{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:34:03Z","timestamp":1780673643209,"version":"3.54.1"},"reference-count":81,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:00:00Z","timestamp":1772496000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This paper explores the feasibility of employing small language models (SLMs) on edge devices powered by batteries in environments with limited\/no internet connectivity. SLMs in fact offer significant advantages in such scenarios due to their lower resource requirements with respect to large language models. The use case in this study is maritime navigation\u2014in particular, the documentation on Sailing Directions (Enroutd) of the World Port Index (WPI) provided by the National Geospatial-Intelligence Agency (NGA), which provides information that cannot be shown graphically on nautical charts and is not readily available elsewhere. In this environment, response immediacy is not critical, as users have sufficient time to query information while navigating and planning activities, making edge devices ideal for running these models. On the contrary, the response quality is fundamental. For this reason, given the constrained knowledge of SLMs in maritime contexts, we investigate the use of the retrieval-augmented generation (RAG) methodology, integrating external information from sailing directions. A comparative analysis is presented to evaluate the performance of various state-of-the-art SLMs, focusing on response quality, the effectiveness of the RAG component, and inference times.<\/jats:p>","DOI":"10.3390\/s26051590","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T14:42:47Z","timestamp":1772548967000},"page":"1590","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Navigating the Seas of AI: Effectiveness of Small Language Models on Edge Devices for Maritime Applications"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8465-4624","authenticated-orcid":false,"given":"Nicol\u00f2","family":"Guainazzo","sequence":"first","affiliation":[{"name":"Department of Informatics, Bioengineering, Robotics and Systems Engineering (DIBRIS), Universit\u00e0 degli Studi di Genova, Via Dodecaneso 35, 16146 Genoa, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7030-1050","authenticated-orcid":false,"given":"Giorgio","family":"Delzanno","sequence":"additional","affiliation":[{"name":"Department of Informatics, Bioengineering, Robotics and Systems Engineering (DIBRIS), Universit\u00e0 degli Studi di Genova, Via Dodecaneso 35, 16146 Genoa, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6297-2011","authenticated-orcid":false,"given":"Davide","family":"Ancona","sequence":"additional","affiliation":[{"name":"Department of Informatics, Bioengineering, Robotics and Systems Engineering (DIBRIS), Universit\u00e0 degli Studi di Genova, Via Dodecaneso 35, 16146 Genoa, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2649-0071","authenticated-orcid":false,"given":"Daniele","family":"D\u2019Agostino","sequence":"additional","affiliation":[{"name":"Department of Informatics, Bioengineering, Robotics and Systems Engineering (DIBRIS), Universit\u00e0 degli Studi di Genova, Via Dodecaneso 35, 16146 Genoa, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,3]]},"reference":[{"key":"ref_1","unstructured":"Epstein, R., Roberts, G., and Beber, G. (2009). Computing Machinery and Intelligence. Parsing the Turing Test: Philosophical and Methodological Issues in the Quest for the Thinking Computer, Springer Netherlands."},{"key":"ref_2","unstructured":"Frederking, R.E., and Taylor, K.B. (2004). The Georgetown-IBM Experiment Demonstrated in January 1954. Proceedings of the Machine Translation: From Real Users to Research, Springer."},{"key":"ref_3","first-page":"11","article-title":"Machine translation: A concise history","volume":"Volume 13","author":"Hutchins","year":"2007","journal-title":"Computer Aided Translation: Theory and Practice"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"5929","DOI":"10.1007\/s10462-020-09838-1","article-title":"A review on the long short-term memory model","volume":"53","author":"Mosquera","year":"2020","journal-title":"Artif. Intell. Rev."},{"key":"ref_5","unstructured":"Vaswani, A. (2017). Attention is all you need. NIPS\u201917: Proceedings of the 31st International Conference on Neural Information Processing Systems, Curran Associates Inc."