reach of cloud platforms. In this paper we present an efficient black-box monitoring approach for gathering detailed structural information of collaborating processes in a distributed system that can be queried for various purposes, as it includes both information about processes, containers, and hosts, as well as resource usage and amount of data exchanged. The key to achieving high detail and low overhead without custom application instrumentation is to use a kernel-aided event driven strategy. We validate a prototype implementation by applying it to multi-platform microservice deployments, evaluate its performance with micro-benchmarks, and demonstrate its usefulness for container placement in a distributed data storage and processing stack (i.e., Cassandra and Spark).

Improving exploratory information retrieval for neophytes

Digital libraries have become an essential tool for researchers in all scientific domains. With almost unlimited storage capacities, current digital libraries hold a tremendous number of documents. Though some efforts have been made to facilitate access to documents relevant to a specific information need, such a task remains a real challenge for a new researcher. Indeed neophytes do not necessarily use appropriate keywords to express their information need and they might not be qualified enough to evaluate correctly the relevance of documents retrieved by the system. In this study, we suppose that to better meet the needs of neophytes, the information retrieval system in a digital library should take into consideration features other than content-based relevance. To test this hypothesis, we use machine learning methods and build new features from several metadata related to documents. More precisely, we propose to consider as features for machine learning: content-based scores, scores based on the citation graph and scores based on metadata extracted from external resources. As acquiring such features is not a trivial task, we analyze their usefulness and their capacity to detect relevant documents. Our analysis concludes that the use of these additional features improves the performance of the system for a neophyte. In fact, by adding the new features we find more documents suitable for neophytes within the results returned by the system than when using content-based features alone.

What changes in where?

A deep understanding of the common patterns of bug-fixing changes is useful in several ways: (a) such knowledge can help developers in proactively avoiding coding patterns that lead to bugs and (b) bug-fixing patterns are exploited in devising techniques for automatic bug localization and program repair. This work includes an in-depth quantitative and qualitative analysis over 4,653 buggy revisions of five software systems. Our study identifies 38 bug-fixing edit patterns and discovers 37 new patterns of nested code structures, which frequently host the bug-fixing edits. While some of the edit patterns were reported in earlier studies, these nesting patterns are new and were never targeted before.