Automatic and real-time pose estimation is important in monitoring animal behavior, health and welfare. In this paper, we utilized pose estimation for monitoring farrowing process to prevent piglet mortality and preserve the health and welfare of sow. State-of-the-art Deep Learning (DL) methods have lately been used for animal pose estimation. The aim of this paper was to probe the generalization ability of five common DL networks (ResNet50, ResNet101, MobileNet, EfficientNet and DLCRNet) for sow and piglet pose estimation. These architectures predict body parts of several piglets and the sow directly from input video sequences. Real farrowing data from a commercial farm was used for training and validation of the proposed networks. The experimental results demonstrated that MobileNet was able to detect seven body parts of the sow with median test error of 0.61 pixels.

Fahimeh Farahnakian; Stefan Björkman; Farshad Farahnakian; Victor Bloch; Matti Pastell; Jukka Heikkonen. Pose Estimation of Sow and Piglets During Free Farrowing Using Deep Learning. Preprints.org 2023 .

Fahimeh Farahnakian, Stefan Björkman, Farshad Farahnakian, Victor Bloch, Matti Pastell, Jukka Heikkonen. Pose Estimation of Sow and Piglets During Free Farrowing Using Deep Learning. Preprints.org. 2023; ():.

Fahimeh Farahnakian; Stefan Björkman; Farshad Farahnakian; Victor Bloch; Matti Pastell; Jukka Heikkonen. 2023. "Pose Estimation of Sow and Piglets During Free Farrowing Using Deep Learning." Preprints.org , no. : .

Abnormal behavior detection is currently receiving much attention because of the availability of marine equipment and data allowing maritime agents to track vessels. One of the most popular tools for developing an efficient anomaly detection system is the Automatic Identification System (AIS). The aim of this paper is to explore the performance of existing well-known clustering methods for detecting the two most dangerous abnormal behaviors based on the AIS. The methods include K-means, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Affinity Propagation (AP), and the Gaussian Mixtures Model (GMM). In order to evaluate the performance of the clustering methods, we also used the AIS data of vessels, which were collected through the Finnish transport agency from the whole Baltic Sea for three months. Although most existing studies focus on ocean route recognition, deviations from regulated ocean routes, or irregular speed, we focused on dark ships or those sets of vessels that turn off the AIS to perform illegal activities and spiral vessel movements. The experimental results demonstrate that the K-means clustering method can effectively detect dark ships and spiral vessel movements, which are the most threatening events for maritime safety.

Farshad Farahnakian; Florent Nicolas; Fahimeh Farahnakian; Paavo Nevalainen; Javad Sheikh; Jukka Heikkonen; Csaba Raduly-Baka. A Comprehensive Study of Clustering-Based Techniques for Detecting Abnormal Vessel Behavior. Remote Sensing 2023, 15, 1477 .

Farshad Farahnakian, Florent Nicolas, Fahimeh Farahnakian, Paavo Nevalainen, Javad Sheikh, Jukka Heikkonen, Csaba Raduly-Baka. A Comprehensive Study of Clustering-Based Techniques for Detecting Abnormal Vessel Behavior. Remote Sensing. 2023; 15 (6):1477.

Farshad Farahnakian; Florent Nicolas; Fahimeh Farahnakian; Paavo Nevalainen; Javad Sheikh; Jukka Heikkonen; Csaba Raduly-Baka. 2023. "A Comprehensive Study of Clustering-Based Techniques for Detecting Abnormal Vessel Behavior." Remote Sensing 15, no. 6: 1477.

Detecting driver drowsiness is a very important task for enhancing the safety of road driving and reducing numerous accidents. In this paper, we proposed a fusion drowsiness detection framework based on video images without any additional wearable devices. The framework first applies Haar feature-based cascade classifiers on the input image to extract the region proposal of the driver's face, eyes and mouth. These interest proposals are then fed into three separate Convolutional Neural Network (CNN) to extract features and predict a class for each proposal based on defined classes. To improve classification performance, we applied transfer learning by using the pre-trained CNNs on images that belong to each region proposal. Finally, the framework can identify driver drowsiness through the defined rules applying to the predicted classes of each region. The rules specify the final class based on the class of mouth and eye to increase the robustness of the framework. The obtained results on the real RLDD dataset [1] show that the proposed framework can identify driver drowsiness with high accuracy and speed.

Farshad Farahnakian; Janika Leoste; Fahimeh Farahnakian. Driver Drowsiness Detection Using Deep Convolutional Neural Network. 2021, 1 -6.

Farshad Farahnakian, Janika Leoste, Fahimeh Farahnakian. Driver Drowsiness Detection Using Deep Convolutional Neural Network. . 2021; ():1-6.

Farshad Farahnakian; Janika Leoste; Fahimeh Farahnakian. 2021. "Driver Drowsiness Detection Using Deep Convolutional Neural Network." , no. : 1-6.

