Across the natural and life sciences, images have become a primary measurement modality, yet the dominant analytic paradigm remains semantics-first. Structure is recovered by predicting or enforcing domain-specific labels. This paradigm fails systematically under the conditions that make image-based science most valuable, including open-ended scientific discovery, cross-sensor and cross-site comparability, and long-term monitoring in which domain ontologies and associated label sets drift culturally, institutionally, and ecologically. A deductive inversion is proposed in the form of criteria-first and semantics-later. A unified framework for criteria-first structure discovery is introduced. It separates criterion-defined, semantics-free structure extraction from downstream semantic mapping into domain ontologies or vocabularies and provides a domain-general scaffold for reproducible analysis across image-based sciences. Reproducible science requires that the first analytic layer perform criterion-driven, semantics-free structure discovery, yielding stable partitions, structural fields, or hierarchies defined by explicit optimality criteria rather than local domain ontologies. Semantics is not discarded; it is relocated downstream as an explicit mapping from the discovered structural product to a domain ontology or vocabulary, enabling plural interpretations and explicit crosswalks without rewriting upstream extraction. Grounded in cybernetics, observation-as-distinction, and information theory's separation of information from meaning, the argument is supported by cross-domain evidence showing that criteria-first components recur whenever labels do not scale. Finally, consequences are outlined for validation beyond class accuracy and for treating structural products as FAIR, AI-ready digital objects for long-term monitoring and digital twins.
Restoring precise muscular control in the poststroke wrist/hand (W/H) demands sensorimotor integration to correct compensatory neuroplasticity. However, current rehabilitation robots inadequately modulate ascending somatosensory pathways from specific muscles. This study developed an electromyography (EMG)-driven soft robot with electro-vibro-feedback (EVF-robot) for targeted somatosensory priming in W/H muscles. This system integrates (a) focal vibratory stimulation and neuromuscular electrical stimulation for recruiting the somatosensory pathways of the targeted W/H flexors and extensors; (b) an EMG-driven control algorithm for strengthening the voluntary motor control of a driving muscle; and (c) robot assistance to achieve coordinated joint extension and flexion. In a single-arm trial with 20 sessions, 15 chronic stroke participants assisted by the system achieved significant improvements in voluntary W/H behavioral control, somatosensory feedback, and intermuscular coordination in the paretic upper limb (P < 0.05). During their W/H extension, the cortical peaks of corticomuscular coherence shifted contralaterally for W/H extensors, and the ascending corticomuscular coherence from W/H flexors increased (P < 0.05). These improvements persisted at the 3-month follow-up. The findings provide preliminary evidence that sensorimotor integration training with the EMG-driven EVF-robot may modulate compensatory neuroplasticity and facilitate improvements in coordinated motor control of the distal joints in individuals with chronic stroke.
Miguel Lloret-Climent, Andrés Montoyo-Guijarro, Yoan Gutierrez-Vázquez
et al.
Purpose - The purpose of this paper is to propose a mathematical model to determine invariant sets, set covering, orbits and, in particular, attractors in the set of tourism variables. Analysis was carried out based on an algorithm and applying an interpretation of chaos theory developed in the context of General Systems Theory and Big Data. Design/methodology/approach - Tourism is one of the most digitalized sectors of the economy, and social networks are an important source of data for information gathering. However, the high levels of redundant information on the Web and the appearance of contradictory opinions and facts produce undesirable effects that must be cross-checked against real data. This paper sets out the causal relationships associated with tourist flows to enable the formulation of appropriate strategies. Findings - The results can be applied to numerous cases, for example, in the analysis of tourist flows, these findings can be used to determine whether the behaviour of certain groups affects that of other groups, as well as analysing tourist behaviour in terms of the most relevant variables. Originality/value - The technique presented here breaks with the usual treatment of the tourism topics. Unlike statistical analyses that merely provide information on current data, the authors use orbit analysis to forecast, if attractors are found, the behaviour of tourist variables in the immediate future.
Shubhankar Kapoor, Adrian G. Wills, Johannes Hendriks
et al.
