In this study, the performance of a set of machine learning algorithms was evaluated to classify the freshness levels of frozen-thawed shrimps during storage in refrigerator conditions. The algorithms used include CNN, DenseNet121, InceptionV3, ResNet50, CNN + LSTM, and YOLO_v8. Shrimps were categorised into three classes according to their freshness: fresh, medium, and stale. According to the results, the CNN + LSTM model was the most successful algorithm with a 99.07% accuracy rate. The YOLO_v8 algorithm stood out with 99.23% accuracy in the validation set. However, it was observed that the classification performances of models such as DenseNet121 and ResNet50 were relatively low. In addition, to increase the explainability of the decision processes, the Grad-CAM algorithm was used to visualise the areas that the CNN + LSTM model considers when determining the freshness states. Grad-CAM effectively emphasised visual cues focusing on the surface texture and signs of deterioration of the frozen-thawed shrimps. The results of the study showed that the proposed algorithms provide a non-destructive and accurate method for shrimp freshness classification. This approach offers a potential solution to improve food safety in the seafood industry.

Nowadays, the sustainability of agriculture and food security have an increasing importance on soil fertility. Soil fertility is defined as the capacity of a land to grow crops and its potential crop productivity. However, factors such as increasing population, climate change, land use changes and environmental pollution threaten soil fertility. These threats can result in problems such as erosion, soil salinisation and organic matter depletion. Soil fertility is critical for the long-term health of agriculture and food security. Artificial intelligence techniques used to determine and manage soil fertility analyse the minerals present in the soil as well as other factors. These analyses assess the amount of minerals present in the soil, the availability of nutrients and important parameters such as pH. This information guides farmers in selecting the most appropriate crops. Furthermore, the integration of Internet of Things (IoT) technologies allows real-time monitoring of minerals and nutrients in the soil and optimising irrigation and fertilisation processes based on this data. These developments have the potential to improve soil fertility management and increase agricultural productivity.

Nowadays, computers are indispensable for business processes and home users. The widespread use of the Internet provides convenience in many areas from education to research. However, most of the users are unaware of technical security measures and use the Internet unconsciously. This situation leads to inadequate security measures against cyber-attacks. Various trainings are organised for conscious and safe internet use, but these efforts are not enough. Therefore, artificial intelligence-based solutions that can detect cyber incidents and close security gaps are becoming necessary. DNS tunnelling is a method used by malware to leak data over the internet. Vulnerable computers can put users in difficult situations by learning IP addresses from the wrong DNS servers. Innovative methods have been developed to detect this tunnelling. Some methods can detect low and slow data leakage through DNS in real time. There are also hybrid DNS tunnelling detection systems that achieve high accuracy and F-score using packet length and specific features. Feature-based methods sensitive to cache characteristics effectively characterise DNS tunnelling traffic with low false detection rates. These methods offer effective strategies for internet security. In this study, the detection of DNS tunnelling attacks by machine learning algorithms on the CIC-Bell-DNS-EXF-2021 dataset was investigated.

Many devices have been connected to each other and a wide platform has been formed with the development of internet technologies. The continuous expansion of this platform has revealed requirements such as single point management, accessibility, band...

1990'ların başından bu yana internet kullanımının hızla yaygınlaşması, anlamlı analiz için gelişmiş araçlar gerektiren büyük veri kümelerinin oluşmasına yol açmıştır. Yapay zeka teknolojilerinin, özellikle erken teşhis ve hastalık tespitinde hataların azaltılması için kullanıldıkları sağlık hizmetlerinde bu konuda etkili olduğu kanıtlanmıştır. Bu çalışma, yaşlı bireyler arasında yaygın olan ilerleyici bir nörodejeneratif durum olan Alzheimer Hastalığının (AD) erken teşhisi için yapay zeka tabanlı bir uzman sistem geliştirmeye odaklanmaktadır. Çalışmda 174 örnekli DARWIN veri kümesi (89'u AD'li ve 85'i AD'siz) kullanılarak AdaBoost, Gradient Boost, VotingHard, Stack, Decision Trees, Random Forest, Naive Bayes ve 1D-CNN olmak üzere sekiz makine öğrenimi algoritması ile eğitilmiştir. Çalışmada kullanılan Stack modeli %91,43 doğruluk, %93,75 özgüllük, %94,44 duyarlılık, %89,47 kesinlik, %91,89 F-ölçümü ve %91,43 AUC değeri ile yüksek bir tahmin performansı elde ederek en etkili model olarak ortaya çıkmıştır. Orta düzeyde performans gösteren modeller arasında AdaBoost %88,57 doğruluk, %88,24 özgüllük, %88,89 duyarlılık, %88,89 kesinlik, %88,89 F-ölçümü ve %88,56 AUC değeri elde etmiştir. Buna karşılık, VotingHard modeli %80,00 doğruluk, %77,78 özgüllük, %77,78 duyarlılık, %82,35 hassasiyet, %80,00 F-ölçümü ve %80,00 AUC değeri ile en düşük performansı göstermiştir. Bu bulgular, Stack modelinin güvenilir erken evre AD teşhisi potansiyelini vurgulamakta ve algoritma performansa ilişkin karşılaştırmalı bir bakış açısı sağlamaktadır.

Walnut has an important place in agricultural production and research on it covers various fields. In this study, machine learning algorithms were used for non-destructive estimation of walnut productivity. The researchers developed a setup using audio recordings and images to determine the fullness and void status of walnuts. These data were processed with various machine learning algorithms and the results were evaluated. The algorithms used in the study include RESNET50, DenseNET121, VGG16 and CNN. However, when the results obtained are analyzed, it is seen that the VGG16 algorithm gives the most successful results with 99.79% accuracy and 91.42% val_accuracy values using imagenet weights. These results were found to be quite successful compared to similar studies in the literature. In future studies, it is aimed to expand the obtained dataset and increase the val_accuracy value even more. In addition, similar methods are planned to be applied on other nuts such as hazelnuts and almonds. This could be an important step to increase productivity in agricultural production. In conclusion, this study on walnut yield estimation using non-destructive methods offers a new and effective approach in agricultural applications. The use of machine learning algorithms offers potential in various areas such as increasing productivity in walnut production and detecting diseases.