Article
Geochemistry & Geophysics
Qiangwei Liu, Xiuqiao Xiang, Zhou Yang, Yu Hu, Yuming Hong
Summary: This article proposes a new framework based on an improved Faster R-CNN for detecting ships in arbitrary directions. The method combines global and local features of proposal regions through a multi-region feature-fusion module, and achieves ship bounding-box recognition through multitask learning. Experimental results demonstrate that the proposed approach outperforms other state-of-the-art ship-detection methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Chemistry, Analytical
Rui Miao, Hongxu Jiang, Fangzheng Tian
Summary: The study proposes a ship detection method based on multiscale feature extraction and lightweight CNN to overcome the limitations of ship detection technology in remote sensing images. The method accurately extracts potential targets using a multiscale model and achieves ship classification through multiple feature fusion and lightweight CNN. It also utilizes cascade classifier training and an improved non-maximum suppression method to minimize classification error and maximize generalization, resulting in improved detection performance and robustness.
Article
Engineering, Electrical & Electronic
Yupeng Deng, Jiansheng Chen, Shiming Yi, Anzhi Yue, Yu Meng, Jingbo Chen, Yi Zhang
Summary: In this article, a feature-guided multitask change detection network (MCDnet) is proposed, which achieves state-of-the-art results in the field of change detection and achieves good semantic change detection accuracy with a limited number of labels.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Automation & Control Systems
Zhongke Gao, Linhua Hou, Weidong Dang, Xinmin Wang, Xiaolin Hong, Xiong Yang, Guanrong Chen
Summary: In this study, a novel deep learning based soft measure technique was developed to predict the gas void fraction in gas-liquid two-phase flow. A multitask-based temporal-channelwise convolutional neural network was designed to extract features and predict the gas void fraction, showing superior performance compared to other competitive methods.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Geochemistry & Geophysics
Tao Lei, Xinzhe Geng, Hailong Ning, Zhiyong Lv, Maoguo Gong, Yaochu Jin, Asoke K. K. Nandis
Summary: In this article, an efficient ultralightweight spatial-spectral feature cooperation network (USSFC-Net) is proposed for remote sensing image change detection. The USSFC-Net addresses the high computational costs, high memory usage, and lack of cooperation between spatial and spectral features in existing methods. It achieves better performance in change detection with lower computational costs and fewer parameters compared to other CNNs-based methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Engineering, Electrical & Electronic
Amanuel Hirpa Madessa, Junyu Dong, Eric Rigall, Qingxuan Lv, Hafiza Sadia Nawaz Nawaz, Israel Mugunga, Shaoxiang Guo
Summary: The automatic detection of transmittance surfaces and material class identification is crucial for various applications. A learning model that combines ViT, SIFT, and CNN is proposed to achieve high accuracy in detecting transmittance surfaces and determining their material type.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Geochemistry & Geophysics
Yu Liu, Zhengyang Zhao, Shanwen Zhang, Lei Huang
Summary: In this study, a novel multiregion scale-aware network is proposed to accurately extract buildings with varying scales and layouts in remote sensing images. The network utilizes a multiregion attention module to capture long-range context dependencies and a graph-based scale-aware structure to model and reason the interactions between different scale features. Extensive experiments demonstrate that the proposed method outperforms other state-of-the-art methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Peder Heiselberg, Kristian Sorensen, Henning Heiselberg
Summary: SAR satellites are used to monitor ships worldwide. A novel automatic method based on multitask deep learning is proposed to calculate ship velocity. The method shows effectiveness in estimating ship speed with an accuracy of 1.1 m/s in Sentinel-1 SAR images.
REMOTE SENSING OF ENVIRONMENT
(2023)
Article
Geochemistry & Geophysics
Renlong Hang, Feng Zhou, Qingshan Liu, Pedram Ghamisi
Summary: In this article, a multitask generative adversarial network (MTGAN) is proposed to address the issue of deep learning models heavily depending on the quantity of available training samples in hyperspectral image classification. By utilizing rich information from unlabeled samples and employing an adversarial learning method, the MTGAN model is able to indirectly improve the discrimination and generalization ability of the classification task. Additionally, skip-layer connections are used to fully explore useful information from shallow layers, resulting in higher performance compared to other state-of-the-art deep learning models.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Environmental Sciences
Wei Liu, Xingyu Chen, Jiangjun Ran, Lin Liu, Qiang Wang, Linyang Xin, Gang Li
Summary: This paper introduces a novel lightweight multitask fully convolutional neural network called LaeNet for automatically extracting lake area and shoreline from remote sensing images. Experimental results show that the performance of this model is superior to other models and it achieves significant improvements in computational efficiency and model size.