Grid models, including line impedances, are crucial for the active management and operation of the distribution grid (DG). This paper introduces a novel approach for estimating DG line parameters using available voltage magnitude and node powers from smart meters (SMs), specifically addressing scenarios with missing measurements. We propose an expectation–maximization (EM) based approach and validate the results on an IEEE 37-node network, achieving accurate estimates for line parameters, voltage magnitude, and active/reactive power at nodes. The method is tested with varying levels of missing measurements and noise. Two cases of missing measurements are considered: random and specific node-based. The latter case is used to infer the optimal placement of measurement devices. Additionally, the proposed method is validated on simulated data and real-world consumer loads, consistently providing accurate results.
Production of electric energy or power. Powerplants. Central stations
Putu Sugiartawan, Ni Wayan Wardani, Anak Agung Surya Pradhana
et al.
This research explores the application of Support Vector Machines (SVM) for accurately classifying diabetes risk levels based on a publicly available dataset containing 768 instances and 9 attributes, including glucose levels, BMI, blood pressure, and insulin levels. The model's systematic development process involved data preprocessing, feature selection, and hyperparameter optimization to ensure robust performance. Results indicate an overall accuracy of 76%, with high precision and recall for the non-diabetic risk class, but relatively lower performance for the diabetic risk class, highlighting the challenges posed by class imbalance and overlapping data features. To address these issues, future research should incorporate advanced resampling techniques, refined feature engineering, and alternative machine learning models like Random Forest or XGBoost. This research underscores the potential of SVM as a valuable tool for early diabetes detection, offering healthcare professionals a reliable means to identify at-risk individuals and personalize intervention strategies. By bridging theoretical advancements and practical applications, the research contributes to enhancing predictive analytics in medical diagnostics, paving the way for improved patient outcomes and efficient public health management
Oladipo A. Madamidola, Felix Ngobigha, Adnane Ez-zizi
Machine learning has been successfully applied in developing malware detection systems, with a primary focus on accuracy, and increasing attention to reducing computational overhead and improving model interpretability. However, an important question remains underexplored: How well can machine learning-based models detect entirely new forms of malware not present in the training data? In this study, we present a machine learning-based system for detecting obfuscated malware that is not only highly accurate, lightweight and interpretable, but also capable of successfully adapting to new types of malware attacks. Our system is capable of detecting 15 malware subtypes despite being exclusively trained on one malware subtype, namely the Transponder from the Spyware family. This system was built after training 15 distinct random forest-based models, each on a different malware subtype from the CIC-MalMem-2022 dataset. These models were evaluated against the entire range of malware subtypes, including all unseen malware subtypes. To maintain the system's streamlined nature, training was confined to the top five most important features, which also enhanced interpretability. The Transponder-focused model exhibited high accuracy, exceeding 99.8%, with an average processing speed of 5.7 µs per file. We also illustrate how the Shapley additive explanations technique can facilitate the interpretation of the model predictions. Our research contributes to advancing malware detection methodologies, pioneering the feasibility of detecting obfuscated malware by exclusively training a model on a single or a few carefully selected malware subtype and applying it to detect unseen subtypes.
Ensemble learning has proven effective in improving predictive performance and estimating uncertainty in neural networks. However, conventional ensemble methods often suffer from redundant parameter usage and computational inefficiencies due to entirely independent network training. To address these challenges, we propose the Divergent Ensemble Network (DEN), a novel architecture that combines shared representation learning with independent branching. DEN employs a shared input layer to capture common features across all branches, followed by divergent, independently trainable layers that form an ensemble. This shared-to-branching structure reduces parameter redundancy while maintaining ensemble diversity, enabling efficient and scalable learning.
Due to their large size, generative Large Language Models (LLMs) require significant computing and storage resources. This paper introduces a new post-training quantization method, GPTQT, to reduce memory usage and enhance processing speed by expressing the weight of LLM in 3bit/2bit. Practice has shown that minimizing the quantization error of weights is ineffective, leading to overfitting. Therefore, GPTQT employs a progressive two-step approach: initially quantizing weights using Linear quantization to a relatively high bit, followed by converting obtained int weight to lower bit binary coding. A re-explore strategy is proposed to optimize initial scaling factor. During inference, these steps are merged into pure binary coding, enabling efficient computation. Testing across various models and datasets confirms GPTQT's effectiveness. Compared to the strong 3-bit quantization baseline, GPTQT further reduces perplexity by 4.01 on opt-66B and increases speed by 1.24 times on opt-30b. The results on Llama2 show that GPTQT is currently the best binary coding quantization method for such kind of LLMs.