},{"key":"ref_6","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv."},{"key":"ref_7","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1016\/j.future.2019.09.013","article-title":"A secure cloud-edges computing architecture for metagenomics analysis","volume":"111","author":"Verderame","year":"2020","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.future.2019.01.024","article-title":"SoC-based computing infrastructures for scientific applications and commercial services: Performance and economic evaluations","volume":"96","author":"Quarati","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Li, X., Lu, Z., Cai, D., Ma, X., and Xu, M. (2024). Large Language Models on Mobile Devices: Measurements, Analysis, and Insights. EdgeFM \u201924, Proceedings of the Workshop on Edge and Mobile Foundation Models, Association for Computing Machinery.","DOI":"10.1145\/3662006.3662059"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1365","DOI":"10.26599\/TST.2025.9010166","article-title":"Efficient Inference for Edge Large Language Models: A Survey","volume":"31","author":"Cai","year":"2026","journal-title":"Tsinghua Sci. Technol."},{"key":"ref_12","unstructured":"Lu, Z., Li, X., Cai, D., Yi, R., Liu, F., Zhang, X., Lane, N.D., and Xu, M. (2024). Small Language Models: Survey, Measurements, and Insights. arXiv."},{"key":"ref_13","unstructured":"Lance, E. (2024). Small Language Models Gaining Popularity While LLMs Still Go Strong, Forbes."},{"key":"ref_14","unstructured":"Van Nguyen, C., Shen, X., Aponte, R., Xia, Y., Basu, S., Hu, Z., Chen, J., Parmar, M., Kunapuli, S., and Barrow, J. (2024). A Survey of Small Language Models. arXiv."},{"key":"ref_15","unstructured":"Liu, Z., Zhao, C., Iandola, F., Lai, C., Tian, Y., Fedorov, I., Xiong, Y., Chang, E., Shi, Y., and Krishnamoorthi, R. (2024). Mobilellm: Optimizing sub-billion parameter language models for on-device use cases. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Luo, W., Fan, R., Li, Z., Du, D., Wang, Q., and Chu, X. (2024). Benchmarking and dissecting the nvidia hopper gpu architecture. arXiv.","DOI":"10.1109\/IPDPS57955.2024.00064"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"101272","DOI":"10.1016\/j.iot.2024.101272","article-title":"The computing continuum: From IoT to the cloud","volume":"27","author":"Jansen","year":"2024","journal-title":"Internet Things"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Luo, X., Ding, F., Yang, F., Zhou, Y., Loo, J., Tew, H.H., and Liu, C. (March, January 28). SenseRAG: Constructing Environmental Knowledge Bases with Proactive Querying for LLM-Based Autonomous Driving. Proceedings of the 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), Tucson, AZ, USA.","DOI":"10.1109\/WACVW65960.2025.00111"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3095","DOI":"10.3390\/smartcities7060121","article-title":"A Retrieval-Augmented Generation Approach for Data-Driven Energy Infrastructure Digital Twins","volume":"7","author":"Ieva","year":"2024","journal-title":"Smart Cities"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1109\/TCCN.2025.3558069","article-title":"RFSensingGPT: A Multi-Modal RAG-Enhanced Framework for Integrated Sensing and Communications Intelligence in 6G Networks","volume":"12","author":"Khan","year":"2025","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"28684","DOI":"10.1109\/ACCESS.2024.3367118","article-title":"A survey on integrating edge computing with ai and blockchain in maritime domain, aerial systems, iot, and industry 4.0","volume":"12","author":"Alanhdi","year":"2024","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"O\u2019Donncha, F., Sheehan, J.D., Touma, M., Zemouri, S., and High, R.H. (2024). Towards intelligent ship-edge computing enabling automated configuration of ship models and adaptive self-learning. State-of-the-Art Digital Twin Applications for Shipping Sector Decarbonization, IGI Global.","DOI":"10.4018\/978-1-6684-9848-4.ch004"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"110499","DOI":"10.1016\/j.comnet.2024.110499","article-title":"Paving the way towards safer and more efficient maritime industry with 5g and beyond edge computing systems","volume":"250","author":"Charpentier","year":"2024","journal-title":"Comput. Netw."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"109380","DOI":"10.1016\/j.oceaneng.2021.109380","article-title":"Collision-avoidance navigation systems for Maritime Autonomous Surface Ships: A state of the art survey","volume":"235","author":"Zhang","year":"2021","journal-title":"Ocean. Eng."