{"title":"Integrated model for segmentation of glomeruli in kidney images","authors":"Gurjinder Kaur, Meenu Garg, Sheifali Gupta","doi":"10.1016/j.cogr.2024.11.007","DOIUrl":"10.1016/j.cogr.2024.11.007","url":null,"abstract":"<div><div>Kidney diseases, especially those that affect the glomeruli, have become more common worldwide in recent years. Accurate and early detection of glomeruli is critical for accurately diagnosing kidney problems and determining the most effective treatment options. Our study proposed an advanced model, FResMRCNN, an enhanced version of Mask R-CNN, for automatically detecting and segmenting the glomeruli in PAS-stained human kidney images. The model integrates the power of FPN with a ResNet101 backbone, which was selected after assessing seven different backbone architectures. The integration of FPN and ResNet101 into the FResMRCNN model improves glomeruli detection, segmentation accuracy and stability by representing multi-scale features. We trained and tested our model using the HuBMAP Kidney dataset, which contains high-resolution PAS-stained microscopy images. During the study, the effectiveness of our proposed model is examined by generating bounding boxes and predicted masks of glomeruli. The performance of the FResMRCNN model is evaluated using three performance metrics, including the Dice coefficient, Jaccard index, and binary cross-entropy loss, which show promising results in accurately segmenting glomeruli.</div></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"5 ","pages":"Pages 1-13"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143143538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Hybrid machine learning-based 3-dimensional UAV node localization for UAV-assisted wireless networks","authors":"Workeneh Geleta Negassa, Demissie J. Gelmecha, Ram Sewak Singh, Davinder Singh Rathee","doi":"10.1016/j.cogr.2025.01.002","DOIUrl":"10.1016/j.cogr.2025.01.002","url":null,"abstract":"<div><div>This paper presents a hybrid machine-learning framework for optimizing 3-Dimensional (3D) Unmanned Aerial Vehicles (UAV) node localization and resource distribution in UAV-assisted THz 6G networks to ensure efficient coverage in dynamic, high-density environments. The proposed model efficiently managed interference, adapted to UAV mobility, and ensured optimal throughput by dynamically optimizing UAV trajectories. The hybrid framework combined the strengths of Graph Neural Networks (GNN) for feature aggregation, Deep Neural Networks (DNN) for efficient resource allocation, and Double Deep Q-Networks (DDQN) for distributed decision-making. Simulation results demonstrated that the proposed model outperformed traditional machine learning models, significantly improving energy efficiency, latency, and throughput. The hybrid model achieved an optimized energy efficiency of 90 Tbps/J, reduced latency to 0.0105 ms, and delivered a network throughput of approximately 96 Tbps. The model adapts to varying link densities, maintaining stable performance even in high-density scenarios. These findings underscore the framework's potential to address key challenges in UAV-assisted 6G networks, paving the way for scalable and efficient communication in next-generation wireless systems.</div></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"5 ","pages":"Pages 61-76"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143143956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"LiPE: Lightweight human pose estimator for mobile applications towards automated pose analysis","authors":"Chengxiu Li , Ni Duan","doi":"10.1016/j.cogr.2024.11.005","DOIUrl":"10.1016/j.cogr.2024.11.005","url":null,"abstract":"<div><div>Current human pose estimation models adopt heavy backbones and complex feature enhance- ment modules to pursue higher accuracy. However, they ignore the need for model efficiency in real-world applications. In real-world scenarios such as sports teaching and automated sports analysis for better preservation of traditional folk sports, human pose estimation often needs to be performed on mobile devices with limited computing resources. In this paper, we propose a lightweight human pose estimator termed LiPE. LiPE adopts a lightweight MobileNetV2 backbone for feature extraction and lightweight depthwise separable deconvolution modules for upsampling. Predictions are made at a high resolution with a lightweight prediction head. Compared with the baseline, our model reduces MACs by 93.2 %, and reduces the number of parameters by 93.9 %, while the accuracy drops by only 3.2 %. Based on LiPE, we develop a real- time human pose estimation and evaluation system for automated pose analysis. Experimental results show that our LiPE achieves high computational efficiency and good accuracy for application on mobile devices.