This paper, dealing with the Greek-Roman theatres, aims to focus on four main issues: 1) the origin and the evolution of the theatre and its social role within the Mediterranean area (Milizia); 2) the importance of the Greek and Roman cultures, which, while conquering new lands, spread their culture, too (Mazzarino); 3) how theatres evolved under the Greeks, and under the Roman Empire (Neppi Modona), and 4) to prove that war, not only destroys people, but, moreover, destroys the entire world. Piro considers war any behavior that tries to subdue people by negating their rights, their religion, and their culture. [1] The fusion of the Greek and Roman cultures left their signs whenever and wherever they arrived. The Greek-Roman theatres are an example of the importance of fusing cultures; a fusion which enriches both the people conquered and the people conquering. While talking about drama, as the expression of social aggregation, Milizia writes: "The Greeks and the Romans are the only people who really knew the very spirit of society." [2] In order to follow its aim, this research wants to give a quick look at the first inhabitants of the Mediterranean coast, so as to understand how trade helped them to share both goods and culture. History is a very important subject, not simply for acquiring information, but, moreover, for getting new experiences from past events. We say that grandparents are a great resource, because they provide children with advice which can help them when something new has to be solved. This is also the role of history, to judge the results of people's behaviour when facing political problems. For this reason, talking about the peoples who lived around the Mediterranean Sea, admiring their archaeological sites, and studying the history of their age will facilitate the understanding of the context in which those peoples lived and had to make important decisions. In so doing, it will be easier to judge the results of their actions, and acquire experience from them. In brief, even though war had at first appeared a means to solve problems related to wellness, patriotism, motherland, goods exchange, religion, language, etc., at last, the great conquerors of the past understood that cooperation among peoples is the best way to achieve prosperity both economically and culturally. Nowadays, we are surrounded by wars in every angle of the world, as if it were the first time that a country refuses to share a land, or refuses to accept foreigners, or complains about either a political or religious creed. So that, during this journey of mine, among the mediterranean peoples of the past, I learned a great lesson; a lesson I hope to transfer to you; a lesson I could understand while admiring the archaeological remains left all around the Mediterranean Sea. So, while looking at them, I realized that those wonders are the result of cooperation and not of hate among peoples of different language, religion and culture; peoples, who at last, understood that war, as Pope Francesco says, is a defeat for everybody. "With war, a senseless and inconclusive venture, no one emerges a winner; everyone ends up defeated, because war, right from the beginning, is already a defeat, always. Let us listen to those who suffer its consequences, the victims and those who have lost everything. Let us hear the cry of the young, of ordinary individuals and peoples, who are weary of the rhetoric of war and the empty slogans that constantly put the blame on others, dividing the world into good and evil, weary of leaders who find it difficult to sit at a table, negotiate and find solutions." [3]
Khalid M. Hosny, Nada AbdElFattah Ibrahim, Ehab R. Mohamed
et al.
The COVID-19 virus is causing a global pandemic. The total number of new coronavirus cases worldwide by the end of November 2020 had already surpassed 60 million. The World Health Organization (WHO) has determined that wearing masks is a crucial precaution during the COVID-19 epidemic to limit the growth of viruses, and facemasks are frequently seen in public places worldwide. Also, many public service providers wear face masks (covering their mouths and noses). These events brought attention to the need for automatic computer-vision-based object detection (masked face detection) methods to track public behavior. Therefore, it is necessary to develop tools for monitor people who have not used masks in public service areas in real-time. Reducing the spread of infectious diseases can occur when masked face detection techniques are used for authentication instead of mask removal for face matching. A superior framework of masked face detection could improve security systems and lower the rate of crime. Masked face detection is a computer vision method standard in people's daily lives to recognize, discover, and recognize masked faces in pictures and videos. This study provides a thorough and systematic analysis of masked face detection algorithms. With the help of examples, we have thoroughly examined and reviewed the studies done concerning face mask identification and techniques for masked face detection.Additionally, we compared and explained different masked face detection dataset types, libraries, and techniques. We also discussed the challenges with masked face detection and whether the researchers could overcome them. We have discussed and conducted a thorough evaluation of the accuracy, pros, and cons of various approaches by comparing their performance on multiple datasets. As a result, this study aims to give the researcher a broader viewpoint to aid him in finding patterns and trends in masked face detection in various COVID-19 contexts, overcoming challenges that are still present, and creating future algorithms for masked face detection that are more reliable and accurate.