Ice-water detection is a major challenge for computer vision in the maritime environment. To address this challenge, we present a Convolutional Neural Network (CNN) model that fuses two imaging modalities: synthetic aperture radar (SAR) and advanced microwave scanning radiometer2 (AMSR2). The reasons for fusing these two imaging modalities are threefold. First, SAR provides high spatial resolution images, and AMSR2 provides images independent of wind conditions. In addition, the CNN fusion model can provide complementary information when images have different resolutions. Finally, the model generates a pixel-wise classification map for automatically generating sea ice charts, which reduces labour and time costs. We also investigate the effect of fusion on the segmentation performance by proposing uni-modal architecture, which is limited to the SAR modality. The results of this study show that the proposed model can accurately generate segmentation maps with more detailed sea ice textures and much sharper sea ice edges. The proposed fusion model achieves a pixel-wise accuracy of 94.60% and an F1-score of 94.99%.

Javad Sheikh; Fahimeh Farahnakian; Farshad Farahnakian; Jukka Heikkonen. Ice-Water Segmentation Using Deep Convolutional Neural Network-Based Fusion Approach. 2023, 1 -6.

Javad Sheikh, Fahimeh Farahnakian, Farshad Farahnakian, Jukka Heikkonen. Ice-Water Segmentation Using Deep Convolutional Neural Network-Based Fusion Approach. . 2023; ():1-6.

Javad Sheikh; Fahimeh Farahnakian; Farshad Farahnakian; Jukka Heikkonen. 2023. "Ice-Water Segmentation Using Deep Convolutional Neural Network-Based Fusion Approach." , no. : 1-6.

At this critical juncture in the world, maritime traffic and naval monitoring have become one of the hottest topics among governments to keep the marine environment safe for exporting and importing. As the amount of data used for maritime navigation, communication, and supervision has been growing, researchers are making attempts to find and develop novel, precise, and automated systems to detect anomaly behaviours of vessels in seas and ports. However, recognizing anomaly behaviours in a maritime environment is a difficult task since the wide variety of data. In this paper, we analyse and review existing machine learning-based techniques which can be utilised to recognize abnormal, and illegal ship activities. To identifying the methods and conducted this literature survey, 45 articles from peer-reviewed and high-regarded conferences have been chosen. The found papers are categorized into two groups (a) methods and (b) data. We also review and note research challenges, advantages and disadvantages of each techniques separately to motivate researchers to propose more advanced framework and tools as they are essential to consider during their research and developing stage.

Farshad Farahnakian; Jukka Heikkonen; Paavo Nevalainen. Abnormal Behaviour Detection by Using Machine Learning-Based Approaches in the Marine Environment: A Literature Survey. 2022, 14, 1 -11.

Farshad Farahnakian, Jukka Heikkonen, Paavo Nevalainen. Abnormal Behaviour Detection by Using Machine Learning-Based Approaches in the Marine Environment: A Literature Survey. . 2022; 14 ():1-11.

Farshad Farahnakian; Jukka Heikkonen; Paavo Nevalainen. 2022. "Abnormal Behaviour Detection by Using Machine Learning-Based Approaches in the Marine Environment: A Literature Survey." 14, no. : 1-11.

The modern maritime traffic prediction requires large area models based on the Automatic Identification System (AIS)with prediction interval reaching 2 hours at least. The second requirement is to cover all traffic, if possible.We propose Random Forests (RF) for ship movement prediction and demonstrate how it can be adapted to varying zone shapes and anomalydetection tasks. We also apply it to the clustering of vessels to regularly and irregularly moving ships. Our research area is the Baltic Sea and the recording period of data is 26 July 2022 ... 12 August 2022. Results from the class of regularly behaving ships (499ships out of 634) show 1.1 ... 2.1 km mean absolute error (MAE) over1 ... 2 hours which reaches the same accuracy as many published cases limited to considerably smaller area. The prediction for all time intervals can be updated every 10 minutes, which makes the implementation practical for large-scale situational awareness systems. The computational effort of prediction and keeping the model up-to-date are being discussed.

Tanja Vähämäki; Paavo Nevalainen; Javad Sheikh; Farshad Farahnakian; Jukka Heikkonen. Wide-Area Ship Movement Prediction Using Random Forest. SSRN Electronic Journal 2024 .

Tanja Vähämäki, Paavo Nevalainen, Javad Sheikh, Farshad Farahnakian, Jukka Heikkonen. Wide-Area Ship Movement Prediction Using Random Forest. SSRN Electronic Journal. 2024; ():.

Tanja Vähämäki; Paavo Nevalainen; Javad Sheikh; Farshad Farahnakian; Jukka Heikkonen. 2024. "Wide-Area Ship Movement Prediction Using Random Forest." SSRN Electronic Journal , no. : .

