Direnc Pekaslan

As energy demands and costs rise, enhancing energy efficiency in Food and Drink Cold Storage (FDCS) rooms is important for reducing expenses and achieving environmental sustainability ambitions. Forecasting electricity use in FDCSs can help optimise operations and minimise energy consumption by enabling door opening frequency, maintenance, and restocking to be better scheduled. Although Machine Learning (ML) has been applied to forecast energy use in various domains such as commercial and residential buildings, its use in addressing the specific challenges of FDCS, which require stringent temperature and humidity control for food safety and quality, has been less explored. This work addresses this gap by proposing a tailored ML pipeline for FDCS settings capable of predicting one-week into the future and is suitable for small dataset sizes. It provides comparative analysis by employing two distinct real-world FDCS datasets for training, validation, and testing of the developed models. Moreover, in contrast to existing studies predominantly concerned with energy consumption prediction, this study includes the forecasting of indoor temperature and humidity, given their essential role in preserving the quality and longevity of stored food items. Ensemble-based methods, particularly Random Forest, excelled and achieved the lowest electricity MAEs of 150.65 and 384.88 for each dataset, respectively.

Deep learning models have achieved high performance in numerous semantic segmentation tasks. However, when the input data at test time do not resemble the training data, deep learning models can not handle them properly and will probably produce poor results. Therefore, it is important to design algorithms for deep learning models to reliably detect out-of-distribution (OOD) data. In this paper, we propose a novel fuzzy-uncertainty-based method to detect OOD samples for semantic segmentation. Firstly, to capture both data and model uncertainties, test-time augmentation and Monte Carlo dropout are applied to a ready-trained image segmentation model for generating multiple predicted instances of a given test image. Then interval fuzzy sets are generated from these multiple predictions to describe the captured uncertainty via distance transform operators. Finally, an image-level uncertainty score, which is calculated from the generated interval fuzzy sets, is used to indicate if it is an OOD sample. Experiments on testing three OOD test sets on a skin lesion segmentation model show that our proposed method achieved significantly higher classification accuracy in detecting OOD samples than three other state-of-the-art uncertainty-based algorithms.

Fuzzy Logic Systems can provide a good level of interpretability and may provide a key building block as part of a growing interest in explainable AI. In practice, the level of interpretability of a given fuzzy logic system is dependent on how well its key components, namely, its rule base and its antecedent and consequent fuzzy sets are understood. The latter poses an interesting problem from an optimisation point of view – if we apply optimisation techniques to optimise the parameters of the fuzzy logic system, we may achieve better performance (e.g. prediction), however at the cost of poorer interpretability. In this paper, we build on recent work in non-singleton fuzzification which is designed to model noise and uncertainty ‘where it arises’, limiting any optimisation impact to the fuzzification stage. We explore the potential of such systems to deliver good performance in varying-noise environments by contrasting one example framework - ADONiS, with ANFIS, a traditional optimisation approach designed to tune all fuzzy sets. Within the context of time series prediction, we contrast the behaviour and performance of both approaches with a view to inform future research aimed at developing fuzzy logic systems designed to deliver both – high performance and high interpretability.

Social media (SM) can be an invaluable resource in terms of understanding and managing the effects of catastrophic disasters. In order to use SM platforms for public participatory (PP) mapping of emergency management activities, a bias investigation should be undertaken with regard to the data related to the study area (urban, regional or national, etc.) to determine the spatial data dynamics. Thus, such determinations can be made on how SM can be used and interpreted in terms of PP. In this study, the city of Istanbul was chosen for social media data research area, as it is one of the most crowded cities in the world and expecting a major earthquake. The methodology for the data investigation is: 1. Obtain data and engage sampling, 2. Identify the representation and temporal biases in the data and normalize it in response to representation bias, 3. Identify general anomalies and spatial anomalies, 4. Manipulate the trend of the dataset with the discretization of anomalies and 5. Examine the spatiotemporal bias. Using this bias investigation methodology, citizen footprint dynamics in the city were determined and reference maps (most likely regional anomaly maps, representation maps, time-space bias maps, etc.) were produced. The outcomes of the study can be summarized in four steps. First, highly active users generate the majority of the data and removing this data as a general approach within a pseudo-cleaning process means concealing a large amount of data. Second, data normalization in terms of activity levels, changes the anomaly outcome resulting from diverse representation levels of users. Third, spatiotemporally normalized data present strong spatial anomaly tendency in some parts of the central area. Fourth, trend data is dense in the central area and the spatiotemporal bias assessments show the data density varies in terms of the time of day, day of week and season of the year. The methodology proposed in this study can be used to extract the unbiased daily routines of the social media data of the regions for the normal days and this can be referred for the emergency or unexpected event cases to detect the change or impacts.

Non-Singleton Fuzzy Logic Systems (NSFLSs) have the potential to capture and handle input noise within the design of input fuzzy sets. In this paper, we propose an online learning method which utilises a sequence of observations to continuously update the input Fuzzy Sets (FSs) of an NSFLS, thus providing an improved capacity to deal with variations in the level of input-affecting noise, common in real-world applications. The method removes the requirement for both a priori knowledge of noise levels or relying on offline training procedures to define input FS parameters. To the best of our knowledge, the proposed ADaptive, ONline Non-Singleton (ADONiS) Fuzzy Logic System (FLS) framework represents the first end-to-end framework to adaptively configure non-singleton input FSs. The latter is achieved through online uncertainty detection applied to a sliding window of observations. Since real-world environments are influenced by a broad range of noise sources, which can vary greatly in magnitude over time, the proposed technique for combining online determination of noise levels with associated adaptation of input FSs provides an efficient and effective solution which elegantly models input uncertainty in the FLS's input FSs, without requiring changes in any other part (e.g. antecedents, rules or consequents) of the FLS. In this paper, two common chaotic time series (Mackey-Glass, Lorenz) are used to perform prediction experiments to demonstrate and evaluate the proposed framework. Results indicate that the proposed adaptive NSFLS framework provides significant advantages, particularly in environments that include high variation in noise levels, which are common in real-world applications.