</div></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"5 ","pages":"Pages 26-36"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143143537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Robotic terrain classification based on convolutional and long short-term memory neural networks","authors":"YiGe Hu","doi":"10.1016/j.cogr.2025.04.002","DOIUrl":"10.1016/j.cogr.2025.04.002","url":null,"abstract":"<div><div>Robotic mobility remains constrained by complex terrains and technological limitations, hindering real-world applications. This study presents a terrain classification framework integrating Fourier transform, adaptive filtering, and deep learning to enhance adaptability. Leveraging CNNs, LSTMs, and an attention mechanism, the approach improves feature fusion and classification accuracy. Evaluations on the Tampere University dataset demonstrate an 81 % classification accuracy, validating its effectiveness in terrain perception and autonomous navigation. The findings contribute to advancing robotic mobility in unstructured environments.</div></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"5 ","pages":"Pages 166-175"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143864324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shripad V. Deshpande , Harikrishnan R , Babul Salam KSM Kader Ibrahim , Mahesh Datta Sai Ponnuru
{"title":"Mobile robot path planning using deep deterministic policy gradient with differential gaming (DDPG-DG) exploration","authors":"Shripad V. Deshpande , Harikrishnan R , Babul Salam KSM Kader Ibrahim , Mahesh Datta Sai Ponnuru","doi":"10.1016/j.cogr.2024.08.002","DOIUrl":"10.1016/j.cogr.2024.08.002","url":null,"abstract":"<div><p>Mobile robot path planning involves decision-making in uncertain, dynamic conditions, where Reinforcement Learning (RL) algorithms excel in generating safe and optimal paths. The Deep Deterministic Policy Gradient (DDPG) is an RL technique focused on mobile robot navigation. RL algorithms must balance exploitation and exploration to enable effective learning. The balance between these actions directly impacts learning efficiency.</p><p>This research proposes a method combining the DDPG strategy for exploitation with the Differential Gaming (DG) strategy for exploration. The DG algorithm ensures the mobile robot always reaches its target without collisions, thereby adding positive learning episodes to the memory buffer. An epsilon-greedy strategy determines whether to explore or exploit. When exploration is chosen, the DG algorithm is employed. The combination of DG strategy with DDPG facilitates faster learning by increasing the number of successful episodes and reducing the number of failure episodes in the experience buffer. The DDPG algorithm supports continuous state and action spaces, resulting in smoother, non-jerky movements and improved control over the turns when navigating obstacles. Reward shaping considers finer details, ensuring even small advantages in each iteration contribute to learning.</p><p>Through diverse test scenarios, it is demonstrated that DG exploration, compared to random exploration, results in an average increase of 389% in successful target reaches and a 39% decrease in collisions. Additionally, DG exploration shows a 69% improvement in the number of episodes where convergence is achieved within a maximum of 2000 steps.</p></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"4 ","pages":"Pages 156-173"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667241324000119/pdfft?md5=8c083de5d6ac1af9d3cedcb0733a30fa&pid=1-s2.0-S2667241324000119-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142271646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sk. Khairul Hasan, Subodh B. Bhujel, Gabrielle Sara Niemiec
{"title":"Emerging trends in human upper extremity rehabilitation robot","authors":"Sk. Khairul Hasan, Subodh B. Bhujel, Gabrielle Sara Niemiec","doi":"10.1016/j.cogr.2024.09.001","DOIUrl":"10.1016/j.cogr.2024.09.001","url":null,"abstract":"<div><p>Stroke is a leading cause of neurological disorders that result in physical disability, particularly among the elderly. Neurorehabilitation plays a crucial role in helping stroke patients recover from physical impairments and regain mobility. Physical therapy is one of the most effective forms of neurorehabilitation, but the growing number of patients requires a large workforce of trained therapists, which is currently insufficient. Robotic rehabilitation offers a promising alternative, capable of supplementing or even replacing human-assisted physical therapy through the use of rehabilitation robots. To design effective robotic devices for rehabilitation, a solid foundation of knowledge is essential. This article provides a comprehensive overview of the key elements needed to develop human upper extremity rehabilitation robots. It covers critical aspects such as upper extremity anatomy, joint range of motion, anthropometric parameters, disability assessment techniques, and robot-assisted training methods. Additionally, it reviews recent advancements in rehabilitation robots, including exoskeletons, end-effector-based robots, and planar robots. The article also evaluates existing upper extremity rehabilitation robots based on their mechanical design and functionality, identifies their limitations, and suggests future research directions for further improvement.