Dominika Prajzlerová, Vojtěch Barták, Petr Keil
et al.
To identify areas of high biodiversity and prioritize conservation efforts, it is crucial to understand the drivers of species richness patterns and their scale dependence. While classified land cover products are commonly used to explain bird species richness, recent studies suggest that unclassified remote-sensed images can provide equally good or better results. In our study, we aimed to investigate whether unclassified multispectral data from Landsat 8 can replace image classification for bird diversity modeling. Moreover, we also tested the Spectral Variability Hypothesis.Using the Atlas of Breeding Birds in the Czech Republic 2014-2017, we modeled species richness at two spatial resolutions of approx. 131 km2 (large squares) and 8 km2 (small squares). As predictors of the richness, we assessed 1) classified land cover data (Corine Land Cover 2018 database), 2) spectral heterogeneity (computed in three ways) and landscape composition derived from unclassified remote-sensed reflectance and vegetation indices. Furthermore, we integrated information about the landscape types (expressed by the most prevalent land cover class) into models based on unclassified remote-sensed data to investigate whether the landscape type plays a role in explaining bird species richness.We found that unclassified remote-sensed data, particularly spectral heterogeneity metrics, were better predictors of bird species richness than classified land cover data. The best results were achieved by models that included interactions between the unclassified data and landscape types, indicating that relationships between bird diversity and spectral heterogeneity vary across landscape types.Our findings demonstrate that spectral heterogeneity derived from unclassified multispectral data is effective for assessing bird diversity across the Czech Republic. When explaining bird species richness, it is important to account for the type of landscape and carefully consider the significance of the chosen spatial scale.
Sausar Karaf, Aleksey Fedoseev, Mikhail Martynov
et al.
This paper focuses on a novel robotic system MorphoLander representing heterogeneous swarm of drones for exploring rough terrain environments. The morphogenetic leader drone is capable of landing on uneven terrain, traversing it, and maintaining horizontal position to deploy smaller drones for extensive area exploration. After completing their tasks, these drones return and land back on the landing pads of MorphoGear. The reinforcement learning algorithm was developed for a precise landing of drones on the leader robot that either remains static during their mission or relocates to the new position. Several experiments were conducted to evaluate the performance of the developed landing algorithm under both even and uneven terrain conditions. The experiments revealed that the proposed system results in high landing accuracy of 0.5 cm when landing on the leader drone under even terrain conditions and 2.35 cm under uneven terrain conditions. MorphoLander has the potential to significantly enhance the efficiency of the industrial inspections, seismic surveys, and rescue missions in highly cluttered and unstructured environments.
Shadows in scanned documents pose significant challenges for document analysis and recognition tasks due to their negative impact on visual quality and readability. Current shadow removal techniques, including traditional methods and deep learning approaches, face limitations in handling varying shadow intensities and preserving document details. To address these issues, we propose DocDeshadower, a novel multi-frequency Transformer-based model built upon the Laplacian Pyramid. By decomposing the shadow image into multiple frequency bands and employing two critical modules: the Attention-Aggregation Network for low-frequency shadow removal and the Gated Multi-scale Fusion Transformer for global refinement. DocDeshadower effectively removes shadows at different scales while preserving document content. Extensive experiments demonstrate DocDeshadower's superior performance compared to state-of-the-art methods, highlighting its potential to significantly improve document shadow removal techniques. The code is available at https://github.com/leiyingtie/DocDeshadower.
