Search Results (5)

Aeration systems are among the most energy-intensive components of wastewater treatment plants (WWTPs), consuming up to 75% of total electricity while being prone to performance degradation caused by diffuser fouling and pressure losses. Traditional maintenance strategies are largely reactive or preventive, leading to inefficient interventions, higher operational costs, and limited fault anticipation. This study addresses the need for an advanced predictive maintenance framework capable of early detection and differentiation of multiple aeration system faults. Using the Benchmark Simulation Model No. 2 (BSM2), two representative degradation scenarios—acute airflow pressure loss and chronic diffuser fouling—were simulated to generate a labeled dataset. A hybrid machine learning approach was developed, combining Random Forest-based feature selection with Long Short-Term Memory (LSTM) neural networks for temporal, multi-label fault classification. To enhance interpretability and operator trust, SHapley Additive exPlanations (SHAP) were applied to quantify feature contributions and provide transparent model predictions. The results show that the proposed framework achieves over 94% detection accuracy and provides early warnings compared to static threshold-based methods. The integration of explainable AI ensures actionable insights for maintenance planning. This approach supports more energy-efficient, reliable, and sustainable operation of WWTP aeration systems and offers a benchmark methodology for future predictive maintenance research. Full article

The longstanding debate over early hominin subsistence strategies, particularly the hunting-versus-scavenging hypothesis, as well as discussions regarding the functionality of Oldowan sites, has been primarily centered on the archeological and paleoanthropological record of Olduvai Gorge. Historically, FLK Zinj has been at the core of these debates, serving as a principal empirical reference due to the prevailing assumption that most other Bed I sites at Olduvai represented non-anthropogenic accumulations However, recent discoveries have significantly reshaped this perspective. Newly identified early sites, including PTK, DS, and AGS, situated within the paleolandscape and thin stratigraphic context of FLK Zinj, provide crucial new anthropogenic datasets. These sites offer additional dimensions to the study of early hominin behavior, facilitating a more nuanced reconstruction of their adaptive strategies in this paleoenvironment. Furthermore, methodological advancements in recent years—including controlled experimental and actualistic studies, sophisticated statistical modeling, and the integration of machine learning algorithms—have greatly enhanced the analytical frameworks available for investigating early hominin behavior. These innovations have refined the ability to formulate and test hypotheses within a rigorous scientific paradigm, significantly improving the resolution of archeological and taphonomic interpretations. This study presents an in-depth taphonomic analysis of the faunal assemblage from level 22A at DS, a Bed I site at Olduvai Gorge dated to approximately 1.84 Ma. The assemblage exhibits exceptional preservation, enabling detailed assessments of skeletal part representation, fragmentation patterns, and surface modifications. By combining traditional taphonomic methodologies with state-of-the-art AI-driven bone surface modification (BSM) analyses, this research contributes novel insights into the interactions between early hominins and carnivores, elucidating the complex ecological dynamics of an Early Pleistocene African paleolandscape. Full article

Maintaining effluent quality in wastewater treatment plants (WWTPs) comes with significant challenges under variable weather conditions, where sudden changes in flow rate and increased pollutant loads can affect treatment performance. Traditional physical sensors became both expensive and susceptible to failure under extreme conditions. In this study, we evaluate the performance of soft sensors based on artificial intelligence (AI) to predict the components underlying the calculation of the effluent quality index (EQI). We thus focus our study on three ML models: Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) and Transformer. Using the Benchmark Simulation Model no. 2 (BSM2) as the WWTP, we were able to obtain datasets for training the ML models and to evaluate their performance in dry weather scenarios, rainy episodes, and storm events. To improve the classification of networks according to the type of weather, we developed a Random Forest (RF)-based meta-classifier. The results indicate that for dry weather conditions the Transformer network achieved the best performance, while for rain episodes and storm scenarios the GRU was able to capture sudden variations with the highest accuracy. LSTM performed normally in stable conditions but struggled with rapid fluctuations. These results support the decision to integrate AI-based predictive models in WWTPs, highlighting the top performances of both a recurrent network (GRU) and a feed-forward network (Transformer) in obtaining effluent quality predictions under different weather conditions. Full article

Restriction endonucleases (REs) are intra-bacterial scissors that are considered tools in the fight against foreign genetic material. SspI and BsmAI, examined in this study, cleave dsDNA at their site of recognition or within a short distance of it. Both enzymes are representatives of type II REs, which have played an extremely important role in research on the genetics of organisms and molecular biology. Therefore, the study of agents affecting their activity has become highly important. Ionizing radiation may damage basic cellular mechanisms by inducing lesions in the genome, with 5′,8-cyclo-2′-deoxypurines (cdPus) as a model example. Since cdPus may become components of clustered DNA lesions (CDLs), which are unfavorable for DNA repair pathways, their impact on other cellular mechanisms is worthy of attention. This study investigated the influence of cdPus on the elements of the bacterial restriction–modification system. In this study, it was shown that cdPus present in DNA affect the activity of REs. SspI was blocked by any cdPu lesion present at the enzyme’s recognition site. When lesions were placed near the recognition sequence, the SspI was inhibited up to 46%. Moreover, (5′S)-5′,8-cyclo-2′-deoxyadenosine (ScdA) present in the oligonucleotide sequence lowered BsmAI activity more than (5′R)-5′,8-cyclo-2′-deoxyadenosine (RcdA). Interestingly, in the case of 5′,8-cyclo-2′-deoxyguanosine (cdG), both 5′S and 5′R diastereomers inhibited BsmAI activity (up to 55% more than cdA). The inhibition was weaker when cdG was present at the recognition site rather than the cleavage site. Full article

Whitebark pine is difficult to distinguish from limber pine when seed cones are not present. This is often the case because of young stand age, growth at environmental extremes, or harvesting by vertebrate species. Developing an economical genetic identification tool that distinguishes non-cone-bearing limber from whitebark pine, therefore, could aid many kinds of research on these species. Phylogenetic studies involving limber and whitebark pine suggest that chloroplast DNA sequences differ between these species. We therefore wanted to identify chloroplast loci that could differentiate limber from whitebark pine trees by taking an economical approach involving restriction-site analysis. We generated chloroplast DNA barcode sequences sampled from limber and whitebark pine trees that we identified using attached seed cones. We searched for nucleotide differences associated with restriction endonuclease recognition sites. Our analyses revealed that matK and the psbA-trnH spacer each readily amplified and harbored multiple DNA-sequence differences between limber and whitebark pine. The matK coding sequence of whitebark pine has a BsmAI restriction site not found in limber pine. The psbA-trnH spacer of limber pine has two PsiI restriction sites, neither of which is found in whitebark pine. DNA-sequence and restriction-site analysis of the psbA-trnH spacer from 111 trees showed complete congruence between visually and genetically identified limber (n = 68) and whitebark (n = 43) pine trees. We conclude that restriction site analysis of the chloroplast psbA-trnH spacer and matK involves both minimal technical expertize and research funds. These findings should be of value to foresters interested in species identification and distribution modeling, as well as the analysis of fossil pine pollen, given that gymnosperms transmit chloroplast DNA paternally. Full article