</p></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"4 ","pages":"Pages 174-190"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667241324000120/pdfft?md5=a51e80d94f3f2f6ca53c667c4682ef83&pid=1-s2.0-S2667241324000120-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142271647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Fourier Hilbert: The input transformation to enhance CNN models for speech emotion recognition","authors":"Bao Long Ly","doi":"10.1016/j.cogr.2024.11.002","DOIUrl":"10.1016/j.cogr.2024.11.002","url":null,"abstract":"<div><div>Signal processing in general, and speech emotion recognition in particular, have long been familiar Artificial Intelligence (AI) tasks. With the explosion of deep learning, CNN models are used more frequently, accompanied by the emergence of many signal transformations. However, these methods often require significant hardware and runtime. In an effort to address these issues, we analyze and learn from existing transformations, leading us to propose a new method: Fourier Hilbert Transformation (FHT). In general, this method applies the Hilbert curve to Fourier images. The resulting images are small and dense, which is a shape well-suited to the CNN architecture. Additionally, the better distribution of information on the image allows the filters to fully utilize their power. These points support the argument that FHT provides an optimal input for CNN. Experiments conducted on popular datasets yielded promising results. FHT saves a large amount of hardware usage and runtime while maintaining high performance, even offers greater stability compared to existing methods. This opens up opportunities for deploying signal processing tasks on real-time systems with limited hardware.</div></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"4 ","pages":"Pages 228-236"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142748300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shripad V. Deshpande, Harikrishnan R, Rahee Walambe
{"title":"POMDP-based probabilistic decision making for path planning in wheeled mobile robot","authors":"Shripad V. Deshpande, Harikrishnan R, Rahee Walambe","doi":"10.1016/j.cogr.2024.06.001","DOIUrl":"https://doi.org/10.1016/j.cogr.2024.06.001","url":null,"abstract":"<div><p>Path Planning in a collaborative mobile robot system has been a research topic for many years. Uncertainty in robot states, actions, and environmental conditions makes finding the optimum path for navigation highly challenging for the robot. To achieve robust behavior for mobile robots in the presence of static and dynamic obstacles, it is pertinent that the robot employs a path-finding mechanism that is based on the probabilistic perception of the uncertainty in various parameters governing its movement. Partially Observable Markov Decision Process (POMDP) is being used by many researchers as a proven methodology for handling uncertainty. The POMDP framework requires manually setting up the state transition matrix, the observation matrix, and the reward values. This paper describes an approach for creating the POMDP model and demonstrates its working by simulating it on two mobile robots destined on a collision course. Selective test cases are run on the two robots with three categories – MDP (POMDP with belief state spread of 1), POMDP with distribution spread of belief state over ten observations, and distribution spread across two observations. Uncertainty in the sensor data is simulated with varying levels of up to 10 %. The results are compared and analyzed. It is demonstrated that when the observation probability spread is increased from 2 to 10, collision reduces from 34 % to 22 %, indicating that the system's robustness increases by 12 % with only a marginal increase of 3.4 % in the computational complexity.</p></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"4 ","pages":"Pages 104-115"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667241324000077/pdfft?md5=ccfa806c0ae32c5aba224cbf968b6b8d&pid=1-s2.0-S2667241324000077-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141483724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xuelin Zhang , Feng Liu , Xuelian Cheng , Siyuan Yan , Zhibin Liao , Zongyuan Ge
{"title":"Autonomous novel class discovery for vision-based recognition in non-interactive environments","authors":"Xuelin Zhang , Feng Liu , Xuelian Cheng , Siyuan Yan , Zhibin Liao , Zongyuan Ge","doi":"10.1016/j.cogr.2024.10.002","DOIUrl":"10.1016/j.cogr.2024.10.002","url":null,"abstract":"<div><div>Visual recognition with deep learning has recently been shown to be effective in robotic vision. However, these algorithms tend to be build under fixed and structured environment, which is rarely the case in real life. When facing unknown objects, avoidance or human interactions are required, which may miss critical objects or be prohibitively costly to obtain on robots in the real world. We consider a practical problem setting that aims to allow robots to automatically discover novel classes with only labelled known class samples in hand, defined as open-set clustering (OSC). To address the OSC problem, we propose a framework combining three approaches: 1) using selfsupervised vision transformers to mitigate the discard of information needed for clustering unknown classes; 2) adaptive weighting for image patches to prioritize patches with richer textures; and 3) incorporating a temperature scaling strategy to generate more separable feature embeddings for clustering. We demonstrate the efficacy of our approach in six fine-grained image datasets.</div></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"4 ","pages":"Pages 191-203"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}