We propose a method of analysis of spontaneous emission of a quantum emitter (an atom, a luminescence center, a quantum dot) inside or in vicinity of a cylinder. At the focus of our method are analytical expressions for the scattering matrix of the cylindrical nanoobject. We propose the approach to electromagnetic field quantization based of eigenvalues and eigenvectors of the scattering matrix. The method is applicable for calculation and analysis of spontaneous emission rates and angular dependences of radiation for a set of different systems: semiconductor nanowires with quantum dots, plasmonic nanowires, cylindrical hollows in dielectrics and metals. Relative simplicity of the method allows obtaining analytical and semi-analytical expressions for both cases of radiation into external medium and into guided modes.
Throughout the years neural networks have been based on the perceptron model of the artificial neuron. Attempts to stray from it are few to none. The perceptron simply works and that has discouraged research around other neuron models. New discoveries highlight the importance of dendrites in the neuron, but the perceptron model does not include them. This brings us to the goal of the paper which is to present and test different models of artificial neurons that utilize dendrites to create an artificial neuron that better represents the biological neuron. The authors propose two models. One is made with the purpose of testing the idea of the dendritic neuron. The distinguishing feature of the second model is that it implements activation functions after its dendrites. Results from the second model suggest that it performs as well as or even better than the perceptron model.
Taraf Al Nuaimi, Salama Al Zaabi, Mansor Alyilieli
et al.
We propose and evaluate a data-driven intrusion detection system (IDS) for the Internet of Things (IoT) and Industrial IoT (IIoT) environments using the Edge-IIoT-2022 dataset. We model the IDS problem as a classification problem and learn the classifier via supervised learning algorithms. Our main contribution is an empirical analysis and evaluation of the Edge-IIoT-2022 dataset, which is a recent dataset compiled for developing IDSs in IoT and IIoT environments. We develop several IDSs from standard data analytics algorithms and evaluate their performance on Edge-IIoT-2022. We compare our IDSs with prior arts and demonstrate that highly accurate binary-class IDSs can be built via Edge-IIoT-2022, whereas multi-class IDSs would require careful treatment.
Yutaka Momma, Weimin Wang, Edgar Simo-Serra
et al.
We present a lightweight post-processing method to refine the semantic segmentation results of point cloud sequences. Most existing methods usually segment frame by frame and encounter the inherent ambiguity of the problem: based on a measurement in a single frame, labels are sometimes difficult to predict even for humans. To remedy this problem, we propose to explicitly train a network to refine these results predicted by an existing segmentation method. The network, which we call the P2Net, learns the consistency constraints between coincident points from consecutive frames after registration. We evaluate the proposed post-processing method both qualitatively and quantitatively on the SemanticKITTI dataset that consists of real outdoor scenes. The effectiveness of the proposed method is validated by comparing the results predicted by two representative networks with and without the refinement by the post-processing network. Specifically, qualitative visualization validates the key idea that labels of the points that are difficult to predict can be corrected with P2Net. Quantitatively, overall mIoU is improved from 10.5% to 11.7% for PointNet [1] and from 10.8% to 15.9% for PointNet++ [2].
Domagoj Majstorovic, Simon Hoffmann, Florian Pfab
et al.
In parallel with the advancement of Automated Driving (AD) functions, teleoperation has grown in popularity over recent years. By enabling remote operation of automated vehicles, teleoperation can be established as a reliable fallback solution for operational design domain limits and edge cases of AD functions. Over the years, a variety of different teleoperation concepts as to how a human operator can remotely support or substitute an AD function have been proposed in the literature. This paper presents the results of a literature survey on teleoperation concepts for road vehicles. Furthermore, due to the increasing interest within the industry, insights on patents and overall company activities in the field of teleoperation are presented.
Driverless road maintenance could potentially be highly beneficial to all its stakeholders, with the key goals being increased safety for all road participants, more efficient traffic management, and reduced road maintenance costs such that the standard of the road infrastructure is sufficient for it to be used in Automated Driving (AD). This paper addresses how the current state of technology could be expanded to reach those goals. Within the project 'System for Teleoperated Road-marking' (SToRM), using the road-marking machine as the system, different operation modes based on teleoperation were discussed and developed. Furthermore, a functional system overview considering both hardware and software elements was experimentally validated with an actual road-marking machine and should serve as a baseline for future efforts in this and similar areas.