Utilizing low-resolution images for computer vision tasks such as classification and segmentation can sometimes hinder the model’s ability to accurately learn essential features. While using high-resolution images and designing compatible models might seem like viable solutions, they are not always feasible due to energy efficiency and graphical computation constraints. Downsizing images for model training and application is an effective approach for improving computational efficiency and optimizing model performance.The bilinear resizing method, commonly employed for this purpose, inherently causes information loss due to its numerical approach, which relies solely on the four nearest pixel values to compute each target pixel. This limitation becomes more pronounced with high-resolution images, where the down sampling process intensifies the loss of critical information. However, recent advancements have introduced adaptive resizer modules, which dynamically adjust image dimensions to better preserve essential features before processing by deep learning models. In this study, an adaptive resizer-based segmentation framework is proposed for the gland segmentation task, which is crucial for accurate disease diagnosis, particularly in cancer analysis. Three distinct encoder-decoder architecture segmentation models are assessed for image segmentation using the Colorectal Adenocarcinoma Gland (CRAG) gland segmentation database. Each architecture was tested separately, employing six different backbone encoders that were pretrained on the ImageNet dataset. The comparative analysis showed that the adaptive resizer improved segmentation performance, increasing the Intersection over Union (IoU) metric by an average of 5.6 https://github.com/miralab-ai/adaptive-resizer-segmentation .

In this study, we performed a mechanistic study to understand how the sugar ligand chemistry affected the morphology, size and surface chemistry of Ag/AgCl_NPs synthesized in the presence of L-Arginine hydrochloride and L-Arginine/KCl mixture. The sugar ligands Lactose p-methoxyaniline (LMA) and Galactose 5-aminosalicylic acid (G5AS) resulted in formation of sheet-like Ag/AgCl_NPs while Lactose sulfanilic acid (LSA) and Lactose psulfonyldianiline (LPSA) caused the formation of anisotropic and film-like Ag/AgCl_NPs. The UV-Vis based mechanistic studies showed that the presence of Arginine posed a strong effect on how G5AS and LMA ligands interact with silver ions while the effect was more complicated for the LSA and LPSA ligands due to the fact that they form complexation with Ag+ ions. The mechanism was further investigated using infrared (IR) studies that showed the increases in Argine and chloride ion concentrations resulted in differentiation of the surface chemistry of the Ag/AgCl_NPs, and appearance of Arginine related IR bands became clearer in the case of cointroduction of Arginine and the sugar ligands. The characterized nanoparticles were then used as antibacterial agent for multidrug resistant Escherichia coli species for which less than 10 mu M minimum inhibitory concentrations were obtained. The promising antibacterial activity, which could be assigned to the presence of Arginine, was independent from the sugar ligand chemistry and nanoparticles' morphology and size. Particularly, large Ag/AgCl_NP film forming capacity can call further research to be exploited as coating materials for antibacterial application.

Recent breakthroughs in generative image models, especially those based on diffusion techniques, have radically transformed the landscape of text-guided image synthesis by delivering exceptional fidelity and detailed semantic control. In this study, we present an iterative editing framework that harnesses the inherent strengths of these generative models to progressively refine images with precision. Our approach begins by generating diverse textual descriptions from an initial image, from which the most effective prompt is selected to drive further refinement through a fine-tuned Stable Diffusion process. This pipeline, as detailed in our flow diagram, orchestrates a series of controlled image modifications that preserve the original context while accommodating deliberate stylistic and semantic adjustments. By cycling the augmented output back into the system, our method achieves a harmonious balance between innovation and consistency, paving the way for highquality, context-aware visual transformations. This dynamic, auto-regressive strategy underscores the transformative potential of modern image generation models for applications that require detailed, controlled creative expression. The code is available on Github.