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Cheng, W. (2024). Intelligent Assisted Navigation for Ships Using Edge Computing and Neural Networks. Proceedings of the 2024 International Conference on Intelligent Computing and Robotics (ICICR), IEEE.","DOI":"10.1109\/ICICR61203.2024.00036"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"De, D., Sengupta, D., and Tran, T.A. (2024). Artificial Intelligence and Edge Computing for Sustainable Ocean Health, Springer.","DOI":"10.1007\/978-3-031-64642-3"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"107481","DOI":"10.1016\/j.future.2024.107481","article-title":"Underwater Mediterranean image analysis based on the compute continuum paradigm","volume":"162","author":"Ferrari","year":"2025","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"102788","DOI":"10.1016\/j.ecoinf.2024.102788","article-title":"Automated species classification and counting by deep-sea mobile crawler platforms using YOLO","volume":"82","author":"Ortenzi","year":"2024","journal-title":"Ecol. Inform."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"53646","DOI":"10.1109\/ACCESS.2024.3387529","article-title":"An edge computing-based preventive framework with machine learning-integration for anomaly detection and risk management in maritime wireless communications","volume":"12","author":"Algarni","year":"2024","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Durlik, I., Miller, T., Kostecka, E., and Tu\u0144ski, T. (2024). Artificial Intelligence in Maritime Transportation: A Comprehensive Review of Safety and Risk Management Applications. Appl. Sci., 14.","DOI":"10.3390\/app14188420"},{"key":"ref_31","unstructured":"Zhou, Z., Li, L., Chen, X., and Li, A. (2023). Mini-Giants: \u201cSmall\u201d Language Models and Open Source Win-Win. arXiv."},{"key":"ref_32","unstructured":"Abdin, M., Jacobs, S.A., Awan, A.A., Aneja, J., Awadallah, A., Awadalla, H., Bach, N., Bahree, A., Bakhtiari, A., and Behl, H. (2024). Phi-3 technical report: A highly capable language model locally on your phone. arXiv."},{"key":"ref_33","unstructured":"Hendrycks, D., Burns, C., Basart, S., Zou, A., Mazeika, M., Song, D., and Steinhardt, J. (2021). Measuring Massive Multitask Language Understanding. arXiv."},{"key":"ref_34","unstructured":"Yang, A., Yang, B., Hui, B., Zheng, B., Yu, B., Zhou, C., Li, C., Li, C., Liu, D., and Huang, F. (2024). Qwen2 technical report. arXiv."},{"key":"ref_35","unstructured":"(2024, July 10). QwenTeam Qwen2.5: A Party of Foundation Models. Available online: https:\/\/qwen.ai\/blog?id=qwen2.5."},{"key":"ref_36","unstructured":"Minaee, S., Mikolov, T., Nikzad, N., Chenaghlu, M., Socher, R., Amatriain, X., and Gao, J. (2024). Large language models: A survey. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Sennrich, R. (2015). Neural machine translation of rare words with subword units. arXiv.","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref_38","unstructured":"Kaplan, J., McCandlish, S., Henighan, T., Brown, T.B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., and Amodei, D. (2020). Scaling laws for neural language models. arXiv."},{"key":"ref_39","first-page":"1","article-title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Bach, S.H., Sanh, V., Yong, Z.X., Webson, A., Raffel, C., Nayak, N.V., Sharma, A., Kim, T., Bari, M.S., and Fevry, T. (2022). Promptsource: An integrated development environment and repository for natural language prompts. arXiv.","DOI":"10.18653\/v1\/2022.acl-demo.9"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Xiong, W., Liu, J., Molybog, I., Zhang, H., Bhargava, P., Hou, R., Martin, L., Rungta, R., Sankararaman, K.A., and Oguz, B. (2023). Effective long-context scaling of foundation models. arXiv.","DOI":"10.18653\/v1\/2024.naacl-long.260"},{"key":"ref_42","unstructured":"Gunasekar, S., Zhang, Y., Aneja, J., Mendes, C.C.T., Del Giorno, A., Gopi, S., Javaheripi, M., Kauffmann, P., de Rosa, G., and Saarikivi, O. (2023). Textbooks are all you need. arXiv."},{"key":"ref_43","unstructured":"Team, G., Riviere, M., Pathak, S., Sessa, P.G., Hardin, C., Bhupatiraju, S., Hussenot, L., Mesnard, T., Shahriari, B., and Ram\u00e9, A. (2024). Gemma 2: Improving open language models at a practical size. arXiv."