Article
Geochemistry & Geophysics
Wenbo Yu, Miao Zhang, Yi Shen
Summary: The article proposes a novel unsupervised hyperspectral feature extraction architecture based on spatial revising variational autoencoder, which extracts spatial features from multiple aspects and revises the acquired spectral features. Experimental results demonstrate that this method outperforms comparison methods and is expected to play a significant role in hyperspectral image processing.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Biochemistry & Molecular Biology
Victor Akpokiro, H. M. A. Mohit Chowdhury, Samuel Olowofila, Raisa Nusrat, Oluwatosin Oluwadare
Summary: The article introduces CNNSplice, a set of deep convolutional neural network models for splice site prediction. Through model selection technique, the authors propose five high-performing models that efficiently predict true and false splice sites in balanced and imbalanced datasets. Evaluation results indicate that CNNSplice's models achieve better performance compared with existing methods across five organisms' datasets and also demonstrate generalizability on new or poorly trained genome datasets.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2023)
Article
Medicine, General & Internal
Wei-Chih Lien, Chung-Hsing Yeh, Chun-Yang Chang, Chien-Hsiang Chang, Wei-Ming Wang, Chien-Hsu Chen, Yang-Cheng Lin
Summary: Image recognition and neuroimaging are used to understand Alzheimer's disease progression. This study compared the performance of five CNN models on medical images and established a classification model for epidemiological research. The study proved the effectiveness of transfer learning in identifying mild cognitive impairment, mild AD, and moderate AD scoring based on SPECT images.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Ke Nai, Zhiyong Li, Yihui Gan, Qi Wang
Summary: This article proposes a novel multitask sparse correlation filters (MTSCF) model for visual tracking, which introduces multitask sparse learning into the CFs framework. The MTSCF method exploits the interdependencies among different visual features and performs feature selection to enhance the tracking performance. The extensive experiment results demonstrate that the proposed MTSCF tracker achieves competitive tracking performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
V. P. Manikandan, U. Rahamathunnisa
Summary: This article introduces an Attuned Object Detection Scheme (AODS) for harmful object detection from CCTV inputs. The proposed scheme relies on a convolutional neural network (CNN) for object detection and classification, and achieves accurate detection of hazardous objects through feature attenuation and dimensional representation comparison. Training with external datasets can improve the scheme's performance.
IMAGE AND VISION COMPUTING
(2022)
Article
Chemistry, Physical
Morteza Amini, Mir Mohsen Pedram, Alireza Moradi, Mahshad Ochani
Summary: The research proposes a biosensor based on surface plasmon resonance for highly sensitive detection of Alzheimer's disease. Numerical analysis of different structural parameters shows that the sensor can achieve high sensitivity detection in the early stages.
Article
Oncology
Mojtaba Dehghan, Jafar Hasani, Alireza Moradi, Shahram Mohammadkhani
Summary: This study explored the process of self-change in cancer survivors and developed a model called "transitional self-disappear". This conceptual framework explains the self-disruption, self-reconstruction strategy, and quality of self-coherence. The model highlights the complex paths of journey from self-disappear to self reconstruction/re-coherence in cancer survivors.
SUPPORTIVE CARE IN CANCER
(2022)
Article
Psychology, Clinical
Sepideh Memarian, Alireza Moradi, Jafar Hasani, Barbara Mullan
Summary: Sweet food-specific inhibitory control training through a mobile app can effectively reduce sweet food choice and intake among overweight or obese children, though no significant effects on weight loss were observed.
BRITISH JOURNAL OF HEALTH PSYCHOLOGY
(2022)
Article
Neurosciences
Soroush Lohrasbi, Ali Reza Moradi, Meysam Sadeghi
Summary: This study investigated emotion recognition patterns among Iranians using the Cambridge neuro-psychological test automated battery (CANTAB). The findings showed that different emotions have various correct responses and recognition times, except for sadness and surprise which did not differ significantly.
BASIC AND CLINICAL NEUROSCIENCE
(2023)
Article
Chemistry, Physical
Morteza Amini, Mir Mohsen Pedram, Alireza Moradi, Mahshad Ochani
Summary: A highly sensitive plasmonic nanobiosensor has been proposed for the detection of Alzheimer's disease, utilizing surface plasmon resonance on a nanodevice. The sensor, composed of graphene metasurfaces and samples, achieves high sensitivity and figure of merit, making it a promising tool for future Alzheimer's detection.
Article
Clinical Neurology
Kamal Parhoon, Stephen L. Aita, Hadi Parhoon, Alireza Moradi, Robert M. Roth
Summary: This study investigated the psychometric properties of a Persian translation of the Behavior Rating Inventory of Executive Function, Second Edition (BRIEF2) Self-Report form in Iranian adolescents. The results showed that the Persian version of the BRIEF2 had robust reliability and convergent validity, supporting its clinical use in assessing executive function in this population. Structural equation modeling analysis also confirmed the three-factor structure of the Persian BRIEF2.