Amino acids are not just monomers of proteins, but they can also carry biological functions. L-cysteine (Cys), L-proline (Pro), L-asparagine (Asn), and L-glutamic acid (Glu) were used to evaluate how different amino acid chemistries alter the morphology and size of the silver nanoparticles (AgNPs) synthesized in the presence of two carbohydrate ligands, which were lactose methoxyaniline (LMA) and galactose 5-aminosalicylic acid (G5AS). UV–vis, infrared (IR), High-Resolution Transmission Electron Microscopy (HR-TEM) and X-ray diffraction (XRD) characterizations revealed that the effect of amino acids on the characteristics of the AgNPs showed dependence on the carbohydrate ligand chemistry. In the case of LMA, AgNPs shifted from aggregates to anisotropic nanoparticles, larger aggregates, and a mixture of anisotropic and 1D nanoparticles in the presence of Cys, Glu, Asn and Pro amino acids, respectively. In contrast to this, the introduction of Cys and Asn caused the formation of cluster-like AgNPs and larger rounded nanoparticles, while G5AS-synthesized AgNPs were multigonal 0D particles. Moreover, Glu and Pro contributed the resistance of silver oxide formation on the particles. Antibacterial characterization showed that LMA_Glu_AgNPs were the most effective ones, while LMA_Cys_AgNPs and G5AS_Cys_AgNPs, which were the smallest AgNPs, did not show any significant antibacterial activity.

Deep learning models, integral components of contemporary technological landscapes, exhibit enhanced learning capabilities with larger datasets. Traditional data augmentation techniques, while effective in generating new data, have limitations, especially in fields like ocular disease diagnosis. In response, alternative augmentation approaches, including the utilization of generative AI, have emerged. In our study, we employed a diffusion-based model (Stable Diffusion) to synthesize data by faithfully recreating crucial vascular structures in the retina, vital for detecting eye diseases by using the Ocular Disease Intelligent Recognition dataset. Our goal was to augment retinography images for ocular disease diagnosis using diffusion-based models, optimizing the outputs of the fine-tuned Stable Diffusion model, and ensuring the generated data closely resembles real-world scenarios. This strategic approach resulted in improved performance in classification models and augmentation outperformed traditional methods, exhibiting high precision rates ranging from 85 https://github.com/miralab-ai/generative-data-augmentation .

This work presents an investigation into the domain of dynamic target tracking through object detection, particularly emphasizing the context of open-source applications like PX4, ROS, and YOLO. Over the years, achieving real-time object tracking on UAVs in dynamic environments has been a formidable challenge, necessitating offline computations or substantial onboard processing resources. However, contemporary UAVs are now equipped with advanced edge embedded devices, sensors, and cameras, enabling the integration of deep learning-based vision applications. This advancement offers the prospect of directly deploying cutting-edge applications onto UAVs, thereby expanding their utility in areas such as surveillance, search and rescue, and videography. To fully harness the potential of these vision applications, a communication infrastructure interfacing with the UAV's underneath closed controllers becomes imperative. We've developed an integrated visual target-tracking system that connects a flight controller unit with a graphical unit by leveraging ROS tools and open-source deep learning packages. The overall integrated system based on ROS, deep learning applications, and custom PID controllers is shared on GitHub as open-source software package in a way that benefits everyone interested: https://github.com/miralab-ai/vision-ROS.

Fungi play a pivotal role in our ecosystem and human health, serving as both essential contributors to environmental sustainability and significant agents of disease. The importance of precise fungi detection cannot be overstated, as it underpins effective disease management, agricultural productivity, and the safeguarding of global food security. This research explores the efficacy of vision transformer-based architectures for the classification of microscopic fungi images of various fungal types to enhance the detection of fungal infections. The study compared the pre-trained base Vision Transformer (ViT) and Swin Transformer models, evaluating their capability in feature extraction and fine-tuning. The incorporation of transfer learning and fine-tuning strategies, particularly with data augmentation, significantly enhances model performance. Utilizing a comprehensive dataset with and without data augmentation, the study reveals that Swin Transformer, particularly when fine-tuned, exhibits superior accuracy (98.36%) over ViT model (96.55%). These findings highlight the potential of vision transformer-based models in automating and refining the diagnosis of fungal infections, promising significant advancements in medical imaging analysis.