Sea ice concentration estimation is crucial for secure ship navigation and ice hazard forecasting. In this paper, we propose a Convolutional Neural Network (CNN) architecture for sea ice concentration estimation over the Baltic Sea using two imaging modalities: Sentinel-1 and advanced microwave scanning radiometer2 (AMSR2). The main idea for fusing these two sensors is Sentinel-1 images have high spatial resolution and AMSR2 provides images independent of wind conditions. Our two-stream architecture is to preserve all possible information of the different resolution inputs, instead of interpolating the inputs to the same resolution while losing potentially useful information. We also investigate the impact of two loss functions and skip connection on the performance of the proposed CNN model. The experimental results show that CNN with focal loss function and skip connection can achieve R2 score of 90.6%.

Javad Sheikh; Fahimeh Farahnakian; Farshad Farahnakian; Jukka Heikkonen. Sea Ice Concentration Estimation Via Fusion of Sentinel-1 and AMSR2 Based on Encoder-Decoder Architecture. 2023, 5989 -5994.

Javad Sheikh, Fahimeh Farahnakian, Farshad Farahnakian, Jukka Heikkonen. Sea Ice Concentration Estimation Via Fusion of Sentinel-1 and AMSR2 Based on Encoder-Decoder Architecture. . 2023; ():5989-5994.

Javad Sheikh; Fahimeh Farahnakian; Farshad Farahnakian; Jukka Heikkonen. 2023. "Sea Ice Concentration Estimation Via Fusion of Sentinel-1 and AMSR2 Based on Encoder-Decoder Architecture." , no. : 5989-5994.

Farshad Farahnakian; Fahimeh Farahnakian; Javad Sheikh; Paavo Nevalainen; Jukka Heikkonen. Short and Long Term Vessel Movement Prediction for Maritime Traffic. 2024, 62 -80.

Farshad Farahnakian, Fahimeh Farahnakian, Javad Sheikh, Paavo Nevalainen, Jukka Heikkonen. Short and Long Term Vessel Movement Prediction for Maritime Traffic. . 2024; ():62-80.

Farshad Farahnakian; Fahimeh Farahnakian; Javad Sheikh; Paavo Nevalainen; Jukka Heikkonen. 2024. "Short and Long Term Vessel Movement Prediction for Maritime Traffic." , no. : 62-80.

Accurate and efficient automated rice grain classification systems are vital for rice producers, distributors, and traders, offering improved quality control, cost optimization, and supply chain management. They also hold the potential to aid in the development of rice varieties that are more resistant to disease, pests, and environmental stress. While most existing studies in the rice classification domain rely on traditional machine-learning techniques that necessitate feature extraction engineering processes, our research explores the effectiveness of novel deep-learning models for this task. We evaluated the performance of various contemporary deep-learning models, including Residual Network (ResNet), Visual Geometry Group (VGG) network, EfficientNet, and MobileNet. These models were tested on a dataset comprising 75,000 images, classified into five different rice categories. We assessed each model using established evaluation metrics such as accuracy, F1 score, precision, recall, and per-class accuracy. Our findings showed that the EfficientNet-based model delivered the highest accuracy (99.67%), while the MobileNet-based model excelled in the speed of classification (2556 seconds). We concluded that, compared to traditional machine learning methods, the models employed in our study are highly scalable and capable of managing large volumes of complex data with millions of features and samples.

Farshad Farahnakian; Javad Sheikh; Fahimeh Farahnakian; Jukka Heikkonen. A comparative study of state-of-the-art deep learning architectures for rice grain classification. Journal of Agriculture and Food Research 2024, 15 .

Farshad Farahnakian, Javad Sheikh, Fahimeh Farahnakian, Jukka Heikkonen. A comparative study of state-of-the-art deep learning architectures for rice grain classification. Journal of Agriculture and Food Research. 2024; 15 ():.

Farshad Farahnakian; Javad Sheikh; Fahimeh Farahnakian; Jukka Heikkonen. 2024. "A comparative study of state-of-the-art deep learning architectures for rice grain classification." Journal of Agriculture and Food Research 15, no. : .

Fahimeh Farahnakian; Farshad Farahnakian; Stefan Björkman; Victor Bloch; Matti Pastell; Jukka Heikkonen. Pose estimation of sow and piglets during free farrowing using deep learning. Journal of Agriculture and Food Research 2024, 16 .

Fahimeh Farahnakian, Farshad Farahnakian, Stefan Björkman, Victor Bloch, Matti Pastell, Jukka Heikkonen. Pose estimation of sow and piglets during free farrowing using deep learning. Journal of Agriculture and Food Research. 2024; 16 ():.

Fahimeh Farahnakian; Farshad Farahnakian; Stefan Björkman; Victor Bloch; Matti Pastell; Jukka Heikkonen. 2024. "Pose estimation of sow and piglets during free farrowing using deep learning." Journal of Agriculture and Food Research 16, no. : .