APPLIED NEUROPSYCHOLOGY-CHILD
(2022)
Article
Mathematical & Computational Biology
Morteza Amini, Mir Mohsen Pedram, AliReza Moradi, Mahdieh Jamshidi, Mahshad Ouchani
Summary: The study demonstrates a causal relationship between SNPs and quantitative PET imaging traits in Alzheimer's disease. CNN achieved the highest accuracy of 91.1% in AD classification based on brain tissue variations in PET images. KNN and CNN methods are beneficial in diagnosing AD, while LDA and SVM showed lower accuracy levels.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2022)
Article
Oncology
Reihane Zolfa, Alireza Moradi, Mohammad Mahdavi, Hadi Parhoon, Kamal Parhoon, Laura Jobson
Summary: This study examined the feasibility and acceptability of written exposure therapy (WET) in reducing symptoms of PTSD in Iranian women with breast cancer. The results showed that WET was well-accepted and had positive effects on quality of life, memory, and illness perceptions.
Article
Behavioral Sciences
Fatemeh Eivazi, Javad Hatami, Alireza Moradi, Mohammad-Reza Nazem-Zadeh
Summary: The study found that fluency of future thoughts is associated with DD. Financial contents and engaging in future thinking for planning are related to DD. These variables are significant predictors of intertemporal choices when controlling for education and gender.
BRAIN AND BEHAVIOR
(2022)
Article
Behavioral Sciences
Asiyeh Rezaei Niyasar, Alireza Moradi, Narges Radman, Meysam Sadeghi, Maryam Mahmoudi
Summary: The study demonstrates the effectiveness of online cognitive self-regulation training in weight loss and modifying eating behaviors. This intervention shows promising evidence for weight stabilization in children with obesity.
BRAIN AND BEHAVIOR
(2022)
Article
Psychology, Clinical
Vida Mirabolfathi, Susanne Schweizer, AliReza Moradi, Laura Jobson
Summary: This study reveals that trauma-exposed adolescents with high levels of PTSD symptoms have poorer cognitive functioning in trauma-related contexts. The findings emphasize the importance of investigating posttraumatic cognitive functioning within affective contexts and suggest that affective working memory capacity may be a promising target for intervention.
PSYCHOLOGICAL TRAUMA-THEORY RESEARCH PRACTICE AND POLICY
(2022)
Review
Psychiatry
Saba Mokhtari, Asieh Mokhtari, Farah Bakizadeh, Alireza Moradi, Mohammadreza Shalbafan
Summary: This study conducted a systematic review of controlled randomized clinical trials and found that cognitive rehabilitation has a significant and moderate effect on the executive function, verbal learning, and working memory of patients with MDD. However, there was no significant improvement in attention and depressive symptoms. Therefore, cognitive rehabilitation should be considered an important component in the treatment of MDD.
Article
Psychology, Experimental
Sepideh Mashayekhi, AliReza Moradi, Vida Mirabolfathi, Jafar Hasani, Sharareh Farahimanesh, Laura Jobson
Summary: People living with HIV can experience posttraumatic stress disorder (PTSD), which is associated with cognitive impairments. This study conducted in Iran compared three cognitive impairments (false memory, attentional bias, deficits in future thinking) among HIV-positive individuals with and without PTSD. The results showed that individuals with HIV and PTSD exhibited more false memories, attentional bias towards threat-related words, and difficulties in generating specific future events. This research suggests potential cognitive targets for psychological interventions for people living with HIV in Iran.
APPLIED COGNITIVE PSYCHOLOGY
(2023)
Article
Medicine, General & Internal
Sharareh Farahimanesh, Silvia Serino, Cosimo Tuena, Daniele Di Lernia, Brenda K. Wiederhold, Luca Bernardelli, Giuseppe Riva, Alireza Moradi
Summary: This study aimed to evaluate the effectiveness of a Virtual Reality-based self-help intervention (COVID Feel Good) in reducing psychological distress during the COVID-19 pandemic in Iran. The intervention group showed improvements in depression, stress, anxiety, and perceived stress, but not in hopelessness. Secondary outcomes revealed an increase in perceived social connectedness and a significant reduction in fear of COVID-19. These findings contribute to the growing evidence supporting the use of digital self-help interventions for well-being during this unique period.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Psychology, Multidisciplinary
Sharareh Farahimanesh, Alireza Moradi, Meysam Sadeghi
Summary: This study investigates the correlation between post-traumatic stress disorder (PTSD) and autobiographical memory bias in cancer patients, and explores the effectiveness of Competitive Memory Training (COMET) as an intervention in modifying the processing of autobiographical information and reducing PTSD symptoms. The findings suggest that COMET intervention is promising in alleviating autobiographical memory bias and reducing depression symptoms in cancer patients with PTSD.
CURRENT PSYCHOLOGY
(2023)