Chain of Thought (CoT) was introduced in recent research as a method for improving step-by-step reasoning in Large Language Models. However, CoT has limited applications such as its need for hand-crafted few-shot exemplar prompts and no capability to adjust itself to different queries. In this work, we propose a system to automatically generate rationales using CoT. Our method improves multi-step implicit reasoning capabilities by decomposing the implicit query into several explicit questions. This provides interpretability for the model, improving reasoning in weaker LLMs. We test our approach with two Q&A datasets: StrategyQA and HotpotQA. We show an increase in accuracy with both, especially on StrategyQA. To facilitate further research in this field, the complete source code for this study has been made publicly available on GitHub: https://github.com/miralab-ai/autoreason.

Department between Nov. 10-12, 2023 in Famagusta, TRNC with international participation.In our congress, users, manufacturers, researchers, managers and public representatives working in the field of medical technologies were brought together, scientific research results in the fields of biomedical engineering and clinical engineering were shared and common solutions to the problems experienced in the sector were discussed.As in the TIPTEKNO congresses, which were held with great success in previous years, panels were held on current issues and problems in the development, production, use and management of medical technologies, besides invited speeches by competent scientists in their fields, educational seminars were given and original scientific papers were presented.

Circuit simulators are complex tools that depend highly on modeling of electrical circuit components. Therefore, employing an open-source circuit simulator within individuals’ learning processes of electronics can be beneficial, as in both a stronger grasp of circuit component as well as circuit theory, and deeper understanding of software development. This paper demonstrates the development of an analogous circuit simulator of passive electrical components, aiming to provide a useful and open-source tool that can be used as a study project or be expanded by being further developed for practice purposes. In order to validate the correctness of the outputs of the terminal-based simulator, the simulation results of an exemplary circuit of the terminal-based simulator were compared to the simulation results of LTSpice for the same circuit.

Blockchain technology, employing advanced cryptography, stands as an optimal means to establish trust among unfamiliar online counterparts. It facilitates secure transactions and consensus among participants. Ethereum, a prominent blockchain network, extends this utility by introducing smart contracts. These are predefined programs containing data and methods for execution. Once deployed, these contracts remain unalterable due to blockchain’s immutable nature. However, unlike conventional software that can be readily patched, they may harbor vulnerabilities. Smart contracts operate with the Ethereum cryptocurrency Ether, rendering fixes intricate and economically impactful. Static analyzers exist to spot vulnerabilities in smart contacts during development, but they are time-intensive. We propose a machine learning-based approach for detecting reentrancy vulnerabilities in smart contracts. Our system comprises three components: data preparation, Op2Vec, and an LSTM model. We collected 30,000 smart contracts, dividing them into two sets of 15,000 each for Op2Vec generation and LSTM training, respectively. We mapped opcode keywords to vector representations using a Skip-Gram algorithm, resulting in a 100-dimensional dictionary with 72 unique opcodes. Labeling was done using the Slither static analyzer, with 116 contracts identified as vulnerable and an additional 132 clean contracts for dataset balance. A Bidirectional LSTM (Bi-LSTM) model was devised by employing assembly data to detect flaws. The developed Bi-LSTM model demonstrated promise in reentrancy vulnerability detection, achieving a 96% accuracy rate in testing and reducing the analysis time to less than a fifth of that required by static analyzers. The codes and data are shared on GitHub as an open-source software package in a way that benefits everyone interested: https://github.com/miralabai/blockchain-vulnerability-detection.

Circulatory system abnormalities might be an indicator of diseases or tissue damage. Early detection of vascular abnormalities might have an important role during treatment and also raise the patient's awareness. Current detection methods for vascular imaging are high-cost, invasive, and mostly radiation-based. In this study, a low-cost and portable microcomputer-based tool has been developed as a Near-Infrared (NIR) superficial vascular imaging device. The device uses NIR Light-Emitting Diode (LED) light at 850 nm along with other electronic and optical components. It operates as a non-contact and safe infrared (IR) imaging method in real-time. Image and video analysis are carried out using OpenCV (Open-Source Computer Vision), a library of programming functions mainly used in computer vision. Various tests were carried out to optimize the imaging system and set up a suitable external environment. To test the performance of the device, the images taken from three diabetic volunteers, who are expected to have abnormalities in the vascular structure due to the possibility of deformation caused by high glucose levels in the blood, were compared with the images taken from two non-diabetic volunteers. As a result, tortuosity was observed successfully in the superficial vascular structures, where the results need to be interpreted by the medical experts in the field to understand the underlying reasons. Although this study is an engineering study and does not have an intention to diagnose any diseases, the developed system here might assist healthcare personnel in early diagnosis and treatment follow-up for vascular structures and may enable further opportunities.