},{"key":"ref_44","first-page":"1","article-title":"Privacy and data protection in ChatGPT and other AI Chatbots: Strategies for securing user information","volume":"15","author":"Sebastian","year":"2023","journal-title":"Int. J. Secur. Priv. Pervasive Comput. (IJSPPC)"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Yan, B., Li, K., Xu, M., Dong, Y., Zhang, Y., Ren, Z., and Cheng, X. (2024). On protecting the data privacy of large language models (llms): A survey. arXiv.","DOI":"10.1109\/ICMC60390.2024.00008"},{"key":"ref_46","unstructured":"Brown, T.B. (2020). Language models are few-shot learners. arXiv."},{"key":"ref_47","unstructured":"Zhang, S., Dong, L., Li, X., Zhang, S., Sun, X., Wang, S., Li, J., Hu, R., Zhang, T., and Wu, F. (2023). Instruction tuning for large language models: A survey. arXiv."},{"key":"ref_48","first-page":"3381","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref_49","unstructured":"Wang, W., Chen, W., Luo, Y., Long, Y., Lin, Z., Zhang, L., Lin, B., Cai, D., and He, X. (2024). Model compression and efficient inference for large language models: A survey. arXiv."},{"key":"ref_50","unstructured":"Wang, J., Zhou, H., Song, T., Mao, S., Ma, S., Wang, H., Xia, Y., and Wei, F. (2024). 1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1. 58 Inference on CPUs. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1145\/365153.365168","article-title":"ELIZA\u2014A computer program for the study of natural language communication between man and machine","volume":"9","author":"Weizenbaum","year":"1966","journal-title":"Commun. ACM"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Marietto, M.d.G.B., de Aguiar, R.V., Barbosa, G.d.O., Botelho, W.T., Pimentel, E., Fran\u00e7a, R.d.S., and da Silva, V.L. (2013). Artificial intelligence markup language: A brief tutorial. arXiv.","DOI":"10.5121\/ijcses.2013.4301"},{"key":"ref_53","unstructured":"Wallace, R. (2003). The Elements of AIML Style, Alice AI Foundation."},{"key":"ref_54","unstructured":"Dam, S.K., Hong, C.S., Qiao, Y., and Zhang, C. (2024). A complete survey on llm-based ai chatbots. arXiv."},{"key":"ref_55","unstructured":"Mousavi, S.M., Alghisi, S., and Riccardi, G. (2024). Is Your LLM Outdated? Benchmarking LLMs & Alignment Algorithms for Time-Sensitive Knowledge. arXiv."},{"key":"ref_56","unstructured":"Han, Y., Liu, C., and Wang, P. (2023). A comprehensive survey on vector database: Storage and retrieval technique, challenge. arXiv."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Xiao, S., Liu, Z., Zhang, P., Muennighoff, N., Lian, D., and Nie, J.Y. (2023). C-pack: Packaged resources to advance general chinese embedding. arXiv.","DOI":"10.1145\/3626772.3657878"},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/TPAMI.2018.2889473","article-title":"Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs","volume":"42","author":"Malkov","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_59","unstructured":"Zhao, P., Zhang, H., Yu, Q., Wang, Z., Geng, Y., Fu, F., Yang, L., Zhang, W., and Cui, B. (2024). Retrieval-augmented generation for ai-generated content: A survey. arXiv."},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Ye, X., Yavuz, S., Hashimoto, K., Zhou, Y., and Xiong, C. (2021). Rng-kbqa: Generation augmented iterative ranking for knowledge base question answering. arXiv.","DOI":"10.18653\/v1\/2022.acl-long.417"},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"Kozlov, A., Lazarevich, I., Shamporov, V., Lyalyushkin, N., and Gorbachev, Y. (2021). Neural network compression framework for fast model inference. Proceedings of the Intelligent Computing: Proceedings of the 2021 Computing Conference, Volume 3, Springer.","DOI":"10.1007\/978-3-030-80129-8_17"},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Douze, M., Guzhva, A., Deng, C., Johnson, J., Szilvasy, G., Mazar\u00e9, P.E., Lomeli, M., Hosseini, L., and J\u00e9gou, H. (2024). The faiss library. arXiv.","DOI":"10.1109\/TBDATA.2025.3618474"},{"key":"ref_63","unstructured":"Nogueira, R., and Cho, K. (2019). Passage Re-ranking with BERT. arXiv."},{"key":"ref_64","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., and Liu, Z. (2024). Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv.","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Caffagni, D., Cocchi, F., Barsellotti, L., Moratelli, N., Sarto, S., Baraldi, L., Cornia, M., and Cucchiara, R. (2024). The (r) evolution of multimodal large language models: A survey. arXiv.","DOI":"10.18653\/v1\/2024.findings-acl.807"},{"key":"ref_66","doi-asserted-by":"crossref","unstructured":"Yu, H., Gan, A., Zhang, K., Tong, S., Liu, Q., and Liu, Z. (2024). Evaluation of Retrieval-Augmented Generation: A Survey. arXiv.","DOI":"10.1007\/978-981-96-1024-2_8"},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Saad-Falcon, J., Khattab, O., Potts, C., and Zaharia, M. (2023). Ares: An automated evaluation framework for retrieval-augmented generation systems. arXiv.","DOI":"10.18653\/v1\/2024.naacl-long.20"},{"key":"ref_68","doi-asserted-by":"crossref","unstructured":"Es, S., James, J., Espinosa-Anke, L., and Schockaert, S. (2023). Ragas: Automated evaluation of retrieval augmented generation. arXiv.","DOI":"10.18653\/v1\/2024.eacl-demo.16"},{"key":"ref_69","unstructured":"Chen, J., Lin, H., Han, X., and Sun, L. (2024, January 26\u201327). Benchmarking large language models in retrieval-augmented generation. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada."},{"key":"ref_70","doi-asserted-by":"crossref","unstructured":"Fu, J., Qin, X., Yang, F., Wang, L., Zhang, J., Lin, Q., Chen, Y., Zhang, D., Rajmohan, S., and Zhang, Q. (2024). AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation. arXiv.","DOI":"10.18653\/v1\/2024.findings-emnlp.223"},{"key":"ref_71","doi-asserted-by":"crossref","unstructured":"Lee, M., Liang, P., and Yang, Q. (2022). CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities. CHI \u201922, Proceedings of the Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, Association for Computing Machinery.","DOI":"10.1145\/3491102.3502030"},{"key":"ref_72","unstructured":"Ouyang, S., Zhang, J.M., Harman, M., and Wang, M. (2023). LLM is Like a Box of Chocolates: The Non-determinism of ChatGPT in Code Generation. arXiv."},{"key":"ref_73","doi-asserted-by":"crossref","unstructured":"Guainazzo, N. (2025). Navigating the Seas of AI: Deploying Small Language Models on Compact Edge Computers for Maritime Applications. [Master\u2019s Thesis, Universit\u00e0 Degli Studi di Genova].","DOI":"10.3390\/s26051590"},{"key":"ref_74","unstructured":"Caspari, L., Dastidar, K.G., Zerhoudi, S., Mitrovic, J., and Granitzer, M. (2024). Beyond Benchmarks: Evaluating Embedding Model Similarity for Retrieval Augmented Generation Systems. arXiv."},{"key":"ref_75","doi-asserted-by":"crossref","unstructured":"Briguglio, G., and Crupi, V. (2024). Review on Sensors for Sustainable and Safe Maritime Mobility. J. Mar. Sci. Eng., 12.","DOI":"10.3390\/jmse12020353"},{"key":"ref_76","unstructured":"Hinck, M., Olson, M.L., Cobbley, D., Tseng, S.Y., and Lal, V. (2024). LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model. arXiv."},{"key":"ref_77","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., and Lee, Y.J. (2024, January 16\u201322). Improved baselines with visual instruction tuning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref_78","unstructured":"Yao, Y., Yu, T., Zhang, A., Wang, C., Cui, J., Zhu, H., Cai, T., Li, H., Zhao, W., and He, Z. (2024). Minicpm-v: A gpt-4v level mllm on your phone. arXiv."},{"key":"ref_79","doi-asserted-by":"crossref","unstructured":"Sarmah, B., Mehta, D., Hall, B., Rao, R., Patel, S., and Pasquali, S. (2024, January 14\u201317). HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction. Proceedings of the 5th ACM International Conference on AI in Finance, Brooklyn, NY, USA.","DOI":"10.1145\/3677052.3698671"},{"key":"ref_80","unstructured":"Asai, A., Wu, Z., Wang, Y., Sil, A., and Hajishirzi, H. (2023). Self-rag: Learning to retrieve, generate, and critique through self-reflection. arXiv."},{"key":"ref_81","doi-asserted-by":"crossref","unstructured":"Joshi, P., Gupta, A., Kumar, P., and Sisodia, M. (2024, January 5\u20137). Robust Multi Model RAG Pipeline For Documents Containing Text, Table & Images. Proceedings of the 2024 3rd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), Salem, India.","DOI":"10.1109\/ICAAIC60222.2024.10574972"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/5\/1590\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T05:12:21Z","timestamp":1772687541000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/5\/1590"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,3]]},"references-count":81,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["s26051590"],"URL":"https:\/\/doi.org\/10.3390\/s26051590","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,3]]}}}