Robotic arms are widely prevalent and find utility in a variety of applications. However, a significant and widespread challenge faced by these arms is their inability to replicate the intricate functionalities of a human hand, primarily due to the distinct structure of the hand. The primary objective of this work is to create a simulation of a robotic arm that can replicate the movements and functions of a human hand in real-time. Data obtained from hand and arm gestures created with Mediapipe will be transferred in real-time to the robotic arm that is visualized and simulated on ROS and Gazebo. Thus, the hand and arm movements of the user in front of the camera will be effective in real-time on the manipulable joints. This advancement holds the potential to facilitate the construction of a robot capable of emulating both the hand and the arm of humans with high fidelity, thereby enabling comprehensive control over the robotic arm’s actions in real-time.

Surface functionalized nanostructures have outstanding potential in biological applications owing to their target -specific design. In this study, we utilized laboratory synthesized carbohydrate-derivatives (i.e., galactose, mannose, lactose, and cellobiose derivatives) for aqueous one-pot synthesis of gold (Au) and silver (Ag) nano -structure glycoconjugates (NSs), and iron metal-organic framework glycoconjugates (FeMOFs). This work aims to test whether differences in the surface chemistry of the inorganic nanostructures play roles in revealing their toxicities towards bacterial cells and cancerous cell lines. As of the first step, biological activity of AuNSs, AgNSs, and FeMOFs were tested against a variety of gram (-) and gram (+) bacterial strains, where AgNSs possessed moderate to high antibacterial activities against all the tested bacterial strains, while AuNSs and FeMOFs showed their bacterial toxicity mostly depending on the strain. Minimum inhibitory concentration (MIC) and Minimum bactericidal concentration (MBC) determination studies were performed for the nanostructure glycoconjugates, for which mu g/mL MBC values were obtained such as (Cellobiose p-aminobenzoic acid_AgNS) CBpAB_AgNS gave 50 mu g/mL MBC value for P.aeruginosa and S.kentucy. The activity of selected sugar ligands and corresponding glycoconjugates were further tested on MDA-MB-231 breast cancer and A549 lung cancer cell lines, where se-lective anticancer activity was observed depending on the surface chemistry as well. Besides, D-penicillamine was introduced to galectin specific sugar ligand coated AuNS glycoconjugates, which showed very strong anticancer activities even at low doses. Overall, the importance of this work is that the surface chemistry of the inorganic nanostructures can be critical to reveal their toxicity towards bacterial cells and cancerous cell lines.

Distributed acoustic sensors (DAS) are effective apparatuses that are widely used in many application areas for recording signals of various events with very high spatial resolution along optical fibers. To properly detect and recognize the recorded events, advanced signal processing algorithms with high computational demands are crucial. Convolutional neural networks (CNNs) are highly capable tools to extract spatial information and are suitable for event recognition applications in DAS. Long short-term memory (LSTM) is an effective instrument to process sequential data. In this study, a two-stage feature extraction methodology that combines the capabilities of these neural network architectures with transfer learning is proposed to classify vibrations applied to an optical fiber by a piezoelectric transducer. First, the differential amplitude and phase information is extracted from the phase-sensitive optical time domain reflectometer (Φ-OTDR) recordings and stored in a spatiotemporal data matrix. Then, a state-of-the-art pre-trained CNN without dense layers is used as a feature extractor in the first stage. In the second stage, LSTMs are used to further analyze the features extracted by the CNN. Finally, a dense layer is used to classify the extracted features. To observe the effect of different CNN architectures, the proposed model is tested with five state-of-the-art pre-trained models (VGG-16, ResNet-50, DenseNet-121, MobileNet, and Inception-v3). The results show that using the VGG-16 architecture in the proposed framework manages to obtain a 100% classification accuracy in 50 trainings and got the best results on the Φ-OTDR dataset. The results of this study indicate that pre-trained CNNs combined with LSTM are very suitable to analyze differential amplitude and phase information represented in a spatiotemporal data matrix, which is promising for event recognition operations in DAS applications.

The rapid and accurate detection of COVID-19 cases is critical for timely treatment and preventing the spread of the disease. In this study, a two-stage feature extraction framework using eight state-of-the-art pre-trained deep Convolutional Neural Networks (CNNs) and an autoencoder is proposed to determine the health conditions of patients (COVID-19, Normal, Viral Pneumonia) based on chest X-rays. The X-ray scans are divided into four equally sized sections and analyzed by deep pre-trained CNNs. Subsequently, an autoencoder with three hidden layers is trained to extract reproductive features from the concatenated ouput of CNNs. To evaluate the performance of the proposed framework, three different classifiers, which are single-layer perceptron (SLP), multi-layer perceptron (MLP), and support vector machine (SVM) are used. Furthermore, the deep CNN architectures are used to create benchmark models and trained on the same dataset for comparision. The proposed framework outperforms other frameworks wih pre-trained feature extractors in binary classification and shows competitive results in three-class classification. The proposed methodology is task-independent and suitable for addressing various problems. The results show that the discriminative features are a subset of the reproductive features, suggesting that extracting task-independent features is superior to the extraction only task-based features. The flexibility and task-independence of the reproductive features make the conceptive information approach more favorable. The proposed methodology is novel and shows promising results for analyzing medical image data.

Breast cancer is a major global health concern, and early and accurate diagnosis is crucial for effective treatment. Recent advancements in computer-assisted prediction models have facilitated diagnosis and prognosis using high-resolution histopathology images, which provide detailed information on cancerous tissue. However, these high-resolution images often require resizing, leading to potential data loss. In this study, we demonstrate the effect of a learnable adaptive resizer for breast cancer classification using the BreakHis dataset. Our approach incorporates the adaptive resizer with various convolutional neural network models, including VGG16, VGG19, MobileNetV2, InceptionResnetV2, DenseNet121, DenseNet201, and EfficientNetB0. Despite producing visually less appealing images, the learnable resizer effectively improves classification performance. DenseNet201, when jointly trained with the adaptive resizer, achieves the highest accuracy of 98.96 × 448 resolution. Our experimental results demonstrate that the adaptive resizer performs better at a magnification factor of 40 × compared to higher magnifications. While its effectiveness becomes less pronounced as image resolution increases to 100 × , 200 × , and 400 × , the adaptive resizer still outperforms bilinear interpolation. In conclusion, this study highlights the potential of adaptive resizers in enhancing performance for medical image classification. By outperforming traditional image resizing methods, our work contributes to the advancement of deep neural networks in the field of breast cancer diagnostics.

In our congress, users, manufacturers, researchers, managers and public representatives working in the field of medical technologies were brought together, scientific research results in the fields of biomedical engineering and clinical engineering were shared and common solutions to the problems experienced in the sector were discussed.As in the TIPTEKNO congresses, which were held with great success in previous years, panels were held on current issues and problems in the development, production, use and management of medical technologies, besides invited speeches by competent scientists in their fields, educational seminars were given and original scientific papers were presented.

As an alternative to high-cost near-infrared (NIR) vascular imaging devices in the market [1], a microcomputer-based, real-time, low-cost, non-contact and safe vascular imaging system has been developed. The higher absorption coefficient of blood from skin and fat, as well as the differences in oxy and deoxyhemoglobin spectra in blood, were helpful factors in the use of the NIR region during the acquisition of vessel images. A device, which uses NIR LED light operated at 850 nm, was designed using optical and electronic components. Image analysis were performed using OpenCV, which is an open-source software library, and data visualization libraries. Tests were carried out to optimize the best imaging conditions for the device. In this study, a portable device design with improved vessel image quality is presented which could potentially be used to assist the health professionals to investigate the abnormalities in the superficial vascular structures at different times during patients’ treatments.

In article number 2000411, Muhammad Mustafa Hussain and co-workers demonstrate a wearable personalized medicinal platform built on microfluidics, which gathers a variety of symptoms and vitals from the user's body. Then an artificial intelligence enabled formulation and preparation of a variety of medicine, vitamins or nutrients are conducted in-situ